vaultik/internal/database/models.go
sneak d3afa65420 Fix foreign key constraints and improve snapshot tracking
- Add unified compression/encryption package in internal/blobgen
- Update DATAMODEL.md to reflect current schema implementation
- Refactor snapshot cleanup into well-named methods for clarity
- Add snapshot_id to uploads table to track new blobs per snapshot
- Fix blob count reporting for incremental backups
- Add DeleteOrphaned method to BlobChunkRepository
- Fix cleanup order to respect foreign key constraints
- Update tests to reflect schema changes
2025-07-26 02:22:25 +02:00

121 lines
4.6 KiB
Go

// Package database provides data models and repository interfaces for the Vaultik backup system.
// It includes types for files, chunks, blobs, snapshots, and their relationships.
package database
import "time"
// File represents a file or directory in the backup system.
// It stores metadata about files including timestamps, permissions, ownership,
// and symlink targets. This information is used to restore files with their
// original attributes.
type File struct {
ID string // UUID primary key
Path string
MTime time.Time
CTime time.Time
Size int64
Mode uint32
UID uint32
GID uint32
LinkTarget string // empty for regular files, target path for symlinks
}
// IsSymlink returns true if this file is a symbolic link.
// A file is considered a symlink if it has a non-empty LinkTarget.
func (f *File) IsSymlink() bool {
return f.LinkTarget != ""
}
// FileChunk represents the mapping between files and their constituent chunks.
// Large files are split into multiple chunks for efficient deduplication and storage.
// The Idx field maintains the order of chunks within a file.
type FileChunk struct {
FileID string
Idx int
ChunkHash string
}
// Chunk represents a data chunk in the deduplication system.
// Files are split into chunks which are content-addressed by their hash.
// The ChunkHash is the SHA256 hash of the chunk content, used for deduplication.
type Chunk struct {
ChunkHash string
Size int64
}
// Blob represents a blob record in the database.
// A blob is Vaultik's final storage unit - a large file (up to 10GB) containing
// many compressed and encrypted chunks from multiple source files.
// Blobs are content-addressed, meaning their filename in S3 is derived from
// the SHA256 hash of their compressed and encrypted content.
// The blob creation process is: chunks are accumulated -> compressed with zstd
// -> encrypted with age -> hashed -> uploaded to S3 with the hash as filename.
type Blob struct {
ID string // UUID assigned when blob creation starts
Hash string // SHA256 of final compressed+encrypted content (empty until finalized)
CreatedTS time.Time // When blob creation started
FinishedTS *time.Time // When blob was finalized (nil if still packing)
UncompressedSize int64 // Total size of raw chunks before compression
CompressedSize int64 // Size after compression and encryption
UploadedTS *time.Time // When blob was uploaded to S3 (nil if not uploaded)
}
// BlobChunk represents the mapping between blobs and the chunks they contain.
// This allows tracking which chunks are stored in which blobs, along with
// their position and size within the blob. The offset and length fields
// enable extracting specific chunks from a blob without processing the entire blob.
type BlobChunk struct {
BlobID string
ChunkHash string
Offset int64
Length int64
}
// ChunkFile represents the reverse mapping showing which files contain a specific chunk.
// This is used during deduplication to identify all files that share a chunk,
// which is important for garbage collection and integrity verification.
type ChunkFile struct {
ChunkHash string
FileID string
FileOffset int64
Length int64
}
// Snapshot represents a snapshot record in the database
type Snapshot struct {
ID string
Hostname string
VaultikVersion string
VaultikGitRevision string
StartedAt time.Time
CompletedAt *time.Time // nil if still in progress
FileCount int64
ChunkCount int64
BlobCount int64
TotalSize int64 // Total size of all referenced files
BlobSize int64 // Total size of all referenced blobs (compressed and encrypted)
BlobUncompressedSize int64 // Total uncompressed size of all referenced blobs
CompressionRatio float64 // Compression ratio (BlobSize / BlobUncompressedSize)
CompressionLevel int // Compression level used for this snapshot
UploadBytes int64 // Total bytes uploaded during this snapshot
UploadDurationMs int64 // Total milliseconds spent uploading to S3
}
// IsComplete returns true if the snapshot has completed
func (s *Snapshot) IsComplete() bool {
return s.CompletedAt != nil
}
// SnapshotFile represents the mapping between snapshots and files
type SnapshotFile struct {
SnapshotID string
FileID string
}
// SnapshotBlob represents the mapping between snapshots and blobs
type SnapshotBlob struct {
SnapshotID string
BlobID string
BlobHash string // Denormalized for easier manifest generation
}