Author SHA1 Message Date
sneak 4dc14895d4 Join the S3 prefix to every key with one slash (closes #222)
check / check (push) Successful in 10m54s
The S3 client built each key as prefix + key, and the URL parser keeps
the prefix as written, so s3://bucket/p stored p + "blobs/..." with no
slash while s3://bucket/p/ stored p/blobs/.... A recovery host that wrote
the URL the other way found no snapshots.

NewClient now strips trailing slashes from the prefix and adds one back
when anything is left, giving the README layout for both URL forms; an
empty prefix stays at the bucket root. The s3.prefix config setting
goes through the same client and gets the same join.

A new test writes through each URL shape against an in-process S3
server, checks the key in the bucket, and lists through both List and
ListStream, which every snapshot listing uses.

Model: opus-5-5
2026-10-06 16:44:01 +00:00
163 changed files with 3511 additions and 17278 deletions

No files matched your search

-2
View File
@@ -1,2 +0,0 @@
node_modules/
yarn.lock
-4
View File
@@ -1,4 +0,0 @@
{
"tabWidth": 4,
"proseWrap": "always"
}
+76 -71
View File
@@ -4,122 +4,127 @@ Version: 2025-06-08
# Instructions and Contextual Information # Instructions and Contextual Information
- Be direct, robotic, expert, accurate, and professional. * Be direct, robotic, expert, accurate, and professional.
- Do not butter me up or kiss my ass. * Do not butter me up or kiss my ass.
- Come in hot with strong opinions, even if they are contrary to the direction I * Come in hot with strong opinions, even if they are contrary to the
am headed. direction I am headed.
- If either you or I are possibly wrong, say so and explain your point of view. * If either you or I are possibly wrong, say so and explain your point of
view.
- Point out great alternatives I haven't thought of, even when I'm not asking * Point out great alternatives I haven't thought of, even when I'm not
for them. asking for them.
- Treat me like the world's leading expert in every situation and every * Treat me like the world's leading expert in every situation and every
conversation, and deliver the absolute best recommendations. conversation, and deliver the absolute best recommendations.
- I want excellence, so always be on the lookout for divergences from good data * I want excellence, so always be on the lookout for divergences from good
model design or best practices for object oriented development. data model design or best practices for object oriented development.
- IMPORTANT: This is production code, not a research or teaching exercise. * IMPORTANT: This is production code, not a research or teaching exercise.
Deliver professional-level results, not prototypes. Deliver professional-level results, not prototypes.
- Please read and understand the `README.md` file in the root of the repo for * Please read and understand the `README.md` file in the root of the repo
project-specific contextual information, including development policies, for project-specific contextual information, including development
practices, and current implementation status. policies, practices, and current implementation status.
- Be proactive in suggesting improvements or refactorings in places where we * Be proactive in suggesting improvements or refactorings in places where we
diverge from best practices for clean, modular, maintainable code. diverge from best practices for clean, modular, maintainable code.
# Policies # Policies
1. Before committing, tests must pass (`make test`), linting must pass 1. Before committing, tests must pass (`make test`), linting must pass
(`make lint`), and code must be formatted (`make fmt`). For go, those (`make lint`), and code must be formatted (`make fmt`). For go, those
makefile targets should use `go fmt` and `go test -v ./...` and makefile targets should use `go fmt` and `go test -v ./...` and
`golangci-lint run`. Each Makefile target does exactly one thing — to run `golangci-lint run`. Each Makefile target does exactly one thing — to
lint + fmt-check + test together (the standard pre-commit gate), use run lint + fmt-check + test together (the standard pre-commit gate),
`make check`. use `make check`.
2. Always write a `Makefile` with the default target being `test`, and with a 2. Always write a `Makefile` with the default target being `test`, and with
`fmt` target that formats the code. The `test` target should run all tests in a `fmt` target that formats the code. The `test` target should run all
the project, and the `fmt` target should format the code. `test` should also tests in the project, and the `fmt` target should format the code.
have a prerequisite target `lint` that should run any linters that are `test` should also have a prerequisite target `lint` that should run any
configured for the project. linters that are configured for the project.
3. After each completed bugfix or feature, the code must be committed. Do all of 3. After each completed bugfix or feature, the code must be committed. Do
the pre-commit checks (test, lint, fmt) before committing, of course. all of the pre-commit checks (test, lint, fmt) before committing, of
course.
4. When creating a very simple test script for testing out a new feature, 4. When creating a very simple test script for testing out a new feature,
instead of making a throwaway to be deleted after verification, write an instead of making a throwaway to be deleted after verification, write an
actual test file into the test suite. It doesn't need to be very big or actual test file into the test suite. It doesn't need to be very big or
complex, but it should be a real test that can be run. complex, but it should be a real test that can be run.
5. When you are instructed to make the tests pass, DO NOT delete tests, skip 5. When you are instructed to make the tests pass, DO NOT delete tests, skip
tests, or change the tests specifically to make them pass (unless there is a tests, or change the tests specifically to make them pass (unless there
bug in the test). This is cheating, and it is bad. You should only be is a bug in the test). This is cheating, and it is bad. You should only
modifying the test if it is incorrect or if the test is no longer relevant. be modifying the test if it is incorrect or if the test is no longer
In almost all cases, you should be fixing the code that is being tested, or relevant. In almost all cases, you should be fixing the code that is
updating the tests to match a refactored implementation. being tested, or updating the tests to match a refactored implementation.
6. When dealing with dates and times or timestamps, always use, display, and 6. When dealing with dates and times or timestamps, always use, display, and
store UTC. Set the local timezone to UTC on startup. If the user needs to see store UTC. Set the local timezone to UTC on startup. If the user needs
the time in a different timezone, store the user's timezone in a separate to see the time in a different timezone, store the user's timezone in a
field and convert the UTC time to the user's timezone when displaying it. For separate field and convert the UTC time to the user's timezone when
internal use and internal applications and administrative purposes, always displaying it. For internal use and internal applications and
display UTC. administrative purposes, always display UTC.
7. Always write tests, even if they are extremely simple and just check for 7. Always write tests, even if they are extremely simple and just check for
correct syntax (ability to compile/import). If you are writing a new feature, correct syntax (ability to compile/import). If you are writing a new
write a test for it. You don't need to target complete coverage, but you feature, write a test for it. You don't need to target complete
should at least test any new functionality you add. If you are fixing a bug, coverage, but you should at least test any new functionality you add. If
write a test first that reproduces the bug, and then fix the bug in the code. you are fixing a bug, write a test first that reproduces the bug, and
then fix the bug in the code.
8. When implementing new features, be aware of potential side-effects (such as 8. When implementing new features, be aware of potential side-effects (such
state files on disk, data in the database, etc.) and ensure that it is as state files on disk, data in the database, etc.) and ensure that it is
possible to mock or stub these side-effects in tests. possible to mock or stub these side-effects in tests.
9. Always use structured logging. Log any relevant state/context with the 9. Always use structured logging. Log any relevant state/context with the
messages (but do not log secrets). If the log stream is not a terminal, messages (but do not log secrets). If the log stream is not a terminal,
output the structured logs in jsonl format. output the structured logs in jsonl format.
10. Avoid using bare strings or numbers in code, especially if they appear 10. Avoid using bare strings or numbers in code, especially if they appear
anywhere more than once. Always define a constant (usually at the top of the anywhere more than once. Always define a constant (usually at the top
file) and give it a descriptive name, then use that constant in the code of the file) and give it a descriptive name, then use that constant in
instead of the bare string or number. the code instead of the bare string or number.
11. You do not need to summarize your changes in the chat after making them. 11. You do not need to summarize your changes in the chat after making them.
Making the changes and committing them is sufficient. If anything out of the Making the changes and committing them is sufficient. If anything out
ordinary happened, please explain it, but in the normal case where you found of the ordinary happened, please explain it, but in the normal case
and fixed the bug, or implemented the feature, there is no need for the where you found and fixed the bug, or implemented the feature, there is
end-of-change summary. no need for the end-of-change summary.
12. Do not create additional files in the root directory of the project without 12. Do not create additional files in the root directory of the project
asking permission first. Configuration files, documentation, and build files without asking permission first. Configuration files, documentation, and
are acceptable in the root, but source code and other files should be build files are acceptable in the root, but source code and other files
organized in appropriate subdirectories. should be organized in appropriate subdirectories.
13. Pre-1.0: NEVER add a database migration. Migrations are supported, but 13. Pre-1.0: NEVER add a database migration. Migrations are supported, but
nothing is installed anywhere yet, so there is nothing to migrate. To change nothing is installed anywhere yet, so there is nothing to migrate. To
the schema, edit `internal/database/schema/001.sql` (and any code that change the schema, edit `internal/database/schema/001.sql` (and any
touches the affected tables) directly. After 1.0, each schema change is a code that touches the affected tables) directly. After 1.0, each schema
new numbered file in that directory and a released file is never edited; an change is a new numbered file in that directory and a released file is
existing local database is then migrated when vaultik is updated. Before never edited; an existing local database is then migrated when vaultik
1.0, a local database left on an older schema is deleted and re-created by a is updated. Before 1.0, a local database left on an older schema is
full backup. See [`docs/DATAMODEL.md`](docs/DATAMODEL.md#schema-migrations). deleted and re-created by a full backup. See
[`docs/DATAMODEL.md`](docs/DATAMODEL.md#schema-migrations).
14. Never use `git add -A`. Stage only the files you intentionally changed. 14. Never use `git add -A`. Stage only the files you intentionally
changed.
15. Commit messages carry no attribution or advertising trailers for the tool 15. Commit messages carry no attribution or advertising trailers for the
that helped write the code, or for its vendor: the owner is the sole author tool that helped write the code, or for its vendor: the owner is the
of code written with a tool. sole author of code written with a tool.
16. Run the whole test suite with `make test` every time, and read its full 16. Run the whole test suite with `make test` every time, and read its full
output. Never run `go test`, a single test or a single package, and never output. Never run `go test`, a single test or a single package, and
grep the output. never grep the output.
17. Do not stop working on a task until the definition of done given in the 17. Do not stop working on a task until the definition of done given in the
initial instruction is met: all of the work, not part or most of it. initial instruction is met: all of the work, not part or most of it.
18. For estimates: backing up over 2.5Gbit/s ethernet to an S3 server backed by 18. For estimates: backing up over 2.5Gbit/s ethernet to an S3 server
2000MB/sec SSD takes about 4 seconds per gigabyte. backed by 2000MB/sec SSD takes about 4 seconds per gigabyte.
+36 -134
View File
@@ -1,14 +1,10 @@
# Vaultik Architecture # Vaultik Architecture
This document describes the internal architecture of Vaultik, focusing on the This document describes the internal architecture of Vaultik, focusing on the data model, type instantiation, and the relationships between core modules.
data model, type instantiation, and the relationships between core modules.
## Overview ## Overview
Vaultik is a backup system that uses content-defined chunking for deduplication Vaultik is a backup system that uses content-defined chunking for deduplication and packs chunks into large, compressed, encrypted blobs for efficient cloud storage. The system is built around dependency injection using [uber-go/fx](https://github.com/uber-go/fx).
and packs chunks into large, compressed, encrypted blobs for efficient cloud
storage. The system is built around dependency injection using
[uber-go/fx](https://github.com/uber-go/fx).
## Data Flow ## Data Flow
@@ -57,88 +53,53 @@ The database tracks five primary entities and their relationships:
### Entity Descriptions ### Entity Descriptions
#### File (`database.File`) #### File (`database.File`)
Represents a file, directory, or symlink in the backup system. Stores metadata needed for restoration:
Represents a file, directory, or symlink in the backup system. Stores metadata - Path, source_path (for restore path stripping), mtime
needed for restoration:
- Path, mtime
- Size, mode, ownership (uid, gid) - Size, mode, ownership (uid, gid)
- Symlink target (if applicable) - Symlink target (if applicable)
It also stores `source_path`, the source directory the scan found it under, made
absolute and with symlinks resolved. Restore does not read it.
#### Chunk (`database.Chunk`) #### Chunk (`database.Chunk`)
A content-addressed unit of data. Files are split into variable-size chunks using the FastCDC algorithm:
A content-addressed unit of data. Files are split into variable-size chunks
using the FastCDC algorithm:
- `ChunkHash`: SHA256 hash of chunk content (primary key) - `ChunkHash`: SHA256 hash of chunk content (primary key)
- `Size`: Chunk size in bytes - `Size`: Chunk size in bytes
Chunk sizes vary between `avgChunkSize/4` and `avgChunkSize*4` (2.5MB-40MB for Chunk sizes vary between `avgChunkSize/4` and `avgChunkSize*4` (2.5MB-40MB for the 10MB default average).
the 10MB default average).
#### FileChunk (`database.FileChunk`) #### FileChunk (`database.FileChunk`)
Maps files to their constituent chunks: Maps files to their constituent chunks:
- `FileID`: Reference to the file - `FileID`: Reference to the file
- `Idx`: Position of this chunk within the file (0-indexed) - `Idx`: Position of this chunk within the file (0-indexed)
- `ChunkHash`: Reference to the chunk - `ChunkHash`: Reference to the chunk
#### Blob (`database.Blob`) #### Blob (`database.Blob`)
The final storage unit uploaded to S3. Contains many compressed and encrypted chunks:
The final storage unit uploaded to S3. Contains many compressed and encrypted
chunks:
- `ID`: UUID assigned at creation - `ID`: UUID assigned at creation
- `Hash`: `hex(SHA256(SHA256(uncompressed blob contents)))`, computed before - `Hash`: `hex(SHA256(SHA256(uncompressed blob contents)))`, computed before compression and encryption (see [docs/REPOSTRUCTURE.md](docs/REPOSTRUCTURE.md#blobs-directory-blobs))
compression and encryption (see
[docs/REPOSTRUCTURE.md](REPOSTRUCTURE.md#blobs-directory-blobs))
- `UncompressedSize`: Total raw chunk data before compression - `UncompressedSize`: Total raw chunk data before compression
- `CompressedSize`: Size after zstd compression and age encryption - `CompressedSize`: Size after zstd compression and age encryption
- `CreatedTS`, `FinishedTS`, `UploadedTS`: Lifecycle timestamps - `CreatedTS`, `FinishedTS`, `UploadedTS`: Lifecycle timestamps
Blob creation process: Blob creation process:
1. Chunks are accumulated (up to MaxBlobSize, typically 10GB) 1. Chunks are accumulated (up to MaxBlobSize, typically 10GB)
2. As each chunk is added, its uncompressed bytes are fed to a running SHA-256 2. As each chunk is added, its uncompressed bytes are fed to a running SHA-256
3. Concurrently, the same bytes are compressed with zstd, then encrypted with 3. Concurrently, the same bytes are compressed with zstd, then encrypted with age (recipients configured in config), and streamed to storage
age (recipients configured in config), and written to a temporary file 4. On finalize, the blob's name is the double SHA-256 of the uncompressed contents — `hex(SHA256(SHA256(...)))` — not a hash of the compressed, encrypted bytes
4. On finalize, the blob's name is the double SHA-256 of the uncompressed 5. Uploaded to `blobs/{hash[0:2]}/{hash[2:4]}/{hash}`
contents — `hex(SHA256(SHA256(...)))` — not a hash of the compressed,
encrypted bytes
5. The finished file is uploaded to `blobs/{hash[0:2]}/{hash[2:4]}/{hash}` and
then deleted
A backup needs free temporary space, because each blob is written whole to a
temporary file before it is uploaded (up to about `blob_size_limit`; an rclone
destination that cannot stream uploads needs about twice that) and the metadata
export writes copies of the local index. Temporary files go to `$TMPDIR`
(default `/tmp`); with `TMPDIR` unset, SQLite writes one of those copies to
`/var/tmp`.
#### BlobChunk (`database.BlobChunk`) #### BlobChunk (`database.BlobChunk`)
Maps chunks to their position within blobs: Maps chunks to their position within blobs:
- `BlobID`: Reference to the blob - `BlobID`: Reference to the blob
- `ChunkHash`: Reference to the chunk - `ChunkHash`: Reference to the chunk
- `Offset`: Byte offset within the uncompressed blob - `Offset`: Byte offset within the uncompressed blob
- `Length`: Chunk size - `Length`: Chunk size
#### Snapshot (`database.Snapshot`) #### Snapshot (`database.Snapshot`)
Represents a point-in-time backup: Represents a point-in-time backup:
- `ID`: Format is `{hostname}_{snapshot-name}_{RFC3339}` (e.g. `server1_home_2025-06-01T12:00:00Z`)
- `ID`: Format is `{hostname}_{snapshot-name}_{RFC3339}` (e.g.
`server1_home_2025-06-01T12:00:00Z`)
- Tracks file count, chunk count, blob count, sizes, compression ratio - Tracks file count, chunk count, blob count, sizes, compression ratio
- `CompletedAt`: Null until snapshot finishes successfully - `CompletedAt`: Null until snapshot finishes successfully
#### SnapshotFile / SnapshotBlob #### SnapshotFile / SnapshotBlob
Join tables linking snapshots to their files and blobs. Join tables linking snapshots to their files and blobs.
### Relationship Summary ### Relationship Summary
@@ -175,27 +136,21 @@ fx.New(
### Key Type Instantiation Points ### Key Type Instantiation Points
#### 1. Config (`config.Config`) #### 1. Config (`config.Config`)
- **Created by**: `config.Module` via `config.LoadConfig()` - **Created by**: `config.Module` via `config.LoadConfig()`
- **When**: Application startup (fx DI) - **When**: Application startup (fx DI)
- **Contains**: All configuration from YAML file (S3 credentials, encryption - **Contains**: All configuration from YAML file (S3 credentials, encryption keys, paths, etc.)
keys, paths, etc.)
#### 2. Database (`database.DB`) #### 2. Database (`database.DB`)
- **Created by**: `database.Module` via `database.New()` - **Created by**: `database.Module` via `database.New()`
- **When**: Application startup (fx DI) - **When**: Application startup (fx DI)
- **Contains**: SQLite connection, path reference - **Contains**: SQLite connection, path reference
#### 3. Repositories (`database.Repositories`) #### 3. Repositories (`database.Repositories`)
- **Created by**: `database.Module` via `database.NewRepositories()` - **Created by**: `database.Module` via `database.NewRepositories()`
- **When**: Application startup (fx DI) - **When**: Application startup (fx DI)
- **Contains**: All repository interfaces (Files, Chunks, Blobs, Snapshots, - **Contains**: All repository interfaces (Files, Chunks, Blobs, Snapshots, etc.)
etc.)
#### 4. Vaultik (`vaultik.Vaultik`) #### 4. Vaultik (`vaultik.Vaultik`)
- **Created by**: `vaultik.New(VaultikParams)` - **Created by**: `vaultik.New(VaultikParams)`
- **When**: Application startup (fx DI) - **When**: Application startup (fx DI)
- **Contains**: All dependencies for backup operations - **Contains**: All dependencies for backup operations
@@ -217,13 +172,11 @@ type Vaultik struct {
``` ```
#### 5. SnapshotManager (`snapshot.SnapshotManager`) #### 5. SnapshotManager (`snapshot.SnapshotManager`)
- **Created by**: `snapshot.Module` via `snapshot.NewSnapshotManager()` - **Created by**: `snapshot.Module` via `snapshot.NewSnapshotManager()`
- **When**: Application startup (fx DI) - **When**: Application startup (fx DI)
- **Responsibility**: Creates/completes snapshots, exports metadata to S3 - **Responsibility**: Creates/completes snapshots, exports metadata to S3
#### 6. Scanner (`snapshot.Scanner`) #### 6. Scanner (`snapshot.Scanner`)
- **Created by**: `ScannerFactory(ScannerParams)` - **Created by**: `ScannerFactory(ScannerParams)`
- **When**: Each `CreateSnapshot()` call - **When**: Each `CreateSnapshot()` call
- **Contains**: Chunker, Packer, progress reporter - **Contains**: Chunker, Packer, progress reporter
@@ -237,22 +190,20 @@ scanner := v.ScannerFactory(snapshot.ScannerParams{
``` ```
#### 7. Chunker (`chunker.Chunker`) #### 7. Chunker (`chunker.Chunker`)
- **Created by**: `chunker.NewChunker(avgChunkSize)` - **Created by**: `chunker.NewChunker(avgChunkSize)`
- **When**: Inside `snapshot.NewScanner()` - **When**: Inside `snapshot.NewScanner()`
- **Configuration**: - **Configuration**:
- `avgChunkSize`: From config (default 10MB) - `avgChunkSize`: From config (default 10MB)
- `minChunkSize`: avgChunkSize / 4 - `minChunkSize`: avgChunkSize / 4
- `maxChunkSize`: avgChunkSize \* 4 - `maxChunkSize`: avgChunkSize * 4
#### 8. Packer (`blob.Packer`) #### 8. Packer (`blob.Packer`)
- **Created by**: `blob.NewPacker(PackerConfig)` - **Created by**: `blob.NewPacker(PackerConfig)`
- **When**: Inside `snapshot.NewScanner()` - **When**: Inside `snapshot.NewScanner()`
- **Configuration**: - **Configuration**:
- `MaxBlobSize`: Maximum blob size before finalization (typically 10GB) - `MaxBlobSize`: Maximum blob size before finalization (typically 10GB)
- `CompressionLevel`: zstd level (1-19) - `CompressionLevel`: zstd level (1-19)
- `Recipients`: age public keys for encryption - `Recipients`: age public keys for encryption
```go ```go
// snapshot/scanner.go: NewScanner() // snapshot/scanner.go: NewScanner()
@@ -269,22 +220,17 @@ packer, err := blob.NewPacker(packerCfg)
## Module Responsibilities ## Module Responsibilities
### `internal/cli` ### `internal/cli`
Entry point for fx application. Combines all modules and handles signal interrupts.
Entry point for fx application. Combines all modules and handles signal
interrupts.
Key functions: Key functions:
- `NewApp(AppOptions)` → Creates fx.App with all modules - `NewApp(AppOptions)` → Creates fx.App with all modules
- `RunApp(ctx, app)` → Starts app, handles graceful shutdown - `RunApp(ctx, app)` → Starts app, handles graceful shutdown
- `RunWithApp(ctx, opts)` → Convenience wrapper - `RunWithApp(ctx, opts)` → Convenience wrapper
### `internal/vaultik` ### `internal/vaultik`
Main orchestrator containing all dependencies and command implementations. Main orchestrator containing all dependencies and command implementations.
Key methods: Key methods:
- `New(VaultikParams)` → Constructor (fx DI) - `New(VaultikParams)` → Constructor (fx DI)
- `CreateSnapshot(opts)` → Main backup operation - `CreateSnapshot(opts)` → Main backup operation
- `ListSnapshots(jsonOutput)` → List available snapshots - `ListSnapshots(jsonOutput)` → List available snapshots
@@ -292,34 +238,27 @@ Key methods:
- `PurgeSnapshots(...)` → Remove old snapshots - `PurgeSnapshots(...)` → Remove old snapshots
### `internal/chunker` ### `internal/chunker`
Content-defined chunking using FastCDC algorithm. Content-defined chunking using FastCDC algorithm.
Key types: Key types:
- `Chunk` → Hash, Data, Offset, Size - `Chunk` → Hash, Data, Offset, Size
- `Chunker` → avgChunkSize, minChunkSize, maxChunkSize - `Chunker` → avgChunkSize, minChunkSize, maxChunkSize
Key methods: Key methods:
- `NewChunker(avgChunkSize)` → Constructor - `NewChunker(avgChunkSize)` → Constructor
- `ChunkReaderStreaming(reader, callback)` → Stream chunks with callback - `ChunkReaderStreaming(reader, callback)` → Stream chunks with callback (preferred)
(preferred)
- `ChunkReader(reader)` → Return all chunks at once (memory-intensive) - `ChunkReader(reader)` → Return all chunks at once (memory-intensive)
### `internal/blob` ### `internal/blob`
Blob packing: accumulates chunks, compresses, encrypts, tracks metadata. Blob packing: accumulates chunks, compresses, encrypts, tracks metadata.
Key types: Key types:
- `Packer` → Thread-safe blob accumulator - `Packer` → Thread-safe blob accumulator
- `ChunkRef` → Hash + Data for adding to packer - `ChunkRef` → Hash + Data for adding to packer
- `FinishedBlob` → Completed blob ready for upload - `FinishedBlob` → Completed blob ready for upload
- `BlobWithReader` → FinishedBlob + io.Reader for streaming upload - `BlobWithReader` → FinishedBlob + io.Reader for streaming upload
Key methods: Key methods:
- `NewPacker(PackerConfig)` → Constructor - `NewPacker(PackerConfig)` → Constructor
- `AddChunk(ChunkRef)` → Add chunk to current blob - `AddChunk(ChunkRef)` → Add chunk to current blob
- `FinalizeBlob()` → Compress, encrypt, hash current blob - `FinalizeBlob()` → Compress, encrypt, hash current blob
@@ -329,48 +268,35 @@ Key methods:
### `internal/snapshot` ### `internal/snapshot`
#### Scanner #### Scanner
Orchestrates the backup process for a directory. Orchestrates the backup process for a directory.
Key methods: Key methods:
- `NewScanner(ScannerConfig)` → Constructor (creates Chunker + Packer) - `NewScanner(ScannerConfig)` → Constructor (creates Chunker + Packer)
- `Scan(ctx, path, snapshotID)` → Main scan operation - `Scan(ctx, path, snapshotID)` → Main scan operation
Scan phases: Scan phases:
1. **Phase 0**: Detect deleted files from previous snapshots
1. **Phase 1**: Walk directory, identify files needing processing 2. **Phase 1**: Walk directory, identify files needing processing
2. **Phase 1b**: Count as deleted the files that the previous snapshot of the
same name lists, the walk did not find, and are gone from disk; a file that
is excluded, or inside an excluded directory, is not counted
3. **Phase 2**: Process files (chunk → pack → upload) 3. **Phase 2**: Process files (chunk → pack → upload)
#### SnapshotManager #### SnapshotManager
Manages snapshot lifecycle and metadata export. Manages snapshot lifecycle and metadata export.
Key methods: Key methods:
- `CreateSnapshot(ctx, hostname, version, commit)` → Create snapshot record - `CreateSnapshot(ctx, hostname, version, commit)` → Create snapshot record
- `PopulateSnapshotBlobs(ctx, snapshotID)` → Record every blob the snapshot - `PopulateSnapshotBlobs(ctx, snapshotID)` → Record every blob the snapshot references
references
- `ExportSnapshotMetadata(ctx, dbPath, snapshotID)` → Export to S3 - `ExportSnapshotMetadata(ctx, dbPath, snapshotID)` → Export to S3
- `MarkSnapshotComplete(ctx, snapshotID)` → Record completion, only after a - `MarkSnapshotComplete(ctx, snapshotID)` → Record completion, only after a successful export
successful export - `CompleteSnapshot(ctx, snapshotID)` → Convenience: populate blobs, then mark complete (no export between)
- `CompleteSnapshot(ctx, snapshotID)` → Convenience: populate blobs, then mark
complete (no export between)
### `internal/database` ### `internal/database`
SQLite database for local index. Single-writer mode for thread safety. SQLite database for local index. Single-writer mode for thread safety.
Key types: Key types:
- `DB` → Database connection wrapper - `DB` → Database connection wrapper
- `Repositories` → Collection of all repository interfaces - `Repositories` → Collection of all repository interfaces
Repository interfaces: Repository interfaces:
- `FilesRepository` → CRUD for File records - `FilesRepository` → CRUD for File records
- `ChunksRepository` → CRUD for Chunk records - `ChunksRepository` → CRUD for Chunk records
- `BlobsRepository` → CRUD for Blob records - `BlobsRepository` → CRUD for Blob records
@@ -381,8 +307,6 @@ Repository interfaces:
``` ```
CreateSnapshot(opts) CreateSnapshot(opts)
│
├─► markDestination() // Check the marker (see Storage Layout in S3), then write it
│ │
├─► PruneDatabase() // Critical: avoid dedup errors ├─► PruneDatabase() // Critical: avoid dedup errors
│ │
@@ -392,13 +316,13 @@ CreateSnapshot(opts)
│ │ │ │
│ ├─► scanner.Scan(ctx, path, snapshotID) │ ├─► scanner.Scan(ctx, path, snapshotID)
│ │ │ │ │ │
│ │ ├─► Phase 0: detectDeletedFiles()
│ │ │
│ │ ├─► Phase 1: scanPhase() │ │ ├─► Phase 1: scanPhase()
│ │ │ Walk directory │ │ │ Walk directory
│ │ │ Check file metadata changes │ │ │ Check file metadata changes
│ │ │ Build list of files to process │ │ │ Build list of files to process
│ │ │ │ │ │
│ │ ├─► Phase 1b: detectDeletedFiles()
│ │ │
│ │ └─► Phase 2: processPhase() │ │ └─► Phase 2: processPhase()
│ │ For each file: │ │ For each file:
│ │ chunker.ChunkReaderStreaming() │ │ chunker.ChunkReaderStreaming()
@@ -411,10 +335,10 @@ CreateSnapshot(opts)
│ │ │ │
│ └─► Accumulate statistics │ └─► Accumulate statistics
│ │
├─► SnapshotManager.PopulateSnapshotBlobs() // record referenced blobs
│
├─► SnapshotManager.UpdateSnapshotStatsExtended() ├─► SnapshotManager.UpdateSnapshotStatsExtended()
│ │
├─► SnapshotManager.PopulateSnapshotBlobs() // record referenced blobs
│
├─► SnapshotManager.ExportSnapshotMetadata() ├─► SnapshotManager.ExportSnapshotMetadata()
│ │ │ │
│ ├─► Copy database to temp file │ ├─► Copy database to temp file
@@ -429,23 +353,16 @@ CreateSnapshot(opts)
## Deduplication Strategy ## Deduplication Strategy
1. **File-level**: Files and symlinks unchanged since last backup are skipped 1. **File-level**: Files unchanged since last backup are skipped (metadata comparison: size, mtime, mode, uid, gid), unless the file lists a chunk that no uploaded blob holds; such a file is re-chunked
(metadata comparison: size, mtime, mode, uid, gid, and a symlink's target),
unless the file lists a chunk that no uploaded blob holds; such a file is
re-chunked
2. **Chunk-level**: Chunks are content-addressed by SHA256 hash. If a chunk hash 2. **Chunk-level**: Chunks are content-addressed by SHA256 hash. If a chunk hash already exists in the database, the chunk data is not re-uploaded.
already exists in the database, the chunk data is not re-uploaded.
3. **Blob-level**: Blobs contain only unique chunks. Duplicate chunks within a 3. **Blob-level**: Blobs contain only unique chunks. Duplicate chunks within a blob are skipped.
blob are skipped.
## Storage Layout in S3 ## Storage Layout in S3
``` ```
bucket/ bucket/
├── vaultik-destination.txt # Marker written by every backup
│
├── blobs/ ├── blobs/
│ └── {hash[0:2]}/ │ └── {hash[0:2]}/
│ └── {hash[2:4]}/ │ └── {hash[2:4]}/
@@ -457,30 +374,15 @@ bucket/
└── manifest.json.zst # Blob list (for pruning/verification) └── manifest.json.zst # Blob list (for pruning/verification)
``` ```
A destination that answers a look-up of `vaultik-destination.txt` with not found
is treated as not present while the local index holds snapshots stored there
(`checkDestinationMarker` in `internal/vaultik/destination_marker.go`):
`snapshot create` refuses to write to it, `prune`, `snapshot purge` and
`remote nuke` fail, and `snapshot list` and `snapshot remove` behave as for a
destination that cannot be listed. This keeps those commands from taking an
unplugged volume's empty mount point for a destination whose snapshots are all
gone. When the look-up fails for any reason other than not found, for example
when S3 refuses it to credentials that allow only PUT, the check is skipped, so
a host with such credentials does not notice an emptied destination; see
[docs/REPOSTRUCTURE.md](REPOSTRUCTURE.md#marker-file-vaultik-destinationtxt).
The `file://` backend never creates its destination directory, so a write to a
missing one fails.
The `{remote-key}` directory name is a one-way double SHA-256 hash of the human The `{remote-key}` directory name is a one-way double SHA-256 hash of the human
snapshot ID, so the human ID (hostname, snapshot name, timestamp) is never snapshot ID, so the human ID (hostname, snapshot name, timestamp) is never
written to the store as a directory name. See written to the store as a directory name. See
[docs/REPOSTRUCTURE.md](REPOSTRUCTURE.md#remote-key-derivation) for the [docs/REPOSTRUCTURE.md](docs/REPOSTRUCTURE.md#remote-key-derivation) for the
derivation and a worked example. derivation and a worked example.
## Thread Safety ## Thread Safety
- `Packer`: Thread-safe via mutex. Multiple goroutines can call `AddChunk()`. - `Packer`: Thread-safe via mutex. Multiple goroutines can call `AddChunk()`.
- `Scanner`: Uses `packerMu` mutex to coordinate blob finalization. - `Scanner`: Uses `packerMu` mutex to coordinate blob finalization.
- `Database`: Single-writer mode (`MaxOpenConns=1`) ensures SQLite thread - `Database`: Single-writer mode (`MaxOpenConns=1`) ensures SQLite thread safety.
safety.
- `Repositories.WithTx()`: Handles transaction lifecycle automatically. - `Repositories.WithTx()`: Handles transaction lifecycle automatically.
+3 -24
View File
@@ -5,16 +5,7 @@
FROM golangci/golangci-lint:v2.14.0@sha256:ad862ba6b3798cbe0fd9fd7408d498fd74fbd2623a92406b2fd3898faf0bf98f AS lint FROM golangci/golangci-lint:v2.14.0@sha256:ad862ba6b3798cbe0fd9fd7408d498fd74fbd2623a92406b2fd3898faf0bf98f AS lint
WORKDIR /src WORKDIR /src
COPY go.mod go.sum ./ COPY go.mod go.sum ./
# Without the time limit a stalled connection to the module proxy holds RUN go mod download
# this step, and every build on the host sharing it, until the kernel
# drops the connection, which can take an hour. The limit is well above
# the three minutes a working download can take on a busy build host.
RUN for attempt in 1 2 3; do \
timeout 300 go mod download && exit 0; \
echo "go mod download attempt $attempt failed or ran over 300s" >&2; \
done; \
echo "module download failed: giving up after 3 attempts" >&2; \
exit 1
COPY . . COPY . .
# `golangci-lint run` silently ignores an unknown top-level key in # `golangci-lint run` silently ignores an unknown top-level key in
# .golangci.yml, such as a misspelt `linters:`; `config verify` fails on it. # .golangci.yml, such as a misspelt `linters:`; `config verify` fails on it.
@@ -27,13 +18,7 @@ RUN golangci-lint run --config .golangci.yml ./...
FROM golang:1.26.1@sha256:cd78d88e00afadbedd272f977d375a6247455f3a4b1178f8ae8bbcb201743a8a AS test FROM golang:1.26.1@sha256:cd78d88e00afadbedd272f977d375a6247455f3a4b1178f8ae8bbcb201743a8a AS test
WORKDIR /src WORKDIR /src
COPY go.mod go.sum ./ COPY go.mod go.sum ./
# Limited and retried as in the lint phase above. RUN go mod download
RUN for attempt in 1 2 3; do \
timeout 300 go mod download && exit 0; \
echo "go mod download attempt $attempt failed or ran over 300s" >&2; \
done; \
echo "module download failed: giving up after 3 attempts" >&2; \
exit 1
COPY . . COPY . .
RUN go test -timeout 90s -race -cover ./... || \ RUN go test -timeout 90s -race -cover ./... || \
{ echo "--- Rerunning with -v for details ---"; \ { echo "--- Rerunning with -v for details ---"; \
@@ -51,13 +36,7 @@ RUN apk add --no-cache git
RUN git config --system --add safe.directory /src RUN git config --system --add safe.directory /src
WORKDIR /src WORKDIR /src
COPY go.mod go.sum ./ COPY go.mod go.sum ./
# Limited and retried as in the lint phase above. RUN go mod download
RUN for attempt in 1 2 3; do \
timeout 300 go mod download && exit 0; \
echo "go mod download attempt $attempt failed or ran over 300s" >&2; \
done; \
echo "module download failed: giving up after 3 attempts" >&2; \
exit 1
COPY . . COPY . .
# The VERSION build arg when one is given, otherwise # The VERSION build arg when one is given, otherwise
+523 -701
View File
File diff suppressed because it is too large. Load diff
+791
View File
@@ -0,0 +1,791 @@
# Workflow
* branch (from `main`)
* do the work in Next Step
* move Next Step to the top of Completed Steps
* move the top item of Future Steps into Next Step
* commit (`TODO.md` changes in the same commit as the work)
* merge to `main` if the branch is not protected, otherwise open a PR
* push
# Status
pre-1.0
# Next Step
The 1.0 work is complete on `next`: the scope settled on
[issue #125](https://git.eeqj.de/sneak/vaultik/issues/125) was the work
already planned for 1.0, and all of it has landed. The mechanism to cut
the tag exists and is exercised; what is left is merging `next` to
`main` and tagging, both the owner's.
# Completed Steps
- 2026-10-06: Made `s3://bucket/prefix` and `s3://bucket/prefix/` the same
destination ([issue #222](https://git.eeqj.de/sneak/vaultik/issues/222)).
The S3 client put the prefix directly in front of each key, so a prefix
without a trailing slash stored `prefixblobs/...`. A non-empty prefix is
now joined to every key with one `/`, giving the README's
`<bucket>/<prefix>/blobs/...` layout. The `s3.prefix` config setting goes
through the same client and gets the same join.
- 2026-10-06: Made restore apply owners, modes and times in an order
that keeps them
([issue #219](https://git.eeqj.de/sneak/vaultik/issues/219)). A
directory got its stored mode and mtime before its contents were
written, so a read-only directory came back without its files and a
non-empty one carried the time of the restore. Directories are now
created owner-only and get their stored owner, mode and mtime once the
restore loop is done, each before its parent. A file's mode is applied
after its chown, which on Linux clears setuid and setgid, and a
symlink gets its stored owner (as root) and mtime on the link itself.
- 2026-10-06: Made `go.mod` what `go mod tidy` writes, so the
pre-commit hook no longer stops every commit
([issue #246](https://git.eeqj.de/sneak/vaultik/issues/246)). A test
in `internal/cli` imports `github.com/spf13/pflag` directly, but
`go.mod` still marked it `// indirect`, and `script/precommit` fails
whenever the tidy changes `go.mod`. It is now in the direct `require`
block.
- 2026-10-06: Made the README's steps for restoring on another machine
work ([issue #221](https://git.eeqj.de/sneak/vaultik/issues/221)).
`config init` wrote a placeholder recipient that `config.Load`
rejects, so every command on the new machine failed before reaching
the store. The file now has an empty `age_recipients` list,
`config.Load` accepts an empty list, and `snapshot create` refuses to
run without a recipient.
- 2026-10-06: Made `snapshot restore --skip-errors` skip the files that
need a blob it cannot download
([issue #218](https://git.eeqj.de/sneak/vaultik/issues/218)). A missing
or damaged blob ended the restore even with the flag, after restoring
whichever files happened to come first. Every file that needs such a
blob is now reported as failed, the rest are restored, and the command
still exits non-zero. Without the flag the blob error still aborts.
- 2026-10-06: Re-vendored the canonical files from `sneak/prompts` at
`dd4027b` ([issue #213](https://git.eeqj.de/sneak/vaultik/issues/213)).
Linting and testing are now the `lint` and `test` phases of the
`Dockerfile`, and the build stage depends on both. `Dockerfile.lint`,
`CHECK_EPOCH` and the tests that checked them are gone; every
`docker build` in `script/` passes `--no-cache` instead. golangci-lint
is v2.14.0, with its new findings fixed in the code, and the rules in
`CLAUDE.md` now live in `AGENTS.md`.
- 2026-10-06: Made the local index actually run in WAL mode with a busy
timeout ([issue #217](https://git.eeqj.de/sneak/vaultik/issues/217)).
The connection settings were written in a form the SQLite driver
ignores, so the index ran without either and `snapshot list` or `info`
during a backup could make the backup's next write fail with
`database is locked`. They are now `_pragma=` parameters, and the
metadata export copies the open index with `VACUUM INTO`, because a
copy of the file alone misses rows still in the `-wal` file.
- 2026-10-06: Made a backup record the real uid and gid of files,
directories and symlinks
([issue #216](https://git.eeqj.de/sneak/vaultik/issues/216)). The
scanner asked the stat result for `Uid()` and `Gid()` methods, which
`*syscall.Stat_t` does not have, so every entry was stored as `0:0`
and a restore as root gave every file to root. It now reads the
`Uid` and `Gid` fields of `*syscall.Stat_t`.
- 2026-10-06: Made a `file://` destination whose directory is missing
count as one that cannot be listed
([issue #220](https://git.eeqj.de/sneak/vaultik/issues/220)). The file
backend listed a missing directory as an empty store, so with the
quickstart's USB stick unplugged `snapshot list` reported every local
snapshot as missing from the store, `snapshot remove` claimed to have
removed metadata it never reached, and `prune` dropped every local
snapshot record. Listing a missing destination directory is now an
error; a first backup still creates the directory.
- 2026-10-06: Made `--older-than` and `--keep-newer-than` reject a
duration with characters outside its number-and-unit parts
([issue #215](https://git.eeqj.de/sneak/vaultik/issues/215)). The
parser picked out the parts it recognised and skipped the rest, so
`1.0y` became zero and `--prune --keep-newer-than 1.0y` deleted every
snapshot of the backed-up names, the new one included. `1.0y`,
`1,5y`, `30 days`, `x7d` and a bare `0` are now errors; decimals still
work in Go units such as `1.5h`.
- 2026-10-06: Made a backup re-chunk a known file that lists a chunk no
uploaded blob holds
([issue #214](https://git.eeqj.de/sneak/vaultik/issues/214)). File
rows are shared by every snapshot and updated in place, so removing or
pruning the only snapshot that referenced a changed file's current
blob left an older snapshot keeping a row that matched the disk while
no blob held its chunks. The next backup skipped the file and
completed a snapshot that could not restore it.
- 2026-09-22: Routed the last direct-to-stdout command output through
`internal/ui`
([issue #149](https://git.eeqj.de/sneak/vaultik/issues/149)). The
`version`, `info`, `remote info`, `config`, and `database delete`
commands wrote plain text straight to stdout, so they were unstyled and
ignored `--quiet`. Output now falls in two buckets, both governed by
`internal/ui`: status lines and confirmations go through its message
methods (styled, and `--quiet` silences them), while the data a command
exists to produce — the reports, the `snapshot list` table, `config get`
values, and the `--json` documents — is written plain. `--quiet`
silences the human reports and tables but never the `config get` value
or the `--json` documents, which a script depends on, and the
`database delete` confirmation prompt is always shown. The README
output-style section now states this rule.
- 2026-09-22: Validated blob hashes, offsets and lengths read back from
the destination before using them
([issue #155](https://git.eeqj.de/sneak/vaultik/issues/155)). A blob
hash taken from the downloaded database or the store listing was
trusted unchecked, so a hostile remote could drive a decrypted blob to
be written outside the cache directory (a hash like `aa/../../etc`) or
crash a command with a short or negative value. `blobDiskCache.path`
now refuses any key containing a path separator, and `ReadAt` rejects a
negative offset or length and bounds with `length > size-offset` so a
sum cannot overflow past the check. A new `isBlobHash` helper (a plain
function, not a method — the packer stores `temp-placeholder-{uuid}` as
a hash) gates `FetchBlob`, shallow and deep verify; the `blobs/` and
`metadata/` listings skip a non-conforming name with a warning; and
short-hash prefixes in log and error text go through a `shortHash`
helper that cannot panic. `verify`'s chunk reader also rejects a
negative `blob_chunks` length and streams the chunk instead of
allocating a database-supplied size. `restore.go` and
`internal/database` were left untouched to avoid colliding with the
in-flight [issue #156](https://git.eeqj.de/sneak/vaultik/issues/156)
work; the cache-path and `FetchBlob` guards already stop the unsafe
write and fetch, so restore's own `buildBlobIndexes` early check is
deferred as fail-fast defense in depth.
- 2026-09-21: Stopped an interrupted blob upload from making a later
backup deduplicate against data that was never stored
([issue #148](https://git.eeqj.de/sneak/vaultik/issues/148)). The
packer commits a blob's `chunks`, `blob_chunks`, and `blobs` rows
before the upload is attempted, so a failed upload left chunk rows
behind and the next run skipped re-uploading them, producing a
snapshot that reported success but could not be restored. A run now
deduplicates only against chunks held by a blob whose `uploaded_ts` is
set, and at startup drops any un-uploaded blob rows (and the chunks
they orphan) so the affected data is re-chunked and re-uploaded. Blobs
recorded with no remote backend are marked uploaded so this invariant
holds uniformly.
- 2026-09-22: Made restore refuse any snapshot path that would write
outside the target directory
([issue #154](https://git.eeqj.de/sneak/vaultik/issues/154)).
`restoreFile` and `verifyRestoredFiles` joined the stored path onto the
target with no containment check, so a `..` segment or an absolute path
escaped the target and a restored symlink could redirect a later child
write anywhere on disk. Every stored path is now rejected unless
`filepath.IsLocal` accepts it with the leading separator removed, and
each existing ancestor directory below the target is `Lstat`ed to refuse
descending through a symlink; honest symlinks pointing outside the tree
are still written verbatim. age decryption proves a snapshot is
readable, not honest, and restore usually runs as root.
- 2026-09-21: Stopped `--json` from silencing stderr diagnostics
([issue #112](https://git.eeqj.de/sneak/vaultik/issues/112)). `--json`
used to be folded into `Quiet`, which pinned the log level to `WARN`,
so `prune --json` gave a machine consumer no record of the local index
rows it deleted even under `--verbose`. `--json` now quiets only the
stdout UI (the JSON document must stay clean, per
[issue #108](https://git.eeqj.de/sneak/vaultik/issues/108)); the stderr
log level follows `--verbose`/`--debug` again. The coupling was
removed the same way for `snapshot verify`, `snapshot remove`, and
`remote info`, which carried it for the same outdated reason.
- 2026-09-21: Stopped `prune` from reporting a failed row count as 0
([issue #96](https://git.eeqj.de/sneak/vaultik/issues/96)). The seven
`getTableCount` reads in `PruneDatabase` discarded their error, so a
query that could not run became a plausible `0` and the before/after
delta computed from it looked like real work. Each read now logs at
warn on failure and renders as `unknown`, never `0`, so an empty table
is distinguishable from one that could not be queried. The counts have
no `--json` representation — under `--json` the summary is suppressed
entirely — so nothing there can show a false `0`.
- 2026-09-21: Made the s3 storage backend report a missing object as
`storage.ErrNotFound`, like the `file` and `rclone` backends and as the
`Storer` interface documents. `S3Storer.Get` and `Stat` returned the raw
AWS SDK error, so `errors.Is(err, storage.ErrNotFound)` was false on s3
and callers branched differently per backend. Added a small `s3.IsNotFound`
helper (reused by `HeadObject`) and a test that a missing key maps to
`ErrNotFound`
([issue #129](https://git.eeqj.de/sneak/vaultik/issues/129)).
- 2026-09-21: Fixed `verify --deep` reporting healthy snapshots as
corrupt. Its final blob-integrity check hashed the encrypted
downloaded bytes with a single SHA256 and compared that to the blob
ID, which is the double SHA256 of the plaintext, so the two could
never match. It now hashes the decompressed plaintext and compares the
double SHA256. Added a test that backs up a real snapshot, deep-verifies
it, then flips a byte in one stored blob and confirms deep verification
then fails
([issue #131](https://git.eeqj.de/sneak/vaultik/issues/131)).
- 2026-09-21: Made `snapshot create` VACUUM the per-snapshot metadata
database through the `modernc.org/sqlite` driver instead of shelling
out to the external `sqlite` command-line binary (issue #120). A
backup no longer needs that binary on `PATH`, so `make check` passes
on a stock `go install` host; `script/bootstrap` and the `Dockerfile`
(both the test-build and the shipped runtime stage) no longer install
it, and a new test asserts the uploaded database keeps no pages from
deleted rows. Dropped the now-false note on the 2026-08-07 entry below
that said bootstrap installs it.
- 2026-09-21: Made `.gitea/workflows/check.yml` run on pushes to `main`
and `next` and on pull requests against either, so unit PRs (whose
base is `next`) and `next` itself get a CI run instead of relying on a
local `make check`
([issue #122](https://git.eeqj.de/sneak/vaultik/issues/122)).
- 2026-09-21: Hash-verified the Go toolchain in the release workflow
([issue #105](https://git.eeqj.de/sneak/vaultik/issues/105)). New
`script/install-go` downloads the exact `go.dev` archive for `go.mod`'s
`go` directive and refuses it unless its sha256 matches a value
committed in the script; `.gitea/workflows/release.yml` calls it
instead of `actions/setup-go`, which verified the downloaded toolchain
against nothing in the repo. `GOTOOLCHAIN: local` on the release step
keeps that exact compiler from auto-switching. Bumping Go now touches
`go.mod`, the checksum, and the `Dockerfile` `golang` digest together.
- 2026-09-21: Collapsed the two duration parsers into one and fixed the
`--older-than` months example
([issue #123](https://git.eeqj.de/sneak/vaultik/issues/123)). Two
functions named `parseDuration` existed with different grammars;
`snapshot purge --older-than` and `--keep-newer-than` both already went
through the one in `internal/vaultik`, while the richer copy in
`internal/cli/duration.go` was reachable only from its own test. Kept
the live-path parser and deleted the unused one, so no flag's accepted
grammar changes. The trap the issue was filed over: `README.md`
documented `6m` as the months example for `--older-than`, but `m` is
minutes, so the documented command deleted every snapshot older than
six minutes on a destructive flag. Corrected the doc to `6mo` and put
both flags' help text on one example list that states `m` is minutes
and `mo` is months. The surviving parser now rejects negatives, which
it previously accepted (`-5h`) or silently made positive (`-5d`).
Table-driven tests cover every unit, `6m` as six minutes, `6mo` as 180
days, and rejection of a bare number, an unknown unit, and a negative.
- 2026-08-10: Moved every lint run into its own container, as a build
step ([issue #113](https://git.eeqj.de/sneak/vaultik/issues/113)).
New root `Dockerfile.lint`, built by `script/lint`, runs
`golangci-lint run --config .golangci.yml ./...` as a `RUN`
instruction in the digest-pinned `golangci/golangci-lint` image: a
successful build of that file *is* a clean lint, and it works even
where the daemon is remote and bind mounts are impossible. That
`FROM` line is now the only pin of the linter version in the repo.
This supersedes the per-worktree cache isolation landed for
[issue #99](https://git.eeqj.de/sneak/vaultik/issues/99). Isolation
fixed cross-worktree contamination but not lock contention — two
concurrent runs with entirely separate cache directories still
collided. A container per run has its own cache and its own lock, so
the whole class is gone, and with it the per-worktree cache
machinery, the lock-retry loop, and `script/lint-audit`, which
existed to catch replayed findings from a cache that no longer
exists. The host lint path went too: no escape hatch, no
`VAULTIK_LINT_IN_CONTAINER`, no version detection. Nothing lints on
the host at any version.
A cached build lints nothing, so the same `CHECK_EPOCH` mechanism the
product `Dockerfile` already used is what makes the green mean
something: `ARG CHECK_EPOCH` with no default below the module layers,
a `RUN [ -n "$CHECK_EPOCH" ] || exit 1` guard, the value expanded
into each check command, and a fresh `$(date +%s%N)$$` per invocation
computed as a bare assignment. `cmd/vaultik/lintdocker_test.go`
parses both Dockerfiles and both scripts and fails if any part of
that is dropped, because every way of losing it is silent. No test
asserts that no script runs the host linter: `script/lint` is the one
lint entry point and runs `golangci-lint` only inside the container,
and keeping it that way is a review matter, not something a test
proves.
The product `Dockerfile` lost its lint stage rather than gaining a
second linter pin: `make lint` is now `docker build`, so the stage
would have been docker-in-docker with no daemon, and calling
`golangci-lint` directly there would have restored the two-pins drift
of [issue #78](https://git.eeqj.de/sneak/vaultik/issues/78).
`make fmt-check` moved beside `make test` in the builder stage, and
`script/cibuild` now builds `Dockerfile.lint` and then `Dockerfile`,
each with its own fresh epoch. Consequence, stated rather than left
to be found: `script/docker` builds the product image only and no
longer lints; the gates are `script/check` and `script/cibuild`.
`golangci-lint config verify` runs as its own epoch-keyed layer,
above the lint. `golangci-lint run` rejects a config it cannot parse
but silently ignores an unknown top-level *key*: renaming `linters:`
to `linterz:` discarded `default: all` and every threshold and still
exited 0 on a tree the real config fails. `config verify` catches
that, and it does so with the network off at this pin — checked under
`docker run --network none`, not assumed. An earlier revision omitted
it on the claim that it fetches its schema over live HTTPS; that
claim was false at v2.12.2.
`script/lint-fix` is kept, reimplemented as a
bind-mounted `docker run` against the image parsed out of
`Dockerfile.lint` — it cannot be a build step, because fixes have to
land in the worktree — and marked in its header as a developer
convenience that no gate reads.
- 2026-08-09: Finished the `--json` stdout contract and gave `make build`
a rule ([issue #108](https://git.eeqj.de/sneak/vaultik/issues/108),
[issue #110](https://git.eeqj.de/sneak/vaultik/issues/110)). Two
unrelated defects of the same shape — a command reporting something it
did not do — landed together because both are small.
`CleanupLocalSnapshots` wrote three prose lines to stdout with no
`--json` awareness, covering every branch of the function, so no input
avoided them and `vaultik prune --json | jq` failed even after
[issue #106](https://git.eeqj.de/sneak/vaultik/issues/106) removed the
banner. `-q` never helped either: `printlnStdout` and `stdoutf` write
straight to `Vaultik.Stdout` and never consult `Vaultik.UI`, which is
what `SetQuiet` affects. The issue offered three fixes and asked for a
decision. Taken: thread `*PruneOptions` into the function and gate each
write on `!opts.JSON`, matching `PruneBlobs` (its sibling phase, which
already takes the same struct), `RemoveSnapshot` and `remote info`, so
the package has one pattern rather than two. Rejected: moving the lines
to `log.Info`, because the logger's default level is `slog.LevelWarn`,
so that would not relocate them to stderr — it would delete them from a
plain `vaultik prune`, and the removal of rows from the local index is
not something to narrate only under `--verbose`. Also rejected: putting
the stale-record count into `PruneBlobsResult`, whose every field is
blob-scoped and which is produced by the later phase; a prune document
covering both phases is a reasonable thing to want, but it is a schema
design question and not a stream-hygiene fix. The narration is
duplicated as `log.Info` records, which `PruneBlobs` already does
alongside its own prints, so the events survive on stderr for anyone
running `--verbose`.
`make build` printed "Nothing to be done for 'build'" and exited 0
without producing a binary: `build` was listed in `.PHONY` with no
`build:` rule anywhere, and declaring a name phony is exactly what
converts make's "No rule to make target" error into a silent success.
Fixed with `build: vaultik`, keeping `vaultik:` as the file rule. The
audit the issue asked for covers all 19 `.PHONY` names; `build` was the
only one without a rule, and `vaultik` is correctly absent from
`.PHONY`, being a real file target.
Tests, each verified to fail with the fix reverted rather than assumed
to: `CleanupLocalSnapshots` leaves stdout untouched under `--json` in
all three branches (stale records, none, empty index) and still emits
every line without it, so the guard cannot be satisfied by deleting the
output; `prune --json` run end to end through `Entry`, cobra and fx
over the process's real stdout descriptor against a `file://` store,
asserting exactly one JSON document, in both the stale and non-stale
branches; and a parse of the `Makefile` asserting every `.PHONY` name
has a rule and that `build` reaches the rule that produces the binary,
which keeps the audit true for names added later. That last one is a
parse rather than an invocation of `make`, since `make test` is what
runs it and shelling back into `make build` would nest a build inside
the test run. The property a parse cannot establish — that the recipe
still fails when the build fails — was verified by hand against a
deliberately broken tree: `make build` exits 2 and produces nothing.
`cmd/vaultik` gains its first test file, so `make test` now reports 16
packages `ok` where it reported 15.
- 2026-08-09: Stopped the startup banner from contaminating `--json`
documents ([issue #106](https://git.eeqj.de/sneak/vaultik/issues/106)).
`Entry` writes the banner to stdout before cobra parses anything, and
the flag scan that suppresses it knew `--quiet`, `-q` and `--cron` but
not `--json`, so every `--json` document arrived behind two lines of
prose and a blank line, and `vaultik snapshot list --json | jq` failed.
With the logger already on stderr from
[issue #82](https://git.eeqj.de/sneak/vaultik/issues/82), this was the
last writer that could put something on stdout that the caller did not
ask for. The design question the issue raised — extend the raw-argv
scan, or move the banner after parsing — is answered in favour of the
scan: the banner is printed first deliberately, so that it still
appears when cobra rejects the arguments and on `--help`, and after
parsing there is no single place that covers those paths. The stated
cost of the scan, that `--json` is a subcommand flag matched anywhere
in the vector, is a cost `--cron` already carries — it exists only on
`snapshot create` — so this adds an instance of an accepted
imprecision rather than a new kind, and the two error directions are
not symmetric: a false positive loses a decorative banner, a false
negative corrupts a document. Regression tests at the CLI layer, where
`internal/vaultik`'s existing guard cannot reach: one runs `Entry`
itself over the process's real stdout descriptor, through cobra and fx
to the document, made hermetic by `file://` storage; a second covers
the argument vectors of all five `--json` commands; a third asserts the
banner is still printed without a suppressing flag, so the first
cannot be satisfied by deleting the banner. Also corrected `AGENTS.md`
policy 9, which still keyed the structured-log format on stdout's
TTY-ness after #82 moved that decision to stderr — a rules file that
misdescribes the code misleads exactly the readers who trust it most.
Two smaller findings from the same review: `bytesAttrKey`'s
human-readable byte formatting silently stopped applying under an open
group, because the key reaching the comparison is group-qualified
(`transfer.bytes`), now matched on its final segment and tested both
ways; and `listEnv.stderr` in `snapshot_list_test.go`, assigned but
never read since those tests began capturing the process's stderr, is
removed. `Vaultik.Stderr` is kept — nothing writes to it today, which
its comment now says outright.
- 2026-08-09: Moved the logger to stderr and fixed `TTYHandler`'s
discarded attributes
([issue #82](https://git.eeqj.de/sneak/vaultik/issues/82),
[issue #97](https://git.eeqj.de/sneak/vaultik/issues/97)). Two defects
in `internal/log`, fixed together because both live in the handler
construction path. The first: both handlers were built over
`os.Stdout`, and `WARN`/`ERROR` are never suppressed, so a config file
with group- or world-readable permissions was enough to put a log
record inside a `--json` document and break `jq`. Diagnostics now go
to stderr, and the TTY/JSON format choice follows stderr rather than
stdout — testing the wrong stream would colorize records on a
redirected stderr whenever stdout happened to be a terminal. This is
user-visible: `--verbose` and `--debug` output moves to stderr too,
which is documented in `README.md` under "stdout and stderr". It also
let the local workaround in `internal/vaultik/snapshot_list.go` go:
`warnWhileListing` had been hand-rolling structured-log formatting to
reach a non-stdout writer, and the `jsonOutput` parameter threaded
through the remote-listing helpers existed only to choose between the
two writers. The collect-then-emit machinery around `listingWarning`
stays, but on its remaining merit — warnings emitted in key order
after `group.Wait()` are deterministic run to run, where emitting from
the fetch workers would order them by network timing. The second
defect: `TTYHandler.WithAttrs` and `WithGroup` discarded their
arguments and returned the receiver while their doc comments claimed
otherwise, so `log.With` attributes vanished on a terminal and
appeared correctly in CI — failing precisely when someone is debugging
interactively. Both now return a new handler (the receiver is never
written to, since `slog` permits concurrent derivation), attributes
persist across records, and grouping is implemented as dotted key
prefixes, which is the only honest rendering for a format with nowhere
to nest. New tests cover both, including one that feeds the same
derivation chain to the TTY and JSON handlers and compares the
attribute sets, so the two paths cannot drift apart again. Found and
filed while verifying: the startup banner is written to stdout and
`--json` does not suppress it
([issue #106](https://git.eeqj.de/sneak/vaultik/issues/106)), which is
a separate writer on a separate path and the remaining source of
stdout contamination.
- 2026-08-09: Made the tagged-release path actually work on Gitea
([issue #65](https://git.eeqj.de/sneak/vaultik/issues/65)). Three
independent blockers, one of which was the whole
release: `.goreleaser.yaml` had no `gitea_urls:` block, so goreleaser
defaulted to the GitHub API and a `goreleaser release` from this repo
would have failed or published where nobody is looking. It now points
at `https://git.eeqj.de/api/v1`. The version is the second: it was a
hardcoded `VERSION := 1.0.0-rc.1` in the `Makefile`, so every local
build claimed to be a release candidate that had never been tagged and
did not exist, while `git tag -l` was empty and `internal/globals`
defaulted to `dev`. Version now comes from git via the new
`script/version` — the exact tag with a leading `v` stripped (so a
`make` build and a goreleaser build of one commit report the same
string, and it matches the archive names), otherwise `dev-<12-char
sha>`, with `-dirty` appended in either case when tracked files are
modified. Untracked files are deliberately not counted, matching
`git describe --dirty`. The same honesty was owed by the snapshot
path: `snapshot.version_template` was `{{ incpatch .Version }}-next`,
which manufactures a release number from the last tag and, with no
tags at all, from goreleaser's fabricated `v0.0.0`; it now emits the
same `dev-<sha>`. The one non-obvious consequence is that
`internal/cli/version.go` gated its "this is a development build"
notice on the version being exactly `dev`, so the moment untagged
builds began carrying a commit sha that notice would have gone silent
and an unreleased binary would have read as a release — the gate is
now `globals.IsDevVersion`, which is a predicate over a string rather
than a comparison against a global precisely so it can be tested, and
it is tested at the boundary (`1.0.0-dev` is a release, `dev-<sha>`
is not). Release automation is the third blocker: a tag-triggered
`.gitea/workflows/release.yml` runs the build in CI rather than from
a laptop, with `fetch-depth: 0` because a shallow checkout has no
tags and would silently mislabel the release, and with the
`RELEASE_TOKEN` repository secret passed as `GITEA_TOKEN` (documented
in `README.md`; the runner's automatic token is not used because it
is not guaranteed to carry release write scope). `script/release`
unsets any `GITHUB_TOKEN`/`GITLAB_TOKEN` it finds, since goreleaser
chooses its forge from whichever token variable is set and refuses to
run when it sees more than one — a runner-provided token must not get
to decide where these artifacts are published. `make release` and
`make release-snapshot`, the last two Makefile targets that were not
shims, now call `script/release` and `script/release-snapshot`, which
resolve goreleaser exactly the way `script/lint` resolves the linter:
a `PATH` binary is used only at the pinned version, never as a silent
fallback. `script/bootstrap` installs it, from a sha256-verified
GitHub release archive per `REPO_POLICIES.md`, via a separate
`script/install-goreleaser` — separate because `script/bootstrap`
hard-fails without a usable Docker daemon by design, and the release
runner needs goreleaser without needing Docker. Verified by running
the thing rather than reading it: `make release-snapshot` produced
four archives and `checksums.txt`, and the linux/amd64 binary from
`dist/` reports `dev-<sha>` with the development-build notice. Tag
handling was exercised in a throwaway repository rather than by
tagging this one; no tag was created here, since that is the owner's
call. Signing, SBOM, reproducible builds, completions and a man page
are out of scope by the issue.
- 2026-08-09: Isolated the lint cache per worktree and context-gated the
native lint path (issues #99, #80). One defect seen twice:
`script/lint` decided whether it could skip the pinned image by asking
what version was on `PATH` rather than where it was running, and cache
isolation is part of that same question. The cache was one directory
per repo, shared by every worktree on the host, so two checkouts with
identical Go file contents collided and golangci-lint replayed the
stored analysis — paths and all. The loud direction of that failure
(a clean tree failed by a dirty sibling) is the harmless one; the
silent direction, a dirty tree **passed** by a clean sibling, is a
sixth way for a gate here to report a green it did not earn. The cache
is now keyed on a digest of the worktree path, and every run is
audited by the new `script/lint-audit`, which rejects output citing any
file that is not in the tree being linted — a backstop that runs on
clean output too, because that is the case nobody investigates. Caches
record the worktree they belong to and are collected when it
disappears, so throwaway worktrees do not accumulate them; the whole
tree lives under `XDG_CACHE_HOME` and is disposable. The
`parallel golangci-lint is running` refusal is now a bounded retry
rather than a verdict: it is not a lint result, and exiting non-zero
on it is indistinguishable to a caller from real findings (#88 showed
a private cache does not remove that contention). The native path now
requires `VAULTIK_LINT_IN_CONTAINER=1`, set only by the `Dockerfile`
lint stage, in addition to matching the pin, so a developer's locally
installed 2.12.2 no longer bypasses the digest pin; `/.dockerenv` was
rejected as the signal because `dockerd` creates it for `docker run`
and it is not reliably present during a BuildKit `docker build`, which
is the case the exception exists for. Version detection uses
`golangci-lint version --short` with the old banner scrape kept only
as a fallback. `script/bootstrap` no longer prints `bootstrap
complete` on a machine that cannot run the gate: a missing docker, or
one whose daemon is unreachable, is a hard failure naming exactly what
breaks. Verification was by reproduction rather than inspection — two
concurrent lints from two worktrees of differing cleanliness, a real
run made to report an outside path, a matching linter shimmed onto
`PATH`, and a `PATH` with docker removed — and is recorded on the pull
request.
- 2026-08-09: Closed the fifth false-green mechanism (issues #93, #69).
`script/test` omitted `-count=1`, so Go's test result cache could
satisfy the gate outright: a second back-to-back `make test` printed
the full set of 14 `ok` lines, every one marked `(cached)`, having
executed no test at all. Since `ok <pkg> (cached)` is an `ok` line,
the "14 `ok` lines means the suite ran" signal this repo leans on was
forgeable, one level below the Docker layer cache that #85 addressed.
Fixed with `-count=1` unconditionally rather than only in the
container, because the pre-commit hook runs the same script and a
gate honest only in CI is dishonest where people rely on it most;
`test-coverage` got the same flag, and `script/check` inherits it by
calling `script/test`. In the same area, `make test-integration` was
deleted rather than made real: no file in the repo carried a build
tag, so `-tags=integration` selected nothing and the target was an
exact duplicate of `make test`. Tagging a subset was rejected because
the entire suite runs in well under a minute, and a scheme whose
failure mode is "some tests silently stopped running" is a poor trade
for those seconds in a repo with this particular history. The
`-timeout` was raised from 30s after measuring rather than after
assuming: the standing claim that cold-cache compilation is charged
against `-timeout` is **false**, disproved by a containerised run
that spent 46s compiling and still reported per-package durations
within noise of a warm host run. `-timeout` reaches the test binary
as `-test.timeout` and its clock starts inside `testing.M.Run`, after
the build. The real exposure was margin, not compilation. The 120s
landed on is a **deliberate, documented divergence** from
`REPO_POLICIES.md:192`, which mandates 30s, and from that file's
canonical recipe at `:212-214`; the divergence is recorded in
`script/test`'s comment because `REPO_POLICIES.md` is org-canonical
and not editable here, and issue #101 proposes amending the policy
text upstream. Numbers and the full verification are recorded once,
on the pull request, and are deliberately not restated here.
- 2026-08-09: Triaged all fifteen stale remote branches (issue #71) and
deleted fourteen of them; the full per-branch disposition with
evidence is recorded on that issue. Method mattered more than the
outcome here: a three-dot `git diff main...branch` diffs from the
merge base, so it replays everything that landed on `main` after the
branch diverged and makes any old branch look like it holds unlanded
work. That artifact is what made `golangci-v2.12.2` appear to carry
126 files of unpushed changes when its tree was byte-identical to
`main`'s. Every containment claim here therefore rests on two-dot tip
diffs, tree-hash equality, `git cherry`, and `git branch -r --merged`.
Nine branches were plain ancestors of `main` with zero `git cherry`
`+` commits. `golangci-v2.12.2` had landed squashed as `cc58583`,
whose tree hash equals the branch tip's exactly; note the hash
recorded in the issue had gone stale because `main` advanced, so the
check had to be redone rather than repeated.
`fix/sync-snapshot-cleanup` was redundant, its one line already on
`main` in `syncWithRemote`. `feature/restore-progress-bar` was
superseded by `printRestoreProgress` and the disk-backed blob cache,
and had become actively regressive — it would have deleted
`internal/blobgen/compress_test.go`, the #28 regression test that
landed separately. The two branches this issue was filed for both
turned out to be closed questions that `main` had already moved past
by a recorded decision, so neither was landed and no regression test
was owed: `ctime` no longer exists anywhere in the codebase after
`1c72a37` removed the column, the `File.CTime` field and every use
(#54/#55), and change detection compares size, mtime, mode, uid and
gid only, exactly as `ARCHITECTURE.md` documents — so the
silently-skipped-file data-loss risk that made this a 1.0 item does
not exist. The SQL allow-list branch would have reverted `bfd7334`,
which replaced that very allow-list with regex sanitisation on review
feedback, and would have broken `getTableCount("snapshots")` because
its allow-list omits that table. `feature/daemon-mode` is untouched
and deferred to #94 pending an owner decision, so it is the one
branch besides `main` still on the remote. The stale `TODO.md` entry
named in the issue needed no fix: `e496aa3` had already removed it.
No product code changed.
- 2026-08-09: Adopted the remaining upstream `CHECK_EPOCH` hardening
(issue #91), closing the gap #85 knowingly left open. Four changes,
all four decided as adopt upstream in `sneak/prompts` #26. (1) Each
check stage now asserts `[ -n "$CHECK_EPOCH" ] || exit 1` before
running anything, so a build that supplies no `--build-arg` fails
instead of lying. This is the item that mattered: an unset `ARG` is
an empty string and an empty string is a stable cache key, so the
second and every later bare `docker build .` on an unchanged tree
replayed all three check layers and still exited 0 — and `docker
build .` is the command `REPO_POLICIES.md` names verbatim as a thing
that must be green, so the documented command was precisely the one
that lied. Failed steps are never cached, which is what makes the
guard fire on every invocation rather than once. (2) The epoch is now
expanded into each check command rather than left as a bare
declaration, so the cache miss no longer depends on BuildKit's
unreferenced-`ARG` handling staying as it is, and the value appears
in the build log. (3) `script/cibuild` uses
`epoch="$(date +%s%N)$$"`, unique per invocation rather than per
second; `%N` alone is insufficient because busybox drops it silently
and exits 0, and `$$` is what makes the guarantee hold regardless.
The bare-assignment form is kept deliberately — inlined in an
argument, a failing substitution does not abort under `set -eu` and
would yield an empty constant epoch, restoring the exact false green
being fixed. (4) `script/docker` passes the same fresh arg, so the
two entrypoints cannot disagree about whether the tree is green;
local builds are almost always warm, which made it the likelier
fooling in practice. The `ARG` placement from #85 is unchanged, below
`apk add`, `COPY go.mod go.sum` and `go mod download`, so dependency
layers still cache and the build is not cold. Verified by negative
control rather than inspection — a bare `docker build .` run twice
back to back, plus back-to-back pairs of both scripts and a host-side
`make check`; the measurements are recorded once, in the PR
verification comment, rather than restated here. `.golangci.yml`, the
lint-stage `FROM` line and its digest, `script/lint`,
`REPO_POLICIES.md` and `.gitea/workflows/check.yml` are all
untouched.
- 2026-08-09: Stopped `script/cibuild` from reporting a green it did
not earn (issue #85). A bare `docker build .` let Docker serve the
check layers from the layer cache whenever the tree had not changed:
the checks never executed and the build still exited 0. The fix is an
`ARG CHECK_EPOCH` declared immediately above the check `RUN`s in both
the lint stage and the builder stage (`ARG` scope is per-stage, so
each declares its own), with `script/cibuild` assigning
`epoch="$(date +%s)"` and passing `--build-arg CHECK_EPOCH="$epoch"`.
The assignment is separate on purpose: under `set -eu` a command
substitution that fails inside an argument does not abort the script,
which would leave an empty constant `CHECK_EPOCH` and restore the
very false green being fixed. Placement is the rest of the point —
the `ARG` sits below the `apk add`, `COPY go.mod go.sum`, and `go mod
download` layers, so only the checks are invalidated and the
dependency layers still cache. The guarantee is conditional on a
fresh value rather than absolute: a bare `docker build .` gets an
empty `CHECK_EPOCH` and can still serve the check layers from cache,
which `README.md` and the `Dockerfile` now say plainly, with issue
#91 tracking the upstream hardening (expanded `ARG` form, unset
guard, per-invocation epoch, `script/docker`) that would close it.
Verified by re-running the reproduction plus the withheld-`--build-arg`
counterfactual; the measurements are recorded once, in the PR #89
verification comment, rather than restated here. `.golangci.yml`, the
lint-stage `FROM` line and its digest, `script/lint`, and
`.gitea/workflows/check.yml` are all untouched.
- 2026-08-09: Corrected the `Vaultik.UI` doc comment (issue #84). It
claimed the cli layer replaces the writer with a discarding one in
`--cron` mode; the actual mechanism is `UI.SetQuiet(true)` in
`setupGlobals`, which drops Begin/Complete/Info/Notice/Detail/
Progress/Banner but still emits Warning and Error. The `--cron` line
in `README.md` said "Silent unless error", which understated what
survives, and now names warnings too. The other `--cron` comments
(`internal/log/log.go`, `internal/cli/snapshot.go`,
`internal/vaultik/snapshot.go`) were audited and already accurate.
Comments and docs only, no behavior change.
- 2026-08-09: Made `snapshot list` list the destination store without
the private key (issue #64). The listing is now the union of the
local index and a single streamed listing of the `metadata/` prefix,
with no `age_secret_key` gate — the manifest is unencrypted, so a
host holding only the public key can enumerate its own backups and a
host that lost its local index can still see them. A remote-only
snapshot's hostname and name are deliberately not recovered (they are
not recoverable without the private key, and making them so would
undo the privacy property tracked in issue #81); such rows are
labelled by an abbreviation of their remote key and carry the real
timestamp and compressed size from the manifest, with `<remote only>`
in the two columns that require the local index. Local-only snapshots
are reported as drift, and the hint now names `vaultik prune`, which
exists, instead of `vaultik snapshot cleanup`, which does not.
`reportRemoteDrift` collapsed into the merged view. Every remote
manifest read in the codebase now goes through
`downloadManifestByKey`, so issue #81 has one call site to change.
Review rework: snapshot timestamps now normalize to UTC in
`scanSnapshotRows`, the one place they enter the domain, so the merged
TIMESTAMP column cannot show local time for a locally tracked row and
UTC for a remote-only row on a non-UTC host; `GetIncompleteByHostname`
was folded onto that same scanner. `--json` now reports the
unreadable-manifest count and the 1000-row truncation on stderr
instead of returning a silently short document (the document's shape
is unchanged). The two per-snapshot `log.Warn` calls on the listing
path now route through the same JSON-aware writer as the existing
workaround, so one corrupt manifest can no longer put a log line on
stdout ahead of the document and break `| jq` — still a local
workaround pending issue #82. Verified with `script/cibuild` and with
an uncached `make check` (`0 issues.`, no cached test packages), plus
end to end against a `file://` destination with no secret key present.
- 2026-08-09: Closed the gap between `make lint` and CI (issue #78).
`script/lint` now runs the digest-pinned `golangci-lint` image taken
from the `Dockerfile` lint stage, which is the single source of truth
for the linter version; the duplicate pin in the `Makefile` `deps`
target and the unpinned `golangci-lint` install in `script/bootstrap`
are gone. A `golangci-lint` on `PATH` is used only when its version is
exactly the pinned one (which is how the lint stage runs it inside the
container); anything else goes through Docker, and a missing or
unreachable Docker daemon is a hard error rather than a silent
fallback. Only the **lint** leg of `make check` became equivalent to
`script/cibuild`; its tests and `gofmt` still run on the host against
the host toolchain, as `README.md` states. An earlier version of this
entry claimed `make check` was "as trustworthy as `script/cibuild`"
outright, which overstated it; corrected under issue #80.
- 2026-08-09: Finished the lint remediation under the canonical
`.golangci.yml` (issue #61, which also unblocks issue #59). The
remaining findings were fixed behavior-preservingly: `wsl_v5`
whitespace, `sqlclosecheck`, and `prealloc`. The `sqlclosecheck` sites
now close `sql.Rows` in a deferred closure instead of via the
`CloseRows` helper, which the linter could not see through. Only the
`revive` package-name findings remain suppressed, with per-site
`//nolint` directives; the package-rename question behind them is
tracked in issue #76. Verified with `script/cibuild`, which exits 0 —
that is the only trustworthy gate, because `script/lint` runs whatever
`golangci-lint` happens to be on `PATH` rather than the pinned
v2.12.2 that CI and the `Dockerfile` use, so `make check` can report
green on findings CI still fails. That tooling gap is tracked in issue
#78.
- 2026-08-09: The earlier next step "reconcile the uncommitted
`ARCHITECTURE.md` edits on `main`" needed no work: the working tree is
clean and `ARCHITECTURE.md` is committed on `main`.
- 2026-08-07: Updated golangci-lint to v2.12.2 everywhere it is pinned
(`Dockerfile` lint stage, `Makefile` deps target), replaced
`.golangci.yml` with the canonical config (v2 schema, `default: all`),
and remediated the bulk of the lint findings it surfaced (issue #61):
behavior-preserving fixes across every package, 2,990 findings down to
80. `make test` and `make fmt-check` were green at that point but
`make lint` was still red; the commit message claiming `make check`
was green was wrong.
- 2026-08-07: Added the standard `.golangci.yml` and `.editorconfig`
(issue #59); lint findings under the new config are tracked in issue
#61.
- 2026-07-07 Adopted scripts-to-rule-them-all: `script/` entrypoints,
Makefile shims, README Entrypoints section
- 2026-07-02: Consolidated CLI verbs, retired overlapping commands; bound
the local index to its backup destination URL.
- 2026-06-28: snapshot rm now removes metadata only and prints the prune
command; restore skips chown when running as non-root.
- 2026-06-26: Snapshot IDs hashed at the storage boundary; snapshot list
made resilient to bad remote entries.
- 2026-06-24: Collapsed snapshot prune into vaultik prune; restore streams
blobs to disk and restores files in blob-locality order; cron output
fixes.
- 2026-06-17: Restore overhaul: ReadAt chunk reads from cached blobs,
reference-counted blob sweeper, integration tests; new internal/ui
output layer, banner, and progress lines.
- 2025-12-18: Added ARCHITECTURE.md and godoc coverage for exported API.
- 2025-07-26: End-to-end integration tests; manifest format refactor;
renamed backup to snapshot; afero filesystem abstraction.
- 2025-07-20: Initial design and implementation: cobra + fx CLI skeleton,
SQLite index database, UUID blob storage with streaming chunking.
# Future Steps
Work planned after 1.0 is listed in the README
[roadmap](README.md#roadmap).
-45
View File
@@ -1,45 +0,0 @@
package main_test
import (
"strings"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// TestDockerfileBoundsEveryModuleDownload fails unless every
// `go mod download` in the Dockerfile runs under a time limit, is tried
// a fixed number of times, and then fails the build with a message that
// names the module download (issue #351). Like the version tests, this
// parses the Dockerfile; that a stalled download really is cut off and
// retried was checked by hand.
func TestDockerfileBoundsEveryModuleDownload(t *testing.T) {
t.Parallel()
var downloads []string
for _, instruction := range instructions(t, productDockerfile) {
if strings.Contains(instruction, "go mod download") {
downloads = append(downloads, instruction)
}
}
require.NotEmpty(t, downloads, "%s must download modules",
productDockerfile)
for _, download := range downloads {
assert.Contains(t, download, "timeout 300 go mod download",
"%s: a module download must have a time limit: %s",
productDockerfile, download)
assert.Contains(t, download, "for attempt in 1 2 3",
"%s: a module download must be retried: %s",
productDockerfile, download)
assert.Contains(t, download, "module download failed",
"%s: a module download that never succeeds must say so: %s",
productDockerfile, download)
assert.True(t, strings.HasSuffix(download, "exit 1"),
"%s: a module download that never succeeds must fail the"+
" build: %s", productDockerfile, download)
}
}
@@ -287,23 +287,19 @@ storage_url: "rclone://myremote/path/to/backups"
# #use_ssl: true # #use_ssl: true
# #
# # Part size for multipart uploads # # Part size for multipart uploads
# # Minimum 5MiB, maximum 5GiB; affects memory usage during upload # # Minimum 5MB, affects memory usage during upload
# # A blob too large for 10,000 parts of this size gets larger parts # # Supports: 5MB, 10M, 100MiB, etc.
# # Supports: 10MB, 16MiB, 100MiB, etc. (5MB is below the minimum) # # Default: 5MB
# # Default: 5MiB # #part_size: 5MB
# #part_size: 5MiB
# Path to local SQLite index database # Path to local SQLite index database
# This database tracks file state for incremental backups # This database tracks file state for incremental backups
# Default: the platform data directory, e.g. # Default: /var/lib/vaultik/index.sqlite
# macOS: ~/Library/Application Support/vaultik/index.sqlite #index_path: /var/lib/vaultik/index.sqlite
# Linux: ~/.local/share/vaultik/index.sqlite
#index_path: /path/to/index.sqlite
# Average chunk size for content-defined chunking # Average chunk size for content-defined chunking
# Smaller chunks = better deduplication but more metadata # Smaller chunks = better deduplication but more metadata
# Minimum 1MB # Supports: 10MB, 5M, 1GB, 500KB, 64MiB, etc.
# Supports: 10MB, 5M, 1GB, 64MiB, etc.
# Default: 10MB # Default: 10MB
#chunk_size: 10MB #chunk_size: 10MB
@@ -314,12 +310,6 @@ storage_url: "rclone://myremote/path/to/backups"
# Chunking uses no secret (the FastCDC parameters are fixed and public). At a # Chunking uses no secret (the FastCDC parameters are fixed and public). At a
# large limit a blob holds hundreds of chunks, so individual chunk lengths are # large limit a blob holds hundreds of chunks, so individual chunk lengths are
# not visible in its size; lowering the limit toward chunk_size exposes them. # not visible in its size; lowering the limit toward chunk_size exposes them.
# A backup needs free temporary space, because each blob is written whole to
# a temporary file before it is uploaded (up to about blob_size_limit; an
# rclone destination that cannot stream uploads needs about twice that) and
# the metadata export writes copies of the local index. Temporary files go to
# $TMPDIR (default /tmp); with TMPDIR unset, SQLite writes one of those copies
# to /var/tmp.
# Supports: 1GB, 10G, 500MB, 1GiB, etc. # Supports: 1GB, 10G, 500MB, 1GiB, etc.
# Default: 10GB # Default: 10GB
#blob_size_limit: 10GB #blob_size_limit: 10GB
@@ -328,20 +318,6 @@ storage_url: "rclone://myremote/path/to/backups"
# Higher = better compression but slower # Higher = better compression but slower
# Default: 3 # Default: 3
compression_level: 5 compression_level: 5
# How old a blob that no snapshot lists must be before prune deletes it, and
# how old every object in a directory under metadata/ with no manifest must
# be before prune deletes that directory
# A backup uploads its blobs and its db.zst.age before its manifest, so on a
# destination shared between hosts or users this must be longer than the
# longest backup run
# It does not protect a blob a backup reuses from an earlier run that stopped
# before its manifest: that blob keeps the time of its first upload, so a
# prune can delete it
# Supports: 36h, 90m, etc.; 0s deletes such blobs and directories at once
# Default: 24h
#prune_grace_period: 24h
# Hostname to use in backup metadata # Hostname to use in backup metadata
# Default: system hostname # Default: system hostname
#hostname: myserver #hostname: myserver
+56 -155
View File
@@ -2,9 +2,7 @@
## Overview ## Overview
Vaultik uses a local SQLite database to track file metadata, chunk mappings, and Vaultik uses a local SQLite database to track file metadata, chunk mappings, and blob associations during the backup process. This database serves as an index for incremental backups and enables efficient deduplication.
blob associations during the backup process. This database serves as an index
for incremental backups and enables efficient deduplication.
**Important Notes:** **Important Notes:**
@@ -27,23 +25,18 @@ recorded `001.sql` as run, so it keeps the old schema and can become unusable;
`vaultik database delete` followed by a full backup rebuilds it. `vaultik database delete` followed by a full backup rebuilds it.
**After 1.0** each schema change is a new numbered file, so an existing local **After 1.0** each schema change is a new numbered file, so an existing local
database is migrated the first time an updated vaultik opens it. A file that has database is migrated the first time an updated vaultik opens it. A file that
shipped in a release is never edited. has shipped in a release is never edited.
## Database Tables ## Database Tables
### 1. `files` ### 1. `files`
Stores metadata about files in the filesystem being backed up. Stores metadata about files in the filesystem being backed up.
**Columns:** **Columns:**
- `id` (TEXT PRIMARY KEY) - UUID for the file record - `id` (TEXT PRIMARY KEY) - UUID for the file record
- `path` (TEXT NOT NULL UNIQUE) - Absolute file path - `path` (TEXT NOT NULL UNIQUE) - Absolute file path
- `mtime` (INTEGER NOT NULL) - Modification time, whole seconds since the Unix - `mtime` (INTEGER NOT NULL) - Modification time as Unix timestamp
epoch
- `mtime_nsec` (INTEGER NOT NULL) - Nanoseconds within that second, 0 to
999999999
- `size` (INTEGER NOT NULL) - File size in bytes - `size` (INTEGER NOT NULL) - File size in bytes
- `mode` (INTEGER NOT NULL) - Unix file permissions and type - `mode` (INTEGER NOT NULL) - Unix file permissions and type
- `uid` (INTEGER NOT NULL) - User ID of file owner - `uid` (INTEGER NOT NULL) - User ID of file owner
@@ -51,30 +44,23 @@ Stores metadata about files in the filesystem being backed up.
- `link_target` (TEXT) - Symlink target path (NULL for regular files) - `link_target` (TEXT) - Symlink target path (NULL for regular files)
**Indexes:** **Indexes:**
- `idx_files_path` on `path` for efficient lookups - `idx_files_path` on `path` for efficient lookups
**Purpose:** Tracks file metadata to detect changes between backup runs. Used **Purpose:** Tracks file metadata to detect changes between backup runs. Used for incremental backup decisions. The UUID primary key provides stable references that don't change if files are moved.
for incremental backup decisions. The UUID primary key provides stable
references that don't change if files are moved.
### 2. `chunks` ### 2. `chunks`
Stores information about content-defined chunks created from files. Stores information about content-defined chunks created from files.
**Columns:** **Columns:**
- `chunk_hash` (TEXT PRIMARY KEY) - SHA256 hash of chunk content - `chunk_hash` (TEXT PRIMARY KEY) - SHA256 hash of chunk content
- `size` (INTEGER NOT NULL) - Chunk size in bytes - `size` (INTEGER NOT NULL) - Chunk size in bytes
**Purpose:** Enables deduplication by tracking unique chunks across all files. **Purpose:** Enables deduplication by tracking unique chunks across all files.
### 3. `file_chunks` ### 3. `file_chunks`
Maps files to their constituent chunks in order. Maps files to their constituent chunks in order.
**Columns:** **Columns:**
- `file_id` (TEXT) - File ID (FK to files.id) - `file_id` (TEXT) - File ID (FK to files.id)
- `idx` (INTEGER) - Chunk index within file (0-based) - `idx` (INTEGER) - Chunk index within file (0-based)
- `chunk_hash` (TEXT) - Chunk hash (FK to chunks.chunk_hash) - `chunk_hash` (TEXT) - Chunk hash (FK to chunks.chunk_hash)
@@ -83,49 +69,35 @@ Maps files to their constituent chunks in order.
**Purpose:** Allows reconstruction of files from chunks during restore. **Purpose:** Allows reconstruction of files from chunks during restore.
### 4. `chunk_files` ### 4. `chunk_files`
Reverse mapping showing which files contain each chunk. Reverse mapping showing which files contain each chunk.
**Columns:** **Columns:**
- `chunk_hash` (TEXT) - Chunk hash (FK to chunks.chunk_hash) - `chunk_hash` (TEXT) - Chunk hash (FK to chunks.chunk_hash)
- `file_id` (TEXT) - File ID (FK to files.id) - `file_id` (TEXT) - File ID (FK to files.id)
- `file_offset` (INTEGER) - Byte offset of chunk within file - `file_offset` (INTEGER) - Byte offset of chunk within file
- `length` (INTEGER) - Length of chunk in bytes - `length` (INTEGER) - Length of chunk in bytes
- PRIMARY KEY (`chunk_hash`, `file_id`) - PRIMARY KEY (`chunk_hash`, `file_id`)
**Purpose:** Supports efficient queries for chunk usage and deduplication **Purpose:** Supports efficient queries for chunk usage and deduplication statistics.
statistics.
### 5. `blobs` ### 5. `blobs`
Stores information about packed, compressed, and encrypted blob files. Stores information about packed, compressed, and encrypted blob files.
**Columns:** **Columns:**
- `id` (TEXT PRIMARY KEY) - UUID assigned when blob creation starts - `id` (TEXT PRIMARY KEY) - UUID assigned when blob creation starts
- `blob_hash` (TEXT UNIQUE) - `hex(SHA256(SHA256(uncompressed blob contents)))`, - `blob_hash` (TEXT UNIQUE) - `hex(SHA256(SHA256(uncompressed blob contents)))`, computed before compression and encryption (NULL until finalized); see [REPOSTRUCTURE.md](REPOSTRUCTURE.md#blobs-directory-blobs)
computed before compression and encryption (NULL until finalized); see
[REPOSTRUCTURE.md](REPOSTRUCTURE.md#blobs-directory-blobs)
- `created_ts` (INTEGER NOT NULL) - Creation timestamp - `created_ts` (INTEGER NOT NULL) - Creation timestamp
- `finished_ts` (INTEGER) - Finalization timestamp (NULL if in progress) - `finished_ts` (INTEGER) - Finalization timestamp (NULL if in progress)
- `uncompressed_size` (INTEGER NOT NULL DEFAULT 0) - Total size of chunks before - `uncompressed_size` (INTEGER NOT NULL DEFAULT 0) - Total size of chunks before compression
compression - `compressed_size` (INTEGER NOT NULL DEFAULT 0) - Size after compression and encryption
- `compressed_size` (INTEGER NOT NULL DEFAULT 0) - Size after compression and
encryption. Once uploaded, the size of the object in storage: when the blob
was already stored, under another compression level or other recipients, this
can differ from the size of the local copy
- `uploaded_ts` (INTEGER) - Upload completion timestamp (NULL if not uploaded) - `uploaded_ts` (INTEGER) - Upload completion timestamp (NULL if not uploaded)
**Purpose:** Tracks blob lifecycle from creation through upload. The UUID **Purpose:** Tracks blob lifecycle from creation through upload. The UUID primary key allows immediate association of chunks with blobs.
primary key allows immediate association of chunks with blobs.
### 6. `blob_chunks` ### 6. `blob_chunks`
Maps chunks to the blobs that contain them. Maps chunks to the blobs that contain them.
**Columns:** **Columns:**
- `blob_id` (TEXT) - Blob ID (FK to blobs.id) - `blob_id` (TEXT) - Blob ID (FK to blobs.id)
- `chunk_hash` (TEXT) - Chunk hash (FK to chunks.chunk_hash) - `chunk_hash` (TEXT) - Chunk hash (FK to chunks.chunk_hash)
- `offset` (INTEGER) - Byte offset of chunk within blob (before compression) - `offset` (INTEGER) - Byte offset of chunk within blob (before compression)
@@ -135,46 +107,32 @@ Maps chunks to the blobs that contain them.
**Purpose:** Enables chunk retrieval from blobs during restore operations. **Purpose:** Enables chunk retrieval from blobs during restore operations.
### 7. `snapshots` ### 7. `snapshots`
Tracks backup snapshots. Tracks backup snapshots.
**Columns:** **Columns:**
- `id` (TEXT PRIMARY KEY) - Snapshot ID (format: hostname-YYYYMMDD-HHMMSSZ)
- `id` (TEXT PRIMARY KEY) - Snapshot ID (format: `hostname_name_timestamp`, e.g.
`server1_home_2025-06-01T12:00:00Z`: the hostname up to its first `.`, the
snapshot name, and an RFC 3339 UTC timestamp)
- `hostname` (TEXT) - Hostname where backup was created - `hostname` (TEXT) - Hostname where backup was created
- `vaultik_version` (TEXT) - Version of Vaultik used - `vaultik_version` (TEXT) - Version of Vaultik used
- `vaultik_git_revision` (TEXT) - Git revision of Vaultik used - `vaultik_git_revision` (TEXT) - Git revision of Vaultik used
- `started_at` (INTEGER) - Start timestamp - `started_at` (INTEGER) - Start timestamp
- `completed_at` (INTEGER) - Completion timestamp (NULL if in progress) - `completed_at` (INTEGER) - Completion timestamp (NULL if in progress)
- `file_count` (INTEGER) - Number of files in snapshot - `file_count` (INTEGER) - Number of files in snapshot
- `chunk_count` (INTEGER) - Number of chunks this snapshot stored that were not - `chunk_count` (INTEGER) - Number of unique chunks
stored before - `blob_count` (INTEGER) - Number of blobs referenced
- `new_chunk_size` (INTEGER) - Total size of those chunks before compression;
`snapshot list` shows it as NEW CHUNK SIZE
- `blob_count` (INTEGER) - Number of blobs this snapshot created
- `total_size` (INTEGER) - Total size of all files - `total_size` (INTEGER) - Total size of all files
- `uncompressed_chunk_size` (INTEGER) - Total size before compression of the - `blob_size` (INTEGER) - Total size of all blobs (compressed)
distinct chunks the snapshot's files reference, recorded when its backup ran; - `blob_uncompressed_size` (INTEGER) - Total uncompressed size of all referenced blobs
`snapshot list` shows it as UNCOMPRESSED SIZE
- `blob_size` (INTEGER) - Total compressed size of all referenced blobs
- `blob_uncompressed_size` (INTEGER) - Total uncompressed size of all referenced
blobs
- `compression_ratio` (REAL) - Compression ratio achieved - `compression_ratio` (REAL) - Compression ratio achieved
- `compression_level` (INTEGER) - Compression level used for this snapshot - `compression_level` (INTEGER) - Compression level used for this snapshot
- `upload_bytes` (INTEGER) - Total bytes uploaded during this snapshot - `upload_bytes` (INTEGER) - Total bytes uploaded during this snapshot
- `upload_duration_ms` (INTEGER) - Total milliseconds spent uploading to S3 - `upload_duration_ms` (INTEGER) - Total milliseconds spent uploading to S3
**Purpose:** Provides snapshot metadata and statistics including version **Purpose:** Provides snapshot metadata and statistics including version tracking for compatibility.
tracking for compatibility.
### 8. `snapshot_files` ### 8. `snapshot_files`
Maps snapshots to the files they contain. Maps snapshots to the files they contain.
**Columns:** **Columns:**
- `snapshot_id` (TEXT) - Snapshot ID (FK to snapshots.id) - `snapshot_id` (TEXT) - Snapshot ID (FK to snapshots.id)
- `file_id` (TEXT) - File ID (FK to files.id) - `file_id` (TEXT) - File ID (FK to files.id)
- PRIMARY KEY (`snapshot_id`, `file_id`) - PRIMARY KEY (`snapshot_id`, `file_id`)
@@ -182,147 +140,100 @@ Maps snapshots to the files they contain.
**Purpose:** Records which files are included in each snapshot. **Purpose:** Records which files are included in each snapshot.
### 9. `snapshot_blobs` ### 9. `snapshot_blobs`
Maps snapshots to the blobs they reference. Maps snapshots to the blobs they reference.
**Columns:** **Columns:**
- `snapshot_id` (TEXT) - Snapshot ID (FK to snapshots.id) - `snapshot_id` (TEXT) - Snapshot ID (FK to snapshots.id)
- `blob_id` (TEXT) - Blob ID (FK to blobs.id) - `blob_id` (TEXT) - Blob ID (FK to blobs.id)
- `blob_hash` (TEXT) - Denormalized blob hash for manifest generation - `blob_hash` (TEXT) - Denormalized blob hash for manifest generation
- PRIMARY KEY (`snapshot_id`, `blob_id`) - PRIMARY KEY (`snapshot_id`, `blob_id`)
**Purpose:** Tracks blob dependencies for snapshots and enables manifest **Purpose:** Tracks blob dependencies for snapshots and enables manifest generation.
generation.
### 10. `snapshot_mount_points`
The directories at or below a configured path, the configured path itself
included, that a snapshot's backup found an entry in and, once it had listed
them, found on a different filesystem from their parent directory (a different
device number), as a mount point is. An automount point whose volume cannot be
mounted is not recorded, because the backup finds no entry in it.
**Columns:**
- `snapshot_id` (TEXT) - Snapshot ID (FK to snapshots.id)
- `path` (TEXT) - Absolute path of the directory
- PRIMARY KEY (`snapshot_id`, `path`)
**Purpose:** Lets `snapshot create --prune` skip the prune when a backup does
not find a mount point that an earlier snapshot of the same name found, as when
the volume is not mounted.
### 11. `uploads`
### 10. `uploads`
Tracks blob upload metrics. Tracks blob upload metrics.
**Columns:** **Columns:**
- `blob_hash` (TEXT PRIMARY KEY) - Hash of uploaded blob - `blob_hash` (TEXT PRIMARY KEY) - Hash of uploaded blob
- `snapshot_id` (TEXT NOT NULL) - The snapshot that triggered this upload (FK to - `snapshot_id` (TEXT NOT NULL) - The snapshot that triggered this upload (FK to snapshots.id)
snapshots.id)
- `uploaded_at` (INTEGER) - Upload timestamp - `uploaded_at` (INTEGER) - Upload timestamp
- `size` (INTEGER) - Size of uploaded blob - `size` (INTEGER) - Size of uploaded blob
- `duration_ms` (INTEGER) - Upload duration in milliseconds - `duration_ms` (INTEGER) - Upload duration in milliseconds
**Purpose:** Performance monitoring and tracking which blobs were newly created **Purpose:** Performance monitoring and tracking which blobs were newly created (uploaded) during each snapshot.
(uploaded) during each snapshot.
## Data Flow and Operations ## Data Flow and Operations
### 1. Backup Process ### 1. Backup Process
1. **File Scanning** 1. **File Scanning**
- `INSERT OR REPLACE INTO files` - Update file metadata - `INSERT OR REPLACE INTO files` - Update file metadata
- `SELECT * FROM files WHERE path = ?` - Check if file has changed - `SELECT * FROM files WHERE path = ?` - Check if file has changed
- `INSERT INTO snapshot_files` - Add file to current snapshot - `INSERT INTO snapshot_files` - Add file to current snapshot
- `INSERT OR IGNORE INTO snapshot_mount_points` - Record each directory on a
different filesystem from its parent that the walk found an entry in
2. **Chunking** (for changed files) 2. **Chunking** (for changed files)
- `INSERT OR IGNORE INTO chunks` - Store new chunks - `INSERT OR IGNORE INTO chunks` - Store new chunks
- `INSERT INTO file_chunks` - Map chunks to file - `INSERT INTO file_chunks` - Map chunks to file
- `INSERT INTO chunk_files` - Create reverse mapping - `INSERT INTO chunk_files` - Create reverse mapping
3. **Blob Packing** 3. **Blob Packing**
- `INSERT INTO blobs` - Create blob record with UUID (blob_hash NULL) - `INSERT INTO blobs` - Create blob record with UUID (blob_hash NULL)
- `INSERT INTO blob_chunks` - Associate chunks with blob immediately - `INSERT INTO blob_chunks` - Associate chunks with blob immediately
- `UPDATE blobs SET blob_hash = ?, finished_ts = ?` - Finalize blob after - `UPDATE blobs SET blob_hash = ?, finished_ts = ?` - Finalize blob after packing
packing
4. **Upload** 4. **Upload**
- `UPDATE blobs SET uploaded_ts = ?, compressed_size = ?` - Mark blob as - `UPDATE blobs SET uploaded_ts = ?` - Mark blob as uploaded
uploaded, with the size of the object in storage (the upload is skipped - `INSERT INTO uploads` - Record upload metrics with snapshot_id
when the blob is already stored) - `INSERT INTO snapshot_blobs` - Associate blob with snapshot
- `INSERT INTO uploads` - Record upload metrics with snapshot_id
- `INSERT INTO snapshot_blobs` - Associate blob with snapshot
5. **Snapshot Completion** 5. **Snapshot Completion**
- `UPDATE snapshots SET completed_at = ?, stats...` - Finalize snapshot - `UPDATE snapshots SET completed_at = ?, stats...` - Finalize snapshot
- Generate and upload blob manifest from `snapshot_blobs` - Generate and upload blob manifest from `snapshot_blobs`
### 2. Incremental Backup ### 2. Incremental Backup
1. **Change Detection** 1. **Change Detection**
- `SELECT * FROM files WHERE path = ?` - Get previous file metadata - `SELECT * FROM files WHERE path = ?` - Get previous file metadata
- Compare mtime, size, mode to detect changes - Compare mtime, size, mode to detect changes
- Re-chunk a file that lists a chunk no uploaded blob holds, even when its - Re-chunk a file that lists a chunk no uploaded blob holds, even when its metadata is unchanged
metadata is unchanged - Skip unchanged files but still add to `snapshot_files`
- Skip unchanged files but still add to `snapshot_files`
2. **Chunk Reuse** 2. **Chunk Reuse**
- `SELECT * FROM blob_chunks WHERE chunk_hash = ?` - Find existing chunks - `SELECT * FROM blob_chunks WHERE chunk_hash = ?` - Find existing chunks
- `INSERT INTO snapshot_blobs` - Reference existing blobs for unchanged - `INSERT INTO snapshot_blobs` - Reference existing blobs for unchanged files
files
### 3. Snapshot Metadata Export ### 3. Snapshot Metadata Export
After a snapshot is completed: After a snapshot is completed:
1. Copy database to temporary file 1. Copy database to temporary file
2. Clean temporary database to contain only current snapshot data 2. Clean temporary database to contain only current snapshot data
3. VACUUM the trimmed database so deleted rows leave no pages behind 3. VACUUM the trimmed database so deleted rows leave no pages behind
4. Compress with zstd and encrypt with age 4. Compress with zstd and encrypt with age
5. Upload to S3 as `metadata/{remote-key}/db.zst.age` 5. Upload to S3 as `metadata/{remote-key}/db.zst.age`
6. Generate blob manifest and upload as 6. Generate blob manifest and upload as `metadata/{remote-key}/manifest.json.zst`
`metadata/{remote-key}/manifest.json.zst`
The `{remote-key}` directory name is a one-way hash of the human snapshot ID, so The `{remote-key}` directory name is a one-way hash of the human snapshot ID, so the ID is never written to the store in plaintext. The hash uses no secret, so a guessed hostname and snapshot name can still be confirmed against a listing; see [REPOSTRUCTURE.md](REPOSTRUCTURE.md#remote-key-derivation) and its [Accepted Risks](REPOSTRUCTURE.md#accepted-risks).
the ID is never written to the store in plaintext. The hash uses no secret, so a
guessed hostname and snapshot name can still be confirmed against a listing; see
[REPOSTRUCTURE.md](REPOSTRUCTURE.md#remote-key-derivation) and its
[Accepted Risks](REPOSTRUCTURE.md#accepted-risks).
### 4. Restore Process ### 4. Restore Process
The restore process doesn't use the local database. Instead: The restore process doesn't use the local database. Instead:
1. Downloads snapshot metadata from S3
1. Downloads and decrypts the snapshot's metadata database (`db.zst.age`) from 2. Downloads required blobs based on manifest
S3
2. Downloads the blobs holding the chunks of the files being restored, found
through that database's `blob_chunks` table; the manifest is not read
3. Reconstructs files from decrypted and decompressed chunks 3. Reconstructs files from decrypted and decompressed chunks
### 5. Pruning ### 5. Pruning
1. **Identify Unreferenced Blobs** 1. **Identify Unreferenced Blobs**
- Query blobs not referenced by any remaining snapshot - Query blobs not referenced by any remaining snapshot
- Delete from S3, once older than `prune_grace_period`, and from the local - Delete from S3 and local database
database
2. **Delete Metadata Directories With No Manifest**
- Delete each directory under `metadata/` that has no `manifest.json.zst`
and no local snapshot record, once every object in it is older than
`prune_grace_period`
### 6. Incomplete Snapshot Cleanup ### 6. Incomplete Snapshot Cleanup
Before each backup: Before each backup:
1. Query incomplete snapshots (where `completed_at IS NULL`) 1. Query incomplete snapshots (where `completed_at IS NULL`)
2. Delete each one and all its associations, without checking S3 for its 2. Check if metadata exists in S3
metadata 3. If no metadata, delete snapshot and all associations
3. Clean up orphaned files, chunks, and blobs 4. Clean up orphaned files, chunks, and blobs
## Repository Pattern ## Repository Pattern
@@ -338,13 +249,11 @@ Vaultik uses a repository pattern for database access:
- `UploadRepository` - Track blob upload metrics - `UploadRepository` - Track blob upload metrics
Each repository provides methods like: Each repository provides methods like:
- `Create()` - Insert new record - `Create()` - Insert new record
- `GetByID()` / `GetByPath()` / `GetByHash()` - Retrieve records - `GetByID()` / `GetByPath()` / `GetByHash()` - Retrieve records
- `Update()` - Update existing records - `Update()` - Update existing records
- `Delete()` - Remove records - `Delete()` - Remove records
- Specialized queries for each entity type (e.g., `DeleteOrphaned()`, - Specialized queries for each entity type (e.g., `DeleteOrphaned()`, `GetIncompleteByHostname()`)
`GetIncompleteByHostname()`)
## Transaction Management ## Transaction Management
@@ -357,7 +266,6 @@ err := repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
``` ```
This ensures consistency, especially important for operations like: This ensures consistency, especially important for operations like:
- Creating file-chunk mappings - Creating file-chunk mappings
- Associating chunks with blobs - Associating chunks with blobs
- Updating snapshot statistics - Updating snapshot statistics
@@ -365,25 +273,18 @@ This ensures consistency, especially important for operations like:
## Performance Considerations ## Performance Considerations
1. **Indexes**: 1. **Indexes**:
- Primary keys are automatically indexed - Primary keys are automatically indexed
- `idx_files_path` on `files(path)` for efficient file lookups - `idx_files_path` on `files(path)` for efficient file lookups
2. **Prepared Statements**: All queries use prepared statements for performance 2. **Prepared Statements**: All queries use prepared statements for performance and security
and security
3. **Batch Operations**: Where possible, operations are batched within 3. **Batch Operations**: Where possible, operations are batched within transactions
transactions
4. **Write-Ahead Logging**: The local index runs in SQLite WAL mode with a 4. **Write-Ahead Logging**: The local index runs in SQLite WAL mode with a 10-second busy timeout, so a read-only command such as `snapshot list` can read it while a backup writes to it. Committed rows can sit in the `-wal` file beside the index until a checkpoint, so the metadata export copies the index through SQLite (`VACUUM INTO`), not as a file
10-second busy timeout, so a read-only command such as `snapshot list` can
read it while a backup writes to it. Committed rows can sit in the `-wal`
file beside the index until a checkpoint, so the metadata export copies the
index through SQLite (`VACUUM INTO`), not as a file
## Data Integrity ## Data Integrity
1. **Foreign Keys**: Enforced through CASCADE DELETE and application-level 1. **Foreign Keys**: Enforced through CASCADE DELETE and application-level repository methods
repository methods
2. **Unique Constraints**: Chunk hashes, file paths, and blob hashes are unique 2. **Unique Constraints**: Chunk hashes, file paths, and blob hashes are unique
3. **Null Handling**: Nullable fields clearly indicate in-progress operations 3. **Null Handling**: Nullable fields clearly indicate in-progress operations
4. **Timestamp Tracking**: All major operations record timestamps for auditing 4. **Timestamp Tracking**: All major operations record timestamps for auditing
+52 -229
View File
@@ -1,13 +1,10 @@
# Vaultik S3 Repository Structure # Vaultik S3 Repository Structure
This document describes the structure and organization of data stored in the S3 This document describes the structure and organization of data stored in the S3 bucket by Vaultik.
bucket by Vaultik.
## Overview ## Overview
Vaultik stores all backup data in an S3-compatible object store. The repository Vaultik stores all backup data in an S3-compatible object store. The repository consists of two main components:
consists of two main components, plus a marker file:
1. **Blobs** - The actual backup data (content-addressed, encrypted) 1. **Blobs** - The actual backup data (content-addressed, encrypted)
2. **Metadata** - Snapshot information and manifests (partially encrypted) 2. **Metadata** - Snapshot information and manifests (partially encrypted)
@@ -15,7 +12,6 @@ consists of two main components, plus a marker file:
``` ```
<bucket>/<prefix>/ <bucket>/<prefix>/
├── vaultik-destination.txt
├── blobs/ ├── blobs/
│ └── <hash[0:2]>/ │ └── <hash[0:2]>/
│ └── <hash[2:4]>/ │ └── <hash[2:4]>/
@@ -26,208 +22,114 @@ consists of two main components, plus a marker file:
└── manifest.json.zst └── manifest.json.zst
``` ```
The metadata subdirectory is named with the **remote key**, a one-way hash of The metadata subdirectory is named with the **remote key**, a one-way hash of the snapshot ID, not with the human-readable snapshot ID itself. See [Remote Key Derivation](#remote-key-derivation).
the snapshot ID, not with the human-readable snapshot ID itself. See
[Remote Key Derivation](#remote-key-derivation).
## Marker File (`vaultik-destination.txt`)
Every backup writes this file at the root before it uploads anything. It holds
one fixed line of plain text and names no host, path or time. While the local
index holds snapshots stored there, a destination that answers a look-up of the
marker with not found is treated as not present: `snapshot create` refuses to
write to it, and `prune`, `snapshot purge`, `snapshot remove`, `snapshot list`
and `remote nuke` behave as for a destination that cannot be listed. An
unplugged volume leaves an empty directory at its mount point, and without the
marker that directory would read as a destination whose snapshots are all gone.
`remote nuke` deletes the marker last.
When the look-up of the marker fails for any reason other than not found, the
check is skipped and the command goes on. S3 refuses it on every run to
credentials that allow only PUT, so a host with such credentials does not notice
a destination emptied since its last backup, and its next backup would leave out
the data its local index records as already stored. After the destination is
emptied, run `vaultik database delete` on such a host before it backs up again.
## Blobs Directory (`blobs/`) ## Blobs Directory (`blobs/`)
### Structure ### Structure
- **Path format**: `blobs/<first-2-chars>/<next-2-chars>/<full-hash>` - **Path format**: `blobs/<first-2-chars>/<next-2-chars>/<full-hash>`
- **Example**: - **Example**: `blobs/ca/fe/cafebabe1234567890abcdef1234567890abcdef1234567890abcdef12345678`
`blobs/ca/fe/cafebabe1234567890abcdef1234567890abcdef1234567890abcdef12345678` - **Sharding**: The two-level directory structure (using the first 4 characters of the hash) prevents any single directory from containing too many objects
- **Sharding**: The two-level directory structure (using the first 4 characters
of the hash) prevents any single directory from containing too many objects
### Content ### Content
- **What it contains**: Packed collections of content-defined chunks from files - **What it contains**: Packed collections of content-defined chunks from files
- **Format**: Zstandard compressed, then Age encrypted - **Format**: Zstandard compressed, then Age encrypted
- **Encryption**: Always encrypted with Age using the configured recipients - **Encryption**: Always encrypted with Age using the configured recipients
- **Naming**: Content-addressed. The blob's name is - **Naming**: Content-addressed. The blob's name is `hex(SHA256(SHA256(uncompressed blob contents)))` — the double SHA-256 of the concatenated chunk data, computed before compression and encryption, not a hash of the stored (compressed, encrypted) bytes. One consequence: only a holder of the age private key can check a stored blob's integrity, because matching a blob to its name means decrypting and decompressing it first — which is what `restore` and `verify --deep` do. Implemented in `internal/blobgen` (`DoubleSHA256`). This is the canonical description of blob naming; other documents and comments point here.
`hex(SHA256(SHA256(uncompressed blob contents)))` — the double SHA-256 of the
concatenated chunk data, computed before compression and encryption, not a
hash of the stored (compressed, encrypted) bytes. One consequence: only a
holder of the age private key can check a stored blob's integrity, because
matching a blob to its name means decrypting and decompressing it first —
which is what `restore` and `verify --deep` do. Implemented in
`internal/blobgen` (`DoubleSHA256`). This is the canonical description of blob
naming; other documents and comments point here.
### Why Encrypted ### Why Encrypted
Blobs contain the actual file data from backups and must be encrypted for security. The content-addressing ensures deduplication while the encryption ensures privacy.
Blobs contain the actual file data from backups and must be encrypted for
security. The content-addressing ensures deduplication while the encryption
ensures privacy.
## Metadata Directory (`metadata/`) ## Metadata Directory (`metadata/`)
Each snapshot has its own subdirectory. The directory is **not** named with the Each snapshot has its own subdirectory. The directory is **not** named with the human-readable snapshot ID; it is named with the remote key — a one-way hash of that ID. The human ID is never written to the destination store as a directory name (see [Remote Key Derivation](#remote-key-derivation)).
human-readable snapshot ID; it is named with the remote key — a one-way hash of
that ID. The human ID is never written to the destination store as a directory
name (see [Remote Key Derivation](#remote-key-derivation)).
### Snapshot ID Format ### Snapshot ID Format
The human-readable snapshot ID is used in CLI arguments, log lines, and the The human-readable snapshot ID is used in CLI arguments, log lines, and the local database. It is not written to the destination store.
local database. It is not written to the destination store. - **Format**: `<hostname>_<snapshot-name>_<RFC3339>` (or `<hostname>_<RFC3339>` if no
name was specified)
- **Format**: `<hostname>_<snapshot-name>_<RFC3339>` (or `<hostname>_<RFC3339>`
if no name was specified)
- **Example**: `laptop_home_2024-01-15T14:30:52Z` - **Example**: `laptop_home_2024-01-15T14:30:52Z`
- **Components**: - **Components**:
- Short hostname (everything before the first dot is stripped from the FQDN) - Short hostname (everything before the first dot is stripped from the FQDN)
- Snapshot name from the configured `snapshots:` map (optional) - Snapshot name from the configured `snapshots:` map (optional)
- RFC3339 UTC timestamp - RFC3339 UTC timestamp
This ID reveals the hostname, the configured snapshot name, and the backup time, This ID reveals the hostname, the configured snapshot name, and the backup time, so it is never used as the on-disk directory name — the remote key is used instead.
so it is never used as the on-disk directory name — the remote key is used
instead.
### Remote Key Derivation ### Remote Key Derivation
The remote key is `hex(SHA256(SHA256("vaultik|" + snapshot-id)))`: a double The remote key is `hex(SHA256(SHA256("vaultik|" + snapshot-id)))`: a double SHA-256 over the snapshot ID, with a `vaultik|` domain-separation prefix. The result is a 64-character hex string. The hash is not reversible, but it uses no secret: an observer who guesses a candidate hostname and snapshot name can hash it the same way and confirm whether that snapshot is present. The remote key keeps names out of a plain listing; it does not hide them from a guess. Implemented in `internal/snapshot/remotekey.go`.
SHA-256 over the snapshot ID, with a `vaultik|` domain-separation prefix. The
result is a 64-character hex string. The hash is not reversible, but it uses no
secret: an observer who guesses a candidate hostname and snapshot name can hash
it the same way and confirm whether that snapshot is present. The remote key
keeps names out of a plain listing; it does not hide them from a guess.
Implemented in `internal/snapshot/remotekey.go`.
Worked example: Worked example:
- Snapshot ID: `server1_home_2025-06-01T12:00:00Z` - Snapshot ID: `server1_home_2025-06-01T12:00:00Z`
- Remote key: `17f97bcde958748af076b926af59823943db59e80ce7170b40f124dfa28f64aa` - Remote key: `17f97bcde958748af076b926af59823943db59e80ce7170b40f124dfa28f64aa`
- Directory: - Directory: `metadata/17f97bcde958748af076b926af59823943db59e80ce7170b40f124dfa28f64aa/`
`metadata/17f97bcde958748af076b926af59823943db59e80ce7170b40f124dfa28f64aa/`
A plain listing of the destination store therefore shows only these hashes, not A plain listing of the destination store therefore shows only these hashes, not the hostname or snapshot name of any backup — but because the hash uses no secret, a guessed hostname and snapshot name can be hashed and confirmed against the listing. The same remote key is stored in the manifest's `snapshot_id` field.
the hostname or snapshot name of any backup — but because the hash uses no
secret, a guessed hostname and snapshot name can be hashed and confirmed against
the listing. The same remote key is stored in the manifest's `snapshot_id`
field.
### Files in Each Snapshot Directory ### Files in Each Snapshot Directory
#### `db.zst.age` - Encrypted Database #### `db.zst.age` - Encrypted Database
- **What it contains**: Pruned binary SQLite database for this snapshot - **What it contains**: Pruned binary SQLite database for this snapshot
- **Format**: Binary SQLite → Zstandard compressed → Age encrypted - **Format**: Binary SQLite → Zstandard compressed → Age encrypted
- **Encryption**: Encrypted with Age - **Encryption**: Encrypted with Age
- **Purpose**: Contains full file metadata, chunk mappings, and all - **Purpose**: Contains full file metadata, chunk mappings, and all relationships
relationships - **Why encrypted**: Contains sensitive metadata like file paths, permissions, and ownership
- **Why encrypted**: Contains sensitive metadata like file paths, permissions,
and ownership
#### `manifest.json.zst` - Unencrypted Blob Manifest #### `manifest.json.zst` - Unencrypted Blob Manifest
- **What it contains**: JSON list of all blob hashes referenced by this snapshot - **What it contains**: JSON list of all blob hashes referenced by this snapshot
- **Format**: JSON → Zstandard compressed (NOT encrypted) - **Format**: JSON → Zstandard compressed (NOT encrypted)
- **Encryption**: NOT encrypted - **Encryption**: NOT encrypted
- **Purpose**: Enables pruning operations without requiring decryption keys - **Purpose**: Enables pruning operations without requiring decryption keys
- **Structure**: - **Structure**:
```json ```json
{ {
"snapshot_id": "17f97bcde958748af076b926af59823943db59e80ce7170b40f124dfa28f64aa", "snapshot_id": "17f97bcde958748af076b926af59823943db59e80ce7170b40f124dfa28f64aa",
"timestamp": "2025-06-01T12:00:00Z", "timestamp": "2025-06-01T12:00:00Z",
"blob_count": 42, "blob_count": 42,
"total_compressed_size": 1048576, "total_compressed_size": 1048576,
"blobs": [ "blobs": [
{ { "hash": "cafebabe1234567890abcdef1234567890abcdef1234567890abcdef12345678", "compressed_size": 24576 },
"hash": "cafebabe1234567890abcdef1234567890abcdef1234567890abcdef12345678", { "hash": "deadbeef1234567890abcdef1234567890abcdef1234567890abcdef12345678", "compressed_size": 32768 }
"compressed_size": 24576 ]
},
{
"hash": "deadbeef1234567890abcdef1234567890abcdef1234567890abcdef12345678",
"compressed_size": 32768
}
]
} }
``` ```
`snapshot_id` is the remote key (a hash), not the human ID; `timestamp` is written in the clear.
`snapshot_id` is the remote key (a hash), not the human ID; `timestamp` is
written in the clear.
### Why Manifest is Unencrypted ### Why Manifest is Unencrypted
The manifest must be readable without the private key to enable: The manifest must be readable without the private key to enable:
1. **Pruning operations** - Identifying unreferenced blobs for deletion 1. **Pruning operations** - Identifying unreferenced blobs for deletion
2. **Storage analysis** - Understanding space usage without decryption 2. **Storage analysis** - Understanding space usage without decryption
3. **Verification** - Checking blob existence without decryption 3. **Verification** - Checking blob existence without decryption
4. **Cross-snapshot deduplication analysis** - Finding shared blobs between 4. **Cross-snapshot deduplication analysis** - Finding shared blobs between snapshots
snapshots
The manifest contains the remote key, the backup timestamp, the blob count and The manifest contains the remote key, the backup timestamp, the blob count and total compressed size, and each blob's hash and compressed size. It contains no file names, paths, or other decrypted metadata.
total compressed size, and each blob's hash and compressed size. It contains no
file names, paths, or other decrypted metadata.
## Security Considerations ## Security Considerations
### What's Encrypted ### What's Encrypted
- **All file content** (in blobs) - **All file content** (in blobs)
- **All file metadata** (paths, permissions, timestamps, ownership in - **All file metadata** (paths, permissions, timestamps, ownership in db.zst.age)
db.zst.age)
- **File-to-chunk mappings** (in db.zst.age) - **File-to-chunk mappings** (in db.zst.age)
### What's Not Encrypted ### What's Not Encrypted
- **The remote key** — directory names and the manifest `snapshot_id`, a one-way hash of the snapshot ID (see [Remote Key Derivation](#remote-key-derivation))
- **The remote key** — directory names and the manifest `snapshot_id`, a one-way
hash of the snapshot ID (see [Remote Key Derivation](#remote-key-derivation))
- **The backup timestamp** (in manifest.json.zst) - **The backup timestamp** (in manifest.json.zst)
- **Blob hashes and their compressed sizes** (in manifest.json.zst) - **Blob hashes and their compressed sizes** (in manifest.json.zst)
- **Blob count and total compressed size per snapshot** (in manifest.json.zst) - **Blob count and total compressed size per snapshot** (in manifest.json.zst)
### Privacy Implications ### Privacy Implications
From the unencrypted data, an observer of the destination store can determine: From the unencrypted data, an observer of the destination store can determine:
- **When each backup was taken** — not from the directory name, which is a one-way hash, but from the plaintext `timestamp` field in manifest.json.zst, which is published in the clear
- **When each backup was taken** — not from the directory name, which is a
one-way hash, but from the plaintext `timestamp` field in manifest.json.zst,
which is published in the clear
- How many blobs each snapshot references, and the total compressed size - How many blobs each snapshot references, and the total compressed size
- The compressed size of each blob, and which blobs are shared between snapshots - The compressed size of each blob, and which blobs are shared between snapshots (deduplication patterns)
(deduplication patterns) - **Whether a guessed hostname and snapshot name are present** — the remote key is an unkeyed hash, so an observer holding candidate names can hash each one and match it against the directory listing. The human ID is never published, so it cannot be read off directly, but it can be confirmed by guessing.
- **Whether a guessed hostname and snapshot name are present** — the remote key
is an unkeyed hash, so an observer holding candidate names can hash each one
and match it against the directory listing. The human ID is never published,
so it cannot be read off directly, but it can be confirmed by guessing.
Together these give an observer a timing-and-size profile of every snapshot. Together these give an observer a timing-and-size profile of every snapshot. This is an accepted, documented property of the format, not a defect: the manifest is unencrypted so that pruning can run without the private key, and the timing channel could not be closed by encrypting it anyway — object creation times and per-object sizes stay visible at the storage layer on both `s3://` and `file://` destinations regardless.
This is an accepted, documented property of the format, not a defect: the
manifest is unencrypted so that pruning can run without the private key, and the
timing channel could not be closed by encrypting it anyway — object creation
times and per-object sizes stay visible at the storage layer on both `s3://` and
`file://` destinations regardless.
An observer cannot determine: An observer cannot determine:
- The hostname or snapshot name of any backup by reading it off the store — the directory name and the manifest `snapshot_id` are unkeyed hashes of the human ID, so the text is never published (though a guessed name can be confirmed, as above)
- The hostname or snapshot name of any backup by reading it off the store — the
directory name and the manifest `snapshot_id` are unkeyed hashes of the human
ID, so the text is never published (though a guessed name can be confirmed, as
above)
- File names or paths - File names or paths
- File contents - File contents
- File permissions or ownership - File permissions or ownership
@@ -236,118 +138,39 @@ An observer cannot determine:
### Accepted Risks ### Accepted Risks
These are known, deliberate properties of the format and the tooling, recorded These are known, deliberate properties of the format and the tooling, recorded so an operator can weigh them rather than discover them.
so an operator can weigh them rather than discover them.
1. **No proof of authorship.** Restore and `verify --deep` prove that data 1. **No proof of authorship.** Restore and `verify --deep` prove that data decrypts with the age private key and matches its unkeyed content hashes. They do not prove who wrote it: anyone who knows a recipient public key and can replace objects on the destination can substitute a snapshot they built. The recipient string is not stored at the destination, but a compromised backed-up host has it. Defences live on the destination side — bucket versioning or object lock, credentials for the source host that cannot delete or overwrite existing versions, and pruning from a trusted host. Note that S3 `PutObject` overwrites an existing key, so PUT permission alone is not append-only.
decrypts with the age private key and matches its unkeyed content hashes. 2. **Compression reveals sizes.** Blobs and `db.zst.age` are zstd-compressed then age-encrypted; the manifest is compressed only. age does not pad, so an object's size is the exact compressed length of its contents. All new chunks packed into one blob share a single zstd stream (8 MiB window, 4 MiB at compression levels 1-2), and a blob is closed at `blob_size_limit` and at the end of each configured path. Because a stored chunk is never packed again, someone who can write into a backed-up file and watch blob sizes learns something only when their controlled data and a secret land in the same chunk of a file that keeps changing. Advice: back up any outsider-writable directory as its own snapshot.
They do not prove who wrote it: anyone who knows a recipient public key and 3. **Chunking uses no secret.** The FastCDC parameters are fixed and public. The default 10 MB average yields chunks between 2.5 MB and 40 MB, and any file of 2.5 MB or less is a single chunk. At the default 10 GB `blob_size_limit` a blob holds hundreds of chunks, so individual chunk lengths are not visible in the blob's size; lowering the limit toward the chunk size begins to expose them.
can replace objects on the destination can substitute a snapshot they built. 4. **Decrypted data on local disk.** Several commands stage plaintext under `$TMPDIR`: `snapshot restore` writes decrypted blobs under `vaultik-blobcache-*/` (no size cap) and the decrypted metadata database at `vaultik-restore-*/snapshot.db`; `verify --deep` writes that database at `vaultik-verify-*/snapshot.db`; `snapshot create` keeps a plaintext copy of the index at `vaultik-snapshot-*/snapshot.db`. These files are created `0600` and removed on success, but a `kill -9` or a power loss leaves them behind — delete any leftover `vaultik-*` directory under `$TMPDIR` by hand. `$TMPDIR` should be trusted to the same degree as the restore target.
The recipient string is not stored at the destination, but a compromised 5. **Store permissions differ per command.** The backed-up host needs only PUT to run `snapshot create`: it writes blobs and metadata and neither reads nor deletes them. Other commands need more — `snapshot verify`, `snapshot restore`, and `prune` list and read; `prune`, `snapshot purge`, `snapshot remove`, and `remote nuke` also delete. The recommended cron line uses `--prune`, which runs `prune` on the backed-up host, so granting that host `--prune` gives it credentials that can delete its own backups. To keep the source host to PUT only, prune from a separate trusted host instead.
backed-up host has it. Defences live on the destination side — bucket 6. **Changing recipients does not re-encrypt existing data.** Deduplicated chunks and same-named blobs already on the destination stay encrypted to the recipients in force when they were written. A new snapshot that reuses them cannot be restored with a newly added recipient's key alone, because those reused objects were never encrypted to it. To make everything readable by a new key, run `vaultik database delete` and take a full backup to a fresh destination or prefix.
versioning or object lock, credentials for the source host that cannot delete 7. **X25519 recipients only.** vaultik rejects age ssh and plugin recipients. Long-lived ciphertext held by a third party (the destination operator) has no fallback if X25519 is ever broken: there is no second recipient type and no post-quantum option.
or overwrite existing versions, and pruning from a trusted host. Note that S3
`PutObject` overwrites an existing key, so PUT permission alone is not
append-only.
2. **Compression reveals sizes.** Blobs and `db.zst.age` are zstd-compressed
then age-encrypted; the manifest is compressed only. age does not pad, so an
object's size is the exact compressed length of its contents. All new chunks
packed into one blob share a single zstd stream (8 MiB window, 4 MiB at
compression levels 1-2), and a blob is closed at `blob_size_limit` and at the
end of each configured path. Because a stored chunk is never packed again,
someone who can write into a backed-up file and watch blob sizes learns
something only when their controlled data and a secret land in the same chunk
of a file that keeps changing. Advice: back up any outsider-writable
directory as its own snapshot.
3. **Chunking uses no secret.** The FastCDC parameters are fixed and public. The
default 10 MB average yields chunks between 2.5 MB and 40 MB, and any file of
2.5 MB or less is a single chunk. At the default 10 GB `blob_size_limit` a
blob holds hundreds of chunks, so individual chunk lengths are not visible in
the blob's size; lowering the limit toward the chunk size begins to expose
them.
4. **Decrypted data on local disk.** Several commands stage plaintext under
`$TMPDIR`: `snapshot restore` writes decrypted blobs under
`vaultik-blobcache-*/` (no size cap) and the decrypted metadata database at
`vaultik-restore-*/snapshot.db`; `verify --deep` writes that database at
`vaultik-verify-*/snapshot.db`; `snapshot create` keeps a plaintext copy of
the index at `vaultik-snapshot-*/snapshot.db`. These files are created `0600`
and removed on success, but a `kill -9` or a power loss leaves them behind —
delete any leftover `vaultik-*` directory under `$TMPDIR` by hand. `$TMPDIR`
should be trusted to the same degree as the restore target.
5. **Store permissions differ per command.** The backed-up host needs only PUT
to run `snapshot create`: it writes blobs and metadata and neither reads nor
deletes them. Other commands need more — `snapshot verify`,
`snapshot restore`, and `prune` list and read; `prune`, `snapshot purge`,
`snapshot remove`, and `remote nuke` also delete. The recommended cron line
uses `--prune`, which runs `prune` on the backed-up host, so granting that
host `--prune` gives it credentials that can delete its own backups. To keep
the source host to PUT only, prune from a separate trusted host instead.
6. **Changing recipients does not re-encrypt existing data.** Deduplicated
chunks and same-named blobs already on the destination stay encrypted to the
recipients in force when they were written. A new snapshot that reuses them
cannot be restored with a newly added recipient's key alone, because those
reused objects were never encrypted to it. To make everything readable by a
new key, run `vaultik database delete` and take a full backup to a fresh
destination or prefix.
7. **X25519 recipients only.** vaultik rejects age ssh and plugin recipients.
Long-lived ciphertext held by a third party (the destination operator) has no
fallback if X25519 is ever broken: there is no second recipient type and no
post-quantum option.
## Consistency Guarantees ## Consistency Guarantees
1. **Blobs are immutable** - Once written, a blob is never modified 1. **Blobs are immutable** - Once written, a blob is never modified
2. **Blobs are written before metadata** - A snapshot's metadata is only written 2. **Blobs are written before metadata** - A snapshot's metadata is only written after all its blobs are successfully uploaded
after all its blobs are successfully uploaded 3. **Metadata is written atomically** - Both db.zst.age and manifest.json.zst are written as complete files
3. **Metadata is written atomically** - Both db.zst.age and manifest.json.zst 4. **A snapshot is marked complete in the local DB only after its metadata is uploaded** - `finalizeSnapshotMetadata` runs `ExportSnapshotMetadata` first and records completion (`MarkSnapshotComplete`) only once the export succeeds (see the backup data flow in [ARCHITECTURE.md](../ARCHITECTURE.md)). A crash during the export therefore leaves the snapshot incomplete, so the next backup's `PruneDatabase` drops it and re-backs-up its data, rather than leaving a completed-looking row in the local index with no matching metadata on the destination store. (A crash in the brief moment after the export succeeds but before completion is recorded leaves a fully-restorable snapshot on the destination that the local index drops as incomplete on the next run; `snapshot list` then reports it honestly as remote-only, which is the safe direction: the destination copy stays restorable.)
are written as complete files
4. **A snapshot is marked complete in the local DB only after its metadata is
uploaded** - `finalizeSnapshotMetadata` runs `ExportSnapshotMetadata` first
and records completion (`MarkSnapshotComplete`) only once the export succeeds
(see the backup data flow in [ARCHITECTURE.md](ARCHITECTURE.md)). A crash
during the export therefore leaves the snapshot incomplete, so the next
backup's `PruneDatabase` drops it and re-backs-up its data, rather than
leaving a completed-looking row in the local index with no matching metadata
on the destination store. (A crash in the brief moment after the export
succeeds but before completion is recorded leaves a fully-restorable snapshot
on the destination that the local index drops as incomplete on the next run;
`snapshot list` then reports it honestly as remote-only, which is the safe
direction: the destination copy stays restorable.)
## Pruning Safety ## Pruning Safety
The prune operation is safe because: The prune operation is safe because:
1. It keeps every blob listed in any snapshot's manifest and deletes only blobs that no manifest references
1. It keeps every blob listed in any snapshot's manifest and deletes only blobs
that no manifest references. Under `metadata/` it deletes only a directory
that has no `manifest.json.zst`, whose name is a remote key, and that no
local snapshot record claims
2. Manifests are unencrypted and can be read without keys 2. Manifests are unencrypted and can be read without keys
3. If any manifest cannot be downloaded or decoded, prune deletes nothing and 3. If any manifest cannot be downloaded or decoded, prune deletes nothing and exits with an error, rather than treating that snapshot's blobs as unreferenced
exits with an error, rather than treating that snapshot's blobs as 4. Prune requires exclusive access to the destination: running it during a concurrent backup can race a snapshot whose manifest is not yet written, so do not prune while a backup is in progress
unreferenced
4. It deletes an unreferenced blob only once the blob is older than
`prune_grace_period` (default `24h`), and a directory under `metadata/` with
no manifest only once every object in it is. A backup uploads its blobs and
its `db.zst.age` before its manifest, so a prune running meanwhile, on this
host or another sharing the destination, leaves them as long as no backup run
takes longer than the grace period. The grace period does not protect a blob
a backup reuses from an earlier run that stopped before its manifest: the
backup skips the upload of a blob already on the destination, so that blob
keeps the time of its first upload, and a prune before the backup's manifest
is written can delete it; the new snapshot then cannot be restored.
`remote nuke` has no such check
## Restoration Requirements ## Restoration Requirements
To restore from a backup, you need: To restore from a backup, you need:
1. **The Age private key** - To decrypt blobs and database 1. **The Age private key** - To decrypt blobs and database
2. **The snapshot metadata** - Both files from the snapshot's metadata directory 2. **The snapshot metadata** - Both files from the snapshot's metadata directory
3. **All referenced blobs** - As listed in the manifest 3. **All referenced blobs** - As listed in the manifest
The restoration process: The restoration process:
1. Download and decrypt the database dump to understand file structure 1. Download and decrypt the database dump to understand file structure
2. Download and decrypt the required blobs 2. Download and decrypt the required blobs
3. Reconstruct files from their chunks 3. Reconstruct files from their chunks
-1224
View File
File diff suppressed because it is too large. Load diff
+1 -1
View File
@@ -22,7 +22,6 @@ require (
github.com/spf13/cobra v1.10.1 github.com/spf13/cobra v1.10.1
github.com/spf13/pflag v1.0.10 github.com/spf13/pflag v1.0.10
github.com/stretchr/testify v1.11.1 github.com/stretchr/testify v1.11.1
go.uber.org/dig v1.19.0
go.uber.org/fx v1.24.0 go.uber.org/fx v1.24.0
golang.org/x/sync v0.18.0 golang.org/x/sync v0.18.0
golang.org/x/sys v0.38.0 golang.org/x/sys v0.38.0
@@ -257,6 +256,7 @@ require (
go.opentelemetry.io/otel/metric v1.38.0 // indirect go.opentelemetry.io/otel/metric v1.38.0 // indirect
go.opentelemetry.io/otel/trace v1.38.0 // indirect go.opentelemetry.io/otel/trace v1.38.0 // indirect
go.shabbyrobe.org/gocovmerge v0.0.0-20230507111327-fa4f82cfbf4d // indirect go.shabbyrobe.org/gocovmerge v0.0.0-20230507111327-fa4f82cfbf4d // indirect
go.uber.org/dig v1.19.0 // indirect
go.uber.org/multierr v1.11.0 // indirect go.uber.org/multierr v1.11.0 // indirect
go.uber.org/zap v1.27.0 // indirect go.uber.org/zap v1.27.0 // indirect
go.yaml.in/yaml/v2 v2.4.3 // indirect go.yaml.in/yaml/v2 v2.4.3 // indirect
-11
View File
@@ -245,17 +245,6 @@ func (p *Packer) Flush(ctx context.Context) error {
return nil return nil
} }
// DiscardCurrentBlob closes and removes the temp file of the blob being
// packed, if any, and drops that blob. A caller that stops before Flush
// must call it, or the temp file is left behind. Thread-safe.
func (p *Packer) DiscardCurrentBlob() {
p.mu.Lock()
defer p.mu.Unlock()
p.cleanupTempFile()
p.currentBlob = nil
}
// FinalizeBlob finalizes the current blob being assembled. // FinalizeBlob finalizes the current blob being assembled.
// This compresses the accumulated chunks, encrypts the result, and computes // This compresses the accumulated chunks, encrypts the result, and computes
// the content-addressed hash. The finalized blob is either passed to the // the content-addressed hash. The finalized blob is either passed to the
+39 -55
View File
@@ -8,12 +8,12 @@ import (
"errors" "errors"
"fmt" "fmt"
"path/filepath" "path/filepath"
"strings"
"sync" "sync"
"time" "time"
"github.com/adrg/xdg" "github.com/adrg/xdg"
"github.com/spf13/cobra" "github.com/spf13/cobra"
"go.uber.org/dig"
"go.uber.org/fx" "go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/config" "sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database" "sneak.berlin/go/vaultik/internal/database"
@@ -90,7 +90,7 @@ func setupGlobals(
// blank line. Used both from the fx hook (for subcommand invocations) and // blank line. Used both from the fx hook (for subcommand invocations) and
// from the root cobra Run handler (for `vaultik` with no subcommand). // from the root cobra Run handler (for `vaultik` with no subcommand).
func writeStartupBanner(w *ui.Writer, startTime time.Time, shortCommit string) { func writeStartupBanner(w *ui.Writer, startTime time.Time, shortCommit string) {
w.Bannerf("%s %s by %s (commit %s, commit date %s) starting up at %s.", w.Bannerf("%s %s by %s (commit %s, built on %s) starting up at %s.",
globals.Appname, globals.Version, globals.Author, globals.Appname, globals.Version, globals.Author,
shortCommit, globals.CommitDate, shortCommit, globals.CommitDate,
startTime.Format(time.RFC3339)) startTime.Format(time.RFC3339))
@@ -146,12 +146,16 @@ func (e *startupError) Error() string {
// could not build arguments for function "Y" (file:line): failed to build U: // could not build arguments for function "Y" (file:line): failed to build U:
// received non-nil error from function "Z" (file:line): <real error> // received non-nil error from function "Z" (file:line): <real error>
// //
// Users care about the real error, not the DI plumbing. dig.RootCause, // Users care about the real error, not the DI plumbing. We strip everything
// from the library fx is built on, unwraps those layers and returns the // up through the last "): " (which is always the close-paren of an fx
// real error whole. Cutting the text at "): " instead would also cut a // function-location annotation followed by the wrapped error).
// real error that contains it, such as the blob_size_limit one.
func cleanStartupError(err error) error { func cleanStartupError(err error) error {
return &startupError{msg: dig.RootCause(err).Error()} msg := err.Error()
if idx := strings.LastIndex(msg, "): "); idx >= 0 {
msg = msg[idx+3:]
}
return &startupError{msg: msg}
} }
// RunApp starts the fx application, blocks until it is asked to stop, and // RunApp starts the fx application, blocks until it is asked to stop, and
@@ -196,16 +200,12 @@ func RunApp(ctx context.Context, app *fx.App) error {
} }
// errReported marks a failure the operation has already shown the user // errReported marks a failure the operation has already shown the user
// (or, under `snapshot verify --json`, put in its document). Entry // (and deliberately withheld under --json). Entry turns it into a
// turns it into a non-zero exit status without printing anything // non-zero exit status without printing anything further, so the error
// further, so the error line is not doubled. It flows up from // line is not doubled. It flows up from RunOperation through cobra to
// RunOperation through cobra to Entry. // Entry.
var errReported = errors.New("operation failed") var errReported = errors.New("operation failed")
// errInterrupted marks an operation that SIGINT or SIGTERM stopped
// before it finished. Entry shows it and returns exitCodeInterrupted.
var errInterrupted = errors.New("interrupted before the command finished")
// RunOperation runs op against the Vaultik instance inside the fx app // RunOperation runs op against the Vaultik instance inside the fx app
// and turns a failure into a returned error rather than an os.Exit from // and turns a failure into a returned error rather than an os.Exit from
// within the goroutine. An os.Exit there skipped main's deferred // within the goroutine. An os.Exit there skipped main's deferred
@@ -220,21 +220,17 @@ var errInterrupted = errors.New("interrupted before the command finished")
// interrupt OnStop cancels op and waits for the goroutine to return, so // interrupt OnStop cancels op and waits for the goroutine to return, so
// op's cleanup (removing decrypted scratch files) runs before the // op's cleanup (removing decrypted scratch files) runs before the
// process exits; the wait is bounded by shutdownTimeout. report is // process exits; the wait is bounded by shutdownTimeout. report is
// called with a failure so the caller can show it to the user before // called with a non-canceled failure so the caller can log it (and
// it becomes errReported. // suppress it under --json) before it becomes errReported. A context
// // cancellation is the interrupt path, not a failure: it is neither
// The run counts as interrupted unless op returned, without an // reported nor counted as one.
// interrupt having cancelled it, before RunWithApp returned. An
// interrupted op is not reported, whatever it returned; RunOperation
// returns errInterrupted instead.
func RunOperation( func RunOperation(
ctx context.Context, opts AppOptions, ctx context.Context, opts AppOptions,
op func(v *vaultik.Vaultik) error, report func(err error), op func(v *vaultik.Vaultik) error, report func(err error),
) error { ) error {
var ( var (
mu sync.Mutex mu sync.Mutex
finished bool // op returned before any interrupt cancelled it failed bool
failed bool // op finished with an error
) )
opts.Invokes = append(opts.Invokes, opts.Invokes = append(opts.Invokes,
@@ -245,21 +241,11 @@ func RunOperation(
OnStart: func(_ context.Context) error { OnStart: func(_ context.Context) error {
stop = v.StartOperation(func() { stop = v.StartOperation(func() {
err := op(v) err := op(v)
if err != nil && !errors.Is(err, context.Canceled) {
// Only stop, called from OnStop below, cancels the report(err)
// Vaultik context, so a live context means no
// interrupt cancelled op. Check the context, not
// err: an interrupted op need not return
// context.Canceled (`snapshot verify --json`
// returns a verification failure).
if v.Context().Err() == nil {
if err != nil {
report(err)
}
mu.Lock() mu.Lock()
finished = true failed = true
failed = err != nil
mu.Unlock() mu.Unlock()
} }
@@ -292,34 +278,28 @@ func RunOperation(
return err return err
} }
// RunWithApp returns only after the app was asked to stop, either by // The goroutine sets failed before triggering the shutdown that lets
// an interrupt or by the goroutine's Shutdown call. When op finished // RunWithApp return, so the write is in place by the time we read it.
// without being cancelled, the goroutine set finished before that
// call. So if finished is unset here, an interrupt stopped the app,
// and op either returned after it was cancelled or is still running
// because the shutdown timed out.
mu.Lock() mu.Lock()
defer mu.Unlock() defer mu.Unlock()
switch { if failed {
case !finished:
return errInterrupted
case failed:
return errReported return errReported
default:
return nil
} }
return nil
} }
// runVaultikApp runs the standard single-operation command lifecycle // runVaultikApp runs the standard single-operation command lifecycle
// shared by the snapshot list/purge/remove and remote nuke subcommands: // shared by the snapshot list/purge/remove and remote nuke subcommands:
// resolve the config, then run op against the Vaultik instance through // resolve the config, then run op against the Vaultik instance through
// RunOperation, reporting a failure prefixed with failMsg on stderr. mode // RunOperation, reporting a failure prefixed with failMsg (suppressed
// says whether the command takes the PID lock. jsonOutput marks a command // while suppressErrors is true, e.g. under --json). mode says whether the
// whose stdout is a JSON document: it quiets the UI but, unlike Quiet, // command takes the PID lock. jsonOutput marks a command whose stdout is a
// leaves the stderr log level alone. // JSON document: it quiets the UI but, unlike Quiet, leaves the stderr log
// level alone.
func runVaultikApp( func runVaultikApp(
cmd *cobra.Command, mode lockMode, jsonOutput bool, cmd *cobra.Command, mode lockMode, jsonOutput, suppressErrors bool,
failMsg string, op func(v *vaultik.Vaultik) error, failMsg string, op func(v *vaultik.Vaultik) error,
) error { ) error {
configPath, err := ResolveConfigPath() configPath, err := ResolveConfigPath()
@@ -339,6 +319,10 @@ func runVaultikApp(
}, },
Mode: mode, Mode: mode,
}, op, func(err error) { }, op, func(err error) {
if suppressErrors {
return
}
log.Error(failMsg, "error", err) log.Error(failMsg, "error", err)
ReportErrorf("%s: %v", failMsg, err) ReportErrorf("%s: %v", failMsg, err)
}) })
+40 -47
View File
@@ -2,65 +2,58 @@ package cli //nolint:testpackage // needs access to unexported cleanStartupError
import ( import (
"errors" "errors"
"os"
"path/filepath" "path/filepath"
"testing" "testing"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/pidlock" "sneak.berlin/go/vaultik/internal/pidlock"
) )
// TestCleanStartupError starts a real fx app whose config has a
// blob_size_limit below the minimum. fx puts annotations naming the
// functions it was building in front of the config error; only those
// may be removed, although the config error itself contains "): ".
func TestCleanStartupError(t *testing.T) { func TestCleanStartupError(t *testing.T) {
t.Parallel() t.Parallel()
path := filepath.Join(t.TempDir(), "config.yml") tests := []struct {
name string
err := os.WriteFile(path, []byte("snapshots:\n"+ in string
" test:\n"+ want string
" paths: [/tmp/vaultik-test-source]\n"+ }{
"storage_url: file:///tmp/vaultik-test-storage\n"+ {
"chunk_size: 10MB\n"+ name: "real fx error chain",
"blob_size_limit: 30MB\n"), 0o600) in: `could not build arguments for function ` +
if err != nil { `"sneak.berlin/go/vaultik/internal/cli".newSnapshotCreateCommand.func1.1 ` +
t.Fatalf("write config: %v", err) `(/Users/user/dev/vaultik/internal/cli/snapshot.go:71): ` +
`failed to build *vaultik.Vaultik: ` +
`could not build arguments for function ` +
`"sneak.berlin/go/vaultik/internal/vaultik".New ` +
`(/Users/user/dev/vaultik/internal/vaultik/vaultik.go:59): ` +
`failed to build storage.Storer: ` +
`received non-nil error from function ` +
`"sneak.berlin/go/vaultik/internal/storage".NewStorer ` +
`(/Users/user/dev/vaultik/internal/storage/module.go:23): ` +
`creating base path: mkdir /Volumes/BACKUPS: permission denied`,
want: `creating base path: mkdir /Volumes/BACKUPS: permission denied`,
},
{
name: "no fx wrapping",
in: "plain error",
want: "plain error",
},
{
name: "single fx wrapping",
in: `received non-nil error from function "foo" (file.go:1): underlying problem`,
want: "underlying problem",
},
} }
app := fx.New( for _, tt := range tests {
fx.NopLogger, t.Run(tt.name, func(t *testing.T) {
fx.Supply(config.Path(path)), t.Parallel()
config.Module,
fx.Invoke(func(*config.Config) {}),
)
err = app.Start(t.Context()) //nolint:err113 // test constructs errors from table input
if err == nil { got := cleanStartupError(errors.New(tt.in)).Error()
t.Fatal("app started; want a blob_size_limit error") if got != tt.want {
} t.Errorf("got %q, want %q", got, tt.want)
}
want := "failed to load config: invalid config: blob_size_limit must " + })
"be at least the largest chunk the chunker can emit (chunk_size " +
"times the FastCDC size spread): need at least 40000000 bytes"
got := cleanStartupError(err).Error()
if got != want {
t.Errorf("got %q, want %q", got, want)
}
}
// TestCleanStartupErrorNotFromFx checks that an error fx did not wrap is
// shown unchanged.
func TestCleanStartupErrorNotFromFx(t *testing.T) {
t.Parallel()
//nolint:err113 // a one-off error standing in for a startup failure
got := cleanStartupError(errors.New("plain error")).Error()
if got != "plain error" {
t.Errorf("got %q, want %q", got, "plain error")
} }
} }
+32 -230
View File
@@ -7,16 +7,11 @@ import (
"os" "os"
"os/exec" "os/exec"
"path/filepath" "path/filepath"
"reflect"
"runtime"
"slices"
"strconv" "strconv"
"strings" "strings"
"unicode/utf8"
"github.com/spf13/cobra" "github.com/spf13/cobra"
"gopkg.in/yaml.v3" "gopkg.in/yaml.v3"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/ui" "sneak.berlin/go/vaultik/internal/ui"
) )
@@ -31,14 +26,11 @@ const configSetArgs = 2
// parent config dirs (e.g. ~/.config) are conventionally traversable. // parent config dirs (e.g. ~/.config) are conventionally traversable.
const configDirMode = 0o755 const configDirMode = 0o755
// configYAMLIndent matches the 2-space indentation of the default config, // configYAMLIndent matches the 2-space indentation of defaultConfigTemplate,
// so `config set` writes the file back with the same indentation rather than // so `config set` writes the file back with the same indentation rather than
// yaml.Marshal's 4-space default. // yaml.Marshal's 4-space default.
const configYAMLIndent = 2 const configYAMLIndent = 2
// yamlStringTag is YAML's tag for a string scalar.
const yamlStringTag = "!!str"
var ( var (
errConfigExists = errors.New("config file already exists") errConfigExists = errors.New("config file already exists")
errEmptyConfig = errors.New("empty config file") errEmptyConfig = errors.New("empty config file")
@@ -46,27 +38,9 @@ var (
errNeedNumericIndex = errors.New("key is a list; use a numeric index") errNeedNumericIndex = errors.New("key is a list; use a numeric index")
errIndexOutOfRange = errors.New("index out of range") errIndexOutOfRange = errors.New("index out of range")
errNotMapOrList = errors.New("key is not a map or list") errNotMapOrList = errors.New("key is not a map or list")
errWouldNotLoad = errors.New(
"vaultik would not load the config after this change, " +
"so the file was not changed")
) )
// macOS is the value of runtime.GOOS on macOS. const defaultConfigTemplate = `# vaultik configuration
const macOS = "darwin"
// defaultConfigText returns the file `config init` writes on the operating
// system goos, named as runtime.GOOS names it. Only macOS gets the apps
// snapshot, since /Applications exists nowhere else.
func defaultConfigText(goos string) string {
if goos == macOS {
return defaultConfigHead + appsSnapshotConfig + defaultConfigTail
}
return defaultConfigHead + defaultConfigTail
}
// defaultConfigHead is the default config up to the end of the home snapshot.
const defaultConfigHead = `# vaultik configuration
# Documentation: https://sneak.berlin/go/vaultik # Documentation: https://sneak.berlin/go/vaultik
# ─── REQUIRED ──────────────────────────────────────────────────────────────── # ─── REQUIRED ────────────────────────────────────────────────────────────────
@@ -184,10 +158,7 @@ snapshots:
- "/Movies/ProxyMedia" - "/Movies/ProxyMedia"
- "/Music/iTunes/Album Artwork" - "/Music/iTunes/Album Artwork"
- "/Pictures/iPod Photo Cache" - "/Pictures/iPod Photo Cache"
`
// appsSnapshotConfig is the apps snapshot of the default config.
const appsSnapshotConfig = `
# Third-party applications. OS-provided apps live in /System/Applications # Third-party applications. OS-provided apps live in /System/Applications
# on modern macOS and are never in /Applications, but Apple-installed # on modern macOS and are never in /Applications, but Apple-installed
# App Store apps (Safari, GarageBand, iWork, iMovie) are excluded since # App Store apps (Safari, GarageBand, iWork, iMovie) are excluded since
@@ -208,10 +179,7 @@ const appsSnapshotConfig = `
- "/Steam.app" - "/Steam.app"
- "/VirtualBox.app" - "/VirtualBox.app"
- "/Utilities/Adobe Installers" - "/Utilities/Adobe Installers"
`
// defaultConfigTail is the default config after the snapshots.
const defaultConfigTail = `
# Storage backend (pick ONE of the three forms below). # Storage backend (pick ONE of the three forms below).
# #
# S3-compatible: # S3-compatible:
@@ -231,7 +199,7 @@ storage_url: ""
# access_key_id: YOUR_ACCESS_KEY # access_key_id: YOUR_ACCESS_KEY
# secret_access_key: YOUR_SECRET_KEY # secret_access_key: YOUR_SECRET_KEY
# # region: us-east-1 # Default: us-east-1 # # region: us-east-1 # Default: us-east-1
# # part_size: 5MiB # Upload part size, 5MiB to 5GiB. Default: 5MiB # # part_size: 5MB # Multipart upload part size. Default: 5MB
# # For the s3:// form, disable TLS with ?ssl=false in the URL, not use_ssl. # # For the s3:// form, disable TLS with ?ssl=false in the URL, not use_ssl.
# ─── OPTIONAL ──────────────────────────────────────────────────────────────── # ─── OPTIONAL ────────────────────────────────────────────────────────────────
@@ -246,7 +214,7 @@ storage_url: ""
# Average chunk size for content-defined chunking (FastCDC). # Average chunk size for content-defined chunking (FastCDC).
# Smaller = better deduplication but more metadata overhead. # Smaller = better deduplication but more metadata overhead.
# Minimum 1MB. Accepts: 1MB, 10M, 64MiB, etc. # Accepts: 1MB, 10M, 64KB, etc.
# Default: 10MB # Default: 10MB
# chunk_size: 10MB # chunk_size: 10MB
@@ -261,18 +229,6 @@ storage_url: ""
# Default: 3 # Default: 3
# compression_level: 3 # compression_level: 3
# How old a blob that no snapshot lists must be before prune deletes it,
# and how old every object in a directory under metadata/ with no manifest
# must be before prune deletes that directory. A backup uploads its blobs
# and its db.zst.age before its manifest, so on a destination shared
# between hosts or users this must be longer than the longest backup run.
# It does not protect a blob a backup reuses from an earlier run that
# stopped before its manifest: that blob keeps the time of its first
# upload, so a prune can delete it.
# Accepts: 36h, 90m, etc. 0s deletes such blobs and directories at once.
# Default: 24h
# prune_grace_period: 24h
# Hostname used in snapshot IDs. Default: system hostname. # Hostname used in snapshot IDs. Default: system hostname.
# hostname: myserver # hostname: myserver
@@ -289,12 +245,6 @@ func NewConfigCommand() *cobra.Command {
Use: "config", Use: "config",
Short: "Manage the configuration file", Short: "Manage the configuration file",
Long: "Commands for creating, editing, and querying the vaultik config file.", Long: "Commands for creating, editing, and querying the vaultik config file.",
// cobra checks Args only on a command that has a Run: without
// one, a mistyped subcommand printed help and exited 0.
Args: cobra.NoArgs,
Run: func(cmd *cobra.Command, _ []string) {
_ = cmd.Help()
},
} }
cmd.AddCommand(newConfigInitCommand()) cmd.AddCommand(newConfigInitCommand())
@@ -333,8 +283,7 @@ on macOS, ~/.config/ on Linux, /etc/vaultik/ as root).`,
return fmt.Errorf("creating config directory %s: %w", dir, err) return fmt.Errorf("creating config directory %s: %w", dir, err)
} }
err = os.WriteFile(path, []byte(defaultConfigText(runtime.GOOS)), err = os.WriteFile(path, []byte(defaultConfigTemplate), configFileMode)
configFileMode)
if err != nil { if err != nil {
return fmt.Errorf("writing config file: %w", err) return fmt.Errorf("writing config file: %w", err)
} }
@@ -368,15 +317,8 @@ func newConfigEditCommand() *cobra.Command {
editor = "vi" editor = "vi"
} }
// Run $EDITOR through the shell, as git does, so a value
// with arguments such as "code --wait" works. The path
// goes in as an argument ("$@"), not into the command
// text, so a path with spaces or quotes arrives whole.
// sh -c takes the word after the command as $0, which
// is why editor appears twice.
//nolint:gosec // G204: launching the operator's own $EDITOR is the point //nolint:gosec // G204: launching the operator's own $EDITOR is the point
ed := exec.CommandContext(cmd.Context(), ed := exec.CommandContext(cmd.Context(), editor, path)
"sh", "-c", editor+` "$@"`, editor, path)
ed.Stdin = os.Stdin ed.Stdin = os.Stdin
ed.Stdout = os.Stdout ed.Stdout = os.Stdout
ed.Stderr = os.Stderr ed.Stderr = os.Stderr
@@ -437,17 +379,8 @@ func newConfigSetCommand() *cobra.Command {
Use: "set <key> <value>", Use: "set <key> <value>",
Short: "Set a config value by dotted path (e.g. compression_level 5)", Short: "Set a config value by dotted path (e.g. compression_level 5)",
Long: `Sets a scalar config value addressed by dotted YAML path and writes Long: `Sets a scalar config value addressed by dotted YAML path and writes
the file back, preserving comments and formatting. Missing keys along the file back, preserving comments and formatting. Intermediate maps
the path are created: as a list when the next path element is a are created as needed.
number, otherwise as a map.
If the config loads, a change after which it would not, such as
compression_level 99, is refused and the file is left unchanged. A
config that does not load, such as the one config init writes before
storage_url is set or one with a ${ENV:...} reference to a variable
not set here, is checked one setting at a time: only a change after
which the changed setting cannot be read, such as one giving it the
wrong type, is refused.
Examples: Examples:
vaultik config set storage_url "file:///mnt/backups" vaultik config set storage_url "file:///mnt/backups"
@@ -477,14 +410,7 @@ func writeConfigSet(out *ui.Writer, path, key, value string) error {
return err return err
} }
oldData, err := marshalConfigYAML(root) err = yamlPathSet(root, strings.Split(key, "."), value)
if err != nil {
return fmt.Errorf("marshaling config: %w", err)
}
keys := strings.Split(key, ".")
err = yamlPathSet(root, keys, value)
if err != nil { if err != nil {
return err return err
} }
@@ -494,21 +420,6 @@ func writeConfigSet(out *ui.Writer, path, key, value string) error {
return fmt.Errorf("marshaling config: %w", err) return fmt.Errorf("marshaling config: %w", err)
} }
setting, err := yamlPathOnly(root, keys)
if err != nil {
return err
}
settingData, err := marshalConfigYAML(setting)
if err != nil {
return fmt.Errorf("marshaling config: %w", err)
}
err = checkConfigChange(oldData, data, settingData)
if err != nil {
return fmt.Errorf("%w: %w", errWouldNotLoad, err)
}
err = os.WriteFile(path, data, configFileMode) err = os.WriteFile(path, data, configFileMode)
if err != nil { if err != nil {
return fmt.Errorf("writing config file: %w", err) return fmt.Errorf("writing config file: %w", err)
@@ -530,60 +441,8 @@ func writeConfigSet(out *ui.Writer, path, key, value string) error {
return nil return nil
} }
// checkConfigChange returns the reason vaultik would not load newData, the
// config after a change, if the change brings that failure in. If oldData,
// the config before it, loads, the new one must load too. A config that
// does not load, such as one still being filled in or one with a ${...}
// reference that cannot be filled in here, is checked one setting at a
// time: settingData, the changed setting on its own, must decode into the
// config type.
func checkConfigChange(oldData, newData, settingData []byte) error {
oldCfg, err := config.Parse(oldData)
if err == nil && oldCfg.Validate() == nil {
newCfg, err := config.Parse(newData)
if err != nil {
return err
}
return newCfg.Validate()
}
_, err = config.Parse(settingData)
return err
}
// yamlPathOnly returns a document holding only the value at the dotted key
// path in root, inside the maps and lists that lead to it there.
func yamlPathOnly(root *yaml.Node, keys []string) (*yaml.Node, error) {
node, err := yamlPathGet(root, keys)
if err != nil {
return nil, err
}
for i, key := range slices.Backward(keys) {
parent, err := yamlPathGet(root, keys[:i])
if err != nil {
return nil, err
}
if parent.Kind == yaml.SequenceNode {
node = &yaml.Node{
Kind: yaml.SequenceNode, Content: []*yaml.Node{node},
}
} else {
keyNode := &yaml.Node{Kind: yaml.ScalarNode, Value: key}
node = &yaml.Node{
Kind: yaml.MappingNode, Content: []*yaml.Node{keyNode, node},
}
}
}
return &yaml.Node{Kind: yaml.DocumentNode, Content: []*yaml.Node{node}}, nil
}
// marshalConfigYAML renders a config document tree with 2-space indentation, // marshalConfigYAML renders a config document tree with 2-space indentation,
// matching the default config. yaml.Marshal defaults to 4 spaces, which // matching defaultConfigTemplate. yaml.Marshal defaults to 4 spaces, which
// would reindent the whole file on the first `config set` despite the promise // would reindent the whole file on the first `config set` despite the promise
// to preserve formatting. // to preserve formatting.
func marshalConfigYAML(root *yaml.Node) ([]byte, error) { func marshalConfigYAML(root *yaml.Node) ([]byte, error) {
@@ -688,8 +547,8 @@ func yamlPathGet(root *yaml.Node, keys []string) (*yaml.Node, error) {
return node, nil return node, nil
} }
// yamlPathSet navigates a dotted key path, creating missing keys as needed, // yamlPathSet navigates a dotted key path, creating intermediate maps as
// and sets the final key to the given scalar value. Numeric path // needed, and sets the final key to the given scalar value. Numeric path
// components index into sequences; an index equal to the sequence length // components index into sequences; an index equal to the sequence length
// appends a new element (e.g. "age_recipients.1" on a 1-element list). // appends a new element (e.g. "age_recipients.1" on a 1-element list).
func yamlPathSet(root *yaml.Node, keys []string, value string) error { func yamlPathSet(root *yaml.Node, keys []string, value string) error {
@@ -702,12 +561,12 @@ func yamlPathSet(root *yaml.Node, keys []string, value string) error {
node = node.Content[0] node = node.Content[0]
} }
for i := range keys { for i, key := range keys {
last := i == len(keys)-1 last := i == len(keys)-1
switch node.Kind { switch node.Kind {
case yaml.MappingNode: case yaml.MappingNode:
node = yamlSetInMapping(node, keys, i, value, last) node = yamlSetInMapping(node, key, value, last)
case yaml.SequenceNode: case yaml.SequenceNode:
next, err := yamlSetInSequence(node, keys, i, value, last) next, err := yamlSetInSequence(node, keys, i, value, last)
if err != nil { if err != nil {
@@ -724,68 +583,17 @@ func yamlPathSet(root *yaml.Node, keys []string, value string) error {
} }
} }
// config.Load reads the file through untyped YAML, which turns an
// unquoted 00112233 into the number 38043 and 1e5 into 100000. Tagging
// a string setting as a string makes the encoder quote such a value.
// Other settings stay unquoted, so compression_level 9 is a number.
// The encoder refuses to write a value that is not valid UTF-8 as a
// string. Left untagged, such a value is written as base64 !!binary and
// loads back unchanged.
if configKeyIsString(keys) && utf8.ValidString(value) {
node.Tag = yamlStringTag
}
return nil return nil
} }
// configKeyIsString reports whether the dotted key names a string in // yamlSetInMapping resolves (creating if needed) the value node for key
// config.Config, following the fields' yaml tags, as s3.access_key_id and // within a mapping node, setting it to value when it is the final path
// snapshots.home.exclude.0 do. // element, and returns the node to descend into.
func configKeyIsString(keys []string) bool { func yamlSetInMapping(node *yaml.Node, key, value string, last bool) *yaml.Node {
typ := reflect.TypeFor[config.Config]()
for _, key := range keys {
switch {
case typ.Kind() == reflect.Map || typ.Kind() == reflect.Slice:
// The key is a snapshot name or a list index.
typ = typ.Elem()
case typ.Kind() == reflect.Struct:
field, ok := yamlField(typ, key)
if !ok {
return false
}
typ = field.Type
default:
return false
}
}
return typ.Kind() == reflect.String
}
// yamlField returns the field of struct type typ whose yaml tag names key.
func yamlField(typ reflect.Type, key string) (reflect.StructField, bool) {
for field := range typ.Fields() {
name, _, _ := strings.Cut(field.Tag.Get("yaml"), ",")
if name == key {
return field, true
}
}
return reflect.StructField{}, false
}
// yamlSetInMapping resolves (creating if needed) the value node for the
// path element keys[i] within a mapping node, setting it to value when it
// is the final path element, and returns the node to descend into.
func yamlSetInMapping(
node *yaml.Node, keys []string, i int, value string, last bool,
) *yaml.Node {
var valueNode *yaml.Node var valueNode *yaml.Node
for j := 0; j+1 < len(node.Content); j += 2 { for j := 0; j+1 < len(node.Content); j += 2 {
if node.Content[j].Value == keys[i] { if node.Content[j].Value == key {
valueNode = node.Content[j+1] valueNode = node.Content[j+1]
break break
@@ -793,8 +601,13 @@ func yamlSetInMapping(
} }
if valueNode == nil { if valueNode == nil {
keyNode := &yaml.Node{Kind: yaml.ScalarNode, Value: keys[i]} keyNode := &yaml.Node{Kind: yaml.ScalarNode, Value: key}
valueNode = newPathNode(keys, i, value)
valueNode = &yaml.Node{Kind: yaml.MappingNode}
if last {
valueNode = &yaml.Node{Kind: yaml.ScalarNode, Value: value}
}
node.Content = append(node.Content, keyNode, valueNode) node.Content = append(node.Content, keyNode, valueNode)
} else if last { } else if last {
setScalar(valueNode, value) setScalar(valueNode, value)
@@ -822,7 +635,12 @@ func yamlSetInSequence(
} }
if idx == len(node.Content) { if idx == len(node.Content) {
node.Content = append(node.Content, newPathNode(keys, i, value)) newNode := &yaml.Node{Kind: yaml.MappingNode}
if last {
newNode = &yaml.Node{Kind: yaml.ScalarNode, Value: value}
}
node.Content = append(node.Content, newNode)
} else if last { } else if last {
setScalar(node.Content[idx], value) setScalar(node.Content[idx], value)
} }
@@ -830,22 +648,6 @@ func yamlSetInSequence(
return node.Content[idx], nil return node.Content[idx], nil
} }
// newPathNode returns the node to create for the missing path element
// keys[i]: the value when it is the final path element, otherwise an empty
// list when the next path element is a number and an empty map when not.
func newPathNode(keys []string, i int, value string) *yaml.Node {
if i == len(keys)-1 {
return &yaml.Node{Kind: yaml.ScalarNode, Value: value}
}
_, err := strconv.Atoi(keys[i+1])
if err == nil {
return &yaml.Node{Kind: yaml.SequenceNode}
}
return &yaml.Node{Kind: yaml.MappingNode}
}
// setScalar overwrites a node in place with a plain scalar value. // setScalar overwrites a node in place with a plain scalar value.
func setScalar(n *yaml.Node, value string) { func setScalar(n *yaml.Node, value string) {
n.Kind = yaml.ScalarNode n.Kind = yaml.ScalarNode
+10 -379
View File
@@ -4,7 +4,6 @@ import (
"bytes" "bytes"
"os" "os"
"path/filepath" "path/filepath"
"strconv"
"strings" "strings"
"testing" "testing"
@@ -13,15 +12,14 @@ import (
"sneak.berlin/go/vaultik/internal/ui" "sneak.berlin/go/vaultik/internal/ui"
) )
// TestDefaultConfigParsesOnMacOS ensures the config `config init` writes on // TestDefaultConfigTemplateParses ensures the init template is valid YAML
// macOS is valid YAML that unmarshals into the Config struct with the // that unmarshals into the Config struct with the expected snapshots.
// expected snapshots. func TestDefaultConfigTemplateParses(t *testing.T) {
func TestDefaultConfigParsesOnMacOS(t *testing.T) {
t.Parallel() t.Parallel()
var cfg config.Config var cfg config.Config
err := yaml.Unmarshal([]byte(defaultConfigText("darwin")), &cfg) err := yaml.Unmarshal([]byte(defaultConfigTemplate), &cfg)
if err != nil { if err != nil {
t.Fatalf("default config template is not valid YAML: %v", err) t.Fatalf("default config template is not valid YAML: %v", err)
} }
@@ -59,60 +57,24 @@ func TestDefaultConfigParsesOnMacOS(t *testing.T) {
} }
} }
// TestDefaultConfigOnLinux checks that the config `config init` writes on
// Linux loads with its home snapshot and without the apps snapshot, whose
// /Applications exists only on macOS.
func TestDefaultConfigOnLinux(t *testing.T) {
t.Parallel()
path := filepath.Join(t.TempDir(), "config.yml")
err := os.WriteFile(path, []byte(defaultConfigText("linux")), configFileMode)
if err != nil {
t.Fatalf("write config: %v", err)
}
err = writeConfigSet(ui.NewWithColor(&bytes.Buffer{}, false),
path, "storage_url", "file:///mnt/backups")
if err != nil {
t.Fatalf("config set storage_url: %v", err)
}
cfg, err := config.Load(path)
if err != nil {
t.Fatalf("config.Load: %v", err)
}
if _, ok := cfg.Snapshots["home"]; !ok {
t.Error("expected 'home' snapshot in the Linux default config")
}
if _, ok := cfg.Snapshots["apps"]; ok {
t.Error("the Linux default config should have no 'apps' snapshot")
}
}
// testRecipient is a valid age public key.
const testRecipient = "age1278m9q7dp3chsh2dcy82qk27v047zywyvtxwnj4cvt0z65jw6a7q5dqhfj"
// TestConfigSetRecipientOnFreshConfig follows the README quickstart: on the // TestConfigSetRecipientOnFreshConfig follows the README quickstart: on the
// file `config init` writes, `config set age_recipients.0` and // file `config init` writes, `config set age_recipients.0` and
// `config set storage_url` give a config that loads with that recipient. // `config set storage_url` give a config that loads with that recipient.
// Neither is refused, although the config does not load until both are set;
// once it loads, a recipient that is not a valid key is.
func TestConfigSetRecipientOnFreshConfig(t *testing.T) { func TestConfigSetRecipientOnFreshConfig(t *testing.T) {
t.Parallel() t.Parallel()
const recipient = "age1278m9q7dp3chsh2dcy82qk27v047zywyvtxwnj4cvt0z65jw6a7q5dqhfj"
path := filepath.Join(t.TempDir(), "config.yml") path := filepath.Join(t.TempDir(), "config.yml")
err := os.WriteFile(path, []byte(defaultConfigText(macOS)), configFileMode) err := os.WriteFile(path, []byte(defaultConfigTemplate), configFileMode)
if err != nil { if err != nil {
t.Fatalf("write config: %v", err) t.Fatalf("write config: %v", err)
} }
out := ui.NewWithColor(&bytes.Buffer{}, false) out := ui.NewWithColor(&bytes.Buffer{}, false)
err = writeConfigSet(out, path, "age_recipients.0", testRecipient) err = writeConfigSet(out, path, "age_recipients.0", recipient)
if err != nil { if err != nil {
t.Fatalf("config set age_recipients.0: %v", err) t.Fatalf("config set age_recipients.0: %v", err)
} }
@@ -127,316 +89,9 @@ func TestConfigSetRecipientOnFreshConfig(t *testing.T) {
t.Fatalf("config.Load: %v", err) t.Fatalf("config.Load: %v", err)
} }
if len(cfg.AgeRecipients) != 1 || cfg.AgeRecipients[0] != testRecipient { if len(cfg.AgeRecipients) != 1 || cfg.AgeRecipients[0] != recipient {
t.Errorf("age_recipients = %v, want [%s]", cfg.AgeRecipients, testRecipient) t.Errorf("age_recipients = %v, want [%s]", cfg.AgeRecipients, recipient)
} }
err = writeConfigSet(out, path, "age_recipients.0", "notakey")
if err == nil || !strings.Contains(err.Error(), "not a valid recipient") {
t.Errorf("config set age_recipients.0 notakey gives error %v, "+
"want one saying it is not a valid recipient", err)
}
_, err = config.Load(path)
if err != nil {
t.Errorf("config.Load after the refused change: %v", err)
}
}
// configWithoutRecipients loads, but has no age_recipients key and no
// snapshot named work.
const configWithoutRecipients = `storage_url: file:///mnt/backups
snapshots:
home:
paths:
- "~"
`
// configWithUnsetReference loads only where VAULTIK_TEST_UNSET_SECRET is
// set, as a backup job's environment might set it. No test sets it.
const configWithUnsetReference = configWithoutRecipients + `s3:
secret_access_key: ${ENV:VAULTIK_TEST_UNSET_SECRET}
`
// configWithLevelReference returns configWithoutRecipients with a ${FILE:...}
// reference on compression_level to a file holding 9, so that the config
// loads once the reference is filled in.
func configWithLevelReference(t *testing.T) string {
t.Helper()
levelPath := filepath.Join(t.TempDir(), "level")
err := os.WriteFile(levelPath, []byte("9"), configFileMode)
if err != nil {
t.Fatalf("write level: %v", err)
}
return configWithoutRecipients +
"compression_level: ${FILE:" + levelPath + "}\n"
}
// TestConfigSetIndexUnderMissingKey checks that a list index under a key
// the file does not have creates a list, and that the result loads.
func TestConfigSetIndexUnderMissingKey(t *testing.T) {
t.Parallel()
tests := []struct {
key string
value string
field func(cfg *config.Config) []string
}{
{"age_recipients.0", testRecipient,
func(cfg *config.Config) []string { return cfg.AgeRecipients }},
{"snapshots.work.paths.0", "/srv/work",
func(cfg *config.Config) []string { return cfg.Snapshots["work"].Paths }},
}
for _, tt := range tests {
t.Run(tt.key, func(t *testing.T) {
t.Parallel()
path := filepath.Join(t.TempDir(), "config.yml")
err := os.WriteFile(path, []byte(configWithoutRecipients), configFileMode)
if err != nil {
t.Fatalf("write config: %v", err)
}
err = writeConfigSet(ui.NewWithColor(&bytes.Buffer{}, false),
path, tt.key, tt.value)
if err != nil {
t.Fatalf("config set %s: %v", tt.key, err)
}
cfg, err := config.Load(path)
if err != nil {
t.Fatalf("config.Load: %v", err)
}
got := tt.field(cfg)
if len(got) != 1 || got[0] != tt.value {
t.Errorf("%s gives %v, want [%s]", tt.key, got, tt.value)
}
})
}
}
// TestConfigSetKeepsFileThatWouldNotLoad checks that config set refuses a
// change after which the config would not load, with an error giving the
// reason, and leaves the file as it was. On the file `config init` writes,
// which does not load until storage_url is set, and on one that cannot be
// read here, only a value of the wrong type is refused.
func TestConfigSetKeepsFileThatWouldNotLoad(t *testing.T) {
t.Parallel()
levelReference := configWithLevelReference(t)
tests := []struct {
config string
key string
value string
reason string
}{
// Index 1 of the empty list the missing key gives.
{configWithoutRecipients, "age_recipients.1", testRecipient,
"index out of range"},
// A list set to a single value.
{configWithoutRecipients, "snapshots.home.paths", "/srv",
"into []string"},
{configWithoutRecipients, "chunk_size", "fast",
"invalid size format"},
// Values of the right type that fail validation.
{configWithoutRecipients, "compression_level", "99",
"compression_level must be between 1 and 19"},
{configWithoutRecipients, "chunk_size", "1KB",
"chunk_size must be at least 1MB"},
// With its reference filled in, the config loads.
{levelReference, "blob_size_limit", "1MB",
"blob_size_limit must be at least"},
// The type check on a config that does not load yet.
{defaultConfigText(macOS), "snapshots.apps.paths", "/srv",
"into []string"},
// The type check on a config that cannot be read here.
{configWithUnsetReference, "snapshots.home.paths", "/x",
"cannot unmarshal !!str `/x`"},
}
for _, tt := range tests {
t.Run(tt.key+" "+tt.value, func(t *testing.T) {
t.Parallel()
path := filepath.Join(t.TempDir(), "config.yml")
err := os.WriteFile(path, []byte(tt.config), configFileMode)
if err != nil {
t.Fatalf("write config: %v", err)
}
err = writeConfigSet(ui.NewWithColor(&bytes.Buffer{}, false),
path, tt.key, tt.value)
if err == nil || !strings.Contains(err.Error(), tt.reason) {
t.Errorf("config set %s %s gives error %v, want one saying %q",
tt.key, tt.value, err, tt.reason)
}
data, err := os.ReadFile(path) //nolint:gosec // G304: test-controlled path
if err != nil {
t.Fatalf("read config: %v", err)
}
if string(data) != tt.config {
t.Errorf("config set %s changed the file to:\n%s",
tt.key, data)
}
})
}
}
// TestConfigSetRefusesOnlyItsOwnFailure checks that setting another key
// works on a config with a ${...} reference on compression_level, which
// loads because loading fills the reference in, on one whose
// compression_level already fails to load, and on one with a reference
// that cannot be filled in here.
func TestConfigSetRefusesOnlyItsOwnFailure(t *testing.T) {
t.Parallel()
configs := map[string]string{
"reference": configWithLevelReference(t),
"failing": configWithoutRecipients + "compression_level: fast\n",
"unset reference": configWithUnsetReference,
}
for name, configYAML := range configs {
t.Run(name, func(t *testing.T) {
t.Parallel()
path := filepath.Join(t.TempDir(), "config.yml")
err := os.WriteFile(path, []byte(configYAML), configFileMode)
if err != nil {
t.Fatalf("write config: %v", err)
}
err = writeConfigSet(ui.NewWithColor(&bytes.Buffer{}, false),
path, "hostname", "myhost")
if err != nil {
t.Fatalf("config set hostname: %v", err)
}
data, err := os.ReadFile(path) //nolint:gosec // G304: test-controlled path
if err != nil {
t.Fatalf("read config: %v", err)
}
if !strings.Contains(string(data), "hostname: myhost") {
t.Errorf("config set hostname wrote:\n%s", data)
}
})
}
}
// TestConfigSetStringLooksLikeNumber sets string settings to values that
// YAML reads as numbers or booleans when they are unquoted, and checks that
// config.Load returns each one unchanged.
func TestConfigSetStringLooksLikeNumber(t *testing.T) {
t.Parallel()
tests := []struct {
key string
value string
field func(cfg *config.Config) string
}{
{"s3.access_key_id", "00112233",
func(cfg *config.Config) string { return cfg.S3.AccessKeyID }},
{"s3.secret_access_key", "12345678901234567890123456789012",
func(cfg *config.Config) string { return cfg.S3.SecretAccessKey }},
{"hostname", "007",
func(cfg *config.Config) string { return cfg.Hostname }},
{"s3.prefix", "1e5",
func(cfg *config.Config) string { return cfg.S3.Prefix }},
{"s3.bucket", "true",
func(cfg *config.Config) string { return cfg.S3.Bucket }},
{"s3.region", "FALSE",
func(cfg *config.Config) string { return cfg.S3.Region }},
{"snapshots.home.exclude.0", "1.10",
func(cfg *config.Config) string { return cfg.Snapshots["home"].Exclude[0] }},
}
for _, tt := range tests {
t.Run(tt.key+"="+tt.value, func(t *testing.T) {
t.Parallel()
cfg := loadAfterConfigSet(t, tt.key, tt.value)
got := tt.field(cfg)
if got != tt.value {
t.Errorf("%s = %q after config set %q", tt.key, got, tt.value)
}
})
}
}
// TestConfigSetNonUTF8Path checks that config set still accepts a value that
// is not valid UTF-8, such as a path with a Latin-1 file name, and that
// config.Load returns it unchanged.
func TestConfigSetNonUTF8Path(t *testing.T) {
t.Parallel()
const dir = "/srv/caf\xe9"
cfg := loadAfterConfigSet(t, "snapshots.home.paths.0", dir)
got := cfg.Snapshots["home"].Paths[0]
if got != dir {
t.Errorf("snapshots.home.paths.0 = %q, want %q", got, dir)
}
}
// TestConfigSetNumberStaysNumber checks that a number set for an integer
// setting is still read as a number, not as a quoted string.
func TestConfigSetNumberStaysNumber(t *testing.T) {
t.Parallel()
const level = 9
cfg := loadAfterConfigSet(t, "compression_level", strconv.Itoa(level))
if cfg.CompressionLevel != level {
t.Errorf("compression_level = %d, want %d", cfg.CompressionLevel, level)
}
}
// loadAfterConfigSet writes the file `config init` writes, sets storage_url
// to a local directory so that the file passes validation, applies
// `config set key value` and returns what config.Load reads back.
func loadAfterConfigSet(t *testing.T, key, value string) *config.Config {
t.Helper()
path := filepath.Join(t.TempDir(), "config.yml")
err := os.WriteFile(path, []byte(defaultConfigText(macOS)), configFileMode)
if err != nil {
t.Fatalf("write config: %v", err)
}
out := ui.NewWithColor(&bytes.Buffer{}, false)
err = writeConfigSet(out, path, "storage_url", "file:///mnt/backups")
if err != nil {
t.Fatalf("config set storage_url: %v", err)
}
err = writeConfigSet(out, path, key, value)
if err != nil {
t.Fatalf("config set %s: %v", key, err)
}
cfg, err := config.Load(path)
if err != nil {
t.Fatalf("config.Load: %v", err)
}
return cfg
} }
const testYAML = `# top comment const testYAML = `# top comment
@@ -681,30 +336,6 @@ func TestWriteConfigSetTightensMode(t *testing.T) {
} }
} }
// TestConfigEditEditorWithArgument checks that an $EDITOR carrying an
// argument works and that a config path with a space reaches it whole.
// The "editor" is cp with the replacement file as its argument, so the
// config ends up with the replacement's content only if both arrived.
func TestConfigEditEditorWithArgument(t *testing.T) {
dir := t.TempDir()
path := seedFile(t, dir, "my config.yml", "compression_level: 3\n")
edited := seedFile(t, dir, "edited.yml", "compression_level: 9\n")
setRootFlags(t, RootFlags{ConfigPath: path})
t.Setenv("EDITOR", "cp '"+edited+"'")
mustExecute(t, newConfigEditCommand())
data, err := os.ReadFile(path) //nolint:gosec // G304: test-controlled path
if err != nil {
t.Fatalf("reading config back: %v", err)
}
if string(data) != "compression_level: 9\n" {
t.Errorf("config after edit = %q, want the edited content", data)
}
}
func splitPath(s string) []string { func splitPath(s string) []string {
return strings.Split(s, ".") return strings.Split(s, ".")
} }
-6
View File
@@ -15,12 +15,6 @@ func NewDatabaseCommand() *cobra.Command {
Use: "database", Use: "database",
Short: "Manage the local state database", Short: "Manage the local state database",
Long: `Commands for managing the local SQLite state database.`, Long: `Commands for managing the local SQLite state database.`,
// cobra checks Args only on a command that has a Run: without
// one, a mistyped subcommand printed help and exited 0.
Args: cobra.NoArgs,
Run: func(cmd *cobra.Command, _ []string) {
_ = cmd.Help()
},
} }
cmd.AddCommand( cmd.AddCommand(
+13 -25
View File
@@ -15,25 +15,17 @@ import (
// the startup banner. // the startup banner.
const shortCommitLen = 12 const shortCommitLen = 12
// exitCodeInterrupted is the exit status of a command that SIGINT or
// SIGTERM stopped. It is 128 plus SIGINT's number, 2, which is what a
// shell reports for a command stopped by Ctrl-C.
const exitCodeInterrupted = 130
// Entry is the main entry point for the CLI application. // Entry is the main entry point for the CLI application.
// It prints the startup banner to stderr (unless a banner-suppressing // It prints the startup banner to stdout (unless a banner-suppressing
// flag is present in os.Args — see bannerSuppressedInArgs), executes the // flag is present in os.Args — see bannerSuppressedInArgs), executes the
// root cobra command, and routes any returned error through the // root cobra command, and routes any returned error through the
// ui.Writer so the user sees a properly formatted "🛑 ERROR:" line. // ui.Writer so the user sees a properly formatted "🛑 ERROR:" line.
// The banner goes to stderr because stdout carries only the output the
// user asked for, such as a completion script or a `config get` value.
// //
// It returns the process exit code (0 on success, 130 when interrupted, // It returns the process exit code (0 on success, 1 on error) rather
// 1 on any other error) rather than calling os.Exit, so that main's // than calling os.Exit, so that main's deferred profile writers run
// deferred profile writers run before the process ends. See run in // before the process ends. See run in cmd/vaultik/main.go.
// cmd/vaultik/main.go.
func Entry() int { func Entry() int {
emitStartupBanner(os.Args[1:], os.Stderr) emitStartupBanner(os.Args[1:], os.Stdout)
rootCmd := NewRootCommand() rootCmd := NewRootCommand()
rootCmd.SilenceErrors = true rootCmd.SilenceErrors = true
@@ -41,20 +33,14 @@ func Entry() int {
err := rootCmd.Execute() err := rootCmd.Execute()
if err != nil { if err != nil {
// An operation that ran inside the fx app has already reported // An operation that ran inside the fx app has already reported
// its own failure (`snapshot verify --json` puts it in the // its own failure (and suppressed it under --json); errReported
// document instead); errReported says so. Printing it again // says so. Printing it again here would double the error line.
// here would double the error line.
// Every other error — bad arguments, a config that would not // Every other error — bad arguments, a config that would not
// load, an interrupt — reaches Entry unreported, so it is shown // load — reaches Entry unreported, so it is shown here.
// here.
if !errors.Is(err, errReported) { if !errors.Is(err, errReported) {
ReportErrorf("%s", err.Error()) ReportErrorf("%s", err.Error())
} }
if errors.Is(err, errInterrupted) {
return exitCodeInterrupted
}
return 1 return 1
} }
@@ -63,8 +49,9 @@ func Entry() int {
// emitStartupBanner writes the startup banner to w unless args (the // emitStartupBanner writes the startup banner to w unless args (the
// argument vector with the program name already stripped) contains a // argument vector with the program name already stripped) contains a
// flag that suppresses it. Split out of Entry so that the decision is // flag that suppresses it. Split out of Entry so that the decision — the
// reachable from a test without running the whole CLI. // only thing standing between a --json invocation and a parseable
// stdout — is reachable from a test without running the whole CLI.
func emitStartupBanner(args []string, w io.Writer) { func emitStartupBanner(args []string, w io.Writer) {
if bannerSuppressedInArgs(args) { if bannerSuppressedInArgs(args) {
return return
@@ -99,7 +86,8 @@ func ReportErrorf(format string, args ...any) {
// --json is a subcommand flag rather than a persistent one, but so is // --json is a subcommand flag rather than a persistent one, but so is
// --cron (it exists only on `snapshot create`), so this adds no new // --cron (it exists only on `snapshot create`), so this adds no new
// class of imprecision. The only cost of a false positive is a missing // class of imprecision. The only cost of a false positive is a missing
// decorative banner. // decorative banner; the cost of a false negative is a corrupt document
// on stdout, so the scan errs deliberately in that direction.
func bannerSuppressedInArgs(args []string) bool { func bannerSuppressedInArgs(args []string) bool {
for _, a := range args { for _, a := range args {
if a == "--" { if a == "--" {
+43 -46
View File
@@ -13,7 +13,6 @@ import (
"github.com/adrg/xdg" "github.com/adrg/xdg"
"github.com/stretchr/testify/assert" "github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require" "github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/globals"
) )
// Command words and flags used to build argument vectors below. They are // Command words and flags used to build argument vectors below. They are
@@ -37,14 +36,23 @@ const (
// strips it before scanning, so it has to be present. // strips it before scanning, so it has to be present.
programName = "vaultik" programName = "vaultik"
// someSnapshotID only fills the positional argument; no test needs // someSnapshotID is any snapshot identifier: these tests never run
// the snapshot to exist. // the command, so it only has to occupy the positional argument.
someSnapshotID = "host_2026-01-01T00:00:00Z" someSnapshotID = "host_2026-01-01T00:00:00Z"
) )
// placeholderJSONDocument stands in for whatever document a --json
// command writes to stdout. `snapshot list --json` with no snapshots
// prints exactly this; the other --json commands print an object rather
// than an array, but this test is not about their shape. It is about
// what is on stdout *before* them, which is the same for all of them
// because Entry prints the banner before cobra has parsed anything and
// therefore before it can know which command is running.
const placeholderJSONDocument = "[]\n"
// jsonArgumentVectors are the argument vectors of every --json // jsonArgumentVectors are the argument vectors of every --json
// invocation the CLI accepts, with the program name stripped exactly as // invocation the CLI accepts, with the program name stripped exactly as
// Entry strips it. Each one must suppress the banner. // Entry strips it. Each one must leave stdout untouched by the banner.
// //
//nolint:gochecknoglobals // read-only test fixture shared by two tests //nolint:gochecknoglobals // read-only test fixture shared by two tests
var jsonArgumentVectors = map[string][]string{ var jsonArgumentVectors = map[string][]string{
@@ -66,23 +74,39 @@ var jsonArgumentVectors = map[string][]string{
}, },
} }
// TestJSONInvocationSuppressesBanner checks that every --json // TestJSONInvocationStdoutIsExactlyOneDocument is the CLI-layer
// invocation suppresses the startup banner, as the README says --json // regression guard for issue #106: `vaultik snapshot list --json | jq`
// does along with --quiet and --cron. The scan is over the raw argument // must work with no other flags.
// vector, so each position and spelling of --json is listed. //
func TestJSONInvocationSuppressesBanner(t *testing.T) { // internal/vaultik's TestListSnapshots_JSONStdoutIsOnlyTheDocument
// guards the same contract one layer down, but it calls the library
// function directly and so cannot see Entry, which is where the
// contamination was: the startup banner is written to stdout before
// cobra parses anything, and the suppression scan did not know about
// --json. The two banner lines and the blank line landed ahead of the
// document and `jq` refused the result.
//
// The document is a constant here because this test is about the
// argument vectors, one per --json command; the one that runs a real
// command end to end is TestEntryJSONStdoutIsExactlyOneDocument below.
func TestJSONInvocationStdoutIsExactlyOneDocument(t *testing.T) {
t.Parallel() t.Parallel()
for name, argv := range jsonArgumentVectors { for name, argv := range jsonArgumentVectors {
t.Run(name, func(t *testing.T) { t.Run(name, func(t *testing.T) {
t.Parallel() t.Parallel()
var banner bytes.Buffer var stdout bytes.Buffer
emitStartupBanner(argv, &banner) emitStartupBanner(argv, &stdout)
assert.Empty(t, banner.String(), require.Empty(t, stdout.String(),
"--json suppresses the banner") "nothing may reach stdout ahead of a --json document")
_, err := stdout.WriteString(placeholderJSONDocument)
require.NoError(t, err)
requireExactlyOneJSONDocument(t, stdout.String())
}) })
} }
} }
@@ -103,45 +127,16 @@ func TestBannerStillPrintedWithoutSuppressingFlag(t *testing.T) {
t.Run(name, func(t *testing.T) { t.Run(name, func(t *testing.T) {
t.Parallel() t.Parallel()
var banner bytes.Buffer var stdout bytes.Buffer
emitStartupBanner(argv, &banner) emitStartupBanner(argv, &stdout)
assert.Contains(t, banner.String(), "starting up at", assert.Contains(t, stdout.String(), "starting up at",
"the banner belongs on invocations that did not opt out") "the banner belongs on invocations that did not opt out")
}) })
} }
} }
// TestBannerLabelsCommitDate checks that the banner prints the commit
// and the commit date, each after its own label. Commit and CommitDate
// get different values, so printing the wrong one fails.
//
//nolint:paralleltest // sets globals.Commit and globals.CommitDate
func TestBannerLabelsCommitDate(t *testing.T) {
const (
commit = "abc1234"
commitDate = "2026-11-09"
)
previousCommit, previousCommitDate := globals.Commit, globals.CommitDate
t.Cleanup(func() {
globals.Commit = previousCommit
globals.CommitDate = previousCommitDate
})
globals.Commit = commit
globals.CommitDate = commitDate
var banner bytes.Buffer
emitStartupBanner(nil, &banner)
assert.Contains(t, banner.String(),
"(commit "+commit+", commit date "+commitDate+")")
}
// TestBannerSuppressedInArgs covers the suppression scan directly, // TestBannerSuppressedInArgs covers the suppression scan directly,
// including the flags that suppressed the banner before --json joined // including the flags that suppressed the banner before --json joined
// them, so that adding --json cannot regress them. // them, so that adding --json cannot regress them.
@@ -252,7 +247,9 @@ func TestEntryJSONStdoutIsExactlyOneDocument(t *testing.T) {
// captureProcessStdout redirects the process's own stdout to a pipe for // captureProcessStdout redirects the process's own stdout to a pipe for
// the duration of fn and returns what was written to it. The redirection // the duration of fn and returns what was written to it. The redirection
// has to be at the file-descriptor level rather than through an injected // has to be at the file-descriptor level rather than through an injected
// writer, because the commands Entry runs reach os.Stdout directly. // writer, because the banner and the JSON encoder reach os.Stdout
// independently and the point of the test is that both land in the same
// place.
// //
// Not parallel-safe: os.Stdout is process-global. // Not parallel-safe: os.Stdout is process-global.
func captureProcessStdout(t *testing.T, fn func()) string { func captureProcessStdout(t *testing.T, fn func()) string {
-203
View File
@@ -1,203 +0,0 @@
package cli //nolint:testpackage // shares runEntry and the argument constants
import (
"fmt"
"net/http"
"net/http/httptest"
"os"
"os/signal"
"path/filepath"
"strings"
"testing"
"time"
"github.com/adrg/xdg"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// stalledStoreConfig is hermeticConfig with an s3:// destination store
// in place of the file:// one. The server behind it accepts any
// credentials.
const stalledStoreConfig = `age_recipients:
- age1278m9q7dp3chsh2dcy82qk27v047zywyvtxwnj4cvt0z65jw6a7q5dqhfj
snapshots:
test:
paths:
- %s
storage_url: s3://bucket?endpoint=%s&ssl=false
s3:
access_key_id: key
secret_access_key: secret
index_path: %s
hostname: test-host
`
// interruptRepeat is how often interruptOnFirstRequest sends SIGINT.
const interruptRepeat = 50 * time.Millisecond
// TestEntryInterruptedRun sends SIGINT to the test process while a
// command waits on the destination store, and checks that Entry returns
// 130 and prints one line on stderr saying the run was interrupted. The
// store is a local HTTP server that holds every request open, so the
// command is always mid-operation when the signal arrives. The two
// cases cover --cron and --json, which silence other output.
//
// Not parallel: it signals the process and replaces os.Args, os.Stdout,
// os.Stderr and the xdg globals.
//
//nolint:paralleltest // signals the process and replaces process globals
func TestEntryInterruptedRun(t *testing.T) {
for _, testCase := range []struct {
name string
args []string
}{
{
name: "snapshot create --cron",
args: []string{cmdSnapshot, cmdCreate, "--cron"},
},
{
name: "snapshot verify --json",
args: []string{cmdSnapshot, cmdVerify, someSnapshotID, flagJSON},
},
} {
t.Run(testCase.name, func(t *testing.T) {
endpoint, requestArrived := startStalledStore(t)
configPath := writeStalledStoreConfig(t, endpoint)
interruptOnFirstRequest(t, requestArrived)
code, _, stderr := runEntry(t,
append([]string{flagConfig, configPath}, testCase.args...)...)
assert.Equal(t, 130, code)
assert.Equal(t, 1,
strings.Count(stderr, errInterrupted.Error()), stderr)
})
}
}
// interruptOnFirstRequest sends SIGINT to the test process every
// interruptRepeat, from the first request to the destination store until
// the test ends. One signal is not enough: the command can reach the
// store before fx has started catching signals. The test catches SIGINT
// too, so that a signal fx is not catching does not kill the test
// binary.
func interruptOnFirstRequest(t *testing.T, requestArrived <-chan struct{}) {
t.Helper()
self, err := os.FindProcess(os.Getpid())
require.NoError(t, err)
caught := make(chan os.Signal, 1)
signal.Notify(caught, os.Interrupt)
testEnded := make(chan struct{})
senderDone := make(chan struct{})
// Stop catching SIGINT only after the sender has returned. The sender
// waits for each SIGINT it sends to arrive on caught; one still on
// its way after signal.Stop would kill the test binary.
t.Cleanup(func() {
close(testEnded)
<-senderDone
signal.Stop(caught)
})
go func() {
defer close(senderDone)
select {
case <-requestArrived:
case <-testEnded:
return
}
ticker := time.NewTicker(interruptRepeat)
defer ticker.Stop()
for {
// Empty caught, so that the receive below waits for this
// SIGINT rather than an earlier one.
select {
case <-caught:
default:
}
sendErr := self.Signal(os.Interrupt)
if sendErr != nil {
t.Errorf("sending SIGINT: %v", sendErr)
return
}
<-caught
select {
case <-testEnded:
return
case <-ticker.C:
}
}
}()
}
// startStalledStore starts an HTTP server that never answers: each
// request is held until the client gives up on it or the test ends.
// It returns the server's host:port and a channel that receives a value
// when the first request arrives.
func startStalledStore(t *testing.T) (string, <-chan struct{}) {
t.Helper()
requestArrived := make(chan struct{}, 1)
release := make(chan struct{})
server := httptest.NewServer(http.HandlerFunc(
func(_ http.ResponseWriter, r *http.Request) {
select {
case requestArrived <- struct{}{}:
default:
}
select {
case <-r.Context().Done():
case <-release:
}
}))
// Cleanups run last-registered first, so release lets any held
// request return before Close waits for it.
t.Cleanup(server.Close)
t.Cleanup(func() { close(release) })
return server.Listener.Addr().String(), requestArrived
}
// writeStalledStoreConfig writes a config whose destination store is the
// server at endpoint and whose snapshot source holds one small file, so
// that `snapshot create` has a blob to upload. Returns the config path.
func writeStalledStoreConfig(t *testing.T, endpoint string) string {
t.Helper()
dir := t.TempDir()
configPath := filepath.Join(dir, "config.yml")
sourceDir := filepath.Join(dir, "source")
require.NoError(t, os.Mkdir(sourceDir, 0o750))
require.NoError(t, os.WriteFile(filepath.Join(sourceDir, "file.txt"),
[]byte("contents"), 0o600))
contents := fmt.Sprintf(stalledStoreConfig,
sourceDir, endpoint, filepath.Join(dir, "index.sqlite"))
require.NoError(t,
os.WriteFile(configPath, []byte(contents), configFileMode))
// The PID lock lives under xdg.DataHome, which xdg resolves at
// package init; point it at the temp dir so the test neither
// touches nor collides with the real one.
t.Setenv("XDG_DATA_HOME", filepath.Join(dir, "data"))
xdg.Reload()
t.Cleanup(xdg.Reload)
return configPath
}
+1 -7
View File
@@ -101,8 +101,7 @@ func TestEntryPruneJSONStdoutIsExactlyOneDocument(t *testing.T) {
// writeHermeticPruneConfig builds a config over a temp directory with an // writeHermeticPruneConfig builds a config over a temp directory with an
// empty destination directory and, if seedStale is set, creates the // empty destination directory and, if seedStale is set, creates the
// index database up front with one snapshot record that has no // index database up front with one snapshot record that has no
// counterpart on the destination store, and gives the destination the // counterpart on the destination store. Returns the config path.
// marker a backup writes. Returns the config path.
func writeHermeticPruneConfig(t *testing.T, seedStale bool) string { func writeHermeticPruneConfig(t *testing.T, seedStale bool) string {
t.Helper() t.Helper()
@@ -132,11 +131,6 @@ func writeHermeticPruneConfig(t *testing.T, seedStale bool) string {
if seedStale { if seedStale {
seedStaleSnapshotRecord(t, indexPath) seedStaleSnapshotRecord(t, indexPath)
// While the local index holds a snapshot, prune fails on a
// destination that answers that it has no marker.
require.NoError(t, os.WriteFile(
filepath.Join(storeDir, "vaultik-destination.txt"), nil, 0o600))
} }
return configPath return configPath
-127
View File
@@ -1,127 +0,0 @@
package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
import (
"os"
"path/filepath"
"strings"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// flagCron is used to build the argument vectors below.
const flagCron = "--cron"
// plantUnreferencedBlob writes a blob that no snapshot references to the
// destination store at storeDir, dated long before any prune grace period,
// so that a prune deletes it. Returns its path.
func plantUnreferencedBlob(t *testing.T, storeDir string) string {
t.Helper()
hash := strings.Repeat("b", 64)
path := filepath.Join(storeDir, "blobs", hash[:2], hash[2:4], hash)
require.NoError(t, os.MkdirAll(filepath.Dir(path), 0o750))
require.NoError(t, os.WriteFile(path, []byte("unreferenced"), 0o600))
longAgo := time.Unix(0, 0)
require.NoError(t, os.Chtimes(path, longAgo, longAgo))
return path
}
// TestEntrySnapshotCreatePruneIsSilent checks that a successful
// `snapshot create --prune` under --cron or --quiet prints nothing on
// stdout or stderr, whether or not the prune finds a blob to delete.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntrySnapshotCreatePruneIsSilent(t *testing.T) {
for _, testCase := range []struct {
name string
args []string
plantBlob bool
}{
{
name: "cron, no blob to delete",
args: []string{cmdSnapshot, cmdCreate, flagCron, flagPrune},
},
{
name: "cron, blob to delete",
args: []string{cmdSnapshot, cmdCreate, flagCron, flagPrune},
plantBlob: true,
},
{
name: "cron with keep-newer-than",
args: []string{
cmdSnapshot, cmdCreate, flagCron, flagPrune,
flagKeepNewerThan, "4w",
},
plantBlob: true,
},
{
name: "quiet",
args: []string{flagQuiet, cmdSnapshot, cmdCreate, flagPrune},
plantBlob: true,
},
} {
t.Run(testCase.name, func(t *testing.T) {
configPath, storeDir := writeBackupConfig(t)
var blob string
if testCase.plantBlob {
blob = plantUnreferencedBlob(t, storeDir)
}
code, stdout, stderr := runEntry(t,
append([]string{flagConfig, configPath}, testCase.args...)...)
assert.Equal(t, 0, code)
assert.Empty(t, stdout)
assert.Empty(t, stderr)
if testCase.plantBlob {
assert.NoFileExists(t, blob, "the prune must delete the blob")
}
})
}
}
// TestEntryPruneQuietIsSilent checks that a successful `prune --force`
// under --quiet prints nothing on stdout or stderr, both when there is
// nothing to remove and when it removes a stale local snapshot record
// and an unreferenced blob.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntryPruneQuietIsSilent(t *testing.T) {
for _, testCase := range []struct {
name string
staleRecordAndBlob bool
}{
{name: "nothing to remove"},
{name: "stale record and blob to remove", staleRecordAndBlob: true},
} {
t.Run(testCase.name, func(t *testing.T) {
configPath := writeHermeticPruneConfig(t, testCase.staleRecordAndBlob)
var blob string
if testCase.staleRecordAndBlob {
// writeHermeticPruneConfig puts the store beside the config.
blob = plantUnreferencedBlob(t,
filepath.Join(filepath.Dir(configPath), "store"))
}
code, stdout, stderr := runEntry(t,
flagConfig, configPath, flagQuiet, cmdPrune, flagForce)
assert.Equal(t, 0, code)
assert.Empty(t, stdout)
assert.Empty(t, stderr)
if testCase.staleRecordAndBlob {
assert.NoFileExists(t, blob, "the prune must delete the blob")
}
})
}
}
@@ -1,185 +0,0 @@
package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
import (
"context"
"os"
"path/filepath"
"strings"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
)
// Flags of `snapshot create` used to build argument vectors below.
const (
flagPrune = "--prune"
flagKeepNewerThan = "--keep-newer-than"
)
// TestEntrySnapshotCreateRejectsKeepNewerThanBeforeBackup checks that a
// --keep-newer-than the post-backup prune could not use stops `snapshot
// create` before the backup: the command fails and the destination
// store stays empty. It used to be read only by the prune, after the
// snapshot was uploaded, and without --prune it was ignored.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntrySnapshotCreateRejectsKeepNewerThanBeforeBackup(t *testing.T) {
for _, testCase := range []struct {
name string
args []string
}{
{
name: "decimal in a day count",
args: []string{flagPrune, flagKeepNewerThan, "1.5d"},
},
{
name: "unknown unit",
args: []string{flagPrune, flagKeepNewerThan, "4x"},
},
{
name: "without --prune",
args: []string{flagKeepNewerThan, "4w"},
},
} {
t.Run(testCase.name, func(t *testing.T) {
configPath, storeDir := writeBackupConfig(t)
code, _, _ := runEntry(t, append(
[]string{flagConfig, configPath, cmdSnapshot, cmdCreate},
testCase.args...)...)
assert.Equal(t, 1, code)
stored, err := os.ReadDir(storeDir)
require.NoError(t, err)
assert.Empty(t, stored, "nothing may be uploaded")
})
}
}
// TestEntrySnapshotCreateReportsPostBackupPruneFailure makes the
// post-backup prune fail after a good backup, by planting a manifest
// that cannot be decoded, and checks that the failure is reported as the
// prune's and not as a failed snapshot creation.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntrySnapshotCreateReportsPostBackupPruneFailure(t *testing.T) {
configPath, storeDir := writeBackupConfig(t)
// A remote key is 64 lowercase hex characters. The prune reads every
// manifest on the store and fails on one it cannot decode.
plantedDir := filepath.Join(storeDir, "metadata", strings.Repeat("a", 64))
require.NoError(t, os.MkdirAll(plantedDir, 0o750))
require.NoError(t, os.WriteFile(
filepath.Join(plantedDir, "manifest.json.zst"),
[]byte("not a valid manifest"), 0o600))
code, _, stderr := runEntry(t,
flagConfig, configPath, cmdSnapshot, cmdCreate, flagPrune)
assert.Equal(t, 1, code)
assert.Contains(t, stderr, "Backup completed, but post-backup prune failed")
assert.NotContains(t, stderr, "Snapshot creation failed")
snapshots, err := os.ReadDir(filepath.Join(storeDir, "metadata"))
require.NoError(t, err)
assert.Len(t, snapshots, 2,
"the new snapshot is on the store beside the planted one")
}
// TestEntrySnapshotCreatePruneExitsNonZeroWhenSourceIsEmpty backs up,
// empties the source directory, as a volume that is not mounted leaves
// its mount point, and runs `snapshot create --prune`. The command exits
// non-zero and reports the backup as completed, not as a failed snapshot
// creation. See https://git.eeqj.de/sneak/vaultik/issues/388.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntrySnapshotCreatePruneExitsNonZeroWhenSourceIsEmpty(t *testing.T) {
configPath, storeDir := writeBackupConfig(t)
code, _, _ := runEntry(t, flagConfig, configPath, cmdSnapshot, cmdCreate)
require.Equal(t, 0, code)
// writeBackupConfig puts the source directory beside the config file.
require.NoError(t, os.Remove(
filepath.Join(filepath.Dir(configPath), "source", "file.txt")))
code, _, stderr := runEntry(t,
flagConfig, configPath, cmdSnapshot, cmdCreate, flagPrune)
assert.Equal(t, 1, code)
assert.Contains(t, stderr,
"Backup completed, but 1 source path(s) were empty")
assert.NotContains(t, stderr, "Snapshot creation failed")
snapshots, err := os.ReadDir(filepath.Join(storeDir, "metadata"))
require.NoError(t, err)
assert.Len(t, snapshots, 2, "the older snapshot is kept")
}
// TestEntrySnapshotCreatePruneExitsNonZeroWhenMountPointIsMissing backs
// up, records in the local index that this backup found the source
// directory as a mount point, and runs `snapshot create --prune`, which
// does not find it as one. The command exits non-zero, reports the
// backup as completed, not as a failed snapshot creation, and keeps the
// older snapshot. See https://git.eeqj.de/sneak/vaultik/issues/395.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntrySnapshotCreatePruneExitsNonZeroWhenMountPointIsMissing(
t *testing.T,
) {
configPath, storeDir := writeBackupConfig(t)
code, _, _ := runEntry(t, flagConfig, configPath, cmdSnapshot, cmdCreate)
require.Equal(t, 0, code)
// writeBackupConfig puts the source directory and the local index
// beside the config file.
dir := filepath.Dir(configPath)
ctx := context.Background()
db, err := database.New(ctx, filepath.Join(dir, "index.sqlite"))
require.NoError(t, err)
repos := database.NewRepositories(db)
backedUp, err := repos.Snapshots.GetOnlySnapshot(ctx)
require.NoError(t, err)
require.NoError(t, repos.Snapshots.AddMountPoint(ctx, nil,
backedUp.ID.String(), filepath.Join(dir, "source")))
require.NoError(t, db.Close())
code, _, stderr := runEntry(t,
flagConfig, configPath, cmdSnapshot, cmdCreate, flagPrune)
assert.Equal(t, 1, code)
assert.Contains(t, stderr, "Backup completed, but 1 mount point(s) "+
"an earlier snapshot recorded were not found")
assert.NotContains(t, stderr, "Snapshot creation failed")
snapshots, err := os.ReadDir(filepath.Join(storeDir, "metadata"))
require.NoError(t, err)
assert.Len(t, snapshots, 2, "the older snapshot is kept")
}
// writeBackupConfig builds a hermetic config with one small file in its
// source directory and an empty destination store directory. Returns the
// config path and the store directory.
func writeBackupConfig(t *testing.T) (string, string) {
t.Helper()
configPath := writeHermeticPruneConfig(t, false)
// writeHermeticPruneConfig puts the source and store directories
// beside the config file.
dir := filepath.Dir(configPath)
sourceDir := filepath.Join(dir, "source")
require.NoError(t, os.Mkdir(sourceDir, 0o750))
require.NoError(t, os.WriteFile(
filepath.Join(sourceDir, "file.txt"), []byte("hello"), 0o600))
return configPath, filepath.Join(dir, "store")
}
@@ -1,30 +0,0 @@
package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
import (
"testing"
"github.com/stretchr/testify/assert"
)
// TestEntrySnapshotCreateSkipErrorsExitsNonZeroWhenItSkips backs up,
// under --skip-errors, a source directory that does not exist, which the
// walk skips. The command exits non-zero and reports the backup as
// completed, not as a failed snapshot creation. See
// https://git.eeqj.de/sneak/vaultik/issues/310.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntrySnapshotCreateSkipErrorsExitsNonZeroWhenItSkips(t *testing.T) {
// writeBackupConfig would create the source directory.
configPath := writeHermeticPruneConfig(t, false)
code, stdout, stderr := runEntry(t,
flagConfig, configPath, "--skip-errors", cmdSnapshot, cmdCreate)
assert.Equal(t, 1, code)
assert.Contains(t, stdout,
"Files: 1 examined, 0 backed up, 0 unchanged, 1 failed.")
assert.NotContains(t, stdout, "Finished successfully.")
assert.Contains(t, stderr,
"Backup completed, but 1 file(s) could not be read")
assert.NotContains(t, stderr, "Snapshot creation failed")
}
-75
View File
@@ -1,75 +0,0 @@
package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
import (
"context"
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/snapshot"
)
// Words and flags of `snapshot purge` used to build argument vectors
// below.
const (
cmdPurge = "purge"
flagOlderThan = "--older-than"
flagForce = "--force"
)
// TestEntrySnapshotPurgeKeepsMetadataWhenLocalIndexDeleteFails makes
// the local index refuse to delete an old snapshot and checks that
// `snapshot purge` exits non-zero and leaves that snapshot's metadata on
// the destination store. It used to log the error, delete the metadata
// and exit 0.
//
// `snapshot create --prune` runs the same purge, but cannot be driven
// this way: the refusal also breaks the backup's metadata export, which
// deletes the other snapshots from its copy of the local index.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntrySnapshotPurgeKeepsMetadataWhenLocalIndexDeleteFails(t *testing.T) {
configPath := writeHermeticPruneConfig(t, false)
dir := filepath.Dir(configPath)
indexPath := filepath.Join(dir, "index.sqlite")
// seedStaleSnapshotRecord writes an old snapshot to the local index
// only; the manifest planted here puts it on the destination store
// too, so the purge selects it rather than dropping it as stale.
seedStaleSnapshotRecord(t, indexPath)
// While the local index holds a snapshot, purge fails on a
// destination that answers that it has no marker.
require.NoError(t, os.WriteFile(
filepath.Join(dir, "store", "vaultik-destination.txt"), nil, 0o600))
manifestDir := filepath.Join(dir, "store", "metadata",
snapshot.RemoteSnapshotKey(stalePruneSnapshotID))
require.NoError(t, os.MkdirAll(manifestDir, 0o750))
manifestPath := filepath.Join(manifestDir, "manifest.json.zst")
require.NoError(t, os.WriteFile(manifestPath, []byte("stub"), 0o600))
ctx := context.Background()
db, err := database.New(ctx, indexPath)
require.NoError(t, err)
_, err = db.Conn().ExecContext(ctx, `
CREATE TRIGGER refuse_snapshot_delete BEFORE DELETE ON snapshots
BEGIN SELECT RAISE(ABORT, 'simulated index error'); END`)
require.NoError(t, err)
require.NoError(t, db.Close())
code, _, stderr := runEntry(t, flagConfig, configPath,
cmdSnapshot, cmdPurge, flagOlderThan, "30d", flagForce)
assert.Equal(t, 1, code)
assert.Contains(t, stderr, "simulated index error",
"the purge must fail at the local-index delete")
assert.FileExists(t, manifestPath,
"the snapshot is still in the local index, so its metadata must stay")
}
+3 -3
View File
@@ -15,8 +15,8 @@ import (
// run, so a failing command must come back with a non-zero code rather // run, so a failing command must come back with a non-zero code rather
// than ending the process here. // than ending the process here.
// //
// Stdout and stderr are captured only to keep the banner and command // Stdout is captured only to keep the banner and command output off the
// output off the test log; the assertion is on the returned code. // test log; the assertion is on the returned code.
// //
//nolint:paralleltest // replaces os.Args and rootFlags //nolint:paralleltest // replaces os.Args and rootFlags
func TestEntryReturnsStatusCode(t *testing.T) { func TestEntryReturnsStatusCode(t *testing.T) {
@@ -50,7 +50,7 @@ func TestEntryReturnsStatusCode(t *testing.T) {
var code int var code int
_, _ = captureProcessStdoutAndStderr(t, func() { code = Entry() }) _ = captureProcessStdout(t, func() { code = Entry() })
assert.Equal(t, testCase.want, code) assert.Equal(t, testCase.want, code)
}) })
-200
View File
@@ -1,200 +0,0 @@
package cli //nolint:testpackage // shares hermeticConfig and the capture helpers
import (
"context"
"encoding/json"
"fmt"
"log/slog"
"os"
"path/filepath"
"strings"
"testing"
"github.com/adrg/xdg"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
)
// TestEntryCompletionStdoutIsTheScript runs `vaultik completion bash`,
// whose stdout the README tells the user to source. The script has to
// start on the first line.
//
//nolint:paralleltest // replaces os.Args, os.Stdout and os.Stderr
func TestEntryCompletionStdoutIsTheScript(t *testing.T) {
code, stdout, _ := runEntry(t, "completion", "bash")
require.Equal(t, 0, code)
firstLine, _, _ := strings.Cut(stdout, "\n")
assert.True(t, strings.HasPrefix(firstLine, "# bash completion"),
"the first line of stdout must be the script's, got %q", firstLine)
}
// TestEntryConfigGetStdoutIsTheValue runs `vaultik config get`, whose
// stdout a script reads as the value and nothing else.
//
//nolint:paralleltest // replaces os.Args, os.Stdout and os.Stderr
func TestEntryConfigGetStdoutIsTheValue(t *testing.T) {
configPath := filepath.Join(t.TempDir(), "config.yml")
require.NoError(t, os.WriteFile(configPath,
[]byte("hostname: test-host\n"), configFileMode))
code, stdout, _ := runEntry(t,
flagConfig, configPath, "config", "get", "hostname")
require.Equal(t, 0, code)
assert.Equal(t, "test-host\n", stdout)
}
// TestEntryJSONFailureIsReportedOnStderr runs each --json command that
// writes no document when it fails, against a destination it cannot
// use. The error must reach stderr, and stdout must stay empty.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntryJSONFailureIsReportedOnStderr(t *testing.T) {
for _, testCase := range []struct {
name string
args []string
wantOnStderr string
}{
{
name: "remote info",
args: []string{cmdRemote, cmdInfo, flagJSON},
wantOnStderr: "Failed to get remote info",
},
{
name: "prune",
args: []string{cmdPrune, flagJSON},
wantOnStderr: "Prune failed",
},
{
name: "snapshot remove",
args: []string{cmdSnapshot, cmdRemove, someSnapshotID, flagJSON},
wantOnStderr: "Failed to remove snapshot",
},
} {
t.Run(testCase.name, func(t *testing.T) {
configPath := writeUnusableDestinationConfig(t)
code, stdout, stderr := runEntry(t,
append([]string{flagConfig, configPath}, testCase.args...)...)
assert.Equal(t, 1, code)
assert.Empty(t, stdout,
"a failed --json command has no document to write")
assert.Contains(t, stderr, testCase.wantOnStderr,
"the failure must be reported on stderr")
})
}
}
// TestEntrySnapshotRemoveJSONWarningIsOnStderr runs `snapshot remove
// --json` on a snapshot in the local index, against a destination
// directory that does not exist. The command removes the snapshot from
// the local index and still exits 0. Its stdout must hold the document
// alone, with the warning about the destination store on stderr: the
// command to run again once it is reachable, and the snapshot's ID in
// the record's snapshot_id field.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntrySnapshotRemoveJSONWarningIsOnStderr(t *testing.T) {
configPath, indexPath := writeMissingDestinationConfig(t)
seedStaleSnapshotRecord(t, indexPath)
code, stdout, stderr := runEntry(t, flagConfig, configPath,
cmdSnapshot, cmdRemove, stalePruneSnapshotID, flagJSON)
require.Equal(t, 0, code)
requireExactlyOneJSONDocument(t, stdout)
// stderr is a pipe here, so the logger writes one JSON record a line.
var warning map[string]any
for line := range strings.Lines(stderr) {
if strings.Contains(line,
"Could not remove snapshot metadata from remote storage") {
require.NoError(t, json.Unmarshal([]byte(line), &warning))
}
}
require.NotNil(t, warning, "the warning must reach stderr")
assert.Contains(t, warning[slog.MessageKey],
"run 'vaultik snapshot remove' with the snapshot's ID again")
assert.Equal(t, stalePruneSnapshotID, warning["snapshot_id"])
}
// writeMissingDestinationConfig builds a config whose destination
// directory does not exist. Returns the config path and the path of
// its local index, which is not created here.
func writeMissingDestinationConfig(t *testing.T) (string, string) {
t.Helper()
dir := t.TempDir()
configPath := filepath.Join(dir, "config.yml")
indexPath := filepath.Join(dir, "index.sqlite")
contents := fmt.Sprintf(hermeticConfig,
filepath.Join(dir, "source"),
filepath.Join(dir, "missing-store"),
indexPath)
require.NoError(t,
os.WriteFile(configPath, []byte(contents), configFileMode))
// The PID lock lives under xdg.DataHome, which xdg resolves at
// package init; point it at the temp dir so the test neither
// touches nor collides with the real one.
t.Setenv("XDG_DATA_HOME", filepath.Join(dir, "data"))
xdg.Reload()
t.Cleanup(xdg.Reload)
return configPath, indexPath
}
// writeUnusableDestinationConfig builds a config whose destination
// directory does not exist, which fails `remote info`, and whose local
// index is bound to another destination, which fails `prune` and
// `snapshot remove` (a missing destination alone only makes `snapshot
// remove` warn). Returns the config path.
func writeUnusableDestinationConfig(t *testing.T) string {
t.Helper()
configPath, indexPath := writeMissingDestinationConfig(t)
ctx := context.Background()
db, err := database.New(ctx, indexPath)
require.NoError(t, err)
defer func() { require.NoError(t, db.Close()) }()
require.NoError(t, database.NewRepositories(db).LocalMeta.Set(ctx,
database.LocalMetaKeyStorageURL, "file://"+t.TempDir()))
return configPath
}
// runEntry runs Entry with args after the program name and returns its
// exit code and what it wrote to stdout and stderr.
//
// Not parallel-safe: it replaces os.Args, os.Stdout and os.Stderr.
func runEntry(t *testing.T, args ...string) (int, string, string) {
t.Helper()
previousArgs := os.Args
t.Cleanup(func() {
os.Args = previousArgs
rootFlags = RootFlags{}
})
os.Args = append([]string{programName}, args...)
var code int
stdout, stderr := captureProcessStdoutAndStderr(t,
func() { code = Entry() })
return code, stdout, stderr
}
@@ -1,43 +0,0 @@
package cli //nolint:testpackage // shares runEntry and the command-word constants
import (
"testing"
"github.com/stretchr/testify/assert"
)
// TestEntryGroupRejectsUnknownSubcommand runs each group command with a
// mistyped subcommand, as a crontab line might carry one. It must fail
// with exit 1 and name the word, as `vaultik bogus` does at the top
// level, instead of printing the group's help and exiting 0 having done
// nothing. The group name alone still prints its help.
//
//nolint:paralleltest // replaces os.Args, os.Stdout and os.Stderr
func TestEntryGroupRejectsUnknownSubcommand(t *testing.T) {
for _, testCase := range []struct {
group string
mistyped string
}{
{group: cmdSnapshot, mistyped: "craete"},
{group: "config", mistyped: "inti"},
{group: cmdRemote, mistyped: "ifno"},
{group: "database", mistyped: "delte"},
{group: "completion", mistyped: "nosuchshell"},
} {
t.Run(testCase.group, func(t *testing.T) {
code, stdout, stderr := runEntry(t,
testCase.group, testCase.mistyped)
assert.Equal(t, 1, code)
assert.Empty(t, stdout)
assert.Contains(t, stderr,
`unknown command "`+testCase.mistyped+`"`)
code, stdout, _ = runEntry(t, testCase.group)
assert.Equal(t, 0, code)
assert.Contains(t, stdout,
programName+" "+testCase.group+" [command]")
})
}
}
-24
View File
@@ -1,24 +0,0 @@
package cli //nolint:testpackage // exercises the unexported command constructor
import (
"testing"
"github.com/spf13/cobra"
"github.com/stretchr/testify/assert"
)
// TestJSONHelpSaysConfirmationPromptIsSkipped checks that the --json help
// of `snapshot remove` and `prune` says the flag skips the confirmation
// prompt. Both delete without asking under --json, since a prompt on
// stdout would break the JSON document.
func TestJSONHelpSaysConfirmationPromptIsSkipped(t *testing.T) {
t.Parallel()
for _, cmd := range []*cobra.Command{
newSnapshotRemoveCommand(),
NewPruneCommand(),
} {
assert.Contains(t, cmd.Flags().Lookup("json").Usage,
"skips the confirmation prompt", cmd.Name())
}
}
+11 -20
View File
@@ -13,30 +13,18 @@ func NewPruneCommand() *cobra.Command {
cmd := &cobra.Command{ cmd := &cobra.Command{
Use: "prune", Use: "prune",
Short: "Tidy local database and remote storage", Short: "Tidy local database and remote storage",
Long: `Removes orphaned data from the local index database, and Long: `Removes orphaned data from both the local index database and
unreferenced blobs and directories under metadata/ with no manifest unreferenced blobs from the backup destination store.
from the backup destination store.
Local cleanup drops incomplete snapshots and any files, chunks, or Local cleanup drops incomplete snapshots and any files, chunks, or
blobs no longer referenced by a completed snapshot. Remote cleanup blobs no longer referenced by a completed snapshot. Remote cleanup
scans every snapshot manifest in the destination store, builds the scans every snapshot manifest in the destination store, builds the
set of still-referenced blob hashes, and deletes any blob not in that set of still-referenced blob hashes, and deletes any blob not in that
set that is older than prune_grace_period (default 24h). A newer one set.
is kept: it may belong to a backup still running, on this host or
another sharing the destination store, that has not yet uploaded its
manifest. The grace period does not protect a blob such a backup
reuses from an earlier run that stopped before its manifest: that
blob keeps the time of its first upload, so it can be deleted.
Remote cleanup also deletes each directory under metadata/ with no
manifest, as a backup that stopped before its manifest leaves, once
all its objects are older than prune_grace_period and its snapshot is
not in the local index.
Snapshot create --prune runs the same cleanup automatically; this Snapshot create --prune and snapshot remove run the same cleanup
command is the manual entry point for the same work (e.g. after a automatically; this command is the manual entry point for the same
crashed backup or to reclaim storage). Snapshot remove leaves blobs in work (e.g. after a crashed backup or to reclaim storage).`,
place; run this command afterwards to delete the ones no longer
referenced.`,
Args: cobra.NoArgs, Args: cobra.NoArgs,
RunE: func(cmd *cobra.Command, _ []string) error { RunE: func(cmd *cobra.Command, _ []string) error {
// Use unified config resolution // Use unified config resolution
@@ -60,6 +48,10 @@ referenced.`,
}, func(v *vaultik.Vaultik) error { }, func(v *vaultik.Vaultik) error {
return v.Prune(opts) return v.Prune(opts)
}, func(err error) { }, func(err error) {
if opts.JSON {
return
}
log.Error("Prune operation failed", "error", err) log.Error("Prune operation failed", "error", err)
ReportErrorf("Prune failed: %v", err) ReportErrorf("Prune failed: %v", err)
}) })
@@ -67,8 +59,7 @@ referenced.`,
} }
cmd.Flags().BoolVar(&opts.Force, "force", false, "Skip confirmation prompt") cmd.Flags().BoolVar(&opts.Force, "force", false, "Skip confirmation prompt")
cmd.Flags().BoolVar(&opts.JSON, "json", false, cmd.Flags().BoolVar(&opts.JSON, "json", false, "Output pruning stats as JSON")
"Output pruning stats as JSON; skips the confirmation prompt, as --force does")
return cmd return cmd
} }
+5 -7
View File
@@ -18,12 +18,6 @@ func NewRemoteCommand() *cobra.Command {
Use: "remote", Use: "remote",
Short: "Remote storage management commands", Short: "Remote storage management commands",
Long: "Commands for inspecting and managing remote storage", Long: "Commands for inspecting and managing remote storage",
// cobra checks Args only on a command that has a Run: without
// one, a mistyped subcommand printed help and exited 0.
Args: cobra.NoArgs,
Run: func(cmd *cobra.Command, _ []string) {
_ = cmd.Help()
},
} }
// Add subcommands // Add subcommands
@@ -51,7 +45,7 @@ This is destructive and irreversible. Requires --force.`,
return errNukeNeedsForce return errNukeNeedsForce
} }
return runVaultikApp(cmd, mutating, false, "Remote nuke failed", return runVaultikApp(cmd, mutating, false, false, "Remote nuke failed",
func(v *vaultik.Vaultik) error { func(v *vaultik.Vaultik) error {
return v.NukeRemote(true) return v.NukeRemote(true)
}) })
@@ -98,6 +92,10 @@ func newRemoteInfoCommand() *cobra.Command {
}, func(v *vaultik.Vaultik) error { }, func(v *vaultik.Vaultik) error {
return v.RemoteInfo(jsonOutput) return v.RemoteInfo(jsonOutput)
}, func(err error) { }, func(err error) {
if jsonOutput {
return
}
log.Error("Failed to get remote info", "error", err) log.Error("Failed to get remote info", "error", err)
ReportErrorf("Failed to get remote info: %v", err) ReportErrorf("Failed to get remote info: %v", err)
}) })
-15
View File
@@ -74,21 +74,6 @@ on the source system.`,
NewDatabaseCommand(), NewDatabaseCommand(),
) )
// cobra adds the completion command only when Execute runs, and with
// no Run, so it skipped its own cobra.NoArgs and a mistyped shell name
// printed help and exited 0. Adding it here lets it have a Run. Its
// scripts go to os.Stdout as it is now: a later SetOut does not
// redirect them.
cmd.InitDefaultCompletionCmd()
for _, sub := range cmd.Commands() {
if sub.Name() == "completion" {
sub.Run = func(completion *cobra.Command, _ []string) {
_ = completion.Help()
}
}
}
return cmd return cmd
} }
+14 -56
View File
@@ -41,12 +41,6 @@ func NewSnapshotCommand() *cobra.Command {
Use: "snapshot", Use: "snapshot",
Short: "Snapshot management commands", Short: "Snapshot management commands",
Long: "Commands for creating, listing, and managing snapshots", Long: "Commands for creating, listing, and managing snapshots",
// cobra checks Args only on a command that has a Run: without
// one, a mistyped subcommand printed help and exited 0.
Args: cobra.NoArgs,
Run: func(cmd *cobra.Command, _ []string) {
_ = cmd.Help()
},
} }
// Add subcommands // Add subcommands
@@ -72,16 +66,10 @@ func newSnapshotCreateCommand() *cobra.Command {
If snapshot names are provided, only those snapshots are created. If snapshot names are provided, only those snapshots are created.
If no names are provided, all configured snapshots are created. If no names are provided, all configured snapshots are created.
The config is read from the path given by --config or VAULTIK_CONFIG; Config is located at /etc/vaultik/config.yml by default, but can be overridden by
otherwise from the platform config directory (~/.config/vaultik/config.yml specifying a path using --config or by setting VAULTIK_CONFIG to a path.`,
on Linux), then /etc/vaultik/config.yml.`,
Args: cobra.ArbitraryArgs, Args: cobra.ArbitraryArgs,
RunE: func(cmd *cobra.Command, args []string) error { RunE: func(cmd *cobra.Command, args []string) error {
err := opts.Validate()
if err != nil {
return err
}
// Pass snapshot names from args // Pass snapshot names from args
opts.Snapshots = args opts.Snapshots = args
// --skip-errors is a global flag on the root command. // --skip-errors is a global flag on the root command.
@@ -108,22 +96,6 @@ on Linux), then /etc/vaultik/config.yml.`,
}, func(v *vaultik.Vaultik) error { }, func(v *vaultik.Vaultik) error {
return v.CreateSnapshot(opts) return v.CreateSnapshot(opts)
}, func(err error) { }, func(err error) {
if errors.Is(err, vaultik.ErrPostBackupPruneFailed) {
log.Error("Post-backup prune failed", "error", err)
ReportErrorf("Backup completed, but %v", err)
return
}
if errors.Is(err, vaultik.ErrFilesUnreadable) ||
errors.Is(err, vaultik.ErrSourcePathEmpty) ||
errors.Is(err, vaultik.ErrVolumeNotMounted) {
log.Error("Backup completed with an error", "error", err)
ReportErrorf("Backup completed, but %v", err)
return
}
log.Error("Snapshot creation failed", "error", err) log.Error("Snapshot creation failed", "error", err)
ReportErrorf("Snapshot creation failed: %v", err) ReportErrorf("Snapshot creation failed: %v", err)
}) })
@@ -133,13 +105,8 @@ on Linux), then /etc/vaultik/config.yml.`,
cmd.Flags().BoolVar(&opts.Cron, "cron", false, cmd.Flags().BoolVar(&opts.Cron, "cron", false,
"Run in cron mode (silent unless warning or error)") "Run in cron mode (silent unless warning or error)")
cmd.Flags().BoolVar(&opts.Prune, "prune", false, cmd.Flags().BoolVar(&opts.Prune, "prune", false,
"After backup, drop older snapshots of the same name, remove "+ "After backup, drop older snapshots of the same name and remove "+
"orphaned blobs older than prune_grace_period, and delete each "+ "orphaned blobs")
"directory under metadata/ with no manifest once all its "+
"objects are older than prune_grace_period and its snapshot is "+
"not in the local index (not after a backup that skipped "+
"unreadable files, found a configured path empty, or did not "+
"find a mount point an earlier snapshot found)")
cmd.Flags().StringVar(&opts.KeepNewerThan, "keep-newer-than", "", cmd.Flags().StringVar(&opts.KeepNewerThan, "keep-newer-than", "",
"With --prune: keep snapshots newer than this duration "+ "With --prune: keep snapshots newer than this duration "+
"(e.g. 30d, 4w, 6mo, 1y; m is minutes, mo is months) "+ "(e.g. 30d, 4w, 6mo, 1y; m is minutes, mo is months) "+
@@ -159,7 +126,7 @@ func newSnapshotListCommand() *cobra.Command {
Long: "Lists all snapshots with their ID, timestamp, and compressed size", Long: "Lists all snapshots with their ID, timestamp, and compressed size",
Args: cobra.NoArgs, Args: cobra.NoArgs,
RunE: func(cmd *cobra.Command, _ []string) error { RunE: func(cmd *cobra.Command, _ []string) error {
return runVaultikApp(cmd, readOnly, false, return runVaultikApp(cmd, readOnly, false, false,
"Failed to list snapshots", "Failed to list snapshots",
func(v *vaultik.Vaultik) error { func(v *vaultik.Vaultik) error {
return v.ListSnapshots(jsonOutput) return v.ListSnapshots(jsonOutput)
@@ -195,7 +162,7 @@ restrict the operation to specific snapshot names.`,
return errPurgeCriteriaBoth return errPurgeCriteriaBoth
} }
return runVaultikApp(cmd, mutating, false, return runVaultikApp(cmd, mutating, false, false,
"Failed to purge snapshots", "Failed to purge snapshots",
func(v *vaultik.Vaultik) error { func(v *vaultik.Vaultik) error {
return v.PurgeSnapshotsWithOptions(opts) return v.PurgeSnapshotsWithOptions(opts)
@@ -284,29 +251,21 @@ By default, this removes the snapshot from the local index database and
strips the snapshot's metadata from the backup destination store. Blobs strips the snapshot's metadata from the backup destination store. Blobs
are NOT touched: deleting them requires reading every remaining remote are NOT touched: deleting them requires reading every remaining remote
manifest (the destination store may hold snapshots this host doesn't manifest (the destination store may hold snapshots this host doesn't
know about), which is what 'vaultik prune' does. The command prints the know about), which is what 'vaultik prune' does. On success the command
'vaultik prune' invocation to run as a follow-up only when it removed the prints the exact 'vaultik prune' invocation to run as a follow-up.
snapshot's metadata from the destination store, and never under --json.
An ID that names no snapshot in the local index or on the destination
store is an error.
Use --local-only to skip the remote half (e.g. when you want to forget a Use --local-only to skip the remote half (e.g. when you want to forget a
snapshot locally without touching the destination store); the snapshot snapshot locally without touching the destination store).
must then be in the local index.
If removing the snapshot's metadata from the destination store fails (for If the remote is unreachable, the local-database removal still completes
example because the remote is unreachable), the local-database removal and a warning is emitted; rerun 'vaultik prune' once the destination store
still completes and a warning is emitted; run 'vaultik snapshot remove is reachable to finish remote cleanup.
<snapshot-id>' again once the destination store is reachable to remove
the snapshot's metadata from it ('vaultik prune' does not). For a
snapshot that is only on the destination store, that failure is an error.
To wipe the entire destination store and start over, use 'vaultik remote To wipe the entire destination store and start over, use 'vaultik remote
nuke --force' — it is the single supported entry point for that.`, nuke --force' — it is the single supported entry point for that.`,
Args: requireSnapshotIDArg, Args: requireSnapshotIDArg,
RunE: func(cmd *cobra.Command, args []string) error { RunE: func(cmd *cobra.Command, args []string) error {
return runVaultikApp(cmd, mutating, opts.JSON, return runVaultikApp(cmd, mutating, opts.JSON, opts.JSON,
"Failed to remove snapshot", "Failed to remove snapshot",
func(v *vaultik.Vaultik) error { func(v *vaultik.Vaultik) error {
_, err := v.RemoveSnapshot(args[0], opts) _, err := v.RemoveSnapshot(args[0], opts)
@@ -319,8 +278,7 @@ nuke --force' — it is the single supported entry point for that.`,
cmd.Flags().BoolVarP(&opts.Force, "force", "f", false, "Skip confirmation prompt") cmd.Flags().BoolVarP(&opts.Force, "force", "f", false, "Skip confirmation prompt")
cmd.Flags().BoolVar(&opts.DryRun, "dry-run", false, cmd.Flags().BoolVar(&opts.DryRun, "dry-run", false,
"Show what would be removed without removing") "Show what would be removed without removing")
cmd.Flags().BoolVar(&opts.JSON, "json", false, cmd.Flags().BoolVar(&opts.JSON, "json", false, "Output result as JSON")
"Output result as JSON; skips the confirmation prompt, as --force does")
cmd.Flags().BoolVar(&opts.LocalOnly, "local-only", false, cmd.Flags().BoolVar(&opts.LocalOnly, "local-only", false,
"Skip remote cleanup; only touch the local index") "Skip remote cleanup; only touch the local index")
-2
View File
@@ -30,8 +30,6 @@ This command will restore files from the specified snapshot to the
target directory. target directory.
If no paths are specified, all files are restored. If no paths are specified, all files are restored.
If paths are specified, only matching files/directories are restored. If paths are specified, only matching files/directories are restored.
A path that matches nothing in the snapshot is named in a warning, and
the command exits non-zero after restoring the paths that match.
The snapshot may be named by its ID or, when restoring on a host with no The snapshot may be named by its ID or, when restoring on a host with no
local index, by the remote key that 'snapshot list' prints for a local index, by the remote key that 'snapshot list' prints for a
+7 -7
View File
@@ -37,13 +37,13 @@ func writeVersion(out *ui.Writer) {
w := out.Out() w := out.Out()
_, _ = fmt.Fprintf(w, "vaultik %s\n", globals.Version) _, _ = fmt.Fprintf(w, "vaultik %s\n", globals.Version)
_, _ = fmt.Fprintf(w, " commit: %s\n", globals.Commit) _, _ = fmt.Fprintf(w, " commit: %s\n", globals.Commit)
_, _ = fmt.Fprintf(w, " commit date: %s\n", globals.CommitDate) _, _ = fmt.Fprintf(w, " build date: %s\n", globals.CommitDate)
_, _ = fmt.Fprintf(w, " go: %s\n", runtime.Version()) _, _ = fmt.Fprintf(w, " go: %s\n", runtime.Version())
_, _ = fmt.Fprintf(w, " os/arch: %s/%s\n", runtime.GOOS, runtime.GOARCH) _, _ = fmt.Fprintf(w, " os/arch: %s/%s\n", runtime.GOOS, runtime.GOARCH)
_, _ = fmt.Fprintf(w, " author: %s\n", globals.Author) _, _ = fmt.Fprintf(w, " author: %s\n", globals.Author)
_, _ = fmt.Fprintf(w, " homepage: %s\n", globals.Homepage) _, _ = fmt.Fprintf(w, " homepage: %s\n", globals.Homepage)
_, _ = fmt.Fprintf(w, " license: %s\n", globals.License) _, _ = fmt.Fprintf(w, " license: %s\n", globals.License)
if globals.IsDevVersion(globals.Version) { if globals.IsDevVersion(globals.Version) {
_, _ = fmt.Fprintln(w) _, _ = fmt.Fprintln(w)
-37
View File
@@ -2,7 +2,6 @@ package cli_test
import ( import (
"bytes" "bytes"
"runtime"
"strings" "strings"
"testing" "testing"
@@ -50,42 +49,6 @@ func TestVersionCommandReportsBuildVersion(t *testing.T) {
} }
} }
// TestVersionCommandReportLines checks the label, padding and value of
// every line of the report. Commit and CommitDate get different values,
// so a line that prints the wrong one fails.
//
//nolint:paralleltest // sets globals.Commit and globals.CommitDate
func TestVersionCommandReportLines(t *testing.T) {
const (
commit = "abc1234"
commitDate = "2026-11-09"
)
previousCommit, previousCommitDate := globals.Commit, globals.CommitDate
t.Cleanup(func() {
globals.Commit = previousCommit
globals.CommitDate = previousCommitDate
})
globals.Commit = commit
globals.CommitDate = commitDate
want := "vaultik " + globals.Version + "\n" +
" commit: " + commit + "\n" +
" commit date: " + commitDate + "\n" +
" go: " + runtime.Version() + "\n" +
" os/arch: " + runtime.GOOS + "/" + runtime.GOARCH + "\n" +
" author: " + globals.Author + "\n" +
" homepage: " + globals.Homepage + "\n" +
" license: " + globals.License + "\n"
out := runVersionCommand(t)
if !strings.HasPrefix(out, want) {
t.Errorf("report:\n%s\nwant it to start with:\n%s", out, want)
}
}
// TestVersionCommandFlagsDevelopmentBuild is the regression test for // TestVersionCommandFlagsDevelopmentBuild is the regression test for
// the thing this command exists to prevent: a build that is not a // the thing this command exists to prevent: a build that is not a
// release must say so. The notice used to be gated on the version // release must say so. The notice used to be gated on the version
+36 -103
View File
@@ -4,14 +4,12 @@
package config package config
import ( import (
"bytes"
"errors" "errors"
"fmt" "fmt"
"os" "os"
"path/filepath" "path/filepath"
"sort" "sort"
"strings" "strings"
"time"
"filippo.io/age" "filippo.io/age"
"git.eeqj.de/sneak/smartconfig" "git.eeqj.de/sneak/smartconfig"
@@ -31,21 +29,15 @@ const appName = "vaultik"
//nolint:gosec // G101: marker for detecting a pasted secret key, not a credential //nolint:gosec // G101: marker for detecting a pasted secret key, not a credential
const secretKeyPrefix = "AGE-SECRET-KEY-" const secretKeyPrefix = "AGE-SECRET-KEY-"
// Defaults and validation bounds for tunable settings. MB and GB are // Defaults and validation bounds for tunable settings.
// 1000-based, as the size parser reads them; the S3 part sizes are S3's own
// limits, which are 1024-based (MiB, GiB).
const ( const (
defaultBlobSizeLimit = Size(10 * 1000 * 1000 * 1000) // 10GB defaultBlobSizeLimit = Size(10 * 1024 * 1024 * 1024) // 10GB
defaultChunkSize = Size(10 * 1000 * 1000) // 10MB defaultChunkSize = Size(10 * 1024 * 1024) // 10MB
defaultS3PartSize = Size(5 * 1024 * 1024) // 5MiB defaultS3PartSize = Size(5 * 1024 * 1024) // 5MB
defaultCompressionLevel = 3 defaultCompressionLevel = 3
defaultPruneGracePeriod = 24 * time.Hour minChunkSize = 1024 * 1024 // 1MB
minChunkSize = 1000 * 1000 // 1MB
minCompressionLevel = 1 minCompressionLevel = 1
maxCompressionLevel = 19 maxCompressionLevel = 19
// S3 accepts a multipart upload part from 5MiB to 5GiB.
minS3PartSize = 5 * 1024 * 1024
maxS3PartSize = 5 * 1024 * 1024 * 1024
) )
// Sentinel validation errors. // Sentinel validation errors.
@@ -56,21 +48,15 @@ var (
errRecipientNotX25519 = errors.New( errRecipientNotX25519 = errors.New(
"not a valid recipient; only X25519 age1... public keys are supported") "not a valid recipient; only X25519 age1... public keys are supported")
errNoSnapshots = errors.New( errNoSnapshots = errors.New(
"at least one snapshot must be configured (see configs/config.example.yml)") "at least one snapshot must be configured (see config.example.yml)")
errSnapshotNoPaths = errors.New("snapshot must have at least one path") errSnapshotNoPaths = errors.New("snapshot must have at least one path")
errChunkSizeTooSmall = errors.New("chunk_size must be at least 1MB") errChunkSizeTooSmall = errors.New("chunk_size must be at least 1MB")
errBlobSizeTooSmall = errors.New( errBlobSizeTooSmall = errors.New(
"blob_size_limit must be at least the largest chunk the chunker can " + "blob_size_limit must be at least the largest chunk the chunker can " +
"emit (chunk_size times the FastCDC size spread)") "emit (chunk_size times the FastCDC size spread)")
errBadCompression = errors.New("compression_level must be between 1 and 19") errBadCompression = errors.New("compression_level must be between 1 and 19")
errBadS3PartSize = errors.New("s3.part_size must be between 5MiB and 5GiB")
errBadStorageScheme = errors.New( errBadStorageScheme = errors.New(
"storage_url must start with s3://, file://, or rclone://") "storage_url must start with s3://, file://, or rclone://")
errFileURLNotAbsolute = errors.New(
"a file:// storage_url needs an absolute path, " +
"as in file:///path/to/backup")
errNegativePruneGracePeriod = errors.New(
"prune_grace_period must not be negative")
errStorageNotConfigured = errors.New( errStorageNotConfigured = errors.New(
"storage not configured; set storage_url or provide s3.endpoint + " + "storage not configured; set storage_url or provide s3.endpoint + " +
"s3.bucket + credentials") "s3.bucket + credentials")
@@ -191,15 +177,6 @@ type Config struct {
Snapshots map[string]SnapshotConfig `yaml:"snapshots"` Snapshots map[string]SnapshotConfig `yaml:"snapshots"`
CompressionLevel int `yaml:"compression_level"` CompressionLevel int `yaml:"compression_level"`
// PruneGracePeriod is how old a blob no manifest lists must be before
// a prune deletes it, and how old every object in a directory under
// metadata/ with no manifest must be before a prune deletes that
// directory. A backup writes its manifest only once it has uploaded
// all its blobs and its db.zst.age, so a younger blob or directory may
// belong to a backup still running, on this host or another sharing
// the destination store.
PruneGracePeriod time.Duration `yaml:"prune_grace_period"`
// StorageURL specifies the storage backend using a URL format. // StorageURL specifies the storage backend using a URL format.
// Takes precedence over S3Config if set. // Takes precedence over S3Config if set.
// Supported formats: // Supported formats:
@@ -249,48 +226,14 @@ func New(path Path) (*Config, error) {
return cfg, nil return cfg, nil
} }
// Load reads the configuration file at path, parses it with Parse, warns // Load reads and parses the configuration file from the specified path.
// when others can read the file, and validates the configuration. // It applies default values for optional fields, performs environment variable
// Returns an error if the file cannot be read, parsed, or if validation // substitution using smartconfig, and validates the configuration.
// fails. // The configuration file should be in YAML format. Returns an error if the file
// cannot be read, parsed, or if validation fails.
func Load(path string) (*Config, error) { func Load(path string) (*Config, error) {
data, err := os.ReadFile(path) //nolint:gosec // G304: config path is operator-supplied
if err != nil {
return nil, fmt.Errorf("failed to load config file: %w", err)
}
cfg, err := Parse(data)
if err != nil {
return nil, err
}
// Check config file permissions (warn if world or group readable)
//nolint:gosec // G703: config path is operator-supplied by design
info, statErr := os.Stat(path)
if statErr == nil {
mode := info.Mode().Perm()
if mode&0044 != 0 { // group or world readable
log.Warn(cfg.readableByOthersWarning(),
"path", path,
"mode", fmt.Sprintf("%04o", mode),
"recommendation", "chmod 600 "+path)
}
}
err = cfg.Validate()
if err != nil {
return nil, fmt.Errorf("invalid config: %w", err)
}
return cfg, nil
}
// Parse reads YAML config data as Load does, without validating it. It
// applies default values for optional fields, fills in ${...} references
// using smartconfig, and expands ~ in paths.
func Parse(data []byte) (*Config, error) {
// Load config using smartconfig for interpolation // Load config using smartconfig for interpolation
sc, err := smartconfig.NewFromReader(bytes.NewReader(data)) sc, err := smartconfig.NewFromConfigPath(path)
if err != nil { if err != nil {
return nil, fmt.Errorf("failed to load config file: %w", err) return nil, fmt.Errorf("failed to load config file: %w", err)
} }
@@ -301,8 +244,6 @@ func Parse(data []byte) (*Config, error) {
ChunkSize: defaultChunkSize, ChunkSize: defaultChunkSize,
IndexPath: filepath.Join(xdg.DataHome, appName, "index.sqlite"), IndexPath: filepath.Join(xdg.DataHome, appName, "index.sqlite"),
CompressionLevel: defaultCompressionLevel, CompressionLevel: defaultCompressionLevel,
PruneGracePeriod: defaultPruneGracePeriod,
S3: S3Config{PartSize: defaultS3PartSize},
} }
// Convert smartconfig data to YAML then unmarshal // Convert smartconfig data to YAML then unmarshal
@@ -353,6 +294,28 @@ func Parse(data []byte) (*Config, error) {
cfg.S3.Region = "us-east-1" cfg.S3.Region = "us-east-1"
} }
if cfg.S3.PartSize == 0 {
cfg.S3.PartSize = defaultS3PartSize
}
// Check config file permissions (warn if world or group readable)
//nolint:gosec // G703: config path is operator-supplied by design
info, statErr := os.Stat(path)
if statErr == nil {
mode := info.Mode().Perm()
if mode&0044 != 0 { // group or world readable
log.Warn("Config file has insecure permissions (contains S3 credentials)",
"path", path,
"mode", fmt.Sprintf("%04o", mode),
"recommendation", "chmod 600 "+path)
}
}
err = cfg.Validate()
if err != nil {
return nil, fmt.Errorf("invalid config: %w", err)
}
return cfg, nil return cfg, nil
} }
@@ -369,8 +332,6 @@ func Parse(data []byte) (*Config, error) {
// (chunk_size times chunker.ChunkSizeSpread), so a single-chunk blob never // (chunk_size times chunker.ChunkSizeSpread), so a single-chunk blob never
// exceeds the configured limit // exceeds the configured limit
// - Compression level must be between 1 and 19 // - Compression level must be between 1 and 19
// - S3 part size must be between 5MiB and 5GiB, the part sizes S3 accepts
// - Prune grace period must not be negative
// //
// Returns an error describing the first validation failure encountered. // Returns an error describing the first validation failure encountered.
func (c *Config) Validate() error { func (c *Config) Validate() error {
@@ -415,15 +376,6 @@ func (c *Config) Validate() error {
return errBadCompression return errBadCompression
} }
if c.S3.PartSize.Int64() < minS3PartSize ||
c.S3.PartSize.Int64() > maxS3PartSize {
return errBadS3PartSize
}
if c.PruneGracePeriod < 0 {
return errNegativePruneGracePeriod
}
return nil return nil
} }
@@ -459,18 +411,6 @@ func (c *Config) setAgeSecretKey() {
} }
} }
// readableByOthersWarning is the warning Load logs when others can read
// the config file. It says "may contain" because the S3 credentials are
// seen only after smartconfig has replaced any ${...} reference in the
// file with its value, so a set credential need not be in the file.
func (c *Config) readableByOthersWarning() string {
if c.S3.AccessKeyID != "" || c.S3.SecretAccessKey != "" {
return "Config file is readable by others and may contain S3 credentials"
}
return "Config file is readable by others"
}
// validateStorage validates storage configuration. // validateStorage validates storage configuration.
// If StorageURL is set, it takes precedence. S3 URLs require credentials. // If StorageURL is set, it takes precedence. S3 URLs require credentials.
// File URLs don't require any S3 configuration. // File URLs don't require any S3 configuration.
@@ -502,18 +442,11 @@ func (c *Config) validateStorage() error {
// validateStorageURL validates URL-based storage configuration. File and // validateStorageURL validates URL-based storage configuration. File and
// rclone URLs need no credentials; S3 URLs require the legacy s3.* // rclone URLs need no credentials; S3 URLs require the legacy s3.*
// credential fields. A file URL must name an absolute path: a relative one // credential fields.
// would resolve against the working directory, so the destination would
// move with it.
func (c *Config) validateStorageURL() error { func (c *Config) validateStorageURL() error {
switch { switch {
case strings.HasPrefix(c.StorageURL, "file://"): case strings.HasPrefix(c.StorageURL, "file://"):
// storage.ParseStorageURL applies the same rule, but config // File storage doesn't need S3 credentials
// cannot import storage, which imports config.
if !strings.HasPrefix(c.StorageURL, "file:///") {
return errFileURLNotAbsolute
}
return nil return nil
case strings.HasPrefix(c.StorageURL, "rclone://"): case strings.HasPrefix(c.StorageURL, "rclone://"):
// Rclone storage uses rclone's own config // Rclone storage uses rclone's own config
+3 -415
View File
@@ -6,10 +6,8 @@ import (
"path/filepath" "path/filepath"
"strings" "strings"
"testing" "testing"
"time"
"sneak.berlin/go/vaultik/internal/chunker" "sneak.berlin/go/vaultik/internal/chunker"
"sneak.berlin/go/vaultik/internal/log"
) )
const ( const (
@@ -90,12 +88,12 @@ func TestConfigLoad(t *testing.T) {
} }
// TestExampleConfigIsScrubbedAndLoads checks that the shipped // TestExampleConfigIsScrubbedAndLoads checks that the shipped
// configs/config.example.yml carries only neutral placeholders (no real // config.example.yml carries only neutral placeholders (no real credentials,
// credentials, private addresses, or internal host names) and still parses. // private addresses, or internal host names) and still parses.
func TestExampleConfigIsScrubbedAndLoads(t *testing.T) { func TestExampleConfigIsScrubbedAndLoads(t *testing.T) {
t.Parallel() t.Parallel()
examplePath := filepath.Join("..", "..", "configs", "config.example.yml") examplePath := filepath.Join("..", "..", "config.example.yml")
cfg, err := Load(examplePath) cfg, err := Load(examplePath)
if err != nil { if err != nil {
@@ -168,7 +166,6 @@ func TestValidateBlobSizeLimit(t *testing.T) {
ChunkSize: chunkSize, ChunkSize: chunkSize,
BlobSizeLimit: blobLimit, BlobSizeLimit: blobLimit,
CompressionLevel: 3, CompressionLevel: 3,
S3: S3Config{PartSize: defaultS3PartSize},
} }
} }
@@ -224,292 +221,6 @@ func TestValidateBlobSizeLimit(t *testing.T) {
} }
} }
// TestValidateS3PartSize checks that s3.part_size is held to the part sizes
// S3 accepts, 5MiB to 5GiB, by changing only the part size of the test
// config. "5MB" in the config file is 5,000,000 bytes, below the minimum.
func TestValidateS3PartSize(t *testing.T) {
t.Parallel()
base, err := Load(os.Getenv("VAULTIK_CONFIG"))
if err != nil {
t.Fatalf("Failed to load config: %v", err)
}
tests := []struct {
name string
partSize Size
wantErr bool
}{
{
name: "5MB is rejected",
partSize: 5_000_000,
wantErr: true,
},
{
name: "one byte below 5MiB is rejected",
partSize: minS3PartSize - 1,
wantErr: true,
},
{
name: "5MiB is accepted",
partSize: minS3PartSize,
wantErr: false,
},
{
name: "5GiB is accepted",
partSize: maxS3PartSize,
wantErr: false,
},
{
name: "one byte above 5GiB is rejected",
partSize: maxS3PartSize + 1,
wantErr: true,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
cfg := *base
cfg.S3.PartSize = tt.partSize
err := cfg.Validate()
if tt.wantErr {
if !errors.Is(err, errBadS3PartSize) {
t.Fatalf("Validate() error = %v, want errBadS3PartSize", err)
}
return
}
if err != nil {
t.Fatalf("Validate() unexpected error: %v", err)
}
})
}
}
// TestLoadS3PartSize checks that a config file without s3.part_size loads
// with the 5MiB default, and that an explicit 0 fails at load like any other
// part size S3 refuses.
func TestLoadS3PartSize(t *testing.T) {
t.Parallel()
const withoutPartSize = "snapshots:\n" +
" test:\n" +
" paths: [/tmp/vaultik-test-source]\n" +
"storage_url: file:///tmp/vaultik-test-storage\n"
writeConfig := func(t *testing.T, text string) string {
t.Helper()
path := filepath.Join(t.TempDir(), "config.yml")
err := os.WriteFile(path, []byte(text), 0o600)
if err != nil {
t.Fatalf("write config: %v", err)
}
return path
}
t.Run("absent loads as 5MiB", func(t *testing.T) {
t.Parallel()
cfg, err := Load(writeConfig(t, withoutPartSize))
if err != nil {
t.Fatalf("Load() unexpected error: %v", err)
}
if cfg.S3.PartSize != defaultS3PartSize {
t.Errorf("s3.part_size = %d, want %d",
cfg.S3.PartSize, defaultS3PartSize)
}
})
t.Run("0 is rejected", func(t *testing.T) {
t.Parallel()
_, err := Load(writeConfig(t, withoutPartSize+"s3:\n part_size: 0\n"))
if !errors.Is(err, errBadS3PartSize) {
t.Fatalf("Load() error = %v, want errBadS3PartSize", err)
}
})
}
// TestDocumentedSizeDefaults checks that the defaults are the documented
// chunk_size 10MB and blob_size_limit 10GB as the parser reads those values
// (1000-based), so writing a default out in the config file changes nothing.
func TestDocumentedSizeDefaults(t *testing.T) {
t.Parallel()
cfg, err := Parse([]byte("chunk_size: 10MB\nblob_size_limit: 10GB\n"))
if err != nil {
t.Fatalf("Parse() unexpected error: %v", err)
}
if cfg.ChunkSize != defaultChunkSize {
t.Errorf("chunk_size: 10MB is %d bytes, the default is %d",
cfg.ChunkSize, defaultChunkSize)
}
if cfg.BlobSizeLimit != defaultBlobSizeLimit {
t.Errorf("blob_size_limit: 10GB is %d bytes, the default is %d",
cfg.BlobSizeLimit, defaultBlobSizeLimit)
}
}
// TestDocumentedSizeExamples checks the 1MB minimum chunk_size and that
// every size the README, configs/config.example.yml and the config init template
// list as an example is accepted.
func TestDocumentedSizeExamples(t *testing.T) {
t.Parallel()
const withoutSizes = "snapshots:\n" +
" test:\n" +
" paths: [/tmp/vaultik-test-source]\n" +
"storage_url: file:///tmp/vaultik-test-storage\n"
tests := []struct {
setting string
wantErr error
}{
{"chunk_size: 1MB", nil},
{"chunk_size: 999999", errChunkSizeTooSmall},
{"chunk_size: 5M", nil},
{"chunk_size: 10M", nil},
{"chunk_size: 10MB", nil},
{"chunk_size: 64MiB", nil},
{"chunk_size: 1GB", nil},
// Four times the default chunk_size, the documented minimum.
{"blob_size_limit: 40MB", nil},
{"blob_size_limit: 500MB", nil},
{"blob_size_limit: 1GB", nil},
{"blob_size_limit: 1GiB", nil},
{"blob_size_limit: 10G", nil},
{"blob_size_limit: 10GB", nil},
{"s3: {part_size: 5MiB}", nil},
{"s3: {part_size: 10MB}", nil},
{"s3: {part_size: 16MiB}", nil},
{"s3: {part_size: 100MiB}", nil},
{"s3: {part_size: 5GiB}", nil},
}
for _, tt := range tests {
t.Run(tt.setting, func(t *testing.T) {
t.Parallel()
cfg, err := Parse([]byte(withoutSizes + tt.setting + "\n"))
if err != nil {
t.Fatalf("Parse() unexpected error: %v", err)
}
err = cfg.Validate()
if !errors.Is(err, tt.wantErr) {
t.Fatalf("Validate() error = %v, want %v", err, tt.wantErr)
}
})
}
}
// TestValidatePruneGracePeriod checks that a negative prune_grace_period
// is refused rather than acting like 0s, which deletes unreferenced blobs
// and directories under metadata/ with no manifest at once, and that 0s
// and the documented examples are accepted.
func TestValidatePruneGracePeriod(t *testing.T) {
t.Parallel()
const withoutGracePeriod = "snapshots:\n" +
" test:\n" +
" paths: [/tmp/vaultik-test-source]\n" +
"storage_url: file:///tmp/vaultik-test-storage\n"
tests := []struct {
setting string
wantErr error
}{
{"prune_grace_period: 0s", nil},
{"prune_grace_period: 90m", nil},
{"prune_grace_period: 36h", nil},
{"prune_grace_period: -1h", errNegativePruneGracePeriod},
}
for _, tt := range tests {
t.Run(tt.setting, func(t *testing.T) {
t.Parallel()
cfg, err := Parse([]byte(withoutGracePeriod + tt.setting + "\n"))
if err != nil {
t.Fatalf("Parse() unexpected error: %v", err)
}
err = cfg.Validate()
if !errors.Is(err, tt.wantErr) {
t.Fatalf("Validate() error = %v, want %v", err, tt.wantErr)
}
})
}
}
// TestLoadPruneGracePeriod checks that a config file without
// prune_grace_period loads with the documented 24h. The value is written out
// here rather than taken from defaultPruneGracePeriod, so that a change of the
// default fails this test.
func TestLoadPruneGracePeriod(t *testing.T) {
t.Parallel()
const withoutGracePeriod = "snapshots:\n" +
" test:\n" +
" paths: [/tmp/vaultik-test-source]\n" +
"storage_url: file:///tmp/vaultik-test-storage\n"
path := filepath.Join(t.TempDir(), "config.yml")
err := os.WriteFile(path, []byte(withoutGracePeriod), 0o600)
if err != nil {
t.Fatalf("write config: %v", err)
}
cfg, err := Load(path)
if err != nil {
t.Fatalf("Load() unexpected error: %v", err)
}
if cfg.PruneGracePeriod != 24*time.Hour {
t.Errorf("prune_grace_period = %s, want 24h", cfg.PruneGracePeriod)
}
}
// TestLoadRejectsRelativeFileURL checks that a file:// storage_url with a
// relative path fails at load. Accepted, it would resolve against the
// working directory, so a backup run from another directory would write
// to a different destination and still succeed.
func TestLoadRejectsRelativeFileURL(t *testing.T) {
t.Parallel()
const relativeConfig = "snapshots:\n" +
" test:\n" +
" paths: [/tmp/vaultik-test-source]\n" +
"storage_url: file://dest\n"
path := filepath.Join(t.TempDir(), "config.yml")
err := os.WriteFile(path, []byte(relativeConfig), 0o600)
if err != nil {
t.Fatalf("write config: %v", err)
}
_, err = Load(path)
if !errors.Is(err, errFileURLNotAbsolute) {
t.Fatalf("Load() error = %v, want errFileURLNotAbsolute", err)
}
if !strings.Contains(err.Error(), "absolute path") {
t.Errorf("error %q does not say to use an absolute path", err.Error())
}
}
// TestValidateAgeRecipients checks that recipients are parsed at config load // TestValidateAgeRecipients checks that recipients are parsed at config load
// (a bad entry fails immediately, not mid-backup) and that no invalid entry — // (a bad entry fails immediately, not mid-backup) and that no invalid entry —
// least of all a pasted secret key — is echoed in the error. An empty list // least of all a pasted secret key — is echoed in the error. An empty list
@@ -525,7 +236,6 @@ func TestValidateAgeRecipients(t *testing.T) {
ChunkSize: Size(10 * 1024 * 1024), ChunkSize: Size(10 * 1024 * 1024),
BlobSizeLimit: Size(10 * 1024 * 1024 * 1024), BlobSizeLimit: Size(10 * 1024 * 1024 * 1024),
CompressionLevel: 3, CompressionLevel: 3,
S3: S3Config{PartSize: defaultS3PartSize},
} }
} }
@@ -633,125 +343,3 @@ func TestAgeSecretKeySourceName(t *testing.T) {
}) })
} }
} }
// loadReadableConfig writes configYAML to a file that others can read,
// loads it, and returns what the logger wrote to stderr meanwhile. The
// logger writes to the os.Stderr it finds when it is initialized, so
// os.Stderr is pointed at a file first. Not parallel-safe: os.Stderr and
// the logger are process-global.
func loadReadableConfig(t *testing.T, configYAML string) string {
t.Helper()
dir := t.TempDir()
configPath := filepath.Join(dir, "config.yml")
stderrPath := filepath.Join(dir, "stderr")
err := os.WriteFile(configPath, []byte(configYAML), 0o600)
if err != nil {
t.Fatalf("writing config: %v", err)
}
//nolint:gosec // G302: the test needs a config file others can read
err = os.Chmod(configPath, 0o644)
if err != nil {
t.Fatalf("chmod config: %v", err)
}
stderrFile, err := os.Create(stderrPath) //nolint:gosec // G304: test temp path
if err != nil {
t.Fatalf("creating stderr file: %v", err)
}
previous := os.Stderr
os.Stderr = stderrFile
log.Initialize(log.Config{})
_, loadErr := Load(configPath)
os.Stderr = previous
log.Initialize(log.Config{})
_ = stderrFile.Close()
if loadErr != nil {
t.Fatalf("Load() error = %v", loadErr)
}
captured, err := os.ReadFile(stderrPath) //nolint:gosec // G304: test temp path
if err != nil {
t.Fatalf("reading stderr file: %v", err)
}
return string(captured)
}
// TestLoadWarnsReadableConfigWithoutS3Credentials checks that a config
// file others can read, holding no S3 credentials, is warned about
// without a claim that it holds them.
//
//nolint:paralleltest // loadReadableConfig replaces os.Stderr
func TestLoadWarnsReadableConfigWithoutS3Credentials(t *testing.T) {
stderr := loadReadableConfig(t, `
storage_url: file:///var/backups/vaultik
snapshots:
home:
paths:
- /home
`)
if !strings.Contains(stderr, "Config file is readable by others") {
t.Errorf("expected a warning that the file is readable by others, got %q",
stderr)
}
if strings.Contains(stderr, "S3 credentials") {
t.Errorf("warning names S3 credentials the file does not set: %q", stderr)
}
}
// TestLoadWarnsReadableConfigWithS3Credentials checks that a config file
// others can read and that sets S3 credentials, as values or as ${ENV:...}
// references, is warned about as one that may contain them.
//
//nolint:paralleltest // loadReadableConfig replaces os.Stderr
func TestLoadWarnsReadableConfigWithS3Credentials(t *testing.T) {
t.Setenv("VAULTIK_TEST_ACCESS_KEY_ID", "test-access-key")
t.Setenv("VAULTIK_TEST_SECRET_ACCESS_KEY", "test-secret-key")
configs := map[string]string{
"values": `
storage_url: s3://bucket/prefix?endpoint=s3.example.com
s3:
access_key_id: test-access-key
secret_access_key: test-secret-key
snapshots:
home:
paths:
- /home
`,
"references": `
storage_url: s3://bucket/prefix?endpoint=s3.example.com
s3:
access_key_id: ${ENV:VAULTIK_TEST_ACCESS_KEY_ID}
secret_access_key: ${ENV:VAULTIK_TEST_SECRET_ACCESS_KEY}
snapshots:
home:
paths:
- /home
`,
}
for name, configYAML := range configs {
t.Run(name, func(t *testing.T) {
stderr := loadReadableConfig(t, configYAML)
if !strings.Contains(stderr,
"Config file is readable by others and may contain S3 credentials") {
t.Errorf("expected a warning naming the S3 credentials, got %q",
stderr)
}
})
}
}
+6 -1
View File
@@ -58,7 +58,12 @@ func (r *BlobChunkRepository) GetByBlobID(
return nil, fmt.Errorf("querying blob chunks: %w", err) return nil, fmt.Errorf("querying blob chunks: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
var blobChunks []*BlobChunk var blobChunks []*BlobChunk
+11 -9
View File
@@ -83,7 +83,12 @@ func (r *BlobRepository) GetAll(ctx context.Context) (map[string]*Blob, error) {
return nil, fmt.Errorf("querying blobs: %w", err) return nil, fmt.Errorf("querying blobs: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
out := make(map[string]*Blob) out := make(map[string]*Blob)
@@ -154,16 +159,13 @@ func (r *BlobRepository) UpdateFinished(
return nil return nil
} }
// UpdateUploaded marks a blob as uploaded and records the size of the // UpdateUploaded marks a blob as uploaded
// stored object as its compressed size. That size can differ from the
// local copy's when an identical blob was already stored with another
// compression level or other recipients.
func (r *BlobRepository) UpdateUploaded( func (r *BlobRepository) UpdateUploaded(
ctx context.Context, tx *sql.Tx, id string, storedSize int64, ctx context.Context, tx *sql.Tx, id string,
) error { ) error {
query := ` query := `
UPDATE blobs UPDATE blobs
SET uploaded_ts = ?, compressed_size = ? SET uploaded_ts = ?
WHERE id = ? WHERE id = ?
` `
@@ -171,9 +173,9 @@ func (r *BlobRepository) UpdateUploaded(
var err error var err error
if tx != nil { if tx != nil {
_, err = tx.ExecContext(ctx, query, now, storedSize, id) _, err = tx.ExecContext(ctx, query, now, id)
} else { } else {
_, err = r.db.ExecWithLog(ctx, query, now, storedSize, id) _, err = r.db.ExecWithLog(ctx, query, now, id)
} }
if err != nil { if err != nil {
+2 -6
View File
@@ -122,8 +122,8 @@ func TestBlobRepositoryUpdates(t *testing.T) {
t.Errorf("expected compressed size 500, got %d", updated.CompressedSize) t.Errorf("expected compressed size 500, got %d", updated.CompressedSize)
} }
// Test UpdateUploaded, with a stored object larger than the local copy // Test UpdateUploaded
err = repo.UpdateUploaded(ctx, nil, blob.ID.String(), 600) err = repo.UpdateUploaded(ctx, nil, blob.ID.String())
if err != nil { if err != nil {
t.Fatalf("failed to update blob as uploaded: %v", err) t.Fatalf("failed to update blob as uploaded: %v", err)
} }
@@ -141,10 +141,6 @@ func TestBlobRepositoryUpdates(t *testing.T) {
if uploaded.UploadedTS.Before(now.Add(-1 * time.Second)) { if uploaded.UploadedTS.Before(now.Add(-1 * time.Second)) {
t.Error("uploaded timestamp should be around test time") t.Error("uploaded timestamp should be around test time")
} }
if uploaded.CompressedSize != 600 {
t.Errorf("expected the stored size 600, got %d", uploaded.CompressedSize)
}
} }
func TestBlobRepositoryDuplicate(t *testing.T) { func TestBlobRepositoryDuplicate(t *testing.T) {
+18 -3
View File
@@ -61,7 +61,12 @@ func (r *ChunkFileRepository) GetByChunkHash(
return nil, fmt.Errorf("querying chunk files: %w", err) return nil, fmt.Errorf("querying chunk files: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
return r.scanChunkFiles(rows) return r.scanChunkFiles(rows)
} }
@@ -82,7 +87,12 @@ func (r *ChunkFileRepository) GetByFilePath(
return nil, fmt.Errorf("querying chunk files: %w", err) return nil, fmt.Errorf("querying chunk files: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
return r.scanChunkFiles(rows) return r.scanChunkFiles(rows)
} }
@@ -102,7 +112,12 @@ func (r *ChunkFileRepository) GetByFileID(
return nil, fmt.Errorf("querying chunk files: %w", err) return nil, fmt.Errorf("querying chunk files: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
return r.scanChunkFiles(rows) return r.scanChunkFiles(rows)
} }
+12 -2
View File
@@ -107,7 +107,12 @@ func (r *ChunkRepository) GetByHashes(
return nil, fmt.Errorf("querying chunks: %w", err) return nil, fmt.Errorf("querying chunks: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
var chunks []*Chunk var chunks []*Chunk
@@ -147,7 +152,12 @@ func (r *ChunkRepository) ListUnpacked(
return nil, fmt.Errorf("querying unpacked chunks: %w", err) return nil, fmt.Errorf("querying unpacked chunks: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
var chunks []*Chunk var chunks []*Chunk
+6 -1
View File
@@ -38,7 +38,12 @@ func (r *ChunkRepository) list(ctx context.Context, query string) ([]*Chunk, err
return nil, fmt.Errorf("querying chunks: %w", err) return nil, fmt.Errorf("querying chunks: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
var chunks []*Chunk var chunks []*Chunk
+12
View File
@@ -0,0 +1,12 @@
package database
import (
"fmt"
"os"
)
// Fatalf prints an error message to stderr and exits with status 1
func Fatalf(format string, args ...any) {
fmt.Fprintf(os.Stderr, "FATAL: "+format+"\n", args...)
os.Exit(1)
}
+18 -3
View File
@@ -62,7 +62,12 @@ func (r *FileChunkRepository) GetByPath(
return nil, fmt.Errorf("querying file chunks: %w", err) return nil, fmt.Errorf("querying file chunks: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
return r.scanFileChunks(rows) return r.scanFileChunks(rows)
} }
@@ -83,7 +88,12 @@ func (r *FileChunkRepository) GetByFileID(
return nil, fmt.Errorf("querying file chunks: %w", err) return nil, fmt.Errorf("querying file chunks: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
return r.scanFileChunks(rows) return r.scanFileChunks(rows)
} }
@@ -107,7 +117,12 @@ func (r *FileChunkRepository) GetByPathTx(
return nil, fmt.Errorf("querying file chunks: %w", err) return nil, fmt.Errorf("querying file chunks: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
fileChunks, err := r.scanFileChunks(rows) fileChunks, err := r.scanFileChunks(rows)
LogSQL("GetByPathTx", "Complete", path, "count", len(fileChunks)) LogSQL("GetByPathTx", "Complete", path, "count", len(fileChunks))
+47 -80
View File
@@ -33,13 +33,11 @@ func (r *FileRepository) Create(ctx context.Context, tx *sql.Tx, file *File) err
} }
query := ` query := `
INSERT INTO files INSERT INTO files (id, path, source_path, mtime, size, mode, uid, gid, link_target)
(id, path, source_path, mtime, mtime_nsec, size, mode, uid, gid, link_target) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
ON CONFLICT(path) DO UPDATE SET ON CONFLICT(path) DO UPDATE SET
source_path = excluded.source_path, source_path = excluded.source_path,
mtime = excluded.mtime, mtime = excluded.mtime,
mtime_nsec = excluded.mtime_nsec,
size = excluded.size, size = excluded.size,
mode = excluded.mode, mode = excluded.mode,
uid = excluded.uid, uid = excluded.uid,
@@ -56,19 +54,16 @@ func (r *FileRepository) Create(ctx context.Context, tx *sql.Tx, file *File) err
if tx != nil { if tx != nil {
LogSQL("Execute", query, LogSQL("Execute", query,
file.ID.String(), file.Path.String(), file.SourcePath.String(), file.ID.String(), file.Path.String(), file.SourcePath.String(),
file.MTime.Unix(), file.MTime.Nanosecond(), file.MTime.Unix(), file.Size, file.Mode, file.UID, file.GID,
file.Size, file.Mode, file.UID, file.GID,
file.LinkTarget.String()) file.LinkTarget.String())
err = tx.QueryRowContext(ctx, query, err = tx.QueryRowContext(ctx, query,
file.ID.String(), file.Path.String(), file.SourcePath.String(), file.ID.String(), file.Path.String(), file.SourcePath.String(),
file.MTime.Unix(), file.MTime.Nanosecond(), file.MTime.Unix(), file.Size, file.Mode, file.UID, file.GID,
file.Size, file.Mode, file.UID, file.GID,
file.LinkTarget.String()).Scan(&idStr) file.LinkTarget.String()).Scan(&idStr)
} else { } else {
err = r.db.QueryRowWithLog(ctx, query, err = r.db.QueryRowWithLog(ctx, query,
file.ID.String(), file.Path.String(), file.SourcePath.String(), file.ID.String(), file.Path.String(), file.SourcePath.String(),
file.MTime.Unix(), file.MTime.Nanosecond(), file.MTime.Unix(), file.Size, file.Mode, file.UID, file.GID,
file.Size, file.Mode, file.UID, file.GID,
file.LinkTarget.String()).Scan(&idStr) file.LinkTarget.String()).Scan(&idStr)
} }
@@ -89,7 +84,7 @@ func (r *FileRepository) Create(ctx context.Context, tx *sql.Tx, file *File) err
// in the index. // in the index.
func (r *FileRepository) GetByPath(ctx context.Context, path string) (*File, error) { func (r *FileRepository) GetByPath(ctx context.Context, path string) (*File, error) {
query := ` query := `
SELECT id, path, source_path, mtime, mtime_nsec, size, mode, uid, gid, link_target SELECT id, path, source_path, mtime, size, mode, uid, gid, link_target
FROM files FROM files
WHERE path = ? WHERE path = ?
` `
@@ -109,7 +104,7 @@ func (r *FileRepository) GetByPath(ctx context.Context, path string) (*File, err
// GetByID retrieves a file by its UUID // GetByID retrieves a file by its UUID
func (r *FileRepository) GetByID(ctx context.Context, id types.FileID) (*File, error) { func (r *FileRepository) GetByID(ctx context.Context, id types.FileID) (*File, error) {
query := ` query := `
SELECT id, path, source_path, mtime, mtime_nsec, size, mode, uid, gid, link_target SELECT id, path, source_path, mtime, size, mode, uid, gid, link_target
FROM files FROM files
WHERE id = ? WHERE id = ?
` `
@@ -132,7 +127,7 @@ func (r *FileRepository) GetByPathTx(
ctx context.Context, tx *sql.Tx, path string, ctx context.Context, tx *sql.Tx, path string,
) (*File, error) { ) (*File, error) {
query := ` query := `
SELECT id, path, source_path, mtime, mtime_nsec, size, mode, uid, gid, link_target SELECT id, path, source_path, mtime, size, mode, uid, gid, link_target
FROM files FROM files
WHERE path = ? WHERE path = ?
` `
@@ -163,19 +158,23 @@ func (r *FileRepository) ListModifiedSince(
ctx context.Context, since time.Time, ctx context.Context, since time.Time,
) ([]*File, error) { ) ([]*File, error) {
query := ` query := `
SELECT id, path, source_path, mtime, mtime_nsec, size, mode, uid, gid, link_target SELECT id, path, source_path, mtime, size, mode, uid, gid, link_target
FROM files FROM files
WHERE (mtime, mtime_nsec) >= (?, ?) WHERE mtime >= ?
ORDER BY path ORDER BY path
` `
rows, err := r.db.conn.QueryContext(ctx, query, rows, err := r.db.conn.QueryContext(ctx, query, since.Unix())
since.Unix(), since.Nanosecond())
if err != nil { if err != nil {
return nil, fmt.Errorf("querying files: %w", err) return nil, fmt.Errorf("querying files: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
var files []*File var files []*File
@@ -229,68 +228,29 @@ func (r *FileRepository) DeleteByID(
return nil return nil
} }
// ListUnderPath returns the file at path and every file beneath it, // ListByPrefix returns all files whose path starts with prefix, ordered by
// ordered by path. Paths are compared case-sensitively, and a trailing // path.
// slash on path is ignored, so "/" lists every file. func (r *FileRepository) ListByPrefix(
func (r *FileRepository) ListUnderPath( ctx context.Context, prefix string,
ctx context.Context, path string,
) ([]*File, error) { ) ([]*File, error) {
path = strings.TrimRight(path, "/")
dirPrefix := path + "/"
// LIKE would ignore ASCII case and treat _ and % in path as wildcards.
query := ` query := `
SELECT id, path, source_path, mtime, mtime_nsec, size, mode, uid, gid, link_target SELECT id, path, source_path, mtime, size, mode, uid, gid, link_target
FROM files FROM files
WHERE path = ? OR substr(path, 1, length(?)) = ? WHERE path LIKE ? || '%'
ORDER BY path ORDER BY path
` `
rows, err := r.db.conn.QueryContext(ctx, query, path, dirPrefix, dirPrefix) rows, err := r.db.conn.QueryContext(ctx, query, prefix)
if err != nil { if err != nil {
return nil, fmt.Errorf("querying files: %w", err) return nil, fmt.Errorf("querying files: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
var files []*File
for rows.Next() {
file, err := r.scanFileRows(rows)
if err != nil { if err != nil {
return nil, fmt.Errorf("scanning file: %w", err) Fatalf("failed to close rows: %v", err)
} }
}()
files = append(files, file)
}
return files, rows.Err()
}
// ListUnderPathInSnapshot returns the files that ListUnderPath returns
// for path and that the snapshot lists, in no particular order.
func (r *FileRepository) ListUnderPathInSnapshot(
ctx context.Context, path, snapshotID string,
) ([]*File, error) {
path = strings.TrimRight(path, "/")
dirPrefix := path + "/"
query := `
SELECT f.id, f.path, f.source_path, f.mtime, f.mtime_nsec, f.size,
f.mode, f.uid, f.gid, f.link_target
FROM files f
JOIN snapshot_files sf ON sf.file_id = f.id
WHERE sf.snapshot_id = ?
AND (f.path = ? OR substr(f.path, 1, length(?)) = ?)
`
rows, err := r.db.conn.QueryContext(ctx, query,
snapshotID, path, dirPrefix, dirPrefix)
if err != nil {
return nil, fmt.Errorf("querying files: %w", err)
}
defer func() { _ = rows.Close() }()
var files []*File var files []*File
@@ -333,7 +293,12 @@ func (r *FileRepository) ListIDsWithChunksNotInUploadedBlobs(
return nil, fmt.Errorf("querying files: %w", err) return nil, fmt.Errorf("querying files: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
var ids []types.FileID var ids []types.FileID
@@ -354,7 +319,7 @@ func (r *FileRepository) ListIDsWithChunksNotInUploadedBlobs(
// ListAll returns all files in the database // ListAll returns all files in the database
func (r *FileRepository) ListAll(ctx context.Context) ([]*File, error) { func (r *FileRepository) ListAll(ctx context.Context) ([]*File, error) {
query := ` query := `
SELECT id, path, source_path, mtime, mtime_nsec, size, mode, uid, gid, link_target SELECT id, path, source_path, mtime, size, mode, uid, gid, link_target
FROM files FROM files
ORDER BY path ORDER BY path
` `
@@ -364,7 +329,12 @@ func (r *FileRepository) ListAll(ctx context.Context) ([]*File, error) {
return nil, fmt.Errorf("querying files: %w", err) return nil, fmt.Errorf("querying files: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
var files []*File var files []*File
@@ -390,7 +360,7 @@ func (r *FileRepository) CreateBatch(
} }
// Each files row binds this many SQL variables. // Each files row binds this many SQL variables.
const fileCols = 10 const fileCols = 9
// Batch at 100 rows to be safe with SQLite's variable limit. // Batch at 100 rows to be safe with SQLite's variable limit.
const batchSize = 100 const batchSize = 100
@@ -401,7 +371,7 @@ func (r *FileRepository) CreateBatch(
batch := files[i:end] batch := files[i:end]
query := `INSERT INTO files query := `INSERT INTO files
(id, path, source_path, mtime, mtime_nsec, size, mode, uid, gid, link_target) (id, path, source_path, mtime, size, mode, uid, gid, link_target)
VALUES ` VALUES `
args := make([]any, 0, len(batch)*fileCols) args := make([]any, 0, len(batch)*fileCols)
@@ -413,12 +383,11 @@ func (r *FileRepository) CreateBatch(
querySb325.WriteString(", ") querySb325.WriteString(", ")
} }
querySb325.WriteString("(?, ?, ?, ?, ?, ?, ?, ?, ?, ?)") querySb325.WriteString("(?, ?, ?, ?, ?, ?, ?, ?, ?)")
args = append(args, args = append(args,
f.ID.String(), f.Path.String(), f.SourcePath.String(), f.ID.String(), f.Path.String(), f.SourcePath.String(),
f.MTime.Unix(), f.MTime.Nanosecond(), f.MTime.Unix(), f.Size, f.Mode, f.UID, f.GID,
f.Size, f.Mode, f.UID, f.GID,
f.LinkTarget.String()) f.LinkTarget.String())
} }
@@ -427,7 +396,6 @@ func (r *FileRepository) CreateBatch(
query += ` ON CONFLICT(path) DO UPDATE SET query += ` ON CONFLICT(path) DO UPDATE SET
source_path = excluded.source_path, source_path = excluded.source_path,
mtime = excluded.mtime, mtime = excluded.mtime,
mtime_nsec = excluded.mtime_nsec,
size = excluded.size, size = excluded.size,
mode = excluded.mode, mode = excluded.mode,
uid = excluded.uid, uid = excluded.uid,
@@ -487,7 +455,7 @@ func (r *FileRepository) scanFileFrom(row fileRowScanner) (*File, error) {
var ( var (
file File file File
idStr, pathStr, sourcePathStr string idStr, pathStr, sourcePathStr string
mtimeUnix, mtimeNsec int64 mtimeUnix int64
linkTarget sql.NullString linkTarget sql.NullString
) )
@@ -496,7 +464,6 @@ func (r *FileRepository) scanFileFrom(row fileRowScanner) (*File, error) {
&pathStr, &pathStr,
&sourcePathStr, &sourcePathStr,
&mtimeUnix, &mtimeUnix,
&mtimeNsec,
&file.Size, &file.Size,
&file.Mode, &file.Mode,
&file.UID, &file.UID,
@@ -515,7 +482,7 @@ func (r *FileRepository) scanFileFrom(row fileRowScanner) (*File, error) {
file.Path = types.FilePath(pathStr) file.Path = types.FilePath(pathStr)
file.SourcePath = types.SourcePath(sourcePathStr) file.SourcePath = types.SourcePath(sourcePathStr)
file.MTime = time.Unix(mtimeUnix, mtimeNsec).UTC() file.MTime = time.Unix(mtimeUnix, 0).UTC()
if linkTarget.Valid { if linkTarget.Valid {
file.LinkTarget = types.FilePath(linkTarget.String) file.LinkTarget = types.FilePath(linkTarget.String)
} }
-246
View File
@@ -5,12 +5,10 @@ import (
"database/sql" "database/sql"
"errors" "errors"
"os" "os"
"slices"
"testing" "testing"
"time" "time"
"sneak.berlin/go/vaultik/internal/database" "sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/types"
) )
// errTestRollback is the sentinel returned from transaction bodies to // errTestRollback is the sentinel returned from transaction bodies to
@@ -136,141 +134,6 @@ func TestFileRepositoryListDelete(t *testing.T) {
} }
} }
func TestFileRepositoryListUnderPath(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx := context.Background()
repo := database.NewFileRepository(db)
const (
docDir = "/home/u/doc"
docFile = "/home/u/doc/a.txt"
)
// In path order, so the root case can expect all of them as listed.
paths := []string{
"/home/u/50%/x.txt",
"/home/u/50percent/y.txt",
"/home/u/DOC/c.txt",
"/home/u/a_b/x.txt",
"/home/u/axb/y.txt",
docDir,
"/home/u/doc.txt.bak",
docFile,
"/home/u/doc/sub/b.txt",
"/home/u/doc2/b.txt",
}
for _, path := range paths {
err := repo.Create(ctx, nil, &database.File{
Path: types.FilePath(path),
MTime: time.Now().Truncate(time.Second),
Mode: 0644,
})
if err != nil {
t.Fatalf("failed to create %s: %v", path, err)
}
}
docTree := []string{docDir, docFile, "/home/u/doc/sub/b.txt"}
tests := []struct {
name string
path string
want []string
}{
{"directory", docDir, docTree},
{"directory with trailing slash", docDir + "/", docTree},
{"directory differing only in case", "/home/u/DOC",
[]string{"/home/u/DOC/c.txt"}},
{"file", docFile, []string{docFile}},
{"underscore is literal", "/home/u/a_b",
[]string{"/home/u/a_b/x.txt"}},
{"percent is literal", "/home/u/50%",
[]string{"/home/u/50%/x.txt"}},
{"root", "/", paths},
}
for _, tt := range tests {
files, err := repo.ListUnderPath(ctx, tt.path)
if err != nil {
t.Fatalf("%s: failed to list files: %v", tt.name, err)
}
got := make([]string, 0, len(files))
for _, f := range files {
got = append(got, f.Path.String())
}
if !slices.Equal(got, tt.want) {
t.Errorf("%s: listing %q got %q, want %q",
tt.name, tt.path, got, tt.want)
}
}
}
// ListUnderPathInSnapshot leaves out files outside path and files the
// snapshot does not list, though another snapshot lists them.
func TestFileRepositoryListUnderPathInSnapshot(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx := context.Background()
files := database.NewFileRepository(db)
snapshots := database.NewSnapshotRepository(db)
listed := map[string][]string{
"one": {"/src/a.txt", "/src2/c.txt"},
"two": {"/src/b.txt"},
}
for snapshotID, paths := range listed {
err := snapshots.Create(ctx, nil, &database.Snapshot{
ID: types.SnapshotID(snapshotID),
Hostname: "host",
StartedAt: time.Now(),
})
if err != nil {
t.Fatalf("failed to create snapshot %s: %v", snapshotID, err)
}
for _, path := range paths {
err := files.Create(ctx, nil, &database.File{
Path: types.FilePath(path),
MTime: time.Now().Truncate(time.Second),
Mode: 0644,
})
if err != nil {
t.Fatalf("failed to create %s: %v", path, err)
}
err = snapshots.AddFile(ctx, nil, snapshotID, path)
if err != nil {
t.Fatalf("failed to add %s to %s: %v", path, snapshotID, err)
}
}
}
found, err := files.ListUnderPathInSnapshot(ctx, "/src", "one")
if err != nil {
t.Fatalf("failed to list files: %v", err)
}
got := make([]string, 0, len(found))
for _, f := range found {
got = append(got, f.Path.String())
}
if !slices.Equal(got, []string{"/src/a.txt"}) {
t.Errorf("got %q, want only /src/a.txt", got)
}
}
func TestFileRepositorySymlink(t *testing.T) { func TestFileRepositorySymlink(t *testing.T) {
t.Parallel() t.Parallel()
@@ -311,115 +174,6 @@ func TestFileRepositorySymlink(t *testing.T) {
} }
} }
// An mtime after 2262 or before 1678 does not fit in int64 nanoseconds
// since the epoch, and must still come back from the database unchanged.
func TestFileRepositoryMTimeOutsideInt64NanosecondRange(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx := context.Background()
repo := database.NewFileRepository(db)
mtimes := []time.Time{
time.Date(2300, time.January, 1, 0, 0, 0, 123456789, time.UTC),
time.Date(1601, time.January, 1, 0, 0, 0, 987654321, time.UTC),
}
for _, mtime := range mtimes {
created := &database.File{
Path: types.FilePath("/created-" + mtime.Format(time.RFC3339Nano)),
MTime: mtime,
}
err := repo.Create(ctx, nil, created)
if err != nil {
t.Fatalf("failed to create file: %v", err)
}
batched := &database.File{
ID: types.NewFileID(),
Path: types.FilePath("/batched-" + mtime.Format(time.RFC3339Nano)),
MTime: mtime,
}
err = repo.CreateBatch(ctx, nil, []*database.File{batched})
if err != nil {
t.Fatalf("failed to batch create file: %v", err)
}
for _, path := range []types.FilePath{created.Path, batched.Path} {
retrieved, err := repo.GetByPath(ctx, path.String())
if err != nil {
t.Fatalf("failed to get file: %v", err)
}
if !retrieved.MTime.Equal(mtime) {
t.Errorf("%s: mtime got %v, want %v",
path, retrieved.MTime, mtime)
}
}
}
}
// A file already in the index and rewritten within the same second must get
// its new nanoseconds stored, through both Create and CreateBatch.
func TestFileRepositoryUpsertMTimeInSameSecond(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx := context.Background()
repo := database.NewFileRepository(db)
indexed := time.Date(2026, time.October, 7, 12, 0, 0, 100000000, time.UTC)
rewritten := indexed.Add(800 * time.Millisecond)
tests := []struct {
name string
upsert func(file *database.File) error
}{
{"Create", func(file *database.File) error {
return repo.Create(ctx, nil, file)
}},
{"CreateBatch", func(file *database.File) error {
return repo.CreateBatch(ctx, nil, []*database.File{file})
}},
}
for _, tt := range tests {
file := &database.File{
ID: types.NewFileID(),
Path: types.FilePath("/" + tt.name),
MTime: indexed,
}
err := tt.upsert(file)
if err != nil {
t.Fatalf("%s: failed to create file: %v", tt.name, err)
}
file.MTime = rewritten
err = tt.upsert(file)
if err != nil {
t.Fatalf("%s: failed to update file: %v", tt.name, err)
}
retrieved, err := repo.GetByPath(ctx, file.Path.String())
if err != nil {
t.Fatalf("%s: failed to get file: %v", tt.name, err)
}
if !retrieved.MTime.Equal(rewritten) {
t.Errorf("%s: mtime got %v, want %v",
tt.name, retrieved.MTime, rewritten)
}
}
}
func TestFileRepositoryTransaction(t *testing.T) { func TestFileRepositoryTransaction(t *testing.T) {
t.Parallel() t.Parallel()
+4 -3
View File
@@ -14,7 +14,8 @@ type File struct {
ID types.FileID // UUID primary key ID types.FileID // UUID primary key
Path types.FilePath // Absolute path of the file Path types.FilePath // Absolute path of the file
// SourcePath is the source directory this file came from. // SourcePath is the source directory this file came from (used for
// restore path stripping).
SourcePath types.SourcePath SourcePath types.SourcePath
MTime time.Time MTime time.Time
Size int64 Size int64
@@ -98,8 +99,8 @@ type Snapshot struct {
StartedAt time.Time StartedAt time.Time
CompletedAt *time.Time // nil if still in progress CompletedAt *time.Time // nil if still in progress
FileCount int64 FileCount int64
ChunkCount int64 // Chunks this snapshot stored that were not stored before ChunkCount int64
BlobCount int64 // Blobs this snapshot created BlobCount int64
TotalSize int64 // Total size of all referenced files TotalSize int64 // Total size of all referenced files
// BlobSize is the total size of all referenced blobs (compressed and // BlobSize is the total size of all referenced blobs (compressed and
+18 -23
View File
@@ -3,7 +3,6 @@ package database
import ( import (
"context" "context"
"database/sql" "database/sql"
"errors"
"fmt" "fmt"
) )
@@ -61,24 +60,22 @@ func (r *Repositories) WithTx(ctx context.Context, fn TxFunc) error {
defer func() { defer func() {
if p := recover(); p != nil { if p := recover(); p != nil {
// The panic is the failure to report, so a rollback error rollbackErr := tx.Rollback()
// is dropped. if rollbackErr != nil {
_ = tx.Rollback() Fatalf("failed to rollback transaction: %v", rollbackErr)
}
panic(p) panic(p)
} else if err != nil {
rollbackErr := tx.Rollback()
if rollbackErr != nil {
Fatalf("failed to rollback transaction: %v", rollbackErr)
}
} }
}() }()
err = fn(ctx, tx) err = fn(ctx, tx)
if err != nil { if err != nil {
// Once ctx is cancelled, database/sql rolls the transaction
// back itself and Rollback returns sql.ErrTxDone.
rollbackErr := tx.Rollback()
if rollbackErr != nil && !errors.Is(rollbackErr, sql.ErrTxDone) {
return fmt.Errorf("%w; rolling back transaction: %w",
err, rollbackErr)
}
return err return err
} }
@@ -106,24 +103,22 @@ func (r *Repositories) WithReadTx(ctx context.Context, fn TxFunc) error {
defer func() { defer func() {
if p := recover(); p != nil { if p := recover(); p != nil {
// The panic is the failure to report, so a rollback error rollbackErr := tx.Rollback()
// is dropped. if rollbackErr != nil {
_ = tx.Rollback() Fatalf("failed to rollback transaction: %v", rollbackErr)
}
panic(p) panic(p)
} else if err != nil {
rollbackErr := tx.Rollback()
if rollbackErr != nil {
Fatalf("failed to rollback transaction: %v", rollbackErr)
}
} }
}() }()
err = fn(ctx, tx) err = fn(ctx, tx)
if err != nil { if err != nil {
// Once ctx is cancelled, database/sql rolls the transaction
// back itself and Rollback returns sql.ErrTxDone.
rollbackErr := tx.Rollback()
if rollbackErr != nil && !errors.Is(rollbackErr, sql.ErrTxDone) {
return fmt.Errorf("%w; rolling back transaction: %w",
err, rollbackErr)
}
return err return err
} }
-158
View File
@@ -4,7 +4,6 @@ import (
"context" "context"
"database/sql" "database/sql"
"errors" "errors"
"strings"
"testing" "testing"
"time" "time"
@@ -236,125 +235,6 @@ func TestRepositoriesTransactionRollback(t *testing.T) {
} }
} }
// When the context is cancelled during the body, database/sql rolls the
// transaction back itself, so WithTx's own rollback finds it already
// done. WithTx must return the body's error alone, without that rollback.
func TestRepositoriesTransactionContextCancelled(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
repos := database.NewRepositories(db)
err := repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
file := &database.File{
Path: "/test/cancelled_file.txt",
MTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
GID: 1000,
}
err := repos.Files.Create(ctx, tx, file)
if err != nil {
return err
}
cancel()
// database/sql rolls back from a goroutine of its own; wait
// until it has, so the test does not depend on that race.
for {
_, err = tx.ExecContext(context.WithoutCancel(ctx), "SELECT 1")
if errors.Is(err, sql.ErrTxDone) {
return ctx.Err()
}
time.Sleep(time.Millisecond)
}
})
if !errors.Is(err, context.Canceled) {
t.Fatalf("expected context.Canceled, got: %v", err)
}
if errors.Is(err, sql.ErrTxDone) {
t.Fatalf("the already-done rollback was reported: %v", err)
}
file, err := repos.Files.GetByPath(
context.Background(), "/test/cancelled_file.txt",
)
if err != nil {
t.Fatalf("error checking for file: %v", err)
}
if file != nil {
t.Error("file should not exist after the cancelled transaction")
}
}
// A body that ends the transaction itself with ROLLBACK makes WithTx's
// own rollback fail. WithTx must return that failure together with the
// body's error.
func TestRepositoriesTransactionRollbackFails(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx := context.Background()
repos := database.NewRepositories(db)
err := repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
_, err := tx.ExecContext(ctx, "ROLLBACK")
if err != nil {
return err
}
return errIntentionalRollback
})
if !errors.Is(err, errIntentionalRollback) {
t.Fatalf("expected the body's error, got: %v", err)
}
if !strings.Contains(err.Error(), "rolling back transaction") {
t.Errorf("expected the failed rollback in the error, got: %v", err)
}
}
// When the body ends the transaction itself with ROLLBACK and then
// panics, WithTx's own rollback fails; the panic must still reach the
// caller.
func TestRepositoriesTransactionPanicRollbackFails(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx := context.Background()
repos := database.NewRepositories(db)
defer func() {
if recover() == nil {
t.Error("expected the body's panic to reach the caller")
}
}()
_ = repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
_, err := tx.ExecContext(ctx, "ROLLBACK")
if err != nil {
return err
}
panic(errIntentionalRollback)
})
}
func TestRepositoriesReadTransaction(t *testing.T) { func TestRepositoriesReadTransaction(t *testing.T) {
t.Parallel() t.Parallel()
@@ -411,41 +291,3 @@ func TestRepositoriesReadTransaction(t *testing.T) {
t.Error("expected to retrieve file in read transaction") t.Error("expected to retrieve file in read transaction")
} }
} }
// When the context is cancelled during a read transaction's body,
// database/sql rolls the transaction back itself, so WithReadTx's own
// rollback finds it already done. WithReadTx must return the body's error
// alone, without that rollback.
func TestRepositoriesReadTransactionContextCancelled(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
repos := database.NewRepositories(db)
err := repos.WithReadTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
cancel()
// database/sql rolls back from a goroutine of its own; wait
// until it has, so the test does not depend on that race.
for {
_, err := tx.ExecContext(context.WithoutCancel(ctx), "SELECT 1")
if errors.Is(err, sql.ErrTxDone) {
return ctx.Err()
}
time.Sleep(time.Millisecond)
}
})
if !errors.Is(err, context.Canceled) {
t.Fatalf("expected context.Canceled, got: %v", err)
}
if errors.Is(err, sql.ErrTxDone) {
t.Fatalf("the already-done rollback was reported: %v", err)
}
}
@@ -824,7 +824,7 @@ func TestTransactionIsolation(t *testing.T) {
} }
// Verify the file was not created (transaction rolled back) // Verify the file was not created (transaction rolled back)
files, err := repos.Files.ListUnderPath(ctx, "/tx-test.txt") files, err := repos.Files.ListByPrefix(ctx, "/tx-test")
if err != nil { if err != nil {
t.Fatal(err) t.Fatal(err)
} }
@@ -916,7 +916,7 @@ func TestConcurrentOrphanedCleanup(t *testing.T) {
} }
// Verify correct files were deleted // Verify correct files were deleted
files, err := repos.Files.ListAll(ctx) files, err := repos.Files.ListByPrefix(ctx, "/concurrent-")
if err != nil { if err != nil {
t.Fatal(err) t.Fatal(err)
} }
+1 -1
View File
@@ -147,7 +147,7 @@ func TestOrphanedFileCleanupDebug(t *testing.T) {
t.Logf("Files count after cleanup: %d", count) t.Logf("Files count after cleanup: %d", count)
// List remaining files // List remaining files
files, err := repos.Files.ListUnderPath(ctx, "/") files, err := repos.Files.ListByPrefix(ctx, "/")
if err != nil { if err != nil {
t.Fatal(err) t.Fatal(err)
} }
+27 -34
View File
@@ -3,7 +3,6 @@ package database
import ( import (
"context" "context"
"database/sql"
"fmt" "fmt"
"strings" "strings"
"testing" "testing"
@@ -368,7 +367,7 @@ func verifyBlobNullUploadTS(
} }
// createLargeDatasetFiles creates fileCount files and adds every other // createLargeDatasetFiles creates fileCount files and adds every other
// one to the snapshot, in one transaction as a backup writes them. // one to the snapshot.
func createLargeDatasetFiles( func createLargeDatasetFiles(
t *testing.T, t *testing.T,
repos *Repositories, repos *Repositories,
@@ -377,38 +376,31 @@ func createLargeDatasetFiles(
) { ) {
t.Helper() t.Helper()
ctx := context.Background()
start := time.Now() start := time.Now()
err := repos.WithTx(context.Background(), for i := range fileCount {
func(ctx context.Context, tx *sql.Tx) error { file := &File{
for i := range fileCount { Path: types.FilePath(fmt.Sprintf("/large/file%05d.txt", i)),
file := &File{ MTime: time.Now(),
Path: types.FilePath(fmt.Sprintf("/large/file%05d.txt", i)), Size: int64(i * 1024),
MTime: time.Now(), Mode: 0644,
Size: int64(i * 1024), UID: uint32(1000 + (i % 10)),
Mode: 0644, GID: uint32(1000 + (i % 10)),
UID: uint32(1000 + (i % 10)), }
GID: uint32(1000 + (i % 10)),
}
err := repos.Files.Create(ctx, tx, file) err := repos.Files.Create(ctx, nil, file)
if err != nil { if err != nil {
return fmt.Errorf("creating file %d: %w", i, err) t.Fatalf("failed to create file %d: %v", i, err)
} }
// Add half to snapshot // Add half to snapshot
if i%2 == 0 { if i%2 == 0 {
err = repos.Snapshots.AddFileByID(ctx, tx, snapshotID, file.ID) err = repos.Snapshots.AddFileByID(ctx, nil, snapshotID, file.ID)
if err != nil { if err != nil {
return err t.Fatal(err)
}
}
} }
}
return nil
})
if err != nil {
t.Fatal(err)
} }
t.Logf("Created %d files in %v", fileCount, time.Since(start)) t.Logf("Created %d files in %v", fileCount, time.Since(start))
@@ -450,12 +442,12 @@ func TestLargeDatasets(t *testing.T) {
createLargeDatasetFiles(t, repos, snapshot.ID.String(), fileCount) createLargeDatasetFiles(t, repos, snapshot.ID.String(), fileCount)
}) })
// Test ListUnderPath performance // Test ListByPrefix performance
//nolint:paralleltest // phases share one database and are order-dependent //nolint:paralleltest // phases share one database and are order-dependent
t.Run("list under path performance", func(t *testing.T) { t.Run("list by prefix performance", func(t *testing.T) {
start := time.Now() start := time.Now()
files, err := repos.Files.ListUnderPath(ctx, "/large/") files, err := repos.Files.ListByPrefix(ctx, "/large/")
if err != nil { if err != nil {
t.Fatal(err) t.Fatal(err)
} }
@@ -480,7 +472,7 @@ func TestLargeDatasets(t *testing.T) {
t.Logf("Cleaned up orphaned files in %v", time.Since(start)) t.Logf("Cleaned up orphaned files in %v", time.Since(start))
// Verify correct number remain // Verify correct number remain
files, err := repos.Files.ListUnderPath(ctx, "/large/") files, err := repos.Files.ListByPrefix(ctx, "/large/")
if err != nil { if err != nil {
t.Fatal(err) t.Fatal(err)
} }
@@ -614,7 +606,8 @@ func TestTimezoneHandling(t *testing.T) {
t.Skip("timezone not available") t.Skip("timezone not available")
} }
nyTime := time.Now().In(loc) // Use Truncate to remove sub-second precision since we store as Unix timestamps
nyTime := time.Now().In(loc).Truncate(time.Second)
file := &File{ file := &File{
Path: "/timezone-test.txt", Path: "/timezone-test.txt",
MTime: nyTime, MTime: nyTime,
+2 -15
View File
@@ -5,9 +5,8 @@
CREATE TABLE IF NOT EXISTS files ( CREATE TABLE IF NOT EXISTS files (
id TEXT PRIMARY KEY, -- UUID id TEXT PRIMARY KEY, -- UUID
path TEXT NOT NULL UNIQUE, path TEXT NOT NULL UNIQUE,
source_path TEXT NOT NULL DEFAULT '', -- The source directory this file came from source_path TEXT NOT NULL DEFAULT '', -- The source directory this file came from (for restore path stripping)
mtime INTEGER NOT NULL, -- whole seconds since the Unix epoch mtime INTEGER NOT NULL,
mtime_nsec INTEGER NOT NULL, -- nanoseconds within that second, 0 to 999999999
size INTEGER NOT NULL, size INTEGER NOT NULL,
mode INTEGER NOT NULL, mode INTEGER NOT NULL,
uid INTEGER NOT NULL, uid INTEGER NOT NULL,
@@ -86,10 +85,8 @@ CREATE TABLE IF NOT EXISTS snapshots (
completed_at INTEGER, completed_at INTEGER,
file_count INTEGER NOT NULL DEFAULT 0, file_count INTEGER NOT NULL DEFAULT 0,
chunk_count INTEGER NOT NULL DEFAULT 0, chunk_count INTEGER NOT NULL DEFAULT 0,
new_chunk_size INTEGER NOT NULL DEFAULT 0,
blob_count INTEGER NOT NULL DEFAULT 0, blob_count INTEGER NOT NULL DEFAULT 0,
total_size INTEGER NOT NULL DEFAULT 0, total_size INTEGER NOT NULL DEFAULT 0,
uncompressed_chunk_size INTEGER NOT NULL DEFAULT 0,
blob_size INTEGER NOT NULL DEFAULT 0, blob_size INTEGER NOT NULL DEFAULT 0,
blob_uncompressed_size INTEGER NOT NULL DEFAULT 0, blob_uncompressed_size INTEGER NOT NULL DEFAULT 0,
compression_ratio REAL NOT NULL DEFAULT 1.0, compression_ratio REAL NOT NULL DEFAULT 1.0,
@@ -123,16 +120,6 @@ CREATE TABLE IF NOT EXISTS snapshot_blobs (
-- Index for efficient blob lookups (used in orphan detection) -- Index for efficient blob lookups (used in orphan detection)
CREATE INDEX IF NOT EXISTS idx_snapshot_blobs_blob_id ON snapshot_blobs(blob_id); CREATE INDEX IF NOT EXISTS idx_snapshot_blobs_blob_id ON snapshot_blobs(blob_id);
-- Snapshot mount points table: the directories at or below a configured
-- path that the snapshot's backup found on a different filesystem from
-- their parent directory, as a mount point is, and found an entry in
CREATE TABLE IF NOT EXISTS snapshot_mount_points (
snapshot_id TEXT NOT NULL,
path TEXT NOT NULL,
PRIMARY KEY (snapshot_id, path),
FOREIGN KEY (snapshot_id) REFERENCES snapshots(id) ON DELETE CASCADE
);
-- Uploads table: tracks blob upload metrics -- Uploads table: tracks blob upload metrics
CREATE TABLE IF NOT EXISTS uploads ( CREATE TABLE IF NOT EXISTS uploads (
blob_hash TEXT PRIMARY KEY, blob_hash TEXT PRIMARY KEY,
+93 -139
View File
@@ -24,8 +24,7 @@ var (
) )
// SnapshotRepository provides access to the snapshots table and its // SnapshotRepository provides access to the snapshots table and its
// snapshot_files / snapshot_blobs association tables, and to the mount // snapshot_files / snapshot_blobs association tables.
// points each snapshot's backup found (snapshot_mount_points).
type SnapshotRepository struct { type SnapshotRepository struct {
db *DB db *DB
} }
@@ -121,20 +120,14 @@ func (r *SnapshotRepository) UpdateCounts(
return nil return nil
} }
// UpdateExtendedStats updates extended statistics for a snapshot. It also // UpdateExtendedStats updates extended statistics for a snapshot
// records the total plaintext size of the distinct chunks the snapshot's
// files reference. Only the snapshot's own backup can take that total: a
// file's row is shared by every snapshot that lists it, and a later
// backup of a changed file rewrites the row with the new chunks.
func (r *SnapshotRepository) UpdateExtendedStats( func (r *SnapshotRepository) UpdateExtendedStats(
ctx context.Context, ctx context.Context,
tx *sql.Tx, tx *sql.Tx,
snapshotID string, snapshotID string,
blobUncompressedSize int64, blobUncompressedSize int64,
compressionLevel int, compressionLevel int,
uploadBytes int64,
uploadDurationMs int64, uploadDurationMs int64,
newChunkSize int64,
) error { ) error {
compressionRatio, err := r.extendedCompressionRatio( compressionRatio, err := r.extendedCompressionRatio(
ctx, tx, snapshotID, blobUncompressedSize, ctx, tx, snapshotID, blobUncompressedSize,
@@ -148,30 +141,19 @@ func (r *SnapshotRepository) UpdateExtendedStats(
SET blob_uncompressed_size = ?, SET blob_uncompressed_size = ?,
compression_ratio = ?, compression_ratio = ?,
compression_level = ?, compression_level = ?,
upload_bytes = ?, upload_bytes = blob_size,
upload_duration_ms = ?, upload_duration_ms = ?
new_chunk_size = ?,
uncompressed_chunk_size = (
SELECT COALESCE(SUM(c.size), 0)
FROM (
SELECT DISTINCT fc.chunk_hash
FROM snapshot_files sf
JOIN file_chunks fc ON sf.file_id = fc.file_id
WHERE sf.snapshot_id = snapshots.id
) sc
JOIN chunks c ON sc.chunk_hash = c.chunk_hash
)
WHERE id = ? WHERE id = ?
` `
if tx != nil { if tx != nil {
_, err = tx.ExecContext(ctx, query, _, err = tx.ExecContext(ctx, query,
blobUncompressedSize, compressionRatio, compressionLevel, blobUncompressedSize, compressionRatio, compressionLevel,
uploadBytes, uploadDurationMs, newChunkSize, snapshotID) uploadDurationMs, snapshotID)
} else { } else {
_, err = r.db.ExecWithLog(ctx, query, _, err = r.db.ExecWithLog(ctx, query,
blobUncompressedSize, compressionRatio, compressionLevel, blobUncompressedSize, compressionRatio, compressionLevel,
uploadBytes, uploadDurationMs, newChunkSize, snapshotID) uploadDurationMs, snapshotID)
} }
if err != nil { if err != nil {
@@ -256,7 +238,12 @@ func (r *SnapshotRepository) GetOnlySnapshot(ctx context.Context) (*Snapshot, er
return nil, fmt.Errorf("querying snapshots: %w", err) return nil, fmt.Errorf("querying snapshots: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
snapshots, err := r.scanSnapshotRows(rows) snapshots, err := r.scanSnapshotRows(rows)
if err != nil { if err != nil {
@@ -291,7 +278,12 @@ func (r *SnapshotRepository) ListRecent(
return nil, fmt.Errorf("querying snapshots: %w", err) return nil, fmt.Errorf("querying snapshots: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
return r.scanSnapshotRows(rows) return r.scanSnapshotRows(rows)
} }
@@ -501,57 +493,32 @@ func (r *SnapshotRepository) GetBlobHashes(
ORDER BY sb.blob_hash ORDER BY sb.blob_hash
` `
blobs, err := r.queryStrings(ctx, query, snapshotID) rows, err := r.db.conn.QueryContext(ctx, query, snapshotID)
if err != nil { if err != nil {
return nil, fmt.Errorf("querying blob hashes: %w", err) return nil, fmt.Errorf("querying blob hashes: %w", err)
} }
return blobs, nil defer func() {
} err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
// AddMountPoint records dir as a directory that the backup of a snapshot var blobs []string
// found on a different filesystem from its parent directory, as a mount
// point is, using tx when non-nil.
func (r *SnapshotRepository) AddMountPoint(
ctx context.Context, tx *sql.Tx, snapshotID string, dir string,
) error {
query := `
INSERT OR IGNORE INTO snapshot_mount_points (snapshot_id, path)
VALUES (?, ?)
`
var err error for rows.Next() {
if tx != nil { var blobHash string
_, err = tx.ExecContext(ctx, query, snapshotID, dir)
} else { err := rows.Scan(&blobHash)
_, err = r.db.ExecWithLog(ctx, query, snapshotID, dir) if err != nil {
return nil, fmt.Errorf("scanning blob hash: %w", err)
}
blobs = append(blobs, blobHash)
} }
if err != nil { return blobs, rows.Err()
return fmt.Errorf("adding mount point to snapshot: %w", err)
}
return nil
}
// GetMountPoints returns the directories AddMountPoint recorded for a
// snapshot, sorted.
func (r *SnapshotRepository) GetMountPoints(
ctx context.Context, snapshotID string,
) ([]string, error) {
query := `
SELECT path
FROM snapshot_mount_points
WHERE snapshot_id = ?
ORDER BY path
`
dirs, err := r.queryStrings(ctx, query, snapshotID)
if err != nil {
return nil, fmt.Errorf("querying mount points: %w", err)
}
return dirs, nil
} }
// GetSnapshotTotalCompressedSize returns the total compressed size of all // GetSnapshotTotalCompressedSize returns the total compressed size of all
@@ -576,66 +543,71 @@ func (r *SnapshotRepository) GetSnapshotTotalCompressedSize(
return totalSize, nil return totalSize, nil
} }
// GetSnapshotBlobSizes returns the total compressed and uncompressed sizes // GetSnapshotUncompressedChunkSize returns the sum of plaintext sizes of all unique
// of all blobs referenced by a snapshot. // chunks referenced by a snapshot (via snapshot_files → file_chunks → chunks).
func (r *SnapshotRepository) GetSnapshotBlobSizes(
ctx context.Context, snapshotID string,
) (int64, int64, error) {
query := `
SELECT COALESCE(SUM(b.compressed_size), 0),
COALESCE(SUM(b.uncompressed_size), 0)
FROM snapshot_blobs sb
JOIN blobs b ON sb.blob_hash = b.blob_hash
WHERE sb.snapshot_id = ?
`
var compressed, uncompressed int64
err := r.db.conn.QueryRowContext(ctx, query, snapshotID).Scan(
&compressed, &uncompressed)
if err != nil {
return 0, 0, fmt.Errorf("querying snapshot blob sizes: %w", err)
}
return compressed, uncompressed, nil
}
// GetSnapshotUncompressedChunkSize returns the total plaintext size of the
// distinct chunks the snapshot's files reference, as the snapshot's backup
// recorded it (see UpdateExtendedStats).
func (r *SnapshotRepository) GetSnapshotUncompressedChunkSize( func (r *SnapshotRepository) GetSnapshotUncompressedChunkSize(
ctx context.Context, snapshotID string, ctx context.Context, snapshotID string,
) (int64, error) { ) (int64, error) {
query := `SELECT uncompressed_chunk_size FROM snapshots WHERE id = ?` query := `
SELECT COALESCE(SUM(c.size), 0)
FROM (
SELECT DISTINCT fc.chunk_hash
FROM snapshot_files sf
JOIN file_chunks fc ON sf.file_id = fc.file_id
WHERE sf.snapshot_id = ?
) sc
JOIN chunks c ON sc.chunk_hash = c.chunk_hash
`
var uncompressedChunkSize int64 var totalSize int64
err := r.db.conn.QueryRowContext(ctx, query, snapshotID).Scan(&uncompressedChunkSize) err := r.db.conn.QueryRowContext(ctx, query, snapshotID).Scan(&totalSize)
if err != nil { if err != nil {
return 0, fmt.Errorf("querying uncompressed chunk size: %w", err) return 0, fmt.Errorf("querying uncompressed chunk size: %w", err)
} }
return uncompressedChunkSize, nil return totalSize, nil
} }
// GetSnapshotNewChunkSize returns the total plaintext size of the chunks the // GetSnapshotNewChunkSize returns the sum of plaintext sizes of chunks that are
// snapshot's backup stored that were not stored before, as the backup // referenced by this snapshot but not by any earlier completed snapshot known to
// recorded it. It is not derived from the snapshot's files: a file's row is // the local database. The result is the marginal uncompressed data this snapshot
// shared by every snapshot that lists it and is rewritten when the file // added to the dedup pool — i.e., the delta from prior snapshots.
// changes, so it shows only the file's latest chunks.
func (r *SnapshotRepository) GetSnapshotNewChunkSize( func (r *SnapshotRepository) GetSnapshotNewChunkSize(
ctx context.Context, snapshotID string, ctx context.Context, snapshotID string,
) (int64, error) { ) (int64, error) {
query := `SELECT new_chunk_size FROM snapshots WHERE id = ?` query := `
WITH this_snap_chunks AS (
SELECT DISTINCT fc.chunk_hash
FROM snapshot_files sf
JOIN file_chunks fc ON sf.file_id = fc.file_id
WHERE sf.snapshot_id = ?
),
prior_chunks AS (
SELECT DISTINCT fc.chunk_hash
FROM snapshots s
JOIN snapshot_files sf ON sf.snapshot_id = s.id
JOIN file_chunks fc ON fc.file_id = sf.file_id
WHERE s.completed_at IS NOT NULL
AND s.id != ?
AND s.started_at < (SELECT started_at FROM snapshots WHERE id = ?)
)
SELECT COALESCE(SUM(c.size), 0)
FROM chunks c
JOIN this_snap_chunks t ON c.chunk_hash = t.chunk_hash
WHERE c.chunk_hash NOT IN (SELECT chunk_hash FROM prior_chunks)
`
var newChunkSize int64 var totalSize int64
err := r.db.conn.QueryRowContext(ctx, query, snapshotID).Scan(&newChunkSize) err := r.db.conn.QueryRowContext(
ctx, query, snapshotID, snapshotID, snapshotID,
).Scan(&totalSize)
if err != nil { if err != nil {
return 0, fmt.Errorf("querying new chunk size: %w", err) return 0, fmt.Errorf("querying new chunk size: %w", err)
} }
return newChunkSize, nil return totalSize, nil
} }
// GetIncompleteSnapshots returns all snapshots that haven't been completed // GetIncompleteSnapshots returns all snapshots that haven't been completed
@@ -656,7 +628,12 @@ func (r *SnapshotRepository) GetIncompleteSnapshots(
return nil, fmt.Errorf("querying incomplete snapshots: %w", err) return nil, fmt.Errorf("querying incomplete snapshots: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
return r.scanSnapshotRows(rows) return r.scanSnapshotRows(rows)
} }
@@ -679,7 +656,12 @@ func (r *SnapshotRepository) GetIncompleteByHostname(
return nil, fmt.Errorf("querying incomplete snapshots: %w", err) return nil, fmt.Errorf("querying incomplete snapshots: %w", err)
} }
defer func() { _ = rows.Close() }() defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
// Same column set as every other multi-row snapshot query, so the // Same column set as every other multi-row snapshot query, so the
// shared scanner applies — including its timestamp normalization. // shared scanner applies — including its timestamp normalization.
@@ -740,34 +722,6 @@ func (r *SnapshotRepository) DeleteSnapshotUploads(
return nil return nil
} }
// queryStrings runs query, which selects one text column, and returns
// its values in the order of the rows.
func (r *SnapshotRepository) queryStrings(
ctx context.Context, query string, args ...any,
) ([]string, error) {
rows, err := r.db.conn.QueryContext(ctx, query, args...)
if err != nil {
return nil, err
}
defer func() { _ = rows.Close() }()
var values []string
for rows.Next() {
var value string
err := rows.Scan(&value)
if err != nil {
return nil, err
}
values = append(values, value)
}
return values, rows.Err()
}
// extendedCompressionRatio computes the compression ratio for a snapshot // extendedCompressionRatio computes the compression ratio for a snapshot
// from its stored blob_size and the given uncompressed size. Returns 1.0 // from its stored blob_size and the given uncompressed size. Returns 1.0
// when the uncompressed size is zero. // when the uncompressed size is zero.
-109
View File
@@ -4,7 +4,6 @@ import (
"context" "context"
"fmt" "fmt"
"math" "math"
"slices"
"testing" "testing"
"time" "time"
@@ -146,65 +145,6 @@ func TestSnapshotRepositoryUpdateCounts(t *testing.T) {
} }
} }
// GetSnapshotBlobSizes totals the blobs the snapshot references, and only
// those.
func TestSnapshotRepositoryGetSnapshotBlobSizes(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx := context.Background()
repos := database.NewRepositories(db)
snapshot := &database.Snapshot{
ID: "2024-01-03T12:00:00Z",
Hostname: testHostname,
VaultikVersion: testVersion,
StartedAt: time.Now().Truncate(time.Second),
}
err := repos.Snapshots.Create(ctx, nil, snapshot)
if err != nil {
t.Fatalf("failed to create snapshot: %v", err)
}
blobs := []*database.Blob{
{Hash: "referenced-1", CompressedSize: 10, UncompressedSize: 100},
{Hash: "referenced-2", CompressedSize: 20, UncompressedSize: 200},
{Hash: "unreferenced", CompressedSize: 40, UncompressedSize: 400},
}
for _, blob := range blobs {
blob.ID = types.NewBlobID()
blob.CreatedTS = time.Now().Truncate(time.Second)
err = repos.Blobs.Create(ctx, nil, blob)
if err != nil {
t.Fatalf("failed to create blob %s: %v", blob.Hash, err)
}
}
for _, blob := range blobs[:2] {
err = repos.Snapshots.AddBlob(ctx, nil, snapshot.ID.String(),
blob.ID, blob.Hash)
if err != nil {
t.Fatalf("failed to add blob %s to snapshot: %v", blob.Hash, err)
}
}
compressed, uncompressed, err := repos.Snapshots.GetSnapshotBlobSizes(
ctx, snapshot.ID.String())
if err != nil {
t.Fatalf("failed to get snapshot blob sizes: %v", err)
}
if compressed != 30 || uncompressed != 300 {
t.Errorf("blob sizes: got %d and %d, want 30 and 300",
compressed, uncompressed)
}
}
func TestSnapshotRepositoryListRecent(t *testing.T) { func TestSnapshotRepositoryListRecent(t *testing.T) {
t.Parallel() t.Parallel()
@@ -423,52 +363,3 @@ func TestSnapshotRepositoryDuplicate(t *testing.T) {
t.Error("expected error for duplicate snapshot") t.Error("expected error for duplicate snapshot")
} }
} }
// Deleting a snapshot from the local index deletes the mount points its
// backup recorded, and no other snapshot's. See
// https://git.eeqj.de/sneak/vaultik/issues/395.
func TestSnapshotRepositoryDeleteRemovesMountPoints(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx := context.Background()
repo := database.NewSnapshotRepository(db)
for _, id := range []types.SnapshotID{"kept", "deleted"} {
err := repo.Create(ctx, nil, &database.Snapshot{
ID: id,
Hostname: testHostname,
VaultikVersion: testVersion,
StartedAt: time.Now().Truncate(time.Second),
})
if err != nil {
t.Fatalf("failed to create snapshot: %v", err)
}
err = repo.AddMountPoint(ctx, nil, id.String(), "/data/nas")
if err != nil {
t.Fatalf("failed to add mount point: %v", err)
}
}
err := repo.Delete(ctx, "deleted")
if err != nil {
t.Fatalf("failed to delete snapshot: %v", err)
}
for id, want := range map[string][]string{
"kept": {"/data/nas"},
"deleted": nil,
} {
got, err := repo.GetMountPoints(ctx, id)
if err != nil {
t.Fatalf("failed to read mount points: %v", err)
}
if !slices.Equal(got, want) {
t.Errorf("mount points of %s: got %v, want %v", id, got, want)
}
}
}
+16
View File
@@ -158,3 +158,19 @@ type UploadStats struct {
MinDurationMs int64 MinDurationMs int64
MaxDurationMs int64 MaxDurationMs int64
} }
// GetCountBySnapshot returns the count of uploads for a specific snapshot
func (r *UploadRepository) GetCountBySnapshot(
ctx context.Context, snapshotID string,
) (int64, error) {
query := `SELECT COUNT(*) FROM uploads WHERE snapshot_id = ?`
var count int64
err := r.conn.QueryRowContext(ctx, query, snapshotID).Scan(&count)
if err != nil {
return 0, err
}
return count, nil
}
+21 -39
View File
@@ -5,14 +5,11 @@ import (
"fmt" "fmt"
"io" "io"
"log/slog" "log/slog"
"os"
"strconv" "strconv"
"strings" "strings"
"sync" "sync"
"time" "time"
"unicode" "unicode"
"github.com/dustin/go-humanize"
) )
// groupSeparator joins an open group path to an attribute key. This // groupSeparator joins an open group path to an attribute key. This
@@ -61,12 +58,6 @@ type TTYHandler struct {
mu *sync.Mutex mu *sync.Mutex
out io.Writer out io.Writer
// color reports whether records are written with ANSI color. It is
// false when NO_COLOR is set, matching internal/ui's shouldColor
// test; the caller already chose this handler for a terminal, so
// TTY-ness is not re-checked here.
color bool
// attrs are the attributes accumulated through WithAttrs, emitted // attrs are the attributes accumulated through WithAttrs, emitted
// ahead of each record's own attributes. Their keys already carry // ahead of each record's own attributes. Their keys already carry
// the group path that was open when they were added, so no // the group path that was open when they were added, so no
@@ -79,19 +70,16 @@ type TTYHandler struct {
groups []string groups []string
} }
// NewTTYHandler creates a new TTY handler. Color is enabled unless the // NewTTYHandler creates a new TTY handler with colored output.
// NO_COLOR environment variable is set to a non-empty value, the same
// test internal/ui applies to status lines.
func NewTTYHandler(out io.Writer, opts *slog.HandlerOptions) *TTYHandler { func NewTTYHandler(out io.Writer, opts *slog.HandlerOptions) *TTYHandler {
if opts == nil { if opts == nil {
opts = &slog.HandlerOptions{} opts = &slog.HandlerOptions{}
} }
return &TTYHandler{ return &TTYHandler{
out: out, out: out,
opts: *opts, opts: *opts,
mu: &sync.Mutex{}, mu: &sync.Mutex{},
color: os.Getenv("NO_COLOR") == "",
} }
} }
@@ -134,10 +122,10 @@ func (h *TTYHandler) Handle(_ context.Context, r slog.Record) error {
// are written around it: it can carry text from an untrusted source // are written around it: it can carry text from an untrusted source
// (a storage error, for one), and a raw control character would // (a storage error, for one), and a raw control character would
// otherwise reach the terminal. // otherwise reach the terminal.
_, _ = fmt.Fprintf(h.out, "%s %s %s", _, _ = fmt.Fprintf(h.out, "%s%s%s %s%s%s %s%s%s",
h.paint(colorGray, timestamp), colorGray, timestamp, colorReset,
h.paint(levelColor, level), levelColor, level, colorReset,
h.paint(colorBold, sanitize(r.Message))) colorBold, sanitize(r.Message), colorReset)
// Attributes carried by the handler come first, then the record's // Attributes carried by the handler come first, then the record's
// own. Handler attributes were qualified when they were added; the // own. Handler attributes were qualified when they were added; the
@@ -246,7 +234,6 @@ func (h *TTYHandler) clone() *TTYHandler {
opts: h.opts, opts: h.opts,
mu: h.mu, mu: h.mu,
out: h.out, out: h.out,
color: h.color,
attrs: make([]slog.Attr, len(h.attrs), len(h.attrs)+1), attrs: make([]slog.Attr, len(h.attrs), len(h.attrs)+1),
groups: make([]string, len(h.groups), len(h.groups)+1), groups: make([]string, len(h.groups), len(h.groups)+1),
} }
@@ -284,19 +271,9 @@ func (h *TTYHandler) writeAttr(a slog.Attr) {
// the snapshot database — so a control character in one of them must // the snapshot database — so a control character in one of them must
// be rendered as an escape sequence rather than reaching the terminal, // be rendered as an escape sequence rather than reaching the terminal,
// where it could move the cursor or inject its own colours. // where it could move the cursor or inject its own colours.
_, _ = fmt.Fprintf(h.out, " %s=%s", _, _ = fmt.Fprintf(h.out, " %s%s%s=%s%s%s",
h.paint(colorCyan, sanitize(a.Key)), colorCyan, sanitize(a.Key), colorReset,
h.paint(colorBlue, sanitize(value))) colorBlue, sanitize(value), colorReset)
}
// paint wraps s in the given ANSI color when color is enabled, and
// returns s unchanged otherwise.
func (h *TTYHandler) paint(color, s string) string {
if !h.color {
return s
}
return color + s + colorReset
} }
// sanitize returns s unchanged when every rune in it is printable, and a // sanitize returns s unchanged when every rune in it is printable, and a
@@ -327,13 +304,18 @@ func formatDuration(d time.Duration) string {
} }
} }
// formatBytes formats a byte count with humanize.Bytes, as every command // formatBytes formats bytes in a human-readable way
// prints one. humanize.Bytes takes no negative count, so one is printed
// as it is.
func formatBytes(b int64) string { func formatBytes(b int64) string {
if b < 0 { const unit = 1024
if b < unit {
return fmt.Sprintf("%d B", b) return fmt.Sprintf("%d B", b)
} }
return humanize.Bytes(uint64(b)) div, exp := int64(unit), 0
for n := b / unit; n >= unit; n /= unit {
div *= unit
exp++
}
return fmt.Sprintf("%.1f %cB", float64(b)/float64(div), "KMGTPE"[exp])
} }
+4 -46
View File
@@ -200,8 +200,7 @@ func TestTTYHandlerWithGroupQualifiesKeys(t *testing.T) {
func TestTTYHandlerByteFormattingSurvivesGrouping(t *testing.T) { func TestTTYHandlerByteFormattingSurvivesGrouping(t *testing.T) {
t.Parallel() t.Parallel()
// Printed as "1.0 MB", in powers of 1000 like every other byte count. const oneAndAHalfKiB = 1536
const oneMegabyte = 1_000_000
for name, testCase := range map[string]struct { for name, testCase := range map[string]struct {
derive func(*slog.Logger) *slog.Logger derive func(*slog.Logger) *slog.Logger
@@ -224,13 +223,13 @@ func TestTTYHandlerByteFormattingSurvivesGrouping(t *testing.T) {
var buf bytes.Buffer var buf bytes.Buffer
logger := slog.New(log.NewTTYHandler(&buf, debugHandlerOptions())) logger := slog.New(log.NewTTYHandler(&buf, debugHandlerOptions()))
testCase.derive(logger).Info("uploaded", "bytes", oneMegabyte) testCase.derive(logger).Info("uploaded", "bytes", oneAndAHalfKiB)
line := ansiEscape.ReplaceAllString(buf.String(), "") line := ansiEscape.ReplaceAllString(buf.String(), "")
assert.Contains(t, line, testCase.key+"=1.0 MB", assert.Contains(t, line, testCase.key+"=1.5 KB",
"a byte count must be human-readable however it is qualified") "a byte count must be human-readable however it is qualified")
assert.NotContains(t, line, strconv.Itoa(oneMegabyte), assert.NotContains(t, line, strconv.Itoa(oneAndAHalfKiB),
"the raw number must not survive the formatting") "the raw number must not survive the formatting")
}) })
} }
@@ -421,44 +420,3 @@ func TestTTYHandlerEmptyGroupAndAttrsAreNoOps(t *testing.T) {
assert.Contains(t, plain, "kept=yes") assert.Contains(t, plain, "kept=yes")
assert.NotContains(t, plain, " =") assert.NotContains(t, plain, " =")
} }
// TestTTYHandlerRespectsNoColor checks that only a non-empty NO_COLOR
// turns color off, matching internal/ui's shouldColor test. The handler
// is only ever chosen for a terminal, so this is the one remaining
// condition that can still leave color in log output.
func TestTTYHandlerRespectsNoColor(t *testing.T) {
cases := []struct {
name string
noColor string
colored bool
}{
{
name: "NO_COLOR turns color off",
noColor: "1",
},
{
name: "empty NO_COLOR keeps color on",
noColor: "",
colored: true,
},
}
for _, testCase := range cases {
t.Run(testCase.name, func(t *testing.T) {
t.Setenv("NO_COLOR", testCase.noColor)
var buf bytes.Buffer
logger := slog.New(log.NewTTYHandler(&buf, debugHandlerOptions()))
logger.Info("hello", "key", "value")
if testCase.colored {
assert.Contains(t, buf.String(), "\x1b[",
"an empty NO_COLOR must leave ANSI color in log output")
} else {
assert.NotContains(t, buf.String(), "\x1b[",
"NO_COLOR must suppress every ANSI escape in log output")
}
})
}
}
+49 -64
View File
@@ -10,18 +10,15 @@ import (
"path/filepath" "path/filepath"
"strconv" "strconv"
"strings" "strings"
"syscall"
"golang.org/x/sys/unix"
) )
// ErrAlreadyRunning indicates another vaultik instance is running. // ErrAlreadyRunning indicates another vaultik instance is running.
var ErrAlreadyRunning = errors.New("another vaultik instance is already running") var ErrAlreadyRunning = errors.New("another vaultik instance is already running")
// Lock represents an acquired PID lock: an flock(2) on the PID file, // Lock represents an acquired PID lock.
// held while the file stays open. The kernel drops it when the process
// exits, however it exits, so a crashed run never leaves the lock held.
type Lock struct { type Lock struct {
file *os.File path string
} }
const ( const (
@@ -32,9 +29,10 @@ const (
) )
// Acquire attempts to acquire a PID lock in the specified directory. // Acquire attempts to acquire a PID lock in the specified directory.
// If another process holds the lock, it returns ErrAlreadyRunning with // If the lock file exists and the process is still running, it returns
// that process's PID. On success, it writes the current PID to the lock // ErrAlreadyRunning with details about the existing process.
// file and returns a Lock that must be released with Release(). // On success, it writes the current PID to the lock file and returns
// a Lock that must be released with Release().
func Acquire(lockDir string) (*Lock, error) { func Acquire(lockDir string) (*Lock, error) {
// Ensure lock directory exists // Ensure lock directory exists
err := os.MkdirAll(lockDir, lockDirPerm) err := os.MkdirAll(lockDir, lockDirPerm)
@@ -44,82 +42,56 @@ func Acquire(lockDir string) (*Lock, error) {
lockPath := filepath.Join(lockDir, "vaultik.pid") lockPath := filepath.Join(lockDir, "vaultik.pid")
// No O_TRUNC: the file may hold the PID of the process that has the // Check for existing lock
// lock, which the error below reports. existingPID, err := readPIDFile(lockPath)
file, err := os.OpenFile( //nolint:gosec // G304: path is our own lock file if err == nil {
lockPath, os.O_RDWR|os.O_CREATE, pidFilePerm) // Lock file exists, check if process is running
if err != nil { if isProcessRunning(existingPID) {
return nil, fmt.Errorf("opening PID file: %w", err) return nil, fmt.Errorf("%w (PID %d)", ErrAlreadyRunning, existingPID)
}
err = unix.Flock(int(file.Fd()), unix.LOCK_EX|unix.LOCK_NB)
if err != nil {
_ = file.Close()
if errors.Is(err, unix.EWOULDBLOCK) {
return nil, alreadyRunningError(lockPath)
} }
// Process is not running, stale lock file - we can take over
return nil, fmt.Errorf("locking PID file: %w", err)
} }
err = writePID(file) // Write our PID
pid := os.Getpid()
err = os.WriteFile(lockPath, []byte(strconv.Itoa(pid)), pidFilePerm)
if err != nil { if err != nil {
_ = file.Close() return nil, fmt.Errorf("writing PID file: %w", err)
return nil, err
} }
return &Lock{file: file}, nil return &Lock{path: lockPath}, nil
} }
// Release empties the PID file and closes it, which drops the lock. // Release removes the PID lock file.
// It is safe to call Release multiple times. // It is safe to call Release multiple times.
func (l *Lock) Release() error { func (l *Lock) Release() error {
if l == nil || l.file == nil { if l == nil || l.path == "" {
return nil return nil
} }
file := l.file // Verify we still own the lock (our PID is in the file)
l.file = nil existingPID, err := readPIDFile(l.path)
// Do not remove the file here. A process that opened it a moment
// earlier could then lock the removed file while another creates and
// locks a new one, and both would run.
truncateErr := file.Truncate(0)
closeErr := file.Close()
return errors.Join(truncateErr, closeErr)
}
// writePID replaces the contents of the locked PID file with the current
// PID.
func writePID(file *os.File) error {
err := file.Truncate(0)
if err != nil { if err != nil {
return fmt.Errorf("truncating PID file: %w", err) // File already gone or unreadable - that's fine
return nil //nolint:nilerr // unreadable lock file means nothing to release
} }
_, err = file.WriteAt([]byte(strconv.Itoa(os.Getpid())), 0) if existingPID != os.Getpid() {
if err != nil { // Someone else wrote to our lock file - don't remove it
return fmt.Errorf("writing PID file: %w", err) return nil
} }
err = os.Remove(l.path)
if err != nil && !os.IsNotExist(err) {
return fmt.Errorf("removing PID file: %w", err)
}
l.path = "" // Prevent double-release
return nil return nil
} }
// alreadyRunningError reports that another process holds the lock,
// naming its PID when the file holds one. The holder writes its PID just
// after it locks, so the file can briefly be empty.
func alreadyRunningError(lockPath string) error {
pid, err := readPIDFile(lockPath)
if err != nil {
return ErrAlreadyRunning
}
return fmt.Errorf("%w (PID %d)", ErrAlreadyRunning, pid)
}
// readPIDFile reads and parses the PID from a lock file. // readPIDFile reads and parses the PID from a lock file.
func readPIDFile(path string) (int, error) { func readPIDFile(path string) (int, error) {
data, err := os.ReadFile(path) //nolint:gosec // G304: path is our own lock file data, err := os.ReadFile(path) //nolint:gosec // G304: path is our own lock file
@@ -134,3 +106,16 @@ func readPIDFile(path string) (int, error) {
return pid, nil return pid, nil
} }
// isProcessRunning checks if a process with the given PID is running.
func isProcessRunning(pid int) bool {
process, err := os.FindProcess(pid)
if err != nil {
return false
}
// On Unix, FindProcess always succeeds. We need to send signal 0 to check.
err = process.Signal(syscall.Signal(0))
return err == nil
}
+3 -63
View File
@@ -4,7 +4,6 @@ import (
"os" "os"
"path/filepath" "path/filepath"
"strconv" "strconv"
"sync"
"testing" "testing"
"github.com/stretchr/testify/assert" "github.com/stretchr/testify/assert"
@@ -34,10 +33,9 @@ func TestAcquireAndRelease(t *testing.T) {
err = lock.Release() err = lock.Release()
require.NoError(t, err) require.NoError(t, err)
// Verify PID file is empty // Verify PID file is gone
data, err = os.ReadFile(pidPath) //nolint:gosec // G304: test's own temp file _, err = os.Stat(pidPath)
require.NoError(t, err) assert.True(t, os.IsNotExist(err))
assert.Empty(t, data)
} }
func TestAcquireBlocksSecondInstance(t *testing.T) { func TestAcquireBlocksSecondInstance(t *testing.T) {
@@ -57,64 +55,6 @@ func TestAcquireBlocksSecondInstance(t *testing.T) {
lock2, err := pidlock.Acquire(tmpDir) lock2, err := pidlock.Acquire(tmpDir)
require.ErrorIs(t, err, pidlock.ErrAlreadyRunning) require.ErrorIs(t, err, pidlock.ErrAlreadyRunning)
assert.Nil(t, lock2) assert.Nil(t, lock2)
// Once the first lock is released, the next Acquire succeeds
require.NoError(t, lock1.Release())
lock3, err := pidlock.Acquire(tmpDir)
require.NoError(t, err)
require.NoError(t, lock3.Release())
}
// TestConcurrentAcquireAdmitsOne starts many Acquire calls at the same
// moment, as two cron entries firing together would, and checks that
// exactly one of them gets the lock.
func TestConcurrentAcquireAdmitsOne(t *testing.T) {
t.Parallel()
const callers = 50
tmpDir := t.TempDir()
start := make(chan struct{})
var (
mu sync.Mutex
acquired []*pidlock.Lock
failures []error
wg sync.WaitGroup
)
for range callers {
wg.Go(func() {
<-start
lock, err := pidlock.Acquire(tmpDir)
mu.Lock()
defer mu.Unlock()
if err != nil {
failures = append(failures, err)
return
}
acquired = append(acquired, lock)
})
}
close(start)
wg.Wait()
for _, lock := range acquired {
require.NoError(t, lock.Release())
}
assert.Len(t, acquired, 1, "exactly one caller should hold the lock")
for _, err := range failures {
require.ErrorIs(t, err, pidlock.ErrAlreadyRunning)
}
} }
func TestAcquireWithStaleLock(t *testing.T) { func TestAcquireWithStaleLock(t *testing.T) {
+10 -60
View File
@@ -8,7 +8,6 @@ import (
"io" "io"
"strings" "strings"
"sync/atomic" "sync/atomic"
"time"
"github.com/aws/aws-sdk-go-v2/aws" "github.com/aws/aws-sdk-go-v2/aws"
"github.com/aws/aws-sdk-go-v2/config" "github.com/aws/aws-sdk-go-v2/config"
@@ -19,13 +18,6 @@ import (
"github.com/aws/smithy-go/logging" "github.com/aws/smithy-go/logging"
) )
// ErrNoContinuationToken is returned by ListObjects and ListObjectsStream
// when the server marks a page of a listing truncated but sends no
// continuation token to fetch the rest with, as a server answering V2
// listings V1-style does.
var ErrNoContinuationToken = errors.New(
"server marked the listing truncated but sent no continuation token")
// Client wraps the AWS S3 client for vaultik operations. // Client wraps the AWS S3 client for vaultik operations.
// It provides a simplified interface for S3 operations with automatic // It provides a simplified interface for S3 operations with automatic
// prefix handling and connection management. All operations are performed // prefix handling and connection management. All operations are performed
@@ -35,12 +27,10 @@ type Client struct {
bucket string bucket string
prefix string prefix string
endpoint string endpoint string
partSize int64
} }
// Config contains S3 client configuration. // Config contains S3 client configuration.
// All fields are required except Prefix, which defaults to an empty string, // All fields are required except Prefix, which defaults to an empty string.
// and PartSize, where zero means the SDK default of 5 MiB.
// A non-empty Prefix is joined to every key with one "/", whether or not // A non-empty Prefix is joined to every key with one "/", whether or not
// it ends with one. // it ends with one.
// The Endpoint field should include the protocol (http:// or https://). // The Endpoint field should include the protocol (http:// or https://).
@@ -51,9 +41,6 @@ type Config struct {
AccessKeyID string AccessKeyID string
SecretAccessKey string SecretAccessKey string
Region string Region string
// PartSize is the size in bytes of each part of a multipart upload.
// An upload too large for S3's limit of 10,000 parts gets larger parts.
PartSize int64
} }
// nopLogger is a logger that discards all output. // nopLogger is a logger that discards all output.
@@ -103,7 +90,6 @@ func NewClient(ctx context.Context, cfg Config) (*Client, error) {
bucket: cfg.Bucket, bucket: cfg.Bucket,
prefix: prefix, prefix: prefix,
endpoint: cfg.Endpoint, endpoint: cfg.Endpoint,
partSize: cfg.PartSize,
}, nil }, nil
} }
@@ -137,9 +123,12 @@ func (c *Client) PutObjectWithProgress(
) error { ) error {
fullKey := c.prefix + key fullKey := c.prefix + key
// uploadPartSize is 10MB for better progress granularity.
const uploadPartSize = 10 * 1024 * 1024
// Create an uploader with the S3 client // Create an uploader with the S3 client
uploader := manager.NewUploader(c.s3Client, func(u *manager.Uploader) { uploader := manager.NewUploader(c.s3Client, func(u *manager.Uploader) {
u.PartSize = uploadPartSize(c.partSize, size) u.PartSize = uploadPartSize
}) })
// Create a progress reader that tracks upload progress // Create a progress reader that tracks upload progress
@@ -160,21 +149,6 @@ func (c *Client) PutObjectWithProgress(
return err return err
} }
// uploadPartSize returns the part size for an upload of size bytes: the
// configured part size (the SDK default when zero), raised where needed so
// the upload fits in S3's limit of 10,000 parts. The uploader cannot raise
// it itself, because it cannot seek the progress reader to learn its size.
func uploadPartSize(configured, size int64) int64 {
if configured == 0 {
configured = manager.DefaultUploadPartSize
}
maxParts := int64(manager.MaxUploadParts)
smallestThatFits := (size + maxParts - 1) / maxParts // rounded up
return max(configured, smallestThatFits)
}
// GetObject downloads an object from S3 with the specified key. // GetObject downloads an object from S3 with the specified key.
// The key is automatically prefixed with the configured prefix. // The key is automatically prefixed with the configured prefix.
// Returns a ReadCloser containing the object data. The caller must // Returns a ReadCloser containing the object data. The caller must
@@ -222,7 +196,7 @@ func (c *Client) ListObjects(ctx context.Context, prefix string) ([]string, erro
}) })
for paginator.HasMorePages() { for paginator.HasMorePages() {
page, err := nextListPage(ctx, paginator) page, err := paginator.NextPage(ctx)
if err != nil { if err != nil {
return nil, err return nil, err
} }
@@ -243,26 +217,6 @@ func (c *Client) ListObjects(ctx context.Context, prefix string) ([]string, erro
return keys, nil return keys, nil
} }
// nextListPage fetches the next page of a listing. The SDK paginator takes
// a page marked truncated without a continuation token for the last page
// and stops without an error, so such a page is ErrNoContinuationToken
// here instead.
func nextListPage(
ctx context.Context, paginator *s3.ListObjectsV2Paginator,
) (*s3.ListObjectsV2Output, error) {
page, err := paginator.NextPage(ctx)
if err != nil {
return nil, err
}
truncated := aws.ToBool(page.IsTruncated)
if truncated && aws.ToString(page.NextContinuationToken) == "" {
return nil, ErrNoContinuationToken
}
return page, nil
}
// HeadObject checks if an object exists in S3. // HeadObject checks if an object exists in S3.
// Returns true if the object exists, false otherwise. // Returns true if the object exists, false otherwise.
// The key is automatically prefixed with the configured prefix. // The key is automatically prefixed with the configured prefix.
@@ -303,10 +257,7 @@ func IsNotFound(err error) bool {
type ObjectInfo struct { type ObjectInfo struct {
Key string Key string
Size int64 Size int64
// ModTime is the object's LastModified time. Only ListObjectsStream Err error
// sets it.
ModTime time.Time
Err error
} }
// ListObjectsStream lists objects with the given prefix and returns a channel. // ListObjectsStream lists objects with the given prefix and returns a channel.
@@ -331,7 +282,7 @@ func (c *Client) ListObjectsStream(
}) })
for paginator.HasMorePages() { for paginator.HasMorePages() {
page, err := nextListPage(ctx, paginator) page, err := paginator.NextPage(ctx)
if err != nil { if err != nil {
ch <- ObjectInfo{Err: err} ch <- ObjectInfo{Err: err}
@@ -347,9 +298,8 @@ func (c *Client) ListObjectsStream(
} }
ch <- ObjectInfo{ ch <- ObjectInfo{
Key: key, Key: key,
Size: *obj.Size, Size: *obj.Size,
ModTime: aws.ToTime(obj.LastModified),
} }
} }
} }
-55
View File
@@ -1,55 +0,0 @@
package s3
import "testing"
// TestUploadPartSize checks that an upload too large for 10,000 parts of the
// configured size gets parts just large enough to fit in 10,000.
func TestUploadPartSize(t *testing.T) {
t.Parallel()
const mib = 1024 * 1024
tests := []struct {
name string
configured int64
size int64
want int64
}{
{
name: "an upload that fits keeps the configured size",
configured: 5 * mib,
size: 10 * 1024 * mib,
want: 5 * mib,
},
{
name: "exactly 10,000 parts keeps the configured size",
configured: 6 * mib,
size: 10_000 * 6 * mib,
want: 6 * mib,
},
{
name: "one byte more than 10,000 parts adds a byte to each",
configured: 6 * mib,
size: 10_000*6*mib + 1,
want: 6*mib + 1,
},
{
name: "zero means the SDK default of 5MiB",
configured: 0,
size: 1,
want: 5 * mib,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
got := uploadPartSize(tt.configured, tt.size)
if got != tt.want {
t.Errorf("uploadPartSize(%d, %d) = %d, want %d",
tt.configured, tt.size, got, tt.want)
}
})
}
}
-1
View File
@@ -28,7 +28,6 @@ func provideClient(lc fx.Lifecycle, cfg *config.Config) (*Client, error) {
AccessKeyID: cfg.S3.AccessKeyID, AccessKeyID: cfg.S3.AccessKeyID,
SecretAccessKey: cfg.S3.SecretAccessKey, SecretAccessKey: cfg.S3.SecretAccessKey,
Region: cfg.S3.Region, Region: cfg.S3.Region,
PartSize: cfg.S3.PartSize.Int64(),
}) })
if err != nil { if err != nil {
return nil, err return nil, err
+1 -1
View File
@@ -71,7 +71,7 @@ func verifyBackupFiles(
) { ) {
t.Helper() t.Helper()
files, err := repos.Files.ListAll(ctx) files, err := repos.Files.ListByPrefix(ctx, "")
if err != nil { if err != nil {
t.Fatalf("Failed to list files: %v", err) t.Fatalf("Failed to list files: %v", err)
} }
-62
View File
@@ -1,62 +0,0 @@
//nolint:testpackage // exercises the unexported cleanupBlobTempFile
package snapshot
import (
"errors"
"os"
"testing"
"github.com/spf13/afero"
"sneak.berlin/go/vaultik/internal/blob"
)
// A blob temp file that cannot be closed or removed must make the cleanup
// return an error, not end the process.
func TestCleanupBlobTempFileReturnsErrors(t *testing.T) {
t.Parallel()
fs := afero.NewOsFs()
s := &Scanner{fs: fs}
tests := []struct {
name string
// prepare runs before the cleanup and makes its close or remove
// fail.
prepare func(tempFile afero.File) error
want error
}{
{
name: "close fails",
prepare: func(tempFile afero.File) error { return tempFile.Close() },
want: os.ErrClosed,
},
{
name: "remove fails",
prepare: func(tempFile afero.File) error {
return fs.Remove(tempFile.Name())
},
want: os.ErrNotExist,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
tempFile, err := afero.TempFile(fs, t.TempDir(), "blob-*.tmp")
if err != nil {
t.Fatal(err)
}
err = tt.prepare(tempFile)
if err != nil {
t.Fatal(err)
}
err = s.cleanupBlobTempFile(&blob.WithReader{TempFile: tempFile})
if !errors.Is(err, tt.want) {
t.Fatalf("expected an error wrapping %v, got: %v", tt.want, err)
}
})
}
}
-40
View File
@@ -1,40 +0,0 @@
//nolint:testpackage // exercises the unexported deviceNumberFromStat
package snapshot
import (
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// The device number a real backup reads is the same for a directory and
// a file in it, and differs between the temp directory and /dev.
// Without it no mount point is ever found. See
// https://git.eeqj.de/sneak/vaultik/issues/395.
func TestDeviceNumberFromStat(t *testing.T) {
t.Parallel()
dir := t.TempDir()
file := filepath.Join(dir, "file.txt")
require.NoError(t, os.WriteFile(file, nil, 0o600))
deviceOf := func(path string) uint64 {
t.Helper()
info, err := os.Stat(path)
require.NoError(t, err)
device, ok := deviceNumberFromStat(info)
require.True(t, ok, "no device number read for %s", path)
return device
}
assert.Equal(t, deviceOf(dir), deviceOf(file))
// /dev is a different filesystem from the temp dir on Linux, macOS and in Docker.
assert.NotEqual(t, deviceOf(dir), deviceOf("/dev"))
}
-98
View File
@@ -531,101 +531,3 @@ func TestExcludePatterns_UnanchoredPatternFile(t *testing.T) {
require.Equal(t, 1, result.FilesScanned, require.Equal(t, 1, result.FilesScanned,
"Unanchored pattern for file should match anywhere") "Unanchored pattern for file should match anywhere")
} }
func TestExcludePatterns_DoubleStarDirectoryAtEveryDepth(t *testing.T) {
t.Parallel()
// As in gitignore, a leading **/ also matches directly under the source dir
fs := setupAnchoredTestFS(t)
scanner, repos, cleanup := createTestScanner(t, fs, []string{"**/projectname"})
defer cleanup()
ctx := context.Background()
createSnapshotRecord(ctx, t, repos, "test-snapshot")
result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
require.NoError(t, err)
// **/projectname should exclude BOTH:
// - /backup/projectname/file.txt
// - /backup/otherproject/projectname/file.txt
// Total files: 4, excluded: 2
require.Equal(t, 2, result.FilesScanned,
"**/ directory pattern should match at the top level and nested")
}
func TestExcludePatterns_DoubleStarFileAtEveryDepth(t *testing.T) {
t.Parallel()
// As in gitignore, a leading **/ also matches directly under the source dir
fs := setupAnchoredTestFS(t)
scanner, repos, cleanup := createTestScanner(t, fs, []string{"**/*.txt"})
defer cleanup()
ctx := context.Background()
createSnapshotRecord(ctx, t, repos, "test-snapshot")
result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
require.NoError(t, err)
// **/*.txt should exclude ALL .txt files:
// - /backup/file.txt
// - /backup/projectname/file.txt
// - /backup/otherproject/projectname/file.txt
// Total files: 4, excluded: 3
require.Equal(t, 1, result.FilesScanned,
"**/ file pattern should match at the top level and nested")
}
func TestExcludePatterns_AnchoredDoubleStarAtEveryDepth(t *testing.T) {
t.Parallel()
// As in gitignore, /**/ also matches directly under the source dir
fs := setupAnchoredTestFS(t)
scanner, repos, cleanup := createTestScanner(t, fs, []string{"/**/projectname"})
defer cleanup()
ctx := context.Background()
createSnapshotRecord(ctx, t, repos, "test-snapshot")
result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
require.NoError(t, err)
// /**/projectname should exclude BOTH:
// - /backup/projectname/file.txt
// - /backup/otherproject/projectname/file.txt
// Total files: 4, excluded: 2
require.Equal(t, 2, result.FilesScanned,
"/**/ pattern should match at the top level and nested")
}
func TestExcludePatterns_DoubleStarInMiddleMatchesZeroDirectories(t *testing.T) {
t.Parallel()
// As in gitignore, a/**/b matches a/b as well as a/c/b. The last part
// is a glob: with a plain name the glob library already matched a/b.
fs := &afero.MemMapFs{}
files := []string{"/backup/a/x.log", "/backup/a/c/y.log", "/backup/a/c/kept.txt"}
for _, path := range files {
require.NoError(t, fs.MkdirAll(filepath.Dir(path), 0755))
require.NoError(t, afero.WriteFile(fs, path, []byte(path), 0644))
}
scanner, repos, cleanup := createTestScanner(t, fs, []string{"a/**/*.log"})
defer cleanup()
ctx := context.Background()
createSnapshotRecord(ctx, t, repos, "test-snapshot")
result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
require.NoError(t, err)
// a/**/*.log should exclude /backup/a/x.log and /backup/a/c/y.log
// Total files: 3, excluded: 2
require.Equal(t, 1, result.FilesScanned,
"a/**/*.log should match a/x.log as well as a/c/y.log")
}
+11 -21
View File
@@ -1,8 +1,6 @@
package snapshot package snapshot
import ( import (
"os"
"github.com/spf13/afero" "github.com/spf13/afero"
"go.uber.org/fx" "go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/config" "sneak.berlin/go/vaultik/internal/config"
@@ -18,12 +16,6 @@ type ScannerParams struct {
Fs afero.Fs Fs afero.Fs
Exclude []string // Exclude patterns (combined global + snapshot-specific) Exclude []string // Exclude patterns (combined global + snapshot-specific)
SkipErrors bool // Skip file read errors (log loudly but continue) SkipErrors bool // Skip file read errors (log loudly but continue)
// PreviousSnapshotID is the most recent completed snapshot of the
// same name, "" for none.
PreviousSnapshotID string
// DeviceNumber is ScannerConfig.DeviceNumber; nil reads it from the
// file's stat.
DeviceNumber func(info os.FileInfo) (uint64, bool)
} }
// Module exports backup functionality as an fx module. // Module exports backup functionality as an fx module.
@@ -52,19 +44,17 @@ func provideScannerFactory(
} }
return NewScanner(ScannerConfig{ return NewScanner(ScannerConfig{
FS: params.Fs, FS: params.Fs,
ChunkSize: cfg.ChunkSize.Int64(), ChunkSize: cfg.ChunkSize.Int64(),
Repositories: repos, Repositories: repos,
Storage: storer, Storage: storer,
MaxBlobSize: cfg.BlobSizeLimit.Int64(), MaxBlobSize: cfg.BlobSizeLimit.Int64(),
CompressionLevel: cfg.CompressionLevel, CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients, AgeRecipients: cfg.AgeRecipients,
EnableProgress: params.EnableProgress, EnableProgress: params.EnableProgress,
UI: params.UI, UI: params.UI,
Exclude: excludes, Exclude: excludes,
SkipErrors: params.SkipErrors, SkipErrors: params.SkipErrors,
PreviousSnapshotID: params.PreviousSnapshotID,
DeviceNumber: params.DeviceNumber,
}) })
} }
} }
-245
View File
@@ -1,245 +0,0 @@
package snapshot_test
import (
"context"
"os"
"path/filepath"
"slices"
"strings"
"syscall"
"testing"
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/snapshot"
)
// A scan records with the snapshot each directory on a different device
// from its parent directory that the walk found an entry in, as a mount
// point is, the scanned path included. A filesystem that gives no device
// numbers, as the in-memory one, records none. See
// https://git.eeqj.de/sneak/vaultik/issues/395.
func TestScanRecordsMountPoints(t *testing.T) {
t.Parallel()
const (
scannedPath = "/data/source"
snapshotID = "mount-points"
)
tests := []struct {
name string
// onVolume names the directories on the volume's device; every
// other directory is on another one. nil leaves the device
// numbers to the in-memory filesystem, which has none.
onVolume []string
want []string
}{
{
name: "volume below the scanned path",
onVolume: []string{"nas"},
want: []string{scannedPath + "/nas"},
},
{
name: "volume at the scanned path",
onVolume: []string{"source", "nas"},
want: []string{scannedPath},
},
{name: "no device numbers", want: nil},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
ctx := context.Background()
fs := afero.NewMemMapFs()
for _, path := range []string{
scannedPath + "/notes.txt", scannedPath + "/nas/a.txt",
} {
require.NoError(t, fs.MkdirAll(filepath.Dir(path), 0o755))
require.NoError(t, afero.WriteFile(fs, path, []byte(path), 0o644))
}
db, err := database.NewTestDB()
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
repos := database.NewRepositories(db)
createTestSnapshotRecord(ctx, t, repos, snapshotID)
cfg := snapshot.ScannerConfig{
FS: fs,
ChunkSize: int64(1024 * 16),
Repositories: repos,
MaxBlobSize: int64(1024 * 1024),
CompressionLevel: 3,
AgeRecipients: []string{testAgePublicKey},
}
if tt.onVolume != nil {
cfg.DeviceNumber = func(info os.FileInfo) (uint64, bool) {
if slices.Contains(tt.onVolume, info.Name()) {
return 2, true
}
return 1, true
}
}
_, err = snapshot.NewScanner(cfg).Scan(ctx, scannedPath, snapshotID)
require.NoError(t, err)
got, err := repos.Snapshots.GetMountPoints(ctx, snapshotID)
require.NoError(t, err)
assert.Equal(t, tt.want, got)
})
}
}
// automountFs is an in-memory filesystem with a volume at mountPoint
// that is mounted on first access: opening mountPoint to list it mounts
// the volume or, if it cannot be mounted, fails with "no such file or
// directory", as with the autofs daemon. Stat records the device an
// entry is on at that moment, as a real stat does: unmountedDevice for
// mountPoint until the volume is mounted; the volume's, 2, for
// mountPoint once it is and for everything in it; 1 for everything else.
type automountFs struct {
afero.Fs
mountPoint string
unmountedDevice uint64
canMount bool
mounted bool
}
//nolint:ireturn // afero.Fs.Open is defined to return the interface.
func (fs *automountFs) Open(name string) (afero.File, error) {
if name == fs.mountPoint && !fs.canMount {
return nil, &os.PathError{Op: "open", Path: name, Err: syscall.ENOENT}
}
if name == fs.mountPoint {
fs.mounted = true
}
return fs.Fs.Open(name)
}
func (fs *automountFs) Stat(name string) (os.FileInfo, error) {
info, err := fs.Fs.Stat(name)
if err != nil {
return nil, err
}
device := uint64(1)
switch {
case name == fs.mountPoint && !fs.mounted:
device = fs.unmountedDevice
case name == fs.mountPoint || strings.HasPrefix(name, fs.mountPoint+"/"):
device = 2
}
return statWithDevice{FileInfo: info, device: device}, nil
}
// statWithDevice is an entry automountFs.Stat looked up, with the device
// it was on then.
type statWithDevice struct {
os.FileInfo
device uint64
}
// deviceAtLookup returns the device automountFs.Stat recorded for info.
func deviceAtLookup(info os.FileInfo) (uint64, bool) {
stat, ok := info.(statWithDevice)
return stat.device, ok
}
// A volume mounted on first access is mounted when the walk lists its
// mount point. Until then the mount point is on the automounter's own
// device (a systemd automount) or on its parent's (an autofs map that
// shows its mount points before mounting them). Either way only the
// mount point is recorded, by the backup that mounts the volume and by a
// later one that finds it mounted. Listing an automount point whose
// volume cannot be mounted fails; it is not recorded, because the walk
// finds no entry in it. See https://git.eeqj.de/sneak/vaultik/issues/395.
func TestScanRecordsOnlyTheMountPointOfAnAutomountedVolume(t *testing.T) {
t.Parallel()
const scannedPath = "/data/source"
mountPoint := scannedPath + "/nas"
tests := []struct {
name string
unmountedDevice uint64
canMount bool
want []string
}{
{
name: "on the automounter's device until listed",
unmountedDevice: 3, canMount: true, want: []string{mountPoint},
},
{
name: "on its parent's device until listed",
unmountedDevice: 1, canMount: true, want: []string{mountPoint},
},
{
name: "volume that cannot be mounted",
unmountedDevice: 1, canMount: false, want: nil,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
ctx := context.Background()
fs := &automountFs{
Fs: afero.NewMemMapFs(), mountPoint: mountPoint,
unmountedDevice: tt.unmountedDevice, canMount: tt.canMount,
}
require.NoError(t, fs.MkdirAll(mountPoint+"/photos", 0o755))
for _, path := range []string{
scannedPath + "/notes.txt", mountPoint + "/photos/a.jpg",
} {
require.NoError(t, afero.WriteFile(fs, path, []byte(path), 0o644))
}
db, err := database.NewTestDB()
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
repos := database.NewRepositories(db)
for _, snapshotID := range []string{"first", "later"} {
createTestSnapshotRecord(ctx, t, repos, snapshotID)
scanner := snapshot.NewScanner(snapshot.ScannerConfig{
FS: fs,
ChunkSize: int64(1024 * 16),
Repositories: repos,
MaxBlobSize: int64(1024 * 1024),
CompressionLevel: 3,
AgeRecipients: []string{testAgePublicKey},
DeviceNumber: deviceAtLookup,
})
_, err = scanner.Scan(ctx, scannedPath, snapshotID)
require.NoError(t, err)
got, err := repos.Snapshots.GetMountPoints(ctx, snapshotID)
require.NoError(t, err)
assert.Equal(t, tt.want, got, "mount points of the %s backup", snapshotID)
}
})
}
}
+57 -69
View File
@@ -56,27 +56,24 @@ const (
// ProgressStats holds atomic counters for progress tracking // ProgressStats holds atomic counters for progress tracking
type ProgressStats struct { type ProgressStats struct {
FilesScanned atomic.Int64 // Total files seen during scan (includes skipped) FilesScanned atomic.Int64 // Total files seen during scan (includes skipped)
FilesProcessed atomic.Int64 // Files actually processed in phase 2 FilesProcessed atomic.Int64 // Files actually processed in phase 2
FilesSkipped atomic.Int64 // Files skipped due to no changes FilesSkipped atomic.Int64 // Files skipped due to no changes
BytesScanned atomic.Int64 // Bytes from new/changed files only BytesScanned atomic.Int64 // Bytes from new/changed files only
BytesSkipped atomic.Int64 // Bytes from unchanged files BytesSkipped atomic.Int64 // Bytes from unchanged files
BytesProcessed atomic.Int64 // Actual bytes processed (for ETA calculation) BytesProcessed atomic.Int64 // Actual bytes processed (for ETA calculation)
ChunksCreated atomic.Int64 ChunksCreated atomic.Int64
BlobsCreated atomic.Int64 BlobsCreated atomic.Int64
BlobsUploaded atomic.Int64 BlobsUploaded atomic.Int64
BytesUploaded atomic.Int64 BytesUploaded atomic.Int64
CurrentFile atomic.Value // stores string UploadDurationMs atomic.Int64 // Total milliseconds spent uploading
TotalSize atomic.Int64 // Size to process in the paths scanned so far CurrentFile atomic.Value // stores string
TotalFiles atomic.Int64 // Files to process in the paths scanned so far TotalSize atomic.Int64 // Total size to process (set after scan phase)
StartTime time.Time TotalFiles atomic.Int64 // Total files to process in phase 2
mu sync.RWMutex ProcessStartTime atomic.Value // stores time.Time when processing starts
lastDetailTime time.Time StartTime time.Time
mu sync.RWMutex
// Guarded by mu: when the last scan phase ended, and lastDetailTime time.Time
// BytesProcessed at that moment.
processStartTime time.Time
processStartBytes int64
// Upload tracking // Upload tracking
CurrentUpload atomic.Value // stores *UploadInfo CurrentUpload atomic.Value // stores *UploadInfo
@@ -152,36 +149,10 @@ func (pr *ProgressReporter) GetStats() *ProgressStats {
return pr.stats return pr.stats
} }
// AddTotalSize adds the size one path of the snapshot has to process to // SetTotalSize sets the total size to process (after scan phase)
// the total, once that path's scan phase is done, and starts measuring func (pr *ProgressReporter) SetTotalSize(size int64) {
// the processing rate again. The processed counts run across every path, pr.stats.TotalSize.Store(size)
// so the total does too. Restarting the rate keeps a path's scan phase, pr.stats.ProcessStartTime.Store(time.Now().UTC())
// which processes nothing, out of the rate while that path is processed.
// During a later path's scan phase the rate is still the previous
// path's, and falls as that scan goes on.
func (pr *ProgressReporter) AddTotalSize(size int64) {
pr.stats.TotalSize.Add(size)
pr.stats.mu.Lock()
defer pr.stats.mu.Unlock()
pr.stats.processStartTime = time.Now().UTC()
pr.stats.processStartBytes = pr.stats.BytesProcessed.Load()
}
// processRate returns the bytes processed per second since the last scan
// phase ended, or 0 before the first path's scan phase is done.
func (s *ProgressStats) processRate() float64 {
s.mu.RLock()
defer s.mu.RUnlock()
if s.processStartTime.IsZero() {
return 0
}
processed := s.BytesProcessed.Load() - s.processStartBytes
return float64(processed) / time.Since(s.processStartTime).Seconds()
} }
// Helper functions // Helper functions
@@ -260,6 +231,9 @@ func (pr *ProgressReporter) ReportUploadComplete(
// Clear current upload // Clear current upload
pr.stats.CurrentUpload.Store((*UploadInfo)(nil)) pr.stats.CurrentUpload.Store((*UploadInfo)(nil))
// Add to total upload duration
pr.stats.UploadDurationMs.Add(duration.Milliseconds())
// Calculate speed // Calculate speed
if duration < time.Millisecond { if duration < time.Millisecond {
duration = time.Millisecond duration = time.Millisecond
@@ -387,12 +361,19 @@ func (pr *ProgressReporter) printSummaryStatus() {
// Calculate ETA if we have total size and are processing // Calculate ETA if we have total size and are processing
etaStr := "" etaStr := ""
processRate := pr.stats.processRate() if totalSize > 0 && bytesProcessed > 0 {
if totalSize > 0 && processRate > 0 { processStart, ok := pr.stats.ProcessStartTime.Load().(time.Time)
remainingBytes := totalSize - bytesProcessed if ok && !processStart.IsZero() {
remainingSeconds := float64(remainingBytes) / processRate processElapsed := time.Since(processStart)
eta := time.Duration(remainingSeconds * float64(time.Second))
etaStr = " | ETA: " + formatDuration(eta) rate := float64(bytesProcessed) / processElapsed.Seconds()
if rate > 0 {
remainingBytes := totalSize - bytesProcessed
remainingSeconds := float64(remainingBytes) / rate
eta := time.Duration(remainingSeconds * float64(time.Second))
etaStr = " | ETA: " + formatDuration(eta)
}
}
} }
rate := float64(bytesScanned+bytesSkipped) / elapsed.Seconds() rate := float64(bytesScanned+bytesSkipped) / elapsed.Seconds()
@@ -444,18 +425,25 @@ func (pr *ProgressReporter) printDetailedStatus() {
log.Info("Elapsed time", "duration", formatDuration(elapsed)) log.Info("Elapsed time", "duration", formatDuration(elapsed))
// Calculate and show ETA if we have data // Calculate and show ETA if we have data
processRate := pr.stats.processRate() if totalSize > 0 && bytesProcessed > 0 {
if totalSize > 0 && processRate > 0 { processStart, ok := pr.stats.ProcessStartTime.Load().(time.Time)
remainingBytes := totalSize - bytesProcessed if ok && !processStart.IsZero() {
remainingSeconds := float64(remainingBytes) / processRate processElapsed := time.Since(processStart)
eta := time.Duration(remainingSeconds * float64(time.Second))
percentComplete := float64(bytesProcessed) / float64(totalSize) * percentScale processRate := float64(bytesProcessed) / processElapsed.Seconds()
log.Info("Overall progress", if processRate > 0 {
"percent", fmt.Sprintf("%.1f%%", percentComplete), remainingBytes := totalSize - bytesProcessed
"processed", humanize.Bytes(safeUint64(bytesProcessed)), remainingSeconds := float64(remainingBytes) / processRate
"total", humanize.Bytes(safeUint64(totalSize)), eta := time.Duration(remainingSeconds * float64(time.Second))
"rate", humanize.Bytes(uint64(processRate))+"/s", percentComplete := float64(bytesProcessed) / float64(totalSize) * percentScale
"eta", formatDuration(eta)) log.Info("Overall progress",
"percent", fmt.Sprintf("%.1f%%", percentComplete),
"processed", humanize.Bytes(safeUint64(bytesProcessed)),
"total", humanize.Bytes(safeUint64(totalSize)),
"rate", humanize.Bytes(uint64(processRate))+"/s",
"eta", formatDuration(eta))
}
}
} }
log.Info("Files processed", log.Info("Files processed",
-54
View File
@@ -1,54 +0,0 @@
//nolint:testpackage // exercises the unexported processRate helper
package snapshot
import (
"testing"
"time"
)
// TestProcessRateNotLoweredByLaterScanPhase feeds the reporter two paths
// that each take 10 seconds to process, the second after a 30-second scan
// phase. That scan phase processes nothing, so the rate while the second
// path is processed must be that path's own.
func TestProcessRateNotLoweredByLaterScanPhase(t *testing.T) {
t.Parallel()
const (
pathSize = 1000
processingTime = 10 * time.Second
scanTime = 30 * time.Second
)
// Never started, but Stop releases its tickers and signal handler.
progress := NewProgressReporter()
defer progress.Stop()
stats := progress.GetStats()
// Moves the processing start time back instead of sleeping.
elapse := func(d time.Duration) {
stats.mu.Lock()
defer stats.mu.Unlock()
stats.processStartTime = stats.processStartTime.Add(-d)
}
progress.AddTotalSize(pathSize)
stats.BytesProcessed.Add(pathSize)
elapse(processingTime)
elapse(scanTime)
progress.AddTotalSize(pathSize)
stats.BytesProcessed.Add(pathSize)
elapse(processingTime)
want := pathSize / processingTime.Seconds()
got := stats.processRate()
// The test's own run time adds to the elapsed time, so got is a hair
// under want.
if got > want || got < want*0.99 {
t.Errorf("rate while the second path is processed is %.1f bytes/s, "+
"want %.1f", got, want)
}
}
-93
View File
@@ -1,93 +0,0 @@
package snapshot_test
import (
"context"
"path/filepath"
"strings"
"testing"
"github.com/spf13/afero"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/snapshot"
)
// TestProgressPercentWithSecondPathSmaller backs up two paths with one
// scanner, as a snapshot with two paths does, the second path smaller
// than the first. The progress line divides the bytes processed by the
// total size, so both must count both paths to stay within 100%.
func TestProgressPercentWithSecondPathSmaller(t *testing.T) {
t.Parallel()
fs := afero.NewMemMapFs()
files := map[string]string{
"/large/one.txt": strings.Repeat("1", 4000),
"/large/two.txt": strings.Repeat("2", 4000),
"/small/three.txt": strings.Repeat("3", 1000),
}
for path, content := range files {
err := fs.MkdirAll(filepath.Dir(path), 0755)
if err != nil {
t.Fatalf("mkdir: %v", err)
}
err = afero.WriteFile(fs, path, []byte(content), 0644)
if err != nil {
t.Fatalf("write %s: %v", path, err)
}
}
db, err := database.NewTestDB()
if err != nil {
t.Fatalf("create test db: %v", err)
}
t.Cleanup(func() {
cerr := db.Close()
if cerr != nil {
t.Errorf("close db: %v", cerr)
}
})
repos := database.NewRepositories(db)
scanner := snapshot.NewScanner(snapshot.ScannerConfig{
FS: fs,
ChunkSize: int64(1024 * 16),
Repositories: repos,
MaxBlobSize: int64(1024 * 1024),
CompressionLevel: 3,
AgeRecipients: []string{testAgePublicKey},
EnableProgress: true,
})
// Never started, but Stop releases its tickers and signal handler.
progress := scanner.GetProgress()
defer progress.Stop()
ctx := context.Background()
snapshotID := "test-snapshot-progress"
createTestSnapshotRecord(ctx, t, repos, snapshotID)
for _, path := range []string{"/large", "/small"} {
_, err := scanner.Scan(ctx, path, snapshotID)
if err != nil {
t.Fatalf("scanning %s: %v", path, err)
}
}
stats := progress.GetStats()
// With both paths counted, the percentage must not exceed 100%.
percent := float64(stats.BytesProcessed.Load()) /
float64(stats.TotalSize.Load()) * 100
if percent > 100 {
t.Errorf("progress after both paths is %.1f%%, want at most 100%%",
percent)
}
if stats.FilesProcessed.Load() != stats.TotalFiles.Load() {
t.Errorf("progress after both paths is %d of %d files, want all",
stats.FilesProcessed.Load(), stats.TotalFiles.Load())
}
}
File diff suppressed because it is too large. Load diff
@@ -1,28 +0,0 @@
//nolint:testpackage // exercises the unexported countNonDirectories helper
package snapshot
import (
"os"
"testing"
"sneak.berlin/go/vaultik/internal/database"
)
// The walk counts regular files and symlinks, not directories, so the
// estimate of its count made from the local index's records leaves the
// directories out. See https://git.eeqj.de/sneak/vaultik/issues/305.
func TestCountNonDirectories(t *testing.T) {
t.Parallel()
known := map[string]*database.File{
"/src": {Mode: uint32(os.ModeDir | 0o755)},
"/src/sub": {Mode: uint32(os.ModeDir | 0o755)},
"/src/a.txt": {Mode: 0o644},
"/src/link": {Mode: uint32(os.ModeSymlink | 0o777), LinkTarget: "a.txt"},
}
got := countNonDirectories(known)
if got != 2 {
t.Errorf("countNonDirectories = %d, want 2", got)
}
}
+1 -1
View File
@@ -71,7 +71,7 @@ func verifySimpleScanDatabase(
t.Helper() t.Helper()
// Verify files in database - includes regular files and directories // Verify files in database - includes regular files and directories
files, err := repos.Files.ListUnderPath(ctx, "/source") files, err := repos.Files.ListByPrefix(ctx, "/source")
if err != nil { if err != nil {
t.Fatalf("failed to list files: %v", err) t.Fatalf("failed to list files: %v", err)
} }
+8 -232
View File
@@ -3,7 +3,6 @@ package snapshot_test
import ( import (
"context" "context"
"errors" "errors"
"io"
"os" "os"
"path/filepath" "path/filepath"
"strings" "strings"
@@ -14,7 +13,6 @@ import (
"github.com/spf13/afero" "github.com/spf13/afero"
"sneak.berlin/go/vaultik/internal/database" "sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/snapshot" "sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/ui"
) )
// errSimTempFail is the one-time temp-file creation failure blobTempFailFs // errSimTempFail is the one-time temp-file creation failure blobTempFailFs
@@ -82,56 +80,6 @@ func (f *readFailFs) Open(name string) (afero.File, error) {
return file, nil return file, nil
} }
// cancelOnOpenFs cancels the run when the scanner opens the target file to
// back it up, as Ctrl-C partway through processing would, and records each
// file opened after that.
type cancelOnOpenFs struct {
afero.Fs
target string
cancel context.CancelFunc
cancelled bool
openedAfterCancel []string
}
//nolint:ireturn // afero.Fs.Open is defined to return the interface.
func (f *cancelOnOpenFs) Open(name string) (afero.File, error) {
if f.cancelled {
f.openedAfterCancel = append(f.openedAfterCancel, name)
}
if name == f.target {
f.cancel()
f.cancelled = true
}
return f.Fs.Open(name)
}
// linkRemovedAfterLstatFs is the real filesystem, except that the symlink at
// target is removed right after the walk lstats it, as happens when a link is
// deleted during a backup. The scanner's readlink of it then fails.
type linkRemovedAfterLstatFs struct {
afero.OsFs
t *testing.T
target string
}
func (f *linkRemovedAfterLstatFs) LstatIfPossible(
name string,
) (os.FileInfo, bool, error) {
info, lstatCalled, err := f.OsFs.LstatIfPossible(name)
if err == nil && name == f.target {
rmErr := os.Remove(name)
if rmErr != nil {
f.t.Errorf("removing %s: %v", name, rmErr)
}
}
return info, lstatCalled, err
}
// writeSkipErrorTestFile writes one file into fs with a fixed mtime. // writeSkipErrorTestFile writes one file into fs with a fixed mtime.
func writeSkipErrorTestFile(t *testing.T, fs afero.Fs, path, content string) { func writeSkipErrorTestFile(t *testing.T, fs afero.Fs, path, content string) {
t.Helper() t.Helper()
@@ -154,16 +102,14 @@ func writeSkipErrorTestFile(t *testing.T, fs afero.Fs, path, content string) {
} }
} }
// runSkipErrorScan scans source on fs under ctx with the given skip-errors // runSkipErrorScan scans /source on fs with the given skip-errors setting and
// setting, printing user-facing messages to uiw (nil discards them), and
// returns the repositories (for inspection) and the scan error. // returns the repositories (for inspection) and the scan error.
func runSkipErrorScan( func runSkipErrorScan(
ctx context.Context, t *testing.T, fs afero.Fs, source string, t *testing.T, fs afero.Fs, skipErrors bool,
skipErrors bool, uiw *ui.Writer,
) (*database.Repositories, error) { ) (*database.Repositories, error) {
t.Helper() t.Helper()
db, err := database.New(ctx, ":memory:") db, err := database.NewTestDB()
if err != nil { if err != nil {
t.Fatalf("create test db: %v", err) t.Fatalf("create test db: %v", err)
} }
@@ -184,14 +130,14 @@ func runSkipErrorScan(
MaxBlobSize: int64(1024 * 1024), MaxBlobSize: int64(1024 * 1024),
CompressionLevel: 3, CompressionLevel: 3,
AgeRecipients: []string{testAgePublicKey}, AgeRecipients: []string{testAgePublicKey},
UI: uiw,
SkipErrors: skipErrors, SkipErrors: skipErrors,
}) })
ctx := context.Background()
snapshotID := "test-snapshot-skip-errors" snapshotID := "test-snapshot-skip-errors"
createTestSnapshotRecord(ctx, t, repos, snapshotID) createTestSnapshotRecord(ctx, t, repos, snapshotID)
_, err = scanner.Scan(ctx, source, snapshotID) _, err = scanner.Scan(ctx, "/source", snapshotID)
return repos, err return repos, err
} }
@@ -211,7 +157,7 @@ func TestScannerPackingFailureAbortsUnderSkipErrors(t *testing.T) {
writeSkipErrorTestFile(t, fs, "/source/file1.txt", "first file content") writeSkipErrorTestFile(t, fs, "/source/file1.txt", "first file content")
writeSkipErrorTestFile(t, fs, "/source/file2.txt", "second file content") writeSkipErrorTestFile(t, fs, "/source/file2.txt", "second file content")
repos, err := runSkipErrorScan(context.Background(), t, fs, "/source", true, nil) repos, err := runSkipErrorScan(t, fs, true)
if err == nil { if err == nil {
t.Fatal("expected scan to abort on the packer error, got nil") t.Fatal("expected scan to abort on the packer error, got nil")
} }
@@ -238,7 +184,7 @@ func TestScannerReadErrorAbortsWithoutSkipErrors(t *testing.T) {
fs := &readFailFs{Fs: afero.NewMemMapFs(), target: target} fs := &readFailFs{Fs: afero.NewMemMapFs(), target: target}
writeSkipErrorTestFile(t, fs, target, "content that cannot be read") writeSkipErrorTestFile(t, fs, target, "content that cannot be read")
_, err := runSkipErrorScan(context.Background(), t, fs, "/source", false, nil) _, err := runSkipErrorScan(t, fs, false)
if err == nil { if err == nil {
t.Fatal("expected scan to fail on the read error, got nil") t.Fatal("expected scan to fail on the read error, got nil")
} }
@@ -254,7 +200,7 @@ func TestScannerReadErrorSkippedWithSkipErrors(t *testing.T) {
fs := &readFailFs{Fs: afero.NewMemMapFs(), target: target} fs := &readFailFs{Fs: afero.NewMemMapFs(), target: target}
writeSkipErrorTestFile(t, fs, target, "content that cannot be read") writeSkipErrorTestFile(t, fs, target, "content that cannot be read")
repos, err := runSkipErrorScan(context.Background(), t, fs, "/source", true, nil) repos, err := runSkipErrorScan(t, fs, true)
if err != nil { if err != nil {
t.Fatalf("expected scan to complete with --skip-errors, got %v", err) t.Fatalf("expected scan to complete with --skip-errors, got %v", err)
} }
@@ -268,173 +214,3 @@ func TestScannerReadErrorSkippedWithSkipErrors(t *testing.T) {
t.Fatalf("expected unreadable file skipped, got %d chunks", len(chunks)) t.Fatalf("expected unreadable file skipped, got %d chunks", len(chunks))
} }
} }
// writeSymlinkSource creates a source directory on disk holding one symlink
// and returns the directory and the symlink's path.
func writeSymlinkSource(t *testing.T) (string, string) {
t.Helper()
sourceDir := t.TempDir()
linkPath := filepath.Join(sourceDir, "link")
err := os.Symlink("target.txt", linkPath)
if err != nil {
t.Fatalf("creating symlink: %v", err)
}
return sourceDir, linkPath
}
// TestScannerUnreadableSymlinkAbortsWithoutSkipErrors checks that a symlink
// whose target cannot be read aborts the run when --skip-errors is not set.
func TestScannerUnreadableSymlinkAbortsWithoutSkipErrors(t *testing.T) {
t.Parallel()
sourceDir, linkPath := writeSymlinkSource(t)
fs := &linkRemovedAfterLstatFs{t: t, target: linkPath}
_, err := runSkipErrorScan(context.Background(), t, fs, sourceDir, false, nil)
if !errors.Is(err, os.ErrNotExist) {
t.Fatalf("expected scan to fail on the removed symlink, got %v", err)
}
}
// TestScannerUnreadableSymlinkSkippedWithSkipErrors checks that a symlink
// whose target cannot be read is skipped with an error line, and the run
// completes, when --skip-errors is set.
func TestScannerUnreadableSymlinkSkippedWithSkipErrors(t *testing.T) {
t.Parallel()
sourceDir, linkPath := writeSymlinkSource(t)
fs := &linkRemovedAfterLstatFs{t: t, target: linkPath}
uiw := ui.NewWithColor(io.Discard, false)
repos, err := runSkipErrorScan(context.Background(), t, fs, sourceDir, true, uiw)
if err != nil {
t.Fatalf("expected scan to complete with --skip-errors, got %v", err)
}
if uiw.ErrorCount() != 1 {
t.Fatalf("expected one error line for the symlink, got %d",
uiw.ErrorCount())
}
file, err := repos.Files.GetByPath(context.Background(), linkPath)
if err != nil {
t.Fatalf("getting %s: %v", linkPath, err)
}
if file != nil {
t.Fatalf("expected %s not to be recorded", linkPath)
}
}
// TestScannerCancelStopsSkipErrorsRun checks that a --skip-errors backup
// cancelled partway through processing returns the cancellation error,
// opens no further file, and reports no file as failed.
func TestScannerCancelStopsSkipErrorsRun(t *testing.T) {
t.Parallel()
tests := []struct {
name string
targetContent string
}{
// The cancellation lands while the target is being read.
{name: "while reading a file", targetContent: "first file content"},
// An empty target has no chunks, so the cancellation goes unnoticed
// until the run moves on to the next file.
{name: "between files", targetContent: ""},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
const target = "/source/a.txt"
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
fs := &cancelOnOpenFs{
Fs: afero.NewMemMapFs(), target: target, cancel: cancel,
}
writeSkipErrorTestFile(t, fs, target, tt.targetContent)
writeSkipErrorTestFile(t, fs, "/source/b.txt", "second file content")
writeSkipErrorTestFile(t, fs, "/source/c.txt", "third file content")
uiw := ui.NewWithColor(io.Discard, false)
_, err := runSkipErrorScan(ctx, t, fs, "/source", true, uiw)
if !errors.Is(err, context.Canceled) {
t.Fatalf("expected the cancellation error, got %v", err)
}
if len(fs.openedAfterCancel) != 0 {
t.Fatalf("expected no file opened after the cancellation, got %v",
fs.openedAfterCancel)
}
if uiw.ErrorCount() != 0 {
t.Fatalf("expected no file reported as failed, got %d error lines",
uiw.ErrorCount())
}
})
}
}
// TestScannerRemovesBlobTempFileWhenRunStops checks that a run stopped
// part-way, by a file it cannot read or by a cancellation, removes the
// temp file of the blob it was packing.
func TestScannerRemovesBlobTempFileWhenRunStops(t *testing.T) {
t.Parallel()
// a.txt is backed up first and starts a blob; the run stops at b.txt.
const target = "/source/b.txt"
tests := []struct {
name string
newFs func(cancel context.CancelFunc) afero.Fs
}{
{
name: "file cannot be read",
newFs: func(context.CancelFunc) afero.Fs {
return &readFailFs{Fs: afero.NewMemMapFs(), target: target}
},
},
{
name: "cancelled",
newFs: func(cancel context.CancelFunc) afero.Fs {
return &cancelOnOpenFs{
Fs: afero.NewMemMapFs(), target: target, cancel: cancel,
}
},
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
fs := tt.newFs(cancel)
writeSkipErrorTestFile(t, fs, "/source/a.txt", "first file content")
writeSkipErrorTestFile(t, fs, target, "second file content")
_, err := runSkipErrorScan(ctx, t, fs, "/source", false, nil)
if err == nil {
t.Fatal("expected the scan to stop with an error, got nil")
}
left, err := afero.Glob(fs, filepath.Join(os.TempDir(), "vaultik-blob-*"))
if err != nil {
t.Fatalf("listing blob temp files: %v", err)
}
if len(left) != 0 {
t.Fatalf("expected no blob temp file left, got %v", left)
}
})
}
}
+45 -65
View File
@@ -105,47 +105,26 @@ func (sm *SnapshotManager) CreateSnapshot(
return sm.CreateSnapshotWithName(ctx, hostname, "", version, gitRevision) return sm.CreateSnapshotWithName(ctx, hostname, "", version, gitRevision)
} }
// ShortHostname returns hostname up to its first dot. A snapshot ID starts
// with this form, while the snapshots table stores the full hostname.
func ShortHostname(hostname string) string {
short, _, _ := strings.Cut(hostname, ".")
return short
}
// CreateSnapshotWithName creates a new snapshot record with an optional // CreateSnapshotWithName creates a new snapshot record with an optional
// snapshot name. The snapshot ID format is: hostname_name_timestamp or // snapshot name. The snapshot ID format is: hostname_name_timestamp or
// hostname_timestamp if name is empty. The timestamp is in whole seconds. // hostname_timestamp if name is empty.
// If the local index already has a snapshot with that ID, from a run of the
// same name that started in the same second, it waits a second and takes a
// new timestamp.
func (sm *SnapshotManager) CreateSnapshotWithName( func (sm *SnapshotManager) CreateSnapshotWithName(
ctx context.Context, hostname, name, version, gitRevision string, ctx context.Context, hostname, name, version, gitRevision string,
) (string, error) { ) (string, error) {
shortHostname := ShortHostname(hostname) // Use short hostname (strip domain if present)
shortHostname := hostname
if before, _, ok := strings.Cut(hostname, "."); ok {
shortHostname = before
}
// Build snapshot ID with optional name
timestamp := time.Now().UTC().Format("2006-01-02T15:04:05Z")
var snapshotID string var snapshotID string
if name != "" {
for { snapshotID = fmt.Sprintf("%s_%s_%s", shortHostname, name, timestamp)
// Build snapshot ID with optional name } else {
timestamp := time.Now().UTC().Format("2006-01-02T15:04:05Z") snapshotID = fmt.Sprintf("%s_%s", shortHostname, timestamp)
if name != "" {
snapshotID = fmt.Sprintf("%s_%s_%s", shortHostname, name, timestamp)
} else {
snapshotID = fmt.Sprintf("%s_%s", shortHostname, timestamp)
}
existing, err := sm.repos.Snapshots.GetByID(ctx, snapshotID)
if err != nil {
return "", fmt.Errorf("looking up snapshot %s: %w", snapshotID, err)
}
if existing == nil {
break
}
time.Sleep(time.Second)
} }
snapshot := &database.Snapshot{ snapshot := &database.Snapshot{
@@ -175,6 +154,26 @@ func (sm *SnapshotManager) CreateSnapshotWithName(
return snapshotID, nil return snapshotID, nil
} }
// UpdateSnapshotStats updates the statistics for a snapshot during backup
func (sm *SnapshotManager) UpdateSnapshotStats(
ctx context.Context, snapshotID string, stats BackupStats,
) error {
err := sm.repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
return sm.repos.Snapshots.UpdateCounts(ctx, tx, snapshotID,
int64(stats.FilesScanned),
int64(stats.ChunksCreated),
int64(stats.BlobsCreated),
stats.BytesScanned,
stats.BytesUploaded,
)
})
if err != nil {
return fmt.Errorf("updating snapshot stats: %w", err)
}
return nil
}
// UpdateSnapshotStatsExtended updates snapshot statistics with extended metrics. // UpdateSnapshotStatsExtended updates snapshot statistics with extended metrics.
// This includes compression level, uncompressed blob size, and upload duration. // This includes compression level, uncompressed blob size, and upload duration.
func (sm *SnapshotManager) UpdateSnapshotStatsExtended( func (sm *SnapshotManager) UpdateSnapshotStatsExtended(
@@ -186,8 +185,8 @@ func (sm *SnapshotManager) UpdateSnapshotStatsExtended(
int64(stats.FilesScanned), int64(stats.FilesScanned),
int64(stats.ChunksCreated), int64(stats.ChunksCreated),
int64(stats.BlobsCreated), int64(stats.BlobsCreated),
stats.TotalSize, stats.BytesScanned,
stats.BlobSize, stats.BytesUploaded,
) )
if err != nil { if err != nil {
return err return err
@@ -197,9 +196,7 @@ func (sm *SnapshotManager) UpdateSnapshotStatsExtended(
return sm.repos.Snapshots.UpdateExtendedStats(ctx, tx, snapshotID, return sm.repos.Snapshots.UpdateExtendedStats(ctx, tx, snapshotID,
stats.BlobUncompressedSize, stats.BlobUncompressedSize,
stats.CompressionLevel, stats.CompressionLevel,
stats.BytesUploaded,
stats.UploadDurationMs, stats.UploadDurationMs,
stats.NewChunkSize,
) )
}) })
} }
@@ -271,18 +268,16 @@ func (sm *SnapshotManager) CompleteSnapshot(
return sm.MarkSnapshotComplete(ctx, snapshotID) return sm.MarkSnapshotComplete(ctx, snapshotID)
} }
// ExportSnapshotMetadata exports snapshot metadata to the backup destination store // ExportSnapshotMetadata exports snapshot metadata to S3
// //
// This method executes the complete snapshot metadata export process: // This method executes the complete snapshot metadata export process:
// 1. Creates a temporary directory for working files // 1. Creates a temporary directory for working files
// 2. Copies the main database to preserve its state // 2. Copies the main database to preserve its state
// 3. Cleans the copy to contain only current snapshot data // 3. Cleans the copy to contain only current snapshot data
// 4. Vacuums the copy to remove the deleted data // 4. Dumps the cleaned database to SQL
// 5. Compresses the copy with zstd // 5. Compresses the SQL dump with zstd
// 6. Encrypts the compressed copy with age (always; recipients are required) // 6. Encrypts the compressed data with age (always; recipients are required)
// 7. Builds the blob manifest from the copy, compressed but not encrypted // 7. Uploads to S3 at: snapshots/{snapshot-id}.sql.zst[.age]
// 8. Uploads the database to metadata/{remote-key}/db.zst.age
// 9. Uploads the manifest to metadata/{remote-key}/manifest.json.zst
// //
// The only caller (finalizeSnapshotMetadata) does not close the main database // The only caller (finalizeSnapshotMetadata) does not close the main database
// before calling this method: the index is copied at dbPath while it is still // before calling this method: the index is copied at dbPath while it is still
@@ -520,8 +515,8 @@ type CleanupStats struct {
// //
// The cleanup is performed in a specific order to maintain referential integrity: // The cleanup is performed in a specific order to maintain referential integrity:
// 1. Delete other snapshots // 1. Delete other snapshots
// 2. Delete orphaned snapshot associations (snapshot_files, snapshot_blobs, // 2. Delete orphaned snapshot associations (snapshot_files, snapshot_blobs)
// snapshot_mount_points) for deleted snapshots // for deleted snapshots
// 3. Delete orphaned files (not in the current snapshot) // 3. Delete orphaned files (not in the current snapshot)
// 4. Delete orphaned chunk-to-file mappings (references to deleted files) // 4. Delete orphaned chunk-to-file mappings (references to deleted files)
// 5. Delete orphaned blobs (not in the current snapshot) // 5. Delete orphaned blobs (not in the current snapshot)
@@ -895,7 +890,7 @@ func (sm *SnapshotManager) getFileSize(path string) int64 {
// BackupStats contains statistics from a backup operation // BackupStats contains statistics from a backup operation
type BackupStats struct { type BackupStats struct {
FilesScanned int FilesScanned int
TotalSize int64 // Total size of the files in the snapshot BytesScanned int64
ChunksCreated int ChunksCreated int
BlobsCreated int BlobsCreated int
BytesUploaded int64 BytesUploaded int64
@@ -905,11 +900,9 @@ type BackupStats struct {
type ExtendedBackupStats struct { type ExtendedBackupStats struct {
BackupStats BackupStats
BlobSize int64 // Total compressed size of all referenced blobs
BlobUncompressedSize int64 // Total uncompressed size of all referenced blobs BlobUncompressedSize int64 // Total uncompressed size of all referenced blobs
CompressionLevel int // Compression level used for this snapshot CompressionLevel int // Compression level used for this snapshot
UploadDurationMs int64 // Total milliseconds spent uploading to S3 UploadDurationMs int64 // Total milliseconds spent uploading to S3
NewChunkSize int64 // Total size of the chunks counted in ChunksCreated
} }
// deleteOtherSnapshots deletes all snapshots except the current one // deleteOtherSnapshots deletes all snapshots except the current one
@@ -950,8 +943,8 @@ func (sm *SnapshotManager) deleteOtherSnapshots(
return nil return nil
} }
// deleteOrphanedSnapshotAssociations deletes snapshot_files, // deleteOrphanedSnapshotAssociations deletes snapshot_files and
// snapshot_blobs and snapshot_mount_points for deleted snapshots // snapshot_blobs for deleted snapshots
func (sm *SnapshotManager) deleteOrphanedSnapshotAssociations( func (sm *SnapshotManager) deleteOrphanedSnapshotAssociations(
ctx context.Context, tx *sql.Tx, currentSnapshotID string, ctx context.Context, tx *sql.Tx, currentSnapshotID string,
) error { ) error {
@@ -985,19 +978,6 @@ func (sm *SnapshotManager) deleteOrphanedSnapshotAssociations(
log.Debug("[Temp DB Cleanup] Deleted snapshot_blobs associations", log.Debug("[Temp DB Cleanup] Deleted snapshot_blobs associations",
"count", rowsAffected) "count", rowsAffected)
// Delete the mount points other snapshots recorded
query := "DELETE FROM snapshot_mount_points WHERE snapshot_id != ?"
database.LogSQL("Execute", query, currentSnapshotID)
result, err = tx.ExecContext(ctx, query, currentSnapshotID)
if err != nil {
return fmt.Errorf("deleting orphaned snapshot_mount_points: %w", err)
}
rowsAffected, _ = result.RowsAffected()
log.Debug("[Temp DB Cleanup] Deleted snapshot_mount_points rows",
"count", rowsAffected)
return nil return nil
} }
-106
View File
@@ -7,14 +7,12 @@ import (
"database/sql" "database/sql"
"io" "io"
"path/filepath" "path/filepath"
"slices"
"testing" "testing"
"github.com/spf13/afero" "github.com/spf13/afero"
"sneak.berlin/go/vaultik/internal/config" "sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database" "sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log" "sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/types"
) )
const ( const (
@@ -388,107 +386,3 @@ func TestCleanSnapshotDBNonExistentSnapshot(t *testing.T) {
t.Fatalf("unexpected error: %v", err) t.Fatalf("unexpected error: %v", err)
} }
} }
// The exported metadata database keeps only the mount points that the
// exported snapshot recorded. See
// https://git.eeqj.de/sneak/vaultik/issues/395.
func TestCleanSnapshotDBKeepsOnlyTheSnapshotsMountPoints(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
dbPath := filepath.Join(t.TempDir(), "export.db")
db, err := database.New(ctx, dbPath)
if err != nil {
t.Fatalf("failed to create database: %v", err)
}
repos := database.NewRepositories(db)
for _, id := range []types.SnapshotID{"exported", "other"} {
err = repos.Snapshots.Create(ctx, nil, &database.Snapshot{ID: id})
if err != nil {
t.Fatalf("failed to create snapshot: %v", err)
}
err = repos.Snapshots.AddMountPoint(ctx, nil, id.String(), "/data/"+id.String())
if err != nil {
t.Fatalf("failed to add mount point: %v", err)
}
}
err = db.Close()
if err != nil {
t.Fatalf("failed to close database: %v", err)
}
sm := &SnapshotManager{
config: &config.Config{
CompressionLevel: 3,
AgeRecipients: []string{testAgeRecipient},
},
fs: afero.NewOsFs(),
}
_, err = sm.cleanSnapshotDB(ctx, dbPath, "exported")
if err != nil {
t.Fatalf("failed to clean snapshot database: %v", err)
}
cleaned, err := database.New(ctx, dbPath)
if err != nil {
t.Fatalf("failed to open cleaned database: %v", err)
}
defer func() { _ = cleaned.Close() }()
cleanedRepos := database.NewRepositories(cleaned)
for id, want := range map[string][]string{
"exported": {"/data/exported"},
"other": nil,
} {
got, err := cleanedRepos.Snapshots.GetMountPoints(ctx, id)
if err != nil {
t.Fatalf("failed to read mount points: %v", err)
}
if !slices.Equal(got, want) {
t.Errorf("mount points of %s: got %v, want %v", id, got, want)
}
}
}
// Two creates of one snapshot name back to back start within one second,
// the resolution of the timestamp in a snapshot ID. See
// https://git.eeqj.de/sneak/vaultik/issues/270.
func TestCreateSnapshotWithNameTwiceBackToBack(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
db, err := database.New(ctx, filepath.Join(t.TempDir(), "index.sqlite"))
if err != nil {
t.Fatalf("failed to create database: %v", err)
}
defer func() { _ = db.Close() }()
sm := &SnapshotManager{repos: database.NewRepositories(db)}
first, err := sm.CreateSnapshotWithName(ctx, "test-host", "data", "v", "g")
if err != nil {
t.Fatalf("first create failed: %v", err)
}
second, err := sm.CreateSnapshotWithName(ctx, "test-host", "data", "v", "g")
if err != nil {
t.Fatalf("second create failed: %v", err)
}
if first == second {
t.Fatalf("both creates returned snapshot ID %s", first)
}
}
+5 -38
View File
@@ -8,29 +8,25 @@ import (
"reflect" "reflect"
"sort" "sort"
"testing" "testing"
"time"
"sneak.berlin/go/vaultik/internal/storage" "sneak.berlin/go/vaultik/internal/storage"
) )
// runStorerConformance is the shared Storer contract. Every backend that // runStorerConformance is the shared Storer contract. Every backend that
// can run in-process is expected to pass it: TestFileStorer runs it against // can run in-process is expected to pass it: TestFileStorer runs it against
// file://, TestS3Storer against s3://, TestRcloneStorer against rclone's // file://, TestS3Storer against s3://. A new backend inherits this coverage
// local backend. A new backend inherits this coverage by passing its own // by passing its own constructor, so the contract is defined once.
// constructor, so the contract is defined once.
// //
// It exercises the public Storer interface: round-trip, stat, list with // It exercises the public Storer interface: round-trip, stat, list with
// prefix filtering, the modification time ListStream reports, overwrite, // prefix filtering, overwrite, delete, delete-of-missing, and not-found on
// delete, delete-of-missing, and not-found on Get and Stat. Each section // Get and Stat. Each section takes its own fresh backend instance, so the
// takes its own fresh backend instance, so the order of sections never // order of sections never matters and no section sees another's objects.
// matters and no section sees another's objects.
func runStorerConformance(t *testing.T, newStorer func(*testing.T) storage.Storer) { func runStorerConformance(t *testing.T, newStorer func(*testing.T) storage.Storer) {
t.Helper() t.Helper()
conformanceRoundTrip(t, newStorer(t)) conformanceRoundTrip(t, newStorer(t))
conformanceOverwrite(t, newStorer(t)) conformanceOverwrite(t, newStorer(t))
conformanceList(t, newStorer(t)) conformanceList(t, newStorer(t))
conformanceListStreamModTime(t, newStorer(t))
conformanceDelete(t, newStorer(t)) conformanceDelete(t, newStorer(t))
conformanceNotFound(t, newStorer(t)) conformanceNotFound(t, newStorer(t))
} }
@@ -121,35 +117,6 @@ func conformanceList(t *testing.T, s storage.Storer) {
} }
} }
// conformanceListStreamModTime checks that ListStream gives an object
// just written a modification time of about now, which prune compares
// with its grace period.
func conformanceListStreamModTime(t *testing.T, s storage.Storer) {
t.Helper()
ctx := context.Background()
err := s.Put(ctx, "blobs/dd/written-now", bytes.NewReader([]byte("data")))
if err != nil {
t.Fatalf("Put: %v", err)
}
var listed []storage.ObjectInfo
for info := range s.ListStream(ctx, "blobs/") {
listed = append(listed, info)
}
if len(listed) != 1 || listed[0].Err != nil {
t.Fatalf("ListStream(\"blobs/\") = %v, want the one object", listed)
}
if time.Since(listed[0].ModTime).Abs() > time.Minute {
t.Errorf("ListStream ModTime = %v, want within a minute of now",
listed[0].ModTime)
}
}
// conformanceDelete checks that Delete removes an object and that deleting // conformanceDelete checks that Delete removes an object and that deleting
// a missing key is not an error. // a missing key is not an error.
func conformanceDelete(t *testing.T, s storage.Storer) { func conformanceDelete(t *testing.T, s storage.Storer) {
+10 -44
View File
@@ -1,18 +1,15 @@
// Package faultstore provides a storage.Storer wrapper that injects // Package faultstore provides a storage.Storer wrapper that injects
// faults on demand, so tests can reproduce the failure modes a real // faults on demand, so tests can reproduce the failure modes a real
// backend exhibits: an upload that fails partway, a backend that reports // backend exhibits: an upload that fails partway, a backend that reports
// success while storing nothing, reads that return corrupt or truncated // success while storing nothing, and reads that return corrupt or
// bytes, and a delete or a stat the backend refuses. It is the seam // truncated bytes. It is the seam called for by the fault-injection
// called for by the fault-injection tests (sneak/vaultik issue 72) and // tests (sneak/vaultik issue 72) and is meant to be reused by future
// is meant to be reused by future tests rather than re-implemented per // tests rather than re-implemented per case.
// case.
// //
// The wrapper delegates every method to the inner Storer. Four hooks // The wrapper delegates every method to the inner Storer. Two hooks
// change that: OnPut decides the fate of each write, OnGet decides how // change that: OnPut decides the fate of each write, and OnGet decides
// each read's bytes are returned, OnDelete decides whether each delete // how each read's bytes are returned. Both are keyed by the object key,
// fails, and OnStat whether each stat fails. All are keyed by the object // so a test can fault only blobs, only metadata, or a single object.
// key, so a test can fault only blobs, only metadata, or a single
// object.
package faultstore package faultstore
import ( import (
@@ -28,15 +25,6 @@ import (
// ErrInjectedUpload is returned by a Put the OnPut hook chose to fail. // ErrInjectedUpload is returned by a Put the OnPut hook chose to fail.
var ErrInjectedUpload = errors.New("faultstore: injected upload failure") var ErrInjectedUpload = errors.New("faultstore: injected upload failure")
// ErrInjectedDelete is returned by a Delete the OnDelete hook chose to
// fail.
var ErrInjectedDelete = errors.New("faultstore: injected delete failure")
// ErrInjectedStat is returned by a Stat the OnStat hook chose to fail.
// It is not storage.ErrNotFound: the backend refused the request, as S3
// refuses a HEAD to credentials that allow only PUT.
var ErrInjectedStat = errors.New("faultstore: injected stat failure")
// PutAction is the disposition OnPut assigns to a write. // PutAction is the disposition OnPut assigns to a write.
type PutAction int type PutAction int
@@ -78,15 +66,6 @@ type Storer struct {
// OnGet, when set, is consulted for every Get with the object key // OnGet, when set, is consulted for every Get with the object key
// and damages the returned bytes accordingly. // and damages the returned bytes accordingly.
OnGet func(key string) GetFault OnGet func(key string) GetFault
// OnDelete, when set, is consulted before every Delete with the
// object key. Returning true fails the delete and leaves the object
// in place.
OnDelete func(key string) bool
// OnStat, when set, is consulted before every Stat with the object
// key. Returning true fails the stat with ErrInjectedStat.
OnStat func(key string) bool
} }
// New wraps inner. inner must be non-nil. // New wraps inner. inner must be non-nil.
@@ -170,21 +149,13 @@ func damage(fault GetFault, data []byte) []byte {
return out return out
} }
// Stat returns the object's info unless OnStat fails the stat. // Stat delegates unchanged.
func (f *Storer) Stat(ctx context.Context, key string) (*storage.ObjectInfo, error) { func (f *Storer) Stat(ctx context.Context, key string) (*storage.ObjectInfo, error) {
if f.OnStat != nil && f.OnStat(key) {
return nil, fmt.Errorf("%w for %q", ErrInjectedStat, key)
}
return f.inner.Stat(ctx, key) return f.inner.Stat(ctx, key)
} }
// Delete removes the object unless OnDelete fails the delete. // Delete delegates unchanged.
func (f *Storer) Delete(ctx context.Context, key string) error { func (f *Storer) Delete(ctx context.Context, key string) error {
if f.OnDelete != nil && f.OnDelete(key) {
return fmt.Errorf("%w for %q", ErrInjectedDelete, key)
}
return f.inner.Delete(ctx, key) return f.inner.Delete(ctx, key)
} }
@@ -200,11 +171,6 @@ func (f *Storer) ListStream(
return f.inner.ListStream(ctx, prefix) return f.inner.ListStream(ctx, prefix)
} }
// DeletePartialUploads delegates unchanged.
func (f *Storer) DeletePartialUploads(ctx context.Context, prefix string) error {
return f.inner.DeletePartialUploads(ctx, prefix)
}
// Info delegates unchanged. // Info delegates unchanged.
func (f *Storer) Info() storage.Info { func (f *Storer) Info() storage.Info {
return f.inner.Info() return f.inner.Info()
+19 -123
View File
@@ -21,13 +21,9 @@ type FileStorer struct {
// NewFileStorer creates a new filesystem storage backend. // NewFileStorer creates a new filesystem storage backend.
// //
// Construction is intentionally cheap and does not touch the filesystem. // Construction is intentionally cheap and does not touch the filesystem.
// The backend never creates basePath: the user does, so that when // The basePath is recorded; the directory is created lazily on first
// basePath is a directory on an unplugged volume, a write fails instead // write. Write operations (Put/PutWithProgress) call MkdirAll for the
// of landing on the disk under the mount point. This does not hold when // per-blob parent directory, which also covers basePath on first use.
// basePath is the mount point itself, which stays behind when its volume
// is unplugged.
// Put and PutWithProgress fail on a missing basePath and create the
// directories below it as needed.
// Get and Stat report a key under a missing basePath as ErrNotFound. // Get and Stat report a key under a missing basePath as ErrNotFound.
// List and ListStream fail on a missing basePath, because listing it as // List and ListStream fail on a missing basePath, because listing it as
// an empty store would make `prune` drop every local snapshot record. // an empty store would make `prune` drop every local snapshot record.
@@ -54,10 +50,9 @@ const storageDirPerm = 0o755
// temp file carrying this suffix and only renames it onto the real key once // temp file carrying this suffix and only renames it onto the real key once
// the whole object is on disk, so an interrupted write can never leave a // the whole object is on disk, so an interrupted write can never leave a
// truncated object at the key a later run would Stat and trust as a complete // truncated object at the key a later run would Stat and trust as a complete
// blob. The rclone backend's upload does the same on remotes with a // blob. List and ListStream skip these files, so a leftover from an
// server-side move. List and ListStream skip these files, so a leftover from // interrupted write is never listed or trusted as a blob; it is otherwise
// an interrupted write is never listed or trusted as a blob; it is otherwise // harmless and is overwritten when the same key is written again.
// harmless.
const tempSuffix = ".partial" const tempSuffix = ".partial"
// Put stores data at the specified key. // Put stores data at the specified key.
@@ -124,10 +119,9 @@ func (f *FileStorer) Delete(_ context.Context, key string) error {
return nil return nil
} }
// List returns all keys with the given prefix, reading through symlinked // List returns all keys with the given prefix. It fails when the
// directories. It fails when the destination directory is missing, or // destination directory is missing; a missing prefix under it is an
// when the prefix or a directory above it is a symlink whose target is // empty listing.
// missing; a prefix that is truly missing is an empty listing.
func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error) { func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error) {
var keys []string var keys []string
@@ -138,7 +132,8 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
basePath := f.fullPath(prefix) basePath := f.fullPath(prefix)
exists, err := f.prefixExists(prefix) // Check if the prefix exists
exists, err := afero.Exists(f.fs, basePath)
if err != nil { if err != nil {
return nil, fmt.Errorf("checking path: %w", err) return nil, fmt.Errorf("checking path: %w", err)
} }
@@ -147,7 +142,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
return keys, nil // Empty list for non-existent prefix return keys, nil // Empty list for non-existent prefix
} }
err = f.walk(basePath, func(path string, info os.FileInfo, err error) error { err = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
if err != nil { if err != nil {
return err return err
} }
@@ -180,9 +175,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
} }
// ListStream returns a channel of ObjectInfo for large result sets. Like // ListStream returns a channel of ObjectInfo for large result sets. Like
// List, it reads through symlinked directories and sends an error when // List, it sends an error when the destination directory is missing.
// the destination directory is missing, or when the prefix or a directory
// above it is a symlink whose target is missing.
func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan ObjectInfo { func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan ObjectInfo {
ch := make(chan ObjectInfo) ch := make(chan ObjectInfo)
@@ -198,7 +191,8 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
basePath := f.fullPath(prefix) basePath := f.fullPath(prefix)
exists, err := f.prefixExists(prefix) // Check if the prefix exists
exists, err := afero.Exists(f.fs, basePath)
if err != nil { if err != nil {
ch <- ObjectInfo{Err: fmt.Errorf("checking path: %w", err)} ch <- ObjectInfo{Err: fmt.Errorf("checking path: %w", err)}
@@ -209,7 +203,7 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
return // Empty channel for non-existent prefix return // Empty channel for non-existent prefix
} }
_ = f.walk(basePath, func(path string, info os.FileInfo, err error) error { _ = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
// Check context cancellation // Check context cancellation
select { select {
case <-ctx.Done(): case <-ctx.Done():
@@ -235,9 +229,8 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
// Normalize path separators // Normalize path separators
relPath = strings.ReplaceAll(relPath, string(filepath.Separator), "/") relPath = strings.ReplaceAll(relPath, string(filepath.Separator), "/")
ch <- ObjectInfo{ ch <- ObjectInfo{
Key: relPath, Key: relPath,
Size: info.Size(), Size: info.Size(),
ModTime: info.ModTime(),
} }
} }
@@ -248,43 +241,6 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
return ch return ch
} }
// DeletePartialUploads removes every file under prefix whose name ends in
// tempSuffix. Like List, it reads through symlinked directories and fails
// on one whose target is missing. A missing prefix has none to remove.
func (f *FileStorer) DeletePartialUploads(ctx context.Context, prefix string) error {
basePath := f.fullPath(prefix)
exists, err := f.prefixExists(prefix)
if err != nil {
return fmt.Errorf("checking path: %w", err)
}
if !exists {
return nil
}
err = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
if err != nil {
return err
}
if ctx.Err() != nil {
return ctx.Err()
}
if info.IsDir() || !strings.HasSuffix(info.Name(), tempSuffix) {
return nil
}
return f.fs.Remove(path)
})
if err != nil {
return fmt.Errorf("walking directory: %w", err)
}
return nil
}
// Info returns human-readable storage location information. // Info returns human-readable storage location information.
func (f *FileStorer) Info() Info { func (f *FileStorer) Info() Info {
return Info{ return Info{
@@ -304,19 +260,7 @@ func (f *FileStorer) writeAtomic(
path := f.fullPath(key) path := f.fullPath(key)
dir := filepath.Dir(path) dir := filepath.Dir(path)
// Checked on every write, so a destination that disappears part-way err := f.fs.MkdirAll(dir, storageDirPerm)
// through a backup fails it rather than being recreated by MkdirAll.
_, err := f.fs.Stat(f.basePath)
if os.IsNotExist(err) {
return fmt.Errorf("destination directory does not exist; "+
"create it, or mount the volume it is on: %w", err)
}
if err != nil {
return fmt.Errorf("checking destination directory: %w", err)
}
err = f.fs.MkdirAll(dir, storageDirPerm)
if err != nil { if err != nil {
return fmt.Errorf("creating directories: %w", err) return fmt.Errorf("creating directories: %w", err)
} }
@@ -371,54 +315,6 @@ func (f *FileStorer) writeAtomic(
return nil return nil
} }
// walk is afero.Walk, except that it reads through a symlinked directory
// the way Get and Stat do, where afero.Walk reports the link as one file.
// afero.Walk uses Lstat, which does not follow a link, whenever the
// filesystem has one; the struct below carries only the afero.Fs methods,
// so the walk uses Stat instead. A link back up the tree is followed until
// the operating system refuses the path for too many levels of links, and
// the walk then fails.
func (f *FileStorer) walk(root string, fn filepath.WalkFunc) error {
return afero.Walk(struct{ afero.Fs }{f.fs}, root, fn)
}
// prefixExists reports whether prefix exists under the destination
// directory. It checks each directory on the way down to prefix in turn,
// and the first one Stat cannot find decides: if it is not there at all,
// prefix is missing; if it is a symlink whose target is missing, such as
// a link to a volume that is not mounted, prefixExists fails, since
// listing it as empty would let prune delete every blob.
func (f *FileStorer) prefixExists(prefix string) (bool, error) {
lstater, canLstat := f.fs.(afero.Lstater)
path := f.basePath
for name := range strings.SplitSeq(prefix, "/") {
path = filepath.Join(path, name)
_, err := f.fs.Stat(path)
if err == nil {
continue
}
if !os.IsNotExist(err) {
return false, err
}
// Lstat does not follow a symlink at path, so it finds the link
// that Stat could not follow.
if canLstat {
_, _, lstatErr := lstater.LstatIfPossible(path)
if lstatErr == nil {
return false, err
}
}
return false, nil
}
return true, nil
}
// fullPath returns the full filesystem path for a key. // fullPath returns the full filesystem path for a key.
func (f *FileStorer) fullPath(key string) string { func (f *FileStorer) fullPath(key string) string {
return filepath.Join(f.basePath, key) return filepath.Join(f.basePath, key)
+2 -47
View File
@@ -14,9 +14,6 @@ import (
// errStreamInterrupted stands in for an upload cut off mid-stream. // errStreamInterrupted stands in for an upload cut off mid-stream.
var errStreamInterrupted = errors.New("connection reset mid-upload") var errStreamInterrupted = errors.New("connection reset mid-upload")
// testBlobKey is a key laid out as a blob's key is.
const testBlobKey = "blobs/aa/bb/aabbccddeeff"
// failingReader yields its data once, then fails. // failingReader yields its data once, then fails.
type failingReader struct { type failingReader struct {
data []byte data []byte
@@ -46,7 +43,7 @@ func TestFileStorer_InterruptedWriteLeavesNoTrustedObject(t *testing.T) {
} }
ctx := context.Background() ctx := context.Background()
key := testBlobKey key := "blobs/aa/bb/aabbccddeeff"
err = f.PutWithProgress(ctx, key, &failingReader{data: []byte("partial")}, 4096, nil) err = f.PutWithProgress(ctx, key, &failingReader{data: []byte("partial")}, 4096, nil)
if err == nil { if err == nil {
@@ -82,7 +79,7 @@ func TestFileStorer_ListSkipsPartialFiles(t *testing.T) {
} }
ctx := context.Background() ctx := context.Background()
realKey := testBlobKey realKey := "blobs/aa/bb/aabbccddeeff"
err = f.Put(ctx, realKey, strings.NewReader("blob-bytes")) err = f.Put(ctx, realKey, strings.NewReader("blob-bytes"))
if err != nil { if err != nil {
@@ -120,45 +117,3 @@ func TestFileStorer_ListSkipsPartialFiles(t *testing.T) {
t.Fatalf("ListStream should return only the real key, got %v", streamed) t.Fatalf("ListStream should return only the real key, got %v", streamed)
} }
} }
// TestFileStorer_DeletePartialUploads checks that a leftover temp file is
// removed and the object at the real key is kept.
func TestFileStorer_DeletePartialUploads(t *testing.T) {
t.Parallel()
base := t.TempDir()
f, err := storage.NewFileStorer(base)
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
ctx := context.Background()
err = f.Put(ctx, testBlobKey, strings.NewReader("blob-bytes"))
if err != nil {
t.Fatalf("Put: %v", err)
}
leftover := filepath.Join(base, testBlobKey+"-123456.partial")
err = os.WriteFile(leftover, []byte("half"), 0o600)
if err != nil {
t.Fatalf("writing leftover temp file: %v", err)
}
err = f.DeletePartialUploads(ctx, "blobs/")
if err != nil {
t.Fatalf("DeletePartialUploads: %v", err)
}
_, err = os.Stat(leftover)
if !os.IsNotExist(err) {
t.Errorf("leftover temp file was not removed: %v", err)
}
_, err = f.Stat(ctx, testBlobKey)
if err != nil {
t.Errorf("Stat of the real key: %v", err)
}
}
-272
View File
@@ -4,10 +4,7 @@ import (
"context" "context"
"errors" "errors"
"io/fs" "io/fs"
"os"
"path/filepath" "path/filepath"
"reflect"
"strings"
"testing" "testing"
"sneak.berlin/go/vaultik/internal/storage" "sneak.berlin/go/vaultik/internal/storage"
@@ -63,272 +60,3 @@ func TestFileStorerListMissingDestination(t *testing.T) {
t.Errorf("ListStream error = %v, want a not-exist error", streamErr) t.Errorf("ListStream error = %v, want a not-exist error", streamErr)
} }
} }
// The two directories at the top of a destination, either of which the
// tests below replace with a symlink.
const (
metadataDir = "metadata"
blobsDir = "blobs"
)
// moveBehindSymlink moves base/dir to a directory elsewhere and puts a
// symlink to it in its place.
func moveBehindSymlink(t *testing.T, base, dir string) {
t.Helper()
linkPath := filepath.Join(base, dir)
movedPath := filepath.Join(t.TempDir(), dir)
err := os.Rename(linkPath, movedPath)
if err != nil {
t.Fatalf("moving %s away: %v", dir, err)
}
err = os.Symlink(movedPath, linkPath)
if err != nil {
t.Fatalf("linking %s: %v", dir, err)
}
}
// TestFileStorerListsThroughSymlinkedDirectory checks that List and
// ListStream read through a symlinked metadata/ or blobs/ directory, as Get
// and Stat do, instead of listing the link as one key. Listing the whole
// destination meets the link part-way through the walk; listing its prefix
// starts the walk at the link. A prefix missing behind the link lists as
// empty.
func TestFileStorerListsThroughSymlinkedDirectory(t *testing.T) {
t.Parallel()
for _, dir := range []string{metadataDir, blobsDir} {
t.Run(dir, func(t *testing.T) {
t.Parallel()
base := t.TempDir()
key := dir + "/aa/bb/object"
s, err := storage.NewFileStorer(base)
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
err = s.Put(context.Background(), key, strings.NewReader("data"))
if err != nil {
t.Fatalf("Put: %v", err)
}
moveBehindSymlink(t, base, dir)
want := []string{key}
for _, prefix := range []string{"", dir + "/"} {
got := listSorted(t, s, prefix)
if !reflect.DeepEqual(got, want) {
t.Errorf("List(%q) = %v, want %v", prefix, got, want)
}
got = listStreamKeys(t, s, prefix)
if !reflect.DeepEqual(got, want) {
t.Errorf("ListStream(%q) = %v, want %v", prefix, got, want)
}
}
absent := dir + "/absent/"
if got := listSorted(t, s, absent); len(got) != 0 {
t.Errorf("List(%q) = %v, want empty", absent, got)
}
if got := listStreamKeys(t, s, absent); len(got) != 0 {
t.Errorf("ListStream(%q) = %v, want empty", absent, got)
}
})
}
}
// TestFileStorerListFailsOnSymlinkWithMissingTarget checks that List and
// ListStream fail on a symlinked metadata/ or blobs/ directory whose target
// is missing, such as a link to a volume that is not mounted, as they do on
// a missing destination directory, instead of listing it as empty. That
// holds for a prefix below the link too.
func TestFileStorerListFailsOnSymlinkWithMissingTarget(t *testing.T) {
t.Parallel()
ctx := context.Background()
for _, dir := range []string{metadataDir, blobsDir} {
t.Run(dir, func(t *testing.T) {
t.Parallel()
base := t.TempDir()
s, err := storage.NewFileStorer(base)
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
unmounted := filepath.Join(t.TempDir(), "unmounted")
err = os.Symlink(unmounted, filepath.Join(base, dir))
if err != nil {
t.Fatalf("Symlink: %v", err)
}
for _, prefix := range []string{"", dir + "/", dir + "/aa/"} {
keys, err := s.List(ctx, prefix)
if !errors.Is(err, fs.ErrNotExist) {
t.Errorf("List(%q) = %v, %v; want a not-exist error",
prefix, keys, err)
}
var streamErr error
for object := range s.ListStream(ctx, prefix) {
if object.Err != nil {
streamErr = object.Err
}
}
if !errors.Is(streamErr, fs.ErrNotExist) {
t.Errorf("ListStream(%q) error = %v, want a not-exist error",
prefix, streamErr)
}
}
})
}
}
// TestFileStorerListFailsOnSymlinkLoop checks that a symlink pointing back
// at the destination makes List and ListStream fail instead of walking it
// forever.
func TestFileStorerListFailsOnSymlinkLoop(t *testing.T) {
t.Parallel()
ctx := context.Background()
base := t.TempDir()
s, err := storage.NewFileStorer(base)
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
err = s.Put(ctx, testBlobKey, strings.NewReader("data"))
if err != nil {
t.Fatalf("Put: %v", err)
}
err = os.Symlink(base, filepath.Join(base, "blobs", "loop"))
if err != nil {
t.Fatalf("Symlink: %v", err)
}
keys, err := s.List(ctx, "blobs/")
if err == nil {
t.Errorf("List = %d keys and no error, want an error", len(keys))
}
var streamErr error
for object := range s.ListStream(ctx, "blobs/") {
if object.Err != nil {
streamErr = object.Err
}
}
if streamErr == nil {
t.Error("ListStream sent no error, want one")
}
}
// TestFileStorerDeletePartialUploadsThroughSymlinkedDirectory checks that
// DeletePartialUploads, which remote nuke uses, removes a leftover temp
// file behind a symlinked metadata/ or blobs/ directory and keeps the
// object at the real key.
func TestFileStorerDeletePartialUploadsThroughSymlinkedDirectory(t *testing.T) {
t.Parallel()
ctx := context.Background()
for _, dir := range []string{metadataDir, blobsDir} {
t.Run(dir, func(t *testing.T) {
t.Parallel()
base := t.TempDir()
key := dir + "/aa/bb/object"
s, err := storage.NewFileStorer(base)
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
err = s.Put(ctx, key, strings.NewReader("data"))
if err != nil {
t.Fatalf("Put: %v", err)
}
leftover := filepath.Join(base, key+"-123456.partial")
err = os.WriteFile(leftover, []byte("half"), 0o600)
if err != nil {
t.Fatalf("writing leftover temp file: %v", err)
}
moveBehindSymlink(t, base, dir)
err = s.DeletePartialUploads(ctx, dir+"/")
if err != nil {
t.Fatalf("DeletePartialUploads: %v", err)
}
// leftover runs through the link.
_, err = os.Stat(leftover)
if !os.IsNotExist(err) {
t.Errorf("leftover temp file was not removed: %v", err)
}
_, err = s.Stat(ctx, key)
if err != nil {
t.Errorf("Stat of the real key: %v", err)
}
})
}
}
// TestFileStorerPutMissingDestination checks that a write fails when the
// destination directory has gone, even after earlier writes to it
// succeeded, and that it does not create the directory again.
func TestFileStorerPutMissingDestination(t *testing.T) {
t.Parallel()
ctx := context.Background()
base := filepath.Join(t.TempDir(), "usbstick")
err := os.Mkdir(base, 0o750)
if err != nil {
t.Fatalf("Mkdir: %v", err)
}
s, err := storage.NewFileStorer(base)
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
err = s.Put(ctx, "blobs/aa/bb/first", strings.NewReader("first"))
if err != nil {
t.Fatalf("first Put: %v", err)
}
err = os.Rename(base, base+"-unplugged")
if err != nil {
t.Fatalf("Rename: %v", err)
}
err = s.Put(ctx, "blobs/aa/bb/second", strings.NewReader("second"))
if !errors.Is(err, fs.ErrNotExist) {
t.Errorf("Put = %v, want a not-exist error", err)
}
_, err = os.Stat(base)
if !errors.Is(err, fs.ErrNotExist) {
t.Errorf("Put created the destination directory again (Stat = %v)", err)
}
}
-2
View File
@@ -99,7 +99,6 @@ func storerFromParsedS3URL(parsed *URL, cfg *config.Config) (Storer, error) {
AccessKeyID: cfg.S3.AccessKeyID, AccessKeyID: cfg.S3.AccessKeyID,
SecretAccessKey: cfg.S3.SecretAccessKey, SecretAccessKey: cfg.S3.SecretAccessKey,
Region: region, Region: region,
PartSize: cfg.S3.PartSize.Int64(),
}) })
if err != nil { if err != nil {
return nil, fmt.Errorf("creating S3 client: %w", err) return nil, fmt.Errorf("creating S3 client: %w", err)
@@ -135,7 +134,6 @@ func storerFromLegacyS3Config(cfg *config.Config) (Storer, error) {
AccessKeyID: cfg.S3.AccessKeyID, AccessKeyID: cfg.S3.AccessKeyID,
SecretAccessKey: cfg.S3.SecretAccessKey, SecretAccessKey: cfg.S3.SecretAccessKey,
Region: region, Region: region,
PartSize: cfg.S3.PartSize.Int64(),
}) })
if err != nil { if err != nil {
return nil, fmt.Errorf("creating S3 client: %w", err) return nil, fmt.Errorf("creating S3 client: %w", err)
+17 -111
View File
@@ -3,16 +3,13 @@ package storage
import ( import (
"bytes" "bytes"
"context" "context"
"crypto/rand"
"errors" "errors"
"fmt" "fmt"
"io" "io"
"os"
"strings" "strings"
"time" "time"
"github.com/rclone/rclone/fs" "github.com/rclone/rclone/fs"
"github.com/rclone/rclone/fs/config"
"github.com/rclone/rclone/fs/config/configfile" "github.com/rclone/rclone/fs/config/configfile"
"github.com/rclone/rclone/fs/operations" "github.com/rclone/rclone/fs/operations"
@@ -35,15 +32,6 @@ type RcloneStorer struct {
// The remote parameter is the rclone remote name (as configured via `rclone config`). // The remote parameter is the rclone remote name (as configured via `rclone config`).
// The path parameter is the path within the remote. // The path parameter is the path within the remote.
func NewRcloneStorer(ctx context.Context, remote, path string) (*RcloneStorer, error) { func NewRcloneStorer(ctx context.Context, remote, path string) (*RcloneStorer, error) {
// rclone reads RCLONE_CONFIG only as the value of its --config flag,
// which vaultik does not have, so it is applied here as that flag would.
if configPath, ok := os.LookupEnv("RCLONE_CONFIG"); ok {
err := config.SetConfigPath(configPath)
if err != nil {
return nil, fmt.Errorf("using RCLONE_CONFIG %q: %w", configPath, err)
}
}
// Install the default config file handler // Install the default config file handler
configfile.Install() configfile.Install()
@@ -53,14 +41,6 @@ func NewRcloneStorer(ctx context.Context, remote, path string) (*RcloneStorer, e
rclonePath += path rclonePath += path
} }
// On S3, Swift and some other remotes rclone keeps a time of its own in
// each object's metadata, which costs one request per object to read.
// rclone's use_server_modtime setting makes ModTime the time the
// listing gives instead: when the object was stored, which is what
// prune compares with prune_grace_period.
ctx, ci := fs.AddConfig(ctx)
ci.UseServerModTime = true
// Create the rclone filesystem // Create the rclone filesystem
fsys, err := fs.NewFs(ctx, rclonePath) fsys, err := fs.NewFs(ctx, rclonePath)
if err != nil { if err != nil {
@@ -88,7 +68,14 @@ func (r *RcloneStorer) Put(ctx context.Context, key string, data io.Reader) erro
return fmt.Errorf("reading data: %w", err) return fmt.Errorf("reading data: %w", err)
} }
return r.upload(ctx, key, bytes.NewReader(buf)) // Upload the object
_, err = operations.Rcat(ctx, r.fsys, key,
io.NopCloser(bytes.NewReader(buf)), time.Now(), nil)
if err != nil {
return fmt.Errorf("uploading object: %w", err)
}
return nil
} }
// PutWithProgress stores data with progress reporting. // PutWithProgress stores data with progress reporting.
@@ -102,7 +89,13 @@ func (r *RcloneStorer) PutWithProgress(
callback: progress, callback: progress,
} }
return r.upload(ctx, key, pr) // Upload the object
_, err := operations.Rcat(ctx, r.fsys, key, io.NopCloser(pr), time.Now(), nil)
if err != nil {
return fmt.Errorf("uploading object: %w", err)
}
return nil
} }
// Get retrieves data from the specified key. // Get retrieves data from the specified key.
@@ -180,10 +173,6 @@ func (r *RcloneStorer) List(ctx context.Context, prefix string) ([]string, error
err := operations.ListFn(ctx, r.fsys, func(obj fs.Object) { err := operations.ListFn(ctx, r.fsys, func(obj fs.Object) {
key := obj.Remote() key := obj.Remote()
if strings.HasSuffix(key, tempSuffix) {
return
}
if prefix == "" || strings.HasPrefix(key, prefix) { if prefix == "" || strings.HasPrefix(key, prefix) {
keys = append(keys, key) keys = append(keys, key)
} }
@@ -213,15 +202,10 @@ func (r *RcloneStorer) ListStream(
} }
key := obj.Remote() key := obj.Remote()
if strings.HasSuffix(key, tempSuffix) {
return
}
if prefix == "" || strings.HasPrefix(key, prefix) { if prefix == "" || strings.HasPrefix(key, prefix) {
ch <- ObjectInfo{ ch <- ObjectInfo{
Key: key, Key: key,
Size: obj.Size(), Size: obj.Size(),
ModTime: obj.ModTime(ctx),
} }
} }
}) })
@@ -233,31 +217,6 @@ func (r *RcloneStorer) ListStream(
return ch return ch
} }
// DeletePartialUploads removes every object under prefix whose name ends
// in tempSuffix.
func (r *RcloneStorer) DeletePartialUploads(ctx context.Context, prefix string) error {
var partial []fs.Object
err := operations.ListFn(ctx, r.fsys, func(obj fs.Object) {
key := obj.Remote()
if strings.HasPrefix(key, prefix) && strings.HasSuffix(key, tempSuffix) {
partial = append(partial, obj)
}
})
if err != nil {
return fmt.Errorf("listing objects: %w", err)
}
for _, obj := range partial {
err = obj.Remove(ctx)
if err != nil {
return fmt.Errorf("removing object: %w", err)
}
}
return nil
}
// Info returns human-readable storage location information. // Info returns human-readable storage location information.
func (r *RcloneStorer) Info() Info { func (r *RcloneStorer) Info() Info {
location := r.remote location := r.remote
@@ -271,59 +230,6 @@ func (r *RcloneStorer) Info() Info {
} }
} }
// upload writes data to key. Where the remote has a server-side move, it
// writes under a temporary name ending in tempSuffix and moves the object
// onto key once it is complete, so a killed upload cannot leave a truncated
// object at key; a remote without one is written in place. List and
// ListStream skip a temporary object left behind.
//
// rclone's own copy does this only where the remote also sets
// PartialUploads. That flag is not checked here: hdfs, for one, shows a
// file while it is written without setting it.
func (r *RcloneStorer) upload(ctx context.Context, key string, data io.Reader) error {
if r.fsys.Features().Move == nil {
_, err := operations.Rcat(ctx, r.fsys, key, io.NopCloser(data), time.Now(), nil)
if err != nil {
return fmt.Errorf("uploading object: %w", err)
}
return nil
}
tempKey := key + "-" + rand.Text() + tempSuffix
obj, err := operations.Rcat(ctx, r.fsys, tempKey, io.NopCloser(data), time.Now(), nil)
if err != nil {
// Rcat returns the object it wrote when the written data fails its check.
if obj != nil {
_ = obj.Remove(ctx)
}
return fmt.Errorf("uploading object: %w", err)
}
// On drive, dropbox, onedrive and others the remote's own move does not
// replace an object already at key. operations.Move removes the object
// it is given first, and copies where the remote refuses the move.
existing, err := r.fsys.NewObject(ctx, key)
if errors.Is(err, fs.ErrorObjectNotFound) {
existing = nil
} else if err != nil {
_ = obj.Remove(ctx)
return fmt.Errorf("looking up existing object: %w", err)
}
_, err = operations.Move(ctx, r.fsys, existing, key, obj)
if err != nil {
_ = obj.Remove(ctx)
return fmt.Errorf("moving object into place: %w", err)
}
return nil
}
// progressReader wraps an io.Reader to track read progress. // progressReader wraps an io.Reader to track read progress.
type progressReader struct { type progressReader struct {
reader io.Reader reader io.Reader
+14 -462
View File
@@ -1,54 +1,28 @@
package storage_test package storage_test
import ( import (
"bytes"
"context" "context"
"errors" "errors"
"io"
"net/http"
"net/http/httptest"
"os"
"path/filepath"
"strings"
"sync/atomic"
"testing" "testing"
"time"
"github.com/johannesboyne/gofakes3"
"github.com/johannesboyne/gofakes3/backend/s3mem"
"github.com/rclone/rclone/fs"
"github.com/rclone/rclone/fs/config"
"github.com/rclone/rclone/fs/config/configmap"
"sneak.berlin/go/vaultik/internal/storage" "sneak.berlin/go/vaultik/internal/storage"
) )
// The rclone backend is a thin adapter over the rclone library: it turns a
// (remote, path) pair into rclone's "remote:path" string, hands it to
// rclone, and maps rclone's own results back to the Storer interface. What
// can be tested in-process, without a configured remote or network, is that
// adapter layer — how the arguments are shaped and how construction errors
// are reported. The data-plane operations (Put/Get/List/Delete) are rclone's
// own, exercised against a real provider (drive, s3-via-rclone, ...), which
// needs a configured remote with credentials and network access and so is
// out of reach of a unit test. The shared Storer conformance suite therefore
// runs against the in-process file and s3 backends; the rclone backend
// inherits that contract once a remote is configured.
//
// These tests use rclone's ":local:" on-the-fly backend, which addresses the // These tests use rclone's ":local:" on-the-fly backend, which addresses the
// local filesystem directly without any configured remote, so they run // local filesystem directly without any configured remote, so construction
// entirely in-process. A remote that needs credentials and network access // runs entirely in-process.
// (drive, s3 via rclone, ...) is out of reach of a unit test.
// newRcloneStorer builds an rclone backend on rclone's local backend,
// rooted at a fresh temp directory.
//
//nolint:ireturn // conformance runs against the Storer interface by design
func newRcloneStorer(t *testing.T) storage.Storer {
t.Helper()
s, err := storage.NewRcloneStorer(context.Background(), ":local", t.TempDir())
if err != nil {
t.Fatalf("NewRcloneStorer: %v", err)
}
return s
}
// TestRcloneStorer runs the shared Storer contract against the rclone
// backend.
//
//nolint:paralleltest // NewRcloneStorer installs the process-global rclone config
func TestRcloneStorer(t *testing.T) {
runStorerConformance(t, newRcloneStorer)
}
// TestNewRcloneStorerConstruction checks that a valid remote constructs a // TestNewRcloneStorerConstruction checks that a valid remote constructs a
// backend and that Info() reports the shaped "remote:path" location. // backend and that Info() reports the shaped "remote:path" location.
@@ -70,321 +44,6 @@ func TestNewRcloneStorerConstruction(t *testing.T) {
} }
} }
// unbufferedUploadContext returns a context in which rclone neither reads
// ahead of the write nor holds a small upload in memory. Without it, a
// progress callback runs before anything is written to the remote.
func unbufferedUploadContext() context.Context {
ctx, ci := fs.AddConfig(context.Background())
ci.BufferSize = 0
ci.StreamingUploadCutoff = 0
return ctx
}
// objectAtKeyDuringUpload uploads data to testBlobKey and reports whether
// an object was at the key before the upload finished. It fails the test
// unless the key then reads back as the uploaded data.
func objectAtKeyDuringUpload(
ctx context.Context, t *testing.T, s *storage.RcloneStorer,
) bool {
t.Helper()
data := bytes.Repeat([]byte("blob-bytes"), 1000)
seen := false
err := s.PutWithProgress(ctx, testBlobKey, bytes.NewReader(data),
int64(len(data)), func(int64) error {
_, statErr := s.Stat(ctx, testBlobKey)
if statErr == nil {
seen = true
}
return nil
})
if err != nil {
t.Fatalf("PutWithProgress: %v", err)
}
got := readObject(ctx, t, s, testBlobKey)
if !bytes.Equal(got, data) {
t.Errorf("object read back as %d bytes, want the %d uploaded",
len(got), len(data))
}
return seen
}
// readObject returns the contents of the object at key.
func readObject(
ctx context.Context, t *testing.T, s *storage.RcloneStorer, key string,
) []byte {
t.Helper()
rc, err := s.Get(ctx, key)
if err != nil {
t.Fatalf("Get: %v", err)
}
defer func() { _ = rc.Close() }()
got, err := io.ReadAll(rc)
if err != nil {
t.Fatalf("reading object: %v", err)
}
return got
}
// TestRcloneStorerObjectAppearsOnlyWhenComplete checks that on a remote
// with a server-side move, such as local, nothing is at the key until the
// upload has finished, so a killed upload cannot leave a truncated object
// there.
//
//nolint:paralleltest // NewRcloneStorer installs the process-global rclone config
func TestRcloneStorerObjectAppearsOnlyWhenComplete(t *testing.T) {
ctx := unbufferedUploadContext()
s, err := storage.NewRcloneStorer(ctx, ":local", t.TempDir())
if err != nil {
t.Fatalf("NewRcloneStorer: %v", err)
}
if objectAtKeyDuringUpload(ctx, t, s) {
t.Error("object was at its key before the upload finished")
}
}
// TestRcloneStorerListSkipsPartialFiles checks that a temporary file left
// by a killed upload is never listed as a key.
//
//nolint:paralleltest // NewRcloneStorer installs the process-global rclone config
func TestRcloneStorerListSkipsPartialFiles(t *testing.T) {
dir := t.TempDir()
ctx := context.Background()
s, err := storage.NewRcloneStorer(ctx, ":local", dir)
if err != nil {
t.Fatalf("NewRcloneStorer: %v", err)
}
realKey := testBlobKey
err = s.Put(ctx, realKey, strings.NewReader("blob-bytes"))
if err != nil {
t.Fatalf("Put: %v", err)
}
leftover := filepath.Join(dir, realKey+"-123456.partial")
err = os.WriteFile(leftover, []byte("half"), 0o600)
if err != nil {
t.Fatalf("writing leftover temp file: %v", err)
}
keys, err := s.List(ctx, "blobs/")
if err != nil {
t.Fatalf("List: %v", err)
}
if len(keys) != 1 || keys[0] != realKey {
t.Fatalf("List should return only the real key, got %v", keys)
}
var streamed []string
for obj := range s.ListStream(ctx, "blobs/") {
if obj.Err != nil {
t.Fatalf("ListStream: %v", obj.Err)
}
streamed = append(streamed, obj.Key)
}
if len(streamed) != 1 || streamed[0] != realKey {
t.Fatalf("ListStream should return only the real key, got %v", streamed)
}
}
// TestRcloneStorerDeletePartialUploads checks that a temporary file left
// by a killed upload is removed and the object at the real key is kept.
//
//nolint:paralleltest // NewRcloneStorer installs the process-global rclone config
func TestRcloneStorerDeletePartialUploads(t *testing.T) {
dir := t.TempDir()
ctx := context.Background()
s, err := storage.NewRcloneStorer(ctx, ":local", dir)
if err != nil {
t.Fatalf("NewRcloneStorer: %v", err)
}
err = s.Put(ctx, testBlobKey, strings.NewReader("blob-bytes"))
if err != nil {
t.Fatalf("Put: %v", err)
}
leftover := filepath.Join(dir, testBlobKey+"-123456.partial")
err = os.WriteFile(leftover, []byte("half"), 0o600)
if err != nil {
t.Fatalf("writing leftover temp file: %v", err)
}
err = s.DeletePartialUploads(ctx, "blobs/")
if err != nil {
t.Fatalf("DeletePartialUploads: %v", err)
}
_, err = os.Stat(leftover)
if !os.IsNotExist(err) {
t.Errorf("leftover temp file was not removed: %v", err)
}
_, err = s.Stat(ctx, testBlobKey)
if err != nil {
t.Errorf("Stat of the real key: %v", err)
}
}
// newRcloneStorerOnWrappedLocal registers name as rclone's local backend
// wrapped by wrap, and builds an rclone backend on it rooted at a fresh
// temp directory. wrap changes the features the local backend reports, so
// that it behaves like a remote a unit test cannot reach.
func newRcloneStorerOnWrappedLocal(
ctx context.Context, t *testing.T, name string, wrap func(fs.Fs) fs.Fs,
) *storage.RcloneStorer {
t.Helper()
fs.Register(&fs.RegInfo{
Name: name,
NewFs: func(
ctx context.Context, _, root string, _ configmap.Mapper,
) (fs.Fs, error) {
local, err := fs.NewFs(ctx, ":local:"+root)
if err != nil {
return nil, err
}
return wrap(local), nil
},
})
s, err := storage.NewRcloneStorer(ctx, ":"+name, t.TempDir())
if err != nil {
t.Fatalf("NewRcloneStorer: %v", err)
}
return s
}
// withoutPartialUploads is rclone's local backend with the PartialUploads
// flag cleared. Like hdfs, it then has a server-side move and shows a file
// while it is written, without setting that flag.
type withoutPartialUploads struct {
fs.Fs
}
func (f *withoutPartialUploads) Features() *fs.Features {
features := *f.Fs.Features()
features.PartialUploads = false
return &features
}
// TestRcloneStorerMovesIntoPlaceWithoutPartialUploads checks that on a
// remote with a server-side move nothing is at the key until the upload has
// finished, even when rclone does not mark the remote as showing partial
// uploads.
//
//nolint:paralleltest // NewRcloneStorer installs the process-global rclone config
func TestRcloneStorerMovesIntoPlaceWithoutPartialUploads(t *testing.T) {
ctx := unbufferedUploadContext()
s := newRcloneStorerOnWrappedLocal(ctx, t, "withoutpartialuploads",
func(local fs.Fs) fs.Fs { return &withoutPartialUploads{Fs: local} })
if objectAtKeyDuringUpload(ctx, t, s) {
t.Error("object was at its key before the upload finished")
}
}
// withoutMove is rclone's local backend reporting no server-side move.
type withoutMove struct {
fs.Fs
}
func (f *withoutMove) Features() *fs.Features {
features := *f.Fs.Features()
features.Move = nil
return &features
}
// TestRcloneStorerWritesInPlaceWithoutMove checks that on a remote with no
// server-side move an object is written straight to its key and reads back
// from there.
//
//nolint:paralleltest // NewRcloneStorer installs the process-global rclone config
func TestRcloneStorerWritesInPlaceWithoutMove(t *testing.T) {
ctx := unbufferedUploadContext()
s := newRcloneStorerOnWrappedLocal(ctx, t, "withoutmove",
func(local fs.Fs) fs.Fs { return &withoutMove{Fs: local} })
if !objectAtKeyDuringUpload(ctx, t, s) {
t.Error("object was not at its key while it was uploaded")
}
}
var errNameConflict = errors.New("an object with this name already exists")
// moveRefusesExisting is rclone's local backend with a server-side move
// that, like dropbox's or onedrive's, refuses to move onto an existing
// object.
type moveRefusesExisting struct {
fs.Fs
}
func (f *moveRefusesExisting) Features() *fs.Features {
features := *f.Fs.Features()
features.Move = f.move
return &features
}
//nolint:ireturn // the signature is rclone's
func (f *moveRefusesExisting) move(
ctx context.Context, src fs.Object, remote string,
) (fs.Object, error) {
_, err := f.NewObject(ctx, remote)
if err == nil {
return nil, errNameConflict
}
return f.Fs.Features().Move(ctx, src, remote)
}
// TestRcloneStorerOverwritesWhereMoveRefusesExisting checks that writing a
// key twice replaces the object on a remote whose server-side move will not
// replace an existing object.
//
//nolint:paralleltest // NewRcloneStorer installs the process-global rclone config
func TestRcloneStorerOverwritesWhereMoveRefusesExisting(t *testing.T) {
ctx := context.Background()
s := newRcloneStorerOnWrappedLocal(ctx, t, "moverefusesexisting",
func(local fs.Fs) fs.Fs { return &moveRefusesExisting{Fs: local} })
for _, content := range []string{"first", "second"} {
err := s.Put(ctx, testBlobKey, strings.NewReader(content))
if err != nil {
t.Fatalf("Put %q: %v", content, err)
}
}
got := readObject(ctx, t, s, testBlobKey)
if string(got) != "second" {
t.Errorf("object = %q, want %q", got, "second")
}
}
// TestNewRcloneStorerUnknownRemote checks that a remote that is not in the // TestNewRcloneStorerUnknownRemote checks that a remote that is not in the
// rclone config fails construction with the ErrRemoteNotFound sentinel, // rclone config fails construction with the ErrRemoteNotFound sentinel,
// rather than silently returning a backend pointed nowhere. // rather than silently returning a backend pointed nowhere.
@@ -397,110 +56,3 @@ func TestNewRcloneStorerUnknownRemote(t *testing.T) {
t.Errorf("NewRcloneStorer error = %v, want ErrRemoteNotFound", err) t.Errorf("NewRcloneStorer error = %v, want ErrRemoteNotFound", err)
} }
} }
// TestNewRcloneStorerReadsRcloneConfigEnv checks that a remote defined only
// in the file RCLONE_CONFIG names is found and written to, as rclone itself
// would.
func TestNewRcloneStorerReadsRcloneConfigEnv(t *testing.T) {
// rclone keeps the config file path in a process-global variable, which
// NewRcloneStorer leaves pointing at this test's file.
previous := config.GetConfigPath()
t.Cleanup(func() { _ = config.SetConfigPath(previous) })
confFile := filepath.Join(t.TempDir(), "rclone.conf")
err := os.WriteFile(confFile, []byte("[loc]\ntype = local\n"), 0o600)
if err != nil {
t.Fatalf("writing rclone config: %v", err)
}
t.Setenv("RCLONE_CONFIG", confFile)
dir := t.TempDir()
ctx := context.Background()
s, err := storage.NewRcloneStorer(ctx, "loc", dir)
if err != nil {
t.Fatalf("NewRcloneStorer: %v", err)
}
err = s.Put(ctx, testBlobKey, strings.NewReader("blob-bytes"))
if err != nil {
t.Fatalf("Put: %v", err)
}
_, err = os.Stat(filepath.Join(dir, testBlobKey))
if err != nil {
t.Errorf("object is not in the remote's directory: %v", err)
}
}
// TestRcloneListStreamOnS3MakesNoRequestPerObject checks that listing an
// rclone S3 remote takes each object's time from the listing itself. By
// default rclone reads the time it keeps in each object's metadata, one
// request per object, and every command that lists the destination store
// would slow down as it grows.
//
//nolint:paralleltest // NewRcloneStorer installs the process-global rclone config
func TestRcloneListStreamOnS3MakesNoRequestPerObject(t *testing.T) {
backend := s3mem.New()
err := backend.CreateBucket(s3TestBucket)
if err != nil {
t.Fatalf("create bucket: %v", err)
}
const body = "blob-bytes"
_, err = backend.PutObject(s3TestBucket, testBlobKey, nil,
strings.NewReader(body), int64(len(body)))
if err != nil {
t.Fatalf("seed object: %v", err)
}
var headRequests atomic.Int64
fakeS3 := gofakes3.New(backend).Server()
srv := httptest.NewServer(http.HandlerFunc(
func(w http.ResponseWriter, r *http.Request) {
if r.Method == http.MethodHead {
headRequests.Add(1)
}
fakeS3.ServeHTTP(w, r)
}))
t.Cleanup(srv.Close)
remote := ":s3,provider=Other" +
",access_key_id=" + s3TestAccessKeyID +
",secret_access_key=" + s3TestSecretAccessKey +
",endpoint='" + srv.URL + "'"
ctx := context.Background()
s, err := storage.NewRcloneStorer(ctx, remote, s3TestBucket)
if err != nil {
t.Fatalf("NewRcloneStorer: %v", err)
}
headRequests.Store(0)
var listed []storage.ObjectInfo
for info := range s.ListStream(ctx, "blobs/") {
listed = append(listed, info)
}
if len(listed) != 1 || listed[0].Err != nil {
t.Fatalf("ListStream(\"blobs/\") = %v, want the one object", listed)
}
if time.Since(listed[0].ModTime).Abs() > time.Minute {
t.Errorf("ListStream ModTime = %v, want within a minute of now",
listed[0].ModTime)
}
if n := headRequests.Load(); n != 0 {
t.Errorf("ListStream made %d HEAD request(s), want none", n)
}
}
+3 -10
View File
@@ -89,10 +89,9 @@ func (s *S3Storer) ListStream(ctx context.Context, prefix string) <-chan ObjectI
for info := range s.client.ListObjectsStream(ctx, prefix, false) { for info := range s.client.ListObjectsStream(ctx, prefix, false) {
ch <- ObjectInfo{ ch <- ObjectInfo{
Key: info.Key, Key: info.Key,
Size: info.Size, Size: info.Size,
ModTime: info.ModTime, Err: info.Err,
Err: info.Err,
} }
} }
}() }()
@@ -100,12 +99,6 @@ func (s *S3Storer) ListStream(ctx context.Context, prefix string) <-chan ObjectI
return ch return ch
} }
// DeletePartialUploads has nothing to remove: S3 shows an object only once
// its upload has completed, so an upload cut off part-way leaves none.
func (s *S3Storer) DeletePartialUploads(_ context.Context, _ string) error {
return nil
}
// Info returns human-readable storage location information. // Info returns human-readable storage location information.
func (s *S3Storer) Info() Info { func (s *S3Storer) Info() Info {
return Info{ return Info{
+3 -164
View File
@@ -1,15 +1,11 @@
package storage_test package storage_test
import ( import (
"bytes"
"context" "context"
"errors" "errors"
"io"
"net/http"
"net/http/httptest" "net/http/httptest"
"slices" "slices"
"strings" "strings"
"sync/atomic"
"testing" "testing"
"github.com/johannesboyne/gofakes3" "github.com/johannesboyne/gofakes3"
@@ -23,16 +19,6 @@ import (
// s3TestBucket is the bucket created for each in-process S3 server. // s3TestBucket is the bucket created for each in-process S3 server.
const s3TestBucket = "test-bucket" const s3TestBucket = "test-bucket"
// Credentials for the tests' S3 clients. The test servers accept any.
const (
s3TestAccessKeyID = "key"
s3TestSecretAccessKey = "secret"
)
// s3TestRegion is the region of the S3 clients built here with
// s3.NewClient. The test servers ignore it.
const s3TestRegion = "us-east-1"
// newS3Storer builds an s3:// backend backed by a fresh in-process // newS3Storer builds an s3:// backend backed by a fresh in-process
// S3 server. It reuses the same in-memory S3 harness (gofakes3 + s3mem // S3 server. It reuses the same in-memory S3 harness (gofakes3 + s3mem
// over httptest) that internal/s3 and the not-found regression test use, // over httptest) that internal/s3 and the not-found regression test use,
@@ -59,7 +45,7 @@ func newS3Storer(t *testing.T) storage.Storer {
Bucket: s3TestBucket, Bucket: s3TestBucket,
AccessKeyID: "test", AccessKeyID: "test",
SecretAccessKey: "test", SecretAccessKey: "test",
Region: s3TestRegion, Region: "us-east-1",
}) })
if err != nil { if err != nil {
t.Fatalf("new client: %v", err) t.Fatalf("new client: %v", err)
@@ -97,69 +83,6 @@ func TestS3StorerMissingKeyMapsToErrNotFound(t *testing.T) {
} }
} }
// TestS3ListingCutShortIsAnError checks that List and ListStream fail on a
// listing page marked truncated that carries no continuation token, as a
// server answering V2 listings V1-style sends it. Taken as the last page,
// it would hide every later key: prune would treat the blobs of the
// snapshots listed there as unreferenced, and a directory under metadata/
// whose manifest is listed there as one with no manifest.
func TestS3ListingCutShortIsAnError(t *testing.T) {
t.Parallel()
const (
prefix = "metadata/"
truncatedPage = `<?xml version="1.0" encoding="UTF-8"?>
<ListBucketResult xmlns="http://s3.amazonaws.com/doc/2006-03-01/">
<Name>test-bucket</Name>
<Prefix>metadata/</Prefix>
<KeyCount>1</KeyCount>
<MaxKeys>1</MaxKeys>
<IsTruncated>true</IsTruncated>
<Contents>
<Key>metadata/snap/manifest.json.zst</Key>
<Size>8</Size>
</Contents>
</ListBucketResult>`
)
srv := httptest.NewServer(http.HandlerFunc(
func(w http.ResponseWriter, _ *http.Request) {
_, _ = io.WriteString(w, truncatedPage)
}))
t.Cleanup(srv.Close)
client, err := s3.NewClient(context.Background(), s3.Config{
Endpoint: srv.URL,
Bucket: s3TestBucket,
AccessKeyID: s3TestAccessKeyID,
SecretAccessKey: s3TestSecretAccessKey,
Region: s3TestRegion,
})
if err != nil {
t.Fatalf("new client: %v", err)
}
storer := storage.NewS3Storer(client)
ctx := context.Background()
keys, err := storer.List(ctx, prefix)
if !errors.Is(err, s3.ErrNoContinuationToken) {
t.Errorf("List = %q, %v; want ErrNoContinuationToken", keys, err)
}
var streamErr error
for obj := range storer.ListStream(ctx, prefix) {
if obj.Err != nil {
streamErr = obj.Err
}
}
if !errors.Is(streamErr, s3.ErrNoContinuationToken) {
t.Errorf("ListStream error = %v, want ErrNoContinuationToken", streamErr)
}
}
// TestS3URLPrefixKeyLayout pins the bucket keys an s3:// URL reads and // TestS3URLPrefixKeyLayout pins the bucket keys an s3:// URL reads and
// writes: the README's remote storage layout, with the prefix joined to // writes: the README's remote storage layout, with the prefix joined to
// each key by one "/". s3://b/p and s3://b/p/ must be the same // each key by one "/". s3://b/p and s3://b/p/ must be the same
@@ -205,8 +128,8 @@ func TestS3URLPrefixKeyLayout(t *testing.T) {
storer, err := storage.NewStorer(&config.Config{ storer, err := storage.NewStorer(&config.Config{
StorageURL: storageURL + "?endpoint=" + srv.URL, StorageURL: storageURL + "?endpoint=" + srv.URL,
S3: config.S3Config{ S3: config.S3Config{
AccessKeyID: s3TestAccessKeyID, AccessKeyID: "key",
SecretAccessKey: s3TestSecretAccessKey, SecretAccessKey: "secret",
}, },
}) })
if err != nil { if err != nil {
@@ -248,90 +171,6 @@ func TestS3URLPrefixKeyLayout(t *testing.T) {
} }
} }
// TestS3UploadUsesConfiguredPartSize checks that s3.part_size reaches the
// multipart uploader, through storage_url and through the s3.* fields. An
// object three parts long must arrive as three parts; at the SDK's default
// of 5 MiB it would arrive as four.
func TestS3UploadUsesConfiguredPartSize(t *testing.T) {
t.Parallel()
const (
partSize = 6 * 1024 * 1024
wantParts = 3
)
backend := s3mem.New()
err := backend.CreateBucket(s3TestBucket)
if err != nil {
t.Fatalf("create bucket: %v", err)
}
// Every part of a multipart upload is one request with a partNumber.
var parts atomic.Int32
fake := gofakes3.New(backend).Server()
srv := httptest.NewServer(http.HandlerFunc(
func(w http.ResponseWriter, r *http.Request) {
if r.URL.Query().Has("partNumber") {
parts.Add(1)
}
fake.ServeHTTP(w, r)
}))
t.Cleanup(srv.Close)
cases := []struct {
name string
cfg *config.Config
}{
{
name: "storage_url",
cfg: &config.Config{
StorageURL: "s3://" + s3TestBucket + "?endpoint=" + srv.URL,
S3: config.S3Config{
AccessKeyID: s3TestAccessKeyID,
SecretAccessKey: s3TestSecretAccessKey,
PartSize: partSize,
},
},
},
{
name: "s3.endpoint",
cfg: &config.Config{
S3: config.S3Config{
Endpoint: srv.URL,
Bucket: s3TestBucket,
AccessKeyID: s3TestAccessKeyID,
SecretAccessKey: s3TestSecretAccessKey,
PartSize: partSize,
},
},
},
}
for _, tc := range cases {
parts.Store(0)
storer, err := storage.NewStorer(tc.cfg)
if err != nil {
t.Fatalf("%s: NewStorer: %v", tc.name, err)
}
data := bytes.NewReader(make([]byte, wantParts*partSize))
err = storer.PutWithProgress(
context.Background(), "blob", data, data.Size(), nil)
if err != nil {
t.Fatalf("%s: PutWithProgress: %v", tc.name, err)
}
if got := parts.Load(); got != wantParts {
t.Errorf("%s: uploaded in %d parts, want %d", tc.name, got, wantParts)
}
}
}
// listStreamKeys returns the keys ListStream yields under a prefix, and // listStreamKeys returns the keys ListStream yields under a prefix, and
// fails the test on a listing error. // fails the test on a listing error.
func listStreamKeys(t *testing.T, s storage.Storer, prefix string) []string { func listStreamKeys(t *testing.T, s storage.Storer, prefix string) []string {
+3 -15
View File
@@ -14,7 +14,6 @@ import (
"context" "context"
"errors" "errors"
"io" "io"
"time"
) )
// ErrNotFound is returned when an object does not exist. // ErrNotFound is returned when an object does not exist.
@@ -28,10 +27,7 @@ type ProgressCallback func(bytesTransferred int64) error
type ObjectInfo struct { type ObjectInfo struct {
Key string // Object key/path Key string // Object key/path
Size int64 // Size in bytes Size int64 // Size in bytes
// ModTime is when the object was written, as the store reports it. Err error // Error for streaming results (nil on success)
// Only ListStream sets it; Stat leaves it zero.
ModTime time.Time
Err error // Error for streaming results (nil on success)
} }
// Info provides human-readable storage configuration. // Info provides human-readable storage configuration.
@@ -45,8 +41,7 @@ type Info struct {
// directory for filesystem). // directory for filesystem).
type Storer interface { type Storer interface {
// Put stores data at the specified key. // Put stores data at the specified key.
// The filesystem backend fails when its destination directory does // Parent directories are created automatically for filesystem backends.
// not exist, and creates the directories below it as needed.
Put(ctx context.Context, key string, data io.Reader) error Put(ctx context.Context, key string, data io.Reader) error
// PutWithProgress stores data with progress reporting. // PutWithProgress stores data with progress reporting.
@@ -71,18 +66,11 @@ type Storer interface {
// For large result sets, prefer ListStream. // For large result sets, prefer ListStream.
List(ctx context.Context, prefix string) ([]string, error) List(ctx context.Context, prefix string) ([]string, error)
// ListStream returns a channel of ObjectInfo, with each object's key, // ListStream returns a channel of ObjectInfo for large result sets.
// size and modification time, for large result sets.
// The channel is closed when listing completes. // The channel is closed when listing completes.
// If an error occurs during listing, the final item will have Err set. // If an error occurs during listing, the final item will have Err set.
ListStream(ctx context.Context, prefix string) <-chan ObjectInfo ListStream(ctx context.Context, prefix string) <-chan ObjectInfo
// DeletePartialUploads removes every object under prefix that an
// upload cut off part-way left under a temporary name ending in
// `.partial`. The file and rclone backends' List and ListStream skip
// such an object.
DeletePartialUploads(ctx context.Context, prefix string) error
// Info returns human-readable storage location information. // Info returns human-readable storage location information.
Info() Info Info() Info
} }
+18 -73
View File
@@ -17,10 +17,8 @@ const (
// Sentinel errors for storage URL parsing. // Sentinel errors for storage URL parsing.
var ( var (
ErrEmptyStorageURL = errors.New("storage URL is empty") ErrEmptyStorageURL = errors.New("storage URL is empty")
ErrEmptyFilePath = errors.New("file URL path is empty") ErrEmptyFilePath = errors.New("file URL path is empty")
ErrRelativeFilePath = errors.New(
"file URL needs an absolute path, as in file:///path/to/backup")
ErrMissingBucket = errors.New("s3 URL missing bucket name") ErrMissingBucket = errors.New("s3 URL missing bucket name")
ErrMissingRemote = errors.New("rclone URL missing remote name") ErrMissingRemote = errors.New("rclone URL missing remote name")
ErrUnsupportedScheme = errors.New( ErrUnsupportedScheme = errors.New(
@@ -30,12 +28,6 @@ var (
"storage URL must not carry credentials; " + "storage URL must not carry credentials; " +
"set s3.access_key_id and s3.secret_access_key in the config instead") "set s3.access_key_id and s3.secret_access_key in the config instead")
ErrURLUnknownParam = errors.New("unknown query parameter in storage URL") ErrURLUnknownParam = errors.New("unknown query parameter in storage URL")
ErrURLBadQuery = errors.New(
"storage URL query cannot be decoded; " +
"check it for a ; or a % not followed by two hex digits")
ErrRcloneRemoteParams = errors.New(
"rclone URL must not carry parameters in the remote name; " +
"set them on the remote with rclone config instead")
) )
// URL represents a parsed storage URL. // URL represents a parsed storage URL.
@@ -59,8 +51,17 @@ func ParseStorageURL(rawURL string) (*URL, error) {
return nil, ErrEmptyStorageURL return nil, ErrEmptyStorageURL
} }
// Handle file:// URLs
if after, ok := strings.CutPrefix(rawURL, "file://"); ok { if after, ok := strings.CutPrefix(rawURL, "file://"); ok {
return parseFileURL(after) path := after
if path == "" {
return nil, ErrEmptyFilePath
}
return &URL{
Scheme: schemeFile,
Prefix: path,
}, nil
} }
if strings.HasPrefix(rawURL, "s3://") { if strings.HasPrefix(rawURL, "s3://") {
@@ -74,31 +75,9 @@ func ParseStorageURL(rawURL string) (*URL, error) {
return nil, ErrUnsupportedScheme return nil, ErrUnsupportedScheme
} }
// parseFileURL parses the path that follows file://. The path must be
// absolute: a relative one would resolve against the working directory,
// so the destination would move with it. Percent-escapes are decoded, so
// my%20stick names the directory "my stick"; a literal space is kept.
func parseFileURL(rawPath string) (*URL, error) {
if rawPath == "" {
return nil, ErrEmptyFilePath
}
if !strings.HasPrefix(rawPath, "/") {
return nil, ErrRelativeFilePath
}
path, err := url.PathUnescape(rawPath)
if err != nil {
return nil, fmt.Errorf("invalid file URL path: %w", err)
}
return &URL{Scheme: schemeFile, Prefix: path}, nil
}
// parseS3URL parses an s3://bucket/prefix URL. It rejects credentials in // parseS3URL parses an s3://bucket/prefix URL. It rejects credentials in
// the userinfo or in the endpoint parameter's userinfo, a query that // the userinfo and any query parameter other than endpoint, region and
// cannot be decoded, and any query parameter other than endpoint, region // ssl, so a credential-bearing URL is never stored or echoed.
// and ssl, so a credential-bearing URL is never stored or echoed.
func parseS3URL(rawURL string) (*URL, error) { func parseS3URL(rawURL string) (*URL, error) {
u, err := url.Parse(rawURL) u, err := url.Parse(rawURL)
if err != nil { if err != nil {
@@ -114,26 +93,13 @@ func parseS3URL(rawURL string) (*URL, error) {
return nil, ErrMissingBucket return nil, ErrMissingBucket
} }
// u.Query() would silently drop a part it cannot decode, endpoint query := u.Query()
// included. The decode error is not wrapped: it can quote the value.
query, err := url.ParseQuery(u.RawQuery)
if err != nil {
return nil, ErrURLBadQuery
}
err = rejectUnknownParams(query, "endpoint", "region", "ssl") err = rejectUnknownParams(query, "endpoint", "region", "ssl")
if err != nil { if err != nil {
return nil, err return nil, err
} }
// A host name never contains "@", so one in an endpoint, with or
// without a scheme, can only introduce userinfo.
for _, endpoint := range query["endpoint"] {
if strings.Contains(endpoint, "@") {
return nil, ErrURLCredentials
}
}
return &URL{ return &URL{
Scheme: schemeS3, Scheme: schemeS3,
Bucket: bucket, Bucket: bucket,
@@ -145,23 +111,9 @@ func parseS3URL(rawURL string) (*URL, error) {
} }
// parseRcloneURL parses an rclone://remote/path URL. rclone:// takes no // parseRcloneURL parses an rclone://remote/path URL. rclone:// takes no
// query parameters, so credentials in the userinfo, parameters in the // query parameters, so credentials in the userinfo and any parameter at
// remote name, a query that cannot be decoded and any query parameter at
// all are rejected rather than silently ignored. // all are rejected rather than silently ignored.
func parseRcloneURL(rawURL string) (*URL, error) { func parseRcloneURL(rawURL string) (*URL, error) {
// The remote name runs up to the first "/", "?" or "#". It never
// contains a comma; one starts rclone's remote,param=value form,
// whose values can be credentials. This is checked before url.Parse,
// whose error for such a name can print part of it.
remote := strings.TrimPrefix(rawURL, "rclone://")
if end := strings.IndexAny(remote, "/?#"); end >= 0 {
remote = remote[:end]
}
if strings.Contains(remote, ",") {
return nil, ErrRcloneRemoteParams
}
u, err := url.Parse(rawURL) u, err := url.Parse(rawURL)
if err != nil { if err != nil {
return nil, wrapParseError(err) return nil, wrapParseError(err)
@@ -171,19 +123,12 @@ func parseRcloneURL(rawURL string) (*URL, error) {
return nil, ErrURLCredentials return nil, ErrURLCredentials
} }
remote = u.Host remote := u.Host
if remote == "" { if remote == "" {
return nil, ErrMissingRemote return nil, ErrMissingRemote
} }
// As in parseS3URL: u.Query() would drop a part it cannot decode, and err = rejectUnknownParams(u.Query())
// the decode error can quote the value.
query, err := url.ParseQuery(u.RawQuery)
if err != nil {
return nil, ErrURLBadQuery
}
err = rejectUnknownParams(query)
if err != nil { if err != nil {
return nil, err return nil, err
} }
+2 -135
View File
@@ -14,10 +14,7 @@ import (
func TestParseStorageURLValid(t *testing.T) { func TestParseStorageURLValid(t *testing.T) {
t.Parallel() t.Parallel()
const ( const bucket = "mybucket"
bucket = "mybucket"
fileScheme = "file"
)
cases := []struct { cases := []struct {
name string name string
@@ -27,17 +24,7 @@ func TestParseStorageURLValid(t *testing.T) {
{ {
name: "file absolute path", name: "file absolute path",
raw: "file:///var/backups/vaultik", raw: "file:///var/backups/vaultik",
want: &storage.URL{Scheme: fileScheme, Prefix: "/var/backups/vaultik"}, want: &storage.URL{Scheme: "file", Prefix: "/var/backups/vaultik"},
},
{
name: "file percent-escaped path is decoded",
raw: "file:///Volumes/my%20stick/backup",
want: &storage.URL{Scheme: fileScheme, Prefix: "/Volumes/my stick/backup"},
},
{
name: "file path with a literal space",
raw: "file:///Volumes/my stick/backup",
want: &storage.URL{Scheme: fileScheme, Prefix: "/Volumes/my stick/backup"},
}, },
{ {
name: "s3 bucket and prefix, ssl defaults on", name: "s3 bucket and prefix, ssl defaults on",
@@ -103,7 +90,6 @@ func TestParseStorageURLErrors(t *testing.T) {
}{ }{
{"empty url", "", storage.ErrEmptyStorageURL}, {"empty url", "", storage.ErrEmptyStorageURL},
{"file empty path", "file://", storage.ErrEmptyFilePath}, {"file empty path", "file://", storage.ErrEmptyFilePath},
{"file relative path", "file://dest", storage.ErrRelativeFilePath},
{"s3 missing bucket", "s3://", storage.ErrMissingBucket}, {"s3 missing bucket", "s3://", storage.ErrMissingBucket},
{"s3 missing bucket with path", "s3:///justprefix", storage.ErrMissingBucket}, {"s3 missing bucket with path", "s3:///justprefix", storage.ErrMissingBucket},
{"rclone missing remote", "rclone://", storage.ErrMissingRemote}, {"rclone missing remote", "rclone://", storage.ErrMissingRemote},
@@ -150,19 +136,6 @@ func TestParseStorageURLRejectsCredentials(t *testing.T) {
wantErr: storage.ErrURLCredentials, wantErr: storage.ErrURLCredentials,
secrets: []string{key, secret, "mybucket"}, secrets: []string{key, secret, "mybucket"},
}, },
{
name: "s3 userinfo in endpoint",
raw: "s3://mybucket?endpoint=https://" +
key + ":" + secret + "@minio.example.com",
wantErr: storage.ErrURLCredentials,
secrets: []string{key, secret},
},
{
name: "s3 userinfo in endpoint without scheme",
raw: "s3://mybucket?endpoint=" + key + ":" + secret + "@minio.example.com",
wantErr: storage.ErrURLCredentials,
secrets: []string{key, secret},
},
{ {
name: "s3 unknown query param", name: "s3 unknown query param",
raw: "s3://mybucket?access_key=" + key + "&secret=" + secret, raw: "s3://mybucket?access_key=" + key + "&secret=" + secret,
@@ -216,112 +189,6 @@ func TestParseStorageURLRejectsCredentials(t *testing.T) {
} }
} }
// TestParseStorageURLRejectsRcloneRemoteParams checks that an rclone
// remote name carrying parameters (rclone's "remote,param=value" form,
// which can hold a credential) is rejected without echoing the value,
// including the URLs that url.Parse itself refuses.
func TestParseStorageURLRejectsRcloneRemoteParams(t *testing.T) {
t.Parallel()
cases := []struct {
name string
raw string
secrets []string // must not appear in the error message
}{
{
name: "configured remote",
raw: "rclone://gdrive,client_secret=topsecret/backups",
secrets: []string{"topsecret"},
},
{
name: "remote defined inline",
raw: "rclone://:s3,access_key_id=KEY,secret_access_key=SECRET/bucket",
secrets: []string{"KEY", "SECRET"},
},
{
name: "colon in a parameter value",
raw: "rclone://gdrive,client_secret=ab:cd/backups",
secrets: []string{"cd"},
},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
_, err := storage.ParseStorageURL(tc.raw)
if !errors.Is(err, storage.ErrRcloneRemoteParams) {
t.Fatalf("ParseStorageURL(%q) error = %v, want %v",
tc.raw, err, storage.ErrRcloneRemoteParams)
}
for _, secret := range tc.secrets {
if strings.Contains(err.Error(), secret) {
t.Errorf("error message leaked %q: %v", secret, err.Error())
}
}
})
}
}
// TestParseStorageURLRejectsUndecodableQuery checks that an s3 or rclone
// URL whose query cannot be decoded is rejected, not read with that part
// of the query left out, and that the error does not echo it.
func TestParseStorageURLRejectsUndecodableQuery(t *testing.T) {
t.Parallel()
const (
key = "AKIAKEY"
secret = "topsecret"
)
cases := []struct {
name string
raw string
}{
{
name: "semicolon",
raw: "s3://mybucket/prefix?endpoint=https://" + key + ":" + secret +
"@minio.example.com:9000;region=us-east-1",
},
{
name: "bad percent escape",
raw: "s3://mybucket/prefix?endpoint=https://" + key + ":" + secret +
"%zz@minio.example.com:9000",
},
{
name: "rclone semicolon",
raw: "rclone://gdrive/backups?token=" + secret + ";x=1",
},
{
name: "rclone bad percent escape",
raw: "rclone://gdrive/backups?token=" + secret + "%zz",
},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
_, err := storage.ParseStorageURL(tc.raw)
if err == nil {
t.Fatalf("ParseStorageURL(%q) returned no error", tc.raw)
}
if !errors.Is(err, storage.ErrURLBadQuery) {
t.Errorf("ParseStorageURL(%q) error = %v, want %v",
tc.raw, err, storage.ErrURLBadQuery)
}
for _, s := range []string{key, secret, "minio.example.com"} {
if strings.Contains(err.Error(), s) {
t.Errorf("error message leaked %q: %v", s, err.Error())
}
}
})
}
}
// TestParseStorageURLParseFailureHidesURL checks that when url.Parse // TestParseStorageURLParseFailureHidesURL checks that when url.Parse
// itself fails, the wrapped error carries only the inner cause, not the // itself fails, the wrapped error carries only the inner cause, not the
// *url.Error whose text embeds the raw (possibly credential-bearing) URL. // *url.Error whose text embeds the raw (possibly credential-bearing) URL.
+2 -2
View File
@@ -155,8 +155,8 @@ type BlobHash string
// FilePath represents an absolute path to a file or directory. // FilePath represents an absolute path to a file or directory.
type FilePath string type FilePath string
// SourcePath is the source directory a scan found a file under, made // SourcePath represents the root directory from which files are backed up.
// absolute and with symlinks resolved. // Used during restore to strip the source prefix from paths.
type SourcePath string type SourcePath string
// Hostname identifies a host machine. // Hostname identifies a host machine.
+2 -47
View File
@@ -103,9 +103,6 @@ func (v *Vaultik) FetchAndDecryptBlob(
} }
// FetchBlob downloads a blob and returns a reader for the encrypted data. // FetchBlob downloads a blob and returns a reader for the encrypted data.
// The reader is closed as soon as ctx is cancelled, which ends a read
// blocked inside it. A storage error is returned as is: restore and deep
// verify name the blob in their own errors.
func (v *Vaultik) FetchBlob( func (v *Vaultik) FetchBlob(
ctx context.Context, blobHash string, ctx context.Context, blobHash string,
) (io.ReadCloser, error) { ) (io.ReadCloser, error) {
@@ -120,50 +117,8 @@ func (v *Vaultik) FetchBlob(
rc, err := v.Storage.Get(ctx, blobPath) rc, err := v.Storage.Get(ctx, blobPath)
if err != nil { if err != nil {
return nil, err return nil, fmt.Errorf("downloading blob %s: %w", shortHash(blobHash), err)
} }
return newCloseOnCancelReader(ctx, rc), nil return rc, nil
}
// closeOnCancelReader closes the reader it wraps when ctx is cancelled.
// Not every backend's reader stops on cancel by itself (the file
// backend's does not), and a read stalled on a slow or hung source would
// otherwise outlast the shutdown timeout, so the process would exit
// before restore or deep verify removed its decrypted temporary files.
type closeOnCancelReader struct {
io.ReadCloser
ctx context.Context //nolint:containedctx // Read reports its error
stop func() bool
}
func newCloseOnCancelReader(
ctx context.Context, rc io.ReadCloser,
) *closeOnCancelReader {
return &closeOnCancelReader{
ReadCloser: rc,
ctx: ctx,
stop: context.AfterFunc(ctx, func() { _ = rc.Close() }),
}
}
// Read returns the context's error, not the closed reader's, once ctx
// has been cancelled.
func (r *closeOnCancelReader) Read(p []byte) (int, error) {
n, err := r.ReadCloser.Read(p)
if err != nil && r.ctx.Err() != nil {
return n, r.ctx.Err()
}
return n, err
}
// Close closes the wrapped reader, unless the cancel already closed it.
func (r *closeOnCancelReader) Close() error {
if !r.stop() {
return nil
}
return r.ReadCloser.Close()
} }
+3 -3
View File
@@ -39,9 +39,9 @@ type blobDiskCacheEntry struct {
// internally and will fall back to LRU eviction if curBytes exceeds // internally and will fall back to LRU eviction if curBytes exceeds
// maxBytes. Restore passes math.MaxInt64 as maxBytes and drives // maxBytes. Restore passes math.MaxInt64 as maxBytes and drives
// eviction itself via Delete() through restoreSweeper, which deletes // eviction itself via Delete() through restoreSweeper, which deletes
// each blob once no file still to be restored in this run needs it. // each blob the moment every file that references its chunks has been
// LRU never fires under that configuration; it is kept as a safety net // written. LRU never fires under that configuration; it is kept as a
// for callers that don't manage eviction themselves. // safety net for callers that don't manage eviction themselves.
// //
// Get/ReadAt/peak-Len counters are debugging instrumentation used by // Get/ReadAt/peak-Len counters are debugging instrumentation used by
// tests to assert that the restore code path uses ReadAt rather than // tests to assert that the restore code path uses ReadAt rather than
@@ -130,14 +130,15 @@ func assertThirdSnapshotRestores(
// up, and that snapshot is removed. The first snapshot keeps the file row, // up, and that snapshot is removed. The first snapshot keeps the file row,
// which now lists the appended content's chunks, while removal drops the // which now lists the appended content's chunks, while removal drops the
// blob that held them. // blob that held them.
//
//nolint:paralleltest // installs the global logger via log.Initialize
func TestBackupAfterRemovingNewestSnapshotRestoresChangedFile(t *testing.T) { func TestBackupAfterRemovingNewestSnapshotRestoresChangedFile(t *testing.T) {
log.Initialize(log.Config{}) log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs() fs := afero.NewOsFs()
tempDir := t.TempDir() tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src") dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir() storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored") restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite") dbPath := filepath.Join(tempDir, "index.sqlite")
changedPath := filepath.Join(dataDir, "appended.bin") changedPath := filepath.Join(dataDir, "appended.bin")
@@ -177,14 +178,15 @@ func TestBackupAfterRemovingNewestSnapshotRestoresChangedFile(t *testing.T) {
// The next run's prune drops that incomplete snapshot and its blob, while // The next run's prune drops that incomplete snapshot and its blob, while
// the first snapshot keeps the file row, which now lists the appended // the first snapshot keeps the file row, which now lists the appended
// content's chunks. // content's chunks.
//
//nolint:paralleltest // installs the global logger via log.Initialize
func TestBackupAfterInterruptedRunRestoresChangedFile(t *testing.T) { func TestBackupAfterInterruptedRunRestoresChangedFile(t *testing.T) {
log.Initialize(log.Config{}) log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs() fs := afero.NewOsFs()
tempDir := t.TempDir() tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src") dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir() storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored") restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite") dbPath := filepath.Join(tempDir, "index.sqlite")
changedPath := filepath.Join(dataDir, "appended.bin") changedPath := filepath.Join(dataDir, "appended.bin")
+1 -180
View File
@@ -1,20 +1,15 @@
package vaultik_test package vaultik_test
import ( import (
"bytes"
"context" "context"
"crypto/rand"
"io" "io"
"os" "os"
"path"
"path/filepath" "path/filepath"
"testing" "testing"
"github.com/spf13/afero" "github.com/spf13/afero"
"github.com/stretchr/testify/require" "github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/log" "sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/ui" "sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik" "sneak.berlin/go/vaultik/internal/vaultik"
) )
@@ -35,7 +30,7 @@ func TestDeepVerifyAcceptsHealthyAndRejectsCorruptBlob(t *testing.T) {
tempDir := t.TempDir() tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source") dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir() storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite") dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(64 * 1024) chunkSize := int64(64 * 1024)
@@ -82,180 +77,6 @@ func TestDeepVerifyAcceptsHealthyAndRejectsCorruptBlob(t *testing.T) {
"deep verify should fail on a corrupted blob") "deep verify should fail on a corrupted blob")
} }
// TestDeepVerifyJSONCountsBlobs checks the verified and missing counts
// that deep verify reports under --json: on a healthy snapshot, with a
// damaged blob, and with missing blobs. Deep verify stops at the first
// damaged blob, so the blobs read before it are the ones verified; when
// blobs are missing it reads no blob contents, but counts every missing
// blob.
func TestDeepVerifyJSONCountsBlobs(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
ctx := context.Background()
storeDir := t.TempDir()
cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
healthy, err := deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
require.NoError(t, err)
require.Equal(t, "ok", healthy.Status)
require.Len(t, keys, healthy.BlobCount)
require.Equal(t, healthy.BlobCount, healthy.Verified)
require.Zero(t, healthy.Missing)
// Damage the last blob read, keeping its length, so every blob before
// it is read and passes first.
lastPath := filepath.Join(storeDir, keys[len(keys)-1])
blob, err := afero.ReadFile(fs, lastPath)
require.NoError(t, err)
blob[len(blob)/2] ^= 0xff
require.NoError(t, afero.WriteFile(fs, lastPath, blob, 0o600))
got, err := deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
require.Error(t, err)
require.Equal(t, "failed", got.Status)
require.Equal(t, healthy.BlobCount-1, got.Verified)
require.Zero(t, got.Missing)
// Delete the first blob and the damaged last one: both must be
// counted as missing, not only the first one found.
var deletedSize int64
for _, key := range []string{keys[0], keys[len(keys)-1]} {
info, statErr := storer.Stat(ctx, key)
require.NoError(t, statErr)
deletedSize += info.Size
require.NoError(t, storer.Delete(ctx, key))
}
got, err = deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
require.Error(t, err)
require.Equal(t, "failed", got.Status)
require.Equal(t, 2, got.Missing)
require.Equal(t, deletedSize, got.MissingSize)
require.Zero(t, got.Verified)
}
// TestDeepVerifyJSONCountsWrongSizeBlob checks that under --deep --json a
// blob of the wrong size is counted in mismatched and fails the run, and
// that the check goes on past it to count a missing blob after it. The
// store is on disk, so the message must not call it S3.
func TestDeepVerifyJSONCountsWrongSizeBlob(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
ctx := context.Background()
storeDir := t.TempDir()
cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
// Make the first blob checked longer, and delete the last one.
firstPath := filepath.Join(storeDir, keys[0])
blob, err := afero.ReadFile(fs, firstPath)
require.NoError(t, err)
blob = append(blob, []byte("extra")...)
require.NoError(t, afero.WriteFile(fs, firstPath, blob, 0o600))
require.NoError(t, storer.Delete(ctx, keys[len(keys)-1]))
got, err := deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
require.Error(t, err)
require.Equal(t, "failed", got.Status)
require.Equal(t, 1, got.Mismatched)
require.Equal(t, 1, got.Missing)
require.Zero(t, got.Verified)
require.Contains(t, got.ErrorMessage, "with the wrong size")
require.NotContains(t, got.ErrorMessage, "S3")
}
// TestDeepVerifyStopsOnBlobThatCannotBeChecked checks that a blob that is
// present in storage but cannot be checked is not counted as missing:
// deep verify stops and fails, saying it could not check the blob, with
// the storage error.
func TestDeepVerifyStopsOnBlobThatCannotBeChecked(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
storeDir := t.TempDir()
cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
failing := statFailingStorer{Storer: storer, failKeys: []string{keys[0]}}
got, err := deepVerifyJSON(ctx, t, cfg, failing, snapshotID)
require.Error(t, err)
require.Equal(t, "failed", got.Status)
require.Zero(t, got.Missing)
require.Contains(t, got.ErrorMessage,
"could not check blob "+path.Base(keys[0]))
require.Contains(t, got.ErrorMessage, errStatDenied.Error())
}
// backUpSeveralBlobs backs up random data, which does not compress or
// deduplicate, so it fills at least three blobs in a store on disk at
// storeDir. It returns the blobs' storage keys sorted, which is hash
// order, the order deep verify reads them in.
func backUpSeveralBlobs(
ctx context.Context, t *testing.T, storeDir string,
) (*config.Config, *storage.FileStorer, string, []string) {
t.Helper()
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
maxBlobSize := int64(128 * 1024)
data := make([]byte, maxBlobSize*4)
_, err := rand.Read(data)
require.NoError(t, err)
require.NoError(t, fs.MkdirAll(dataDir, 0o755))
require.NoError(t, afero.WriteFile(fs,
filepath.Join(dataDir, "data.bin"), data, 0o644))
cfg, storer, snapshotID := runFileStorageBackup(
ctx, t, fs, dataDir, storeDir, dbPath, chunkSize, maxBlobSize)
keys := storedBlobKeys(t, storeDir)
require.GreaterOrEqual(t, len(keys), 3)
return cfg, storer, snapshotID, keys
}
// deepVerifyJSON runs deep verify with --json on snapshotID and returns
// the decoded result and the error RunDeepVerify returned.
func deepVerifyJSON(
ctx context.Context, t *testing.T,
cfg *config.Config, storer storage.Storer, snapshotID string,
) (vaultik.VerifyResult, error) {
t.Helper()
var out bytes.Buffer
v := &vaultik.Vaultik{
Config: cfg,
Storage: storer,
Fs: afero.NewOsFs(),
Stdout: &out,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
v.SetContext(ctx)
err := v.RunDeepVerify(snapshotID,
&vaultik.VerifyOptions{Deep: true, JSON: true})
return decodeVerifyResult(t, out.Bytes()), err
}
// corruptOneBlob flips a middle byte of the first blob file found under // corruptOneBlob flips a middle byte of the first blob file found under
// blobsDir, leaving the file length unchanged. // blobsDir, leaving the file length unchanged.
func corruptOneBlob(t *testing.T, fs afero.Fs, blobsDir string) { func corruptOneBlob(t *testing.T, fs afero.Fs, blobsDir string) {
Loaded 100 of 163 files, more files were not shown because too many files have changed in this diff. Show more