Add end-to-end integration tests for Vaultik
- Create comprehensive integration tests with mock S3 client - Add in-memory filesystem and SQLite database support for testing - Test full backup workflow including chunking, packing, and uploading - Add test to verify encrypted blob content - Fix scanner to use afero filesystem for temp file cleanup - Demonstrate successful backup and verification with mock dependencies
This commit is contained in:
396
internal/vaultik/verify.go
Normal file
396
internal/vaultik/verify.go
Normal file
@@ -0,0 +1,396 @@
|
||||
package vaultik
|
||||
|
||||
import (
|
||||
"crypto/sha256"
|
||||
"database/sql"
|
||||
"encoding/hex"
|
||||
"fmt"
|
||||
"io"
|
||||
"os"
|
||||
|
||||
"git.eeqj.de/sneak/vaultik/internal/log"
|
||||
"git.eeqj.de/sneak/vaultik/internal/snapshot"
|
||||
"github.com/dustin/go-humanize"
|
||||
"github.com/klauspost/compress/zstd"
|
||||
_ "github.com/mattn/go-sqlite3"
|
||||
)
|
||||
|
||||
// VerifyOptions contains options for the verify command
|
||||
type VerifyOptions struct {
|
||||
Deep bool
|
||||
}
|
||||
|
||||
// RunDeepVerify executes deep verification operation
|
||||
func (v *Vaultik) RunDeepVerify(snapshotID string, opts *VerifyOptions) error {
|
||||
// Check for decryption capability
|
||||
if !v.CanDecrypt() {
|
||||
return fmt.Errorf("age_secret_key missing from config - required for deep verification")
|
||||
}
|
||||
|
||||
log.Info("Starting snapshot verification",
|
||||
"snapshot_id", snapshotID,
|
||||
"mode", map[bool]string{true: "deep", false: "shallow"}[opts.Deep],
|
||||
)
|
||||
|
||||
// Step 1: Download manifest
|
||||
manifestPath := fmt.Sprintf("metadata/%s/manifest.json.zst", snapshotID)
|
||||
log.Info("Downloading manifest", "path", manifestPath)
|
||||
|
||||
manifestReader, err := v.S3Client.GetObject(v.ctx, manifestPath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to download manifest: %w", err)
|
||||
}
|
||||
defer func() { _ = manifestReader.Close() }()
|
||||
|
||||
// Decompress manifest
|
||||
manifest, err := snapshot.DecodeManifest(manifestReader)
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to decode manifest: %w", err)
|
||||
}
|
||||
|
||||
log.Info("Manifest loaded",
|
||||
"blob_count", manifest.BlobCount,
|
||||
"total_size", humanize.Bytes(uint64(manifest.TotalCompressedSize)),
|
||||
)
|
||||
|
||||
// Step 2: Download and decrypt database
|
||||
dbPath := fmt.Sprintf("metadata/%s/db.zst.age", snapshotID)
|
||||
log.Info("Downloading encrypted database", "path", dbPath)
|
||||
|
||||
dbReader, err := v.S3Client.GetObject(v.ctx, dbPath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to download database: %w", err)
|
||||
}
|
||||
defer func() { _ = dbReader.Close() }()
|
||||
|
||||
// Decrypt and decompress database
|
||||
tempDB, err := v.decryptAndLoadDatabase(dbReader, v.Config.AgeSecretKey)
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to decrypt database: %w", err)
|
||||
}
|
||||
defer func() {
|
||||
if tempDB != nil {
|
||||
_ = tempDB.Close()
|
||||
}
|
||||
}()
|
||||
|
||||
// Step 3: Compare blob lists
|
||||
if err := v.verifyBlobLists(snapshotID, manifest, tempDB.DB); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
// Step 4: Verify blob existence
|
||||
if err := v.verifyBlobExistence(manifest); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
// Step 5: Deep verification if requested
|
||||
if opts.Deep {
|
||||
if err := v.performDeepVerification(manifest, tempDB.DB); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
||||
log.Info("✓ Verification completed successfully",
|
||||
"snapshot_id", snapshotID,
|
||||
"mode", map[bool]string{true: "deep", false: "shallow"}[opts.Deep],
|
||||
)
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// tempDB wraps sql.DB with cleanup
|
||||
type tempDB struct {
|
||||
*sql.DB
|
||||
tempPath string
|
||||
}
|
||||
|
||||
func (t *tempDB) Close() error {
|
||||
err := t.DB.Close()
|
||||
_ = os.Remove(t.tempPath)
|
||||
return err
|
||||
}
|
||||
|
||||
// decryptAndLoadDatabase decrypts and loads the database from the encrypted stream
|
||||
func (v *Vaultik) decryptAndLoadDatabase(reader io.ReadCloser, secretKey string) (*tempDB, error) {
|
||||
// Get decryptor
|
||||
decryptor, err := v.GetDecryptor()
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to get decryptor: %w", err)
|
||||
}
|
||||
|
||||
// Decrypt the stream
|
||||
decryptedReader, err := decryptor.DecryptStream(reader)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to decrypt database: %w", err)
|
||||
}
|
||||
|
||||
// Decompress the database
|
||||
decompressor, err := zstd.NewReader(decryptedReader)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to create decompressor: %w", err)
|
||||
}
|
||||
defer decompressor.Close()
|
||||
|
||||
// Create temporary file for database
|
||||
tempFile, err := os.CreateTemp("", "vaultik-verify-*.db")
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to create temp file: %w", err)
|
||||
}
|
||||
tempPath := tempFile.Name()
|
||||
|
||||
// Copy decompressed data to temp file
|
||||
if _, err := io.Copy(tempFile, decompressor); err != nil {
|
||||
_ = tempFile.Close()
|
||||
_ = os.Remove(tempPath)
|
||||
return nil, fmt.Errorf("failed to write database: %w", err)
|
||||
}
|
||||
|
||||
// Close temp file before opening with sqlite
|
||||
if err := tempFile.Close(); err != nil {
|
||||
_ = os.Remove(tempPath)
|
||||
return nil, fmt.Errorf("failed to close temp file: %w", err)
|
||||
}
|
||||
|
||||
// Open the database
|
||||
db, err := sql.Open("sqlite3", tempPath)
|
||||
if err != nil {
|
||||
_ = os.Remove(tempPath)
|
||||
return nil, fmt.Errorf("failed to open database: %w", err)
|
||||
}
|
||||
|
||||
return &tempDB{
|
||||
DB: db,
|
||||
tempPath: tempPath,
|
||||
}, nil
|
||||
}
|
||||
|
||||
// verifyBlobLists compares the blob lists between manifest and database
|
||||
func (v *Vaultik) verifyBlobLists(snapshotID string, manifest *snapshot.Manifest, db *sql.DB) error {
|
||||
log.Info("Verifying blob lists match between manifest and database")
|
||||
|
||||
// Get blobs from database
|
||||
query := `
|
||||
SELECT b.blob_hash, b.compressed_size
|
||||
FROM snapshot_blobs sb
|
||||
JOIN blobs b ON sb.blob_hash = b.blob_hash
|
||||
WHERE sb.snapshot_id = ?
|
||||
ORDER BY b.blob_hash
|
||||
`
|
||||
rows, err := db.QueryContext(v.ctx, query, snapshotID)
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to query snapshot blobs: %w", err)
|
||||
}
|
||||
defer func() { _ = rows.Close() }()
|
||||
|
||||
// Build map of database blobs
|
||||
dbBlobs := make(map[string]int64)
|
||||
for rows.Next() {
|
||||
var hash string
|
||||
var size int64
|
||||
if err := rows.Scan(&hash, &size); err != nil {
|
||||
return fmt.Errorf("failed to scan blob row: %w", err)
|
||||
}
|
||||
dbBlobs[hash] = size
|
||||
}
|
||||
|
||||
// Build map of manifest blobs
|
||||
manifestBlobs := make(map[string]int64)
|
||||
for _, blob := range manifest.Blobs {
|
||||
manifestBlobs[blob.Hash] = blob.CompressedSize
|
||||
}
|
||||
|
||||
// Compare counts
|
||||
if len(dbBlobs) != len(manifestBlobs) {
|
||||
return fmt.Errorf("blob count mismatch: database has %d blobs, manifest has %d blobs",
|
||||
len(dbBlobs), len(manifestBlobs))
|
||||
}
|
||||
|
||||
// Check each blob exists in both
|
||||
for hash, dbSize := range dbBlobs {
|
||||
manifestSize, exists := manifestBlobs[hash]
|
||||
if !exists {
|
||||
return fmt.Errorf("blob %s exists in database but not in manifest", hash)
|
||||
}
|
||||
if dbSize != manifestSize {
|
||||
return fmt.Errorf("blob %s size mismatch: database has %d bytes, manifest has %d bytes",
|
||||
hash, dbSize, manifestSize)
|
||||
}
|
||||
}
|
||||
|
||||
for hash := range manifestBlobs {
|
||||
if _, exists := dbBlobs[hash]; !exists {
|
||||
return fmt.Errorf("blob %s exists in manifest but not in database", hash)
|
||||
}
|
||||
}
|
||||
|
||||
log.Info("✓ Blob lists match", "blob_count", len(dbBlobs))
|
||||
return nil
|
||||
}
|
||||
|
||||
// verifyBlobExistence checks that all blobs exist in S3
|
||||
func (v *Vaultik) verifyBlobExistence(manifest *snapshot.Manifest) error {
|
||||
log.Info("Verifying blob existence in S3", "blob_count", len(manifest.Blobs))
|
||||
|
||||
for i, blob := range manifest.Blobs {
|
||||
// Construct blob path
|
||||
blobPath := fmt.Sprintf("blobs/%s/%s/%s", blob.Hash[:2], blob.Hash[2:4], blob.Hash)
|
||||
|
||||
// Check blob exists with HeadObject
|
||||
stat, err := v.S3Client.StatObject(v.ctx, blobPath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("blob %s missing from S3: %w", blob.Hash, err)
|
||||
}
|
||||
|
||||
// Verify size matches
|
||||
if stat.Size != blob.CompressedSize {
|
||||
return fmt.Errorf("blob %s size mismatch: S3 has %d bytes, manifest has %d bytes",
|
||||
blob.Hash, stat.Size, blob.CompressedSize)
|
||||
}
|
||||
|
||||
// Progress update every 100 blobs
|
||||
if (i+1)%100 == 0 || i == len(manifest.Blobs)-1 {
|
||||
log.Info("Blob existence check progress",
|
||||
"checked", i+1,
|
||||
"total", len(manifest.Blobs),
|
||||
"percent", fmt.Sprintf("%.1f%%", float64(i+1)/float64(len(manifest.Blobs))*100),
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
log.Info("✓ All blobs exist in S3")
|
||||
return nil
|
||||
}
|
||||
|
||||
// performDeepVerification downloads and verifies the content of each blob
|
||||
func (v *Vaultik) performDeepVerification(manifest *snapshot.Manifest, db *sql.DB) error {
|
||||
log.Info("Starting deep verification - downloading and verifying all blobs")
|
||||
|
||||
totalBytes := int64(0)
|
||||
for i, blobInfo := range manifest.Blobs {
|
||||
// Verify individual blob
|
||||
if err := v.verifyBlob(blobInfo, db); err != nil {
|
||||
return fmt.Errorf("blob %s verification failed: %w", blobInfo.Hash, err)
|
||||
}
|
||||
|
||||
totalBytes += blobInfo.CompressedSize
|
||||
|
||||
// Progress update
|
||||
log.Info("Deep verification progress",
|
||||
"blob", fmt.Sprintf("%d/%d", i+1, len(manifest.Blobs)),
|
||||
"total_downloaded", humanize.Bytes(uint64(totalBytes)),
|
||||
"percent", fmt.Sprintf("%.1f%%", float64(i+1)/float64(len(manifest.Blobs))*100),
|
||||
)
|
||||
}
|
||||
|
||||
log.Info("✓ Deep verification completed successfully",
|
||||
"blobs_verified", len(manifest.Blobs),
|
||||
"total_size", humanize.Bytes(uint64(totalBytes)),
|
||||
)
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// verifyBlob downloads and verifies a single blob
|
||||
func (v *Vaultik) verifyBlob(blobInfo snapshot.BlobInfo, db *sql.DB) error {
|
||||
// Download blob
|
||||
blobPath := fmt.Sprintf("blobs/%s/%s/%s", blobInfo.Hash[:2], blobInfo.Hash[2:4], blobInfo.Hash)
|
||||
reader, err := v.S3Client.GetObject(v.ctx, blobPath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to download: %w", err)
|
||||
}
|
||||
defer func() { _ = reader.Close() }()
|
||||
|
||||
// Get decryptor
|
||||
decryptor, err := v.GetDecryptor()
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to get decryptor: %w", err)
|
||||
}
|
||||
|
||||
// Decrypt blob
|
||||
decryptedReader, err := decryptor.DecryptStream(reader)
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to decrypt: %w", err)
|
||||
}
|
||||
|
||||
// Decompress blob
|
||||
decompressor, err := zstd.NewReader(decryptedReader)
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to decompress: %w", err)
|
||||
}
|
||||
defer decompressor.Close()
|
||||
|
||||
// Query blob chunks from database to get offsets and lengths
|
||||
query := `
|
||||
SELECT bc.chunk_hash, bc.offset, bc.length
|
||||
FROM blob_chunks bc
|
||||
JOIN blobs b ON bc.blob_id = b.id
|
||||
WHERE b.blob_hash = ?
|
||||
ORDER BY bc.offset
|
||||
`
|
||||
rows, err := db.QueryContext(v.ctx, query, blobInfo.Hash)
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to query blob chunks: %w", err)
|
||||
}
|
||||
defer func() { _ = rows.Close() }()
|
||||
|
||||
var lastOffset int64 = -1
|
||||
chunkCount := 0
|
||||
totalRead := int64(0)
|
||||
|
||||
// Verify each chunk in the blob
|
||||
for rows.Next() {
|
||||
var chunkHash string
|
||||
var offset, length int64
|
||||
if err := rows.Scan(&chunkHash, &offset, &length); err != nil {
|
||||
return fmt.Errorf("failed to scan chunk row: %w", err)
|
||||
}
|
||||
|
||||
// Verify chunk ordering
|
||||
if offset <= lastOffset {
|
||||
return fmt.Errorf("chunks out of order: offset %d after %d", offset, lastOffset)
|
||||
}
|
||||
lastOffset = offset
|
||||
|
||||
// Read chunk data from decompressed stream
|
||||
if offset > totalRead {
|
||||
// Skip to the correct offset
|
||||
skipBytes := offset - totalRead
|
||||
if _, err := io.CopyN(io.Discard, decompressor, skipBytes); err != nil {
|
||||
return fmt.Errorf("failed to skip to offset %d: %w", offset, err)
|
||||
}
|
||||
totalRead = offset
|
||||
}
|
||||
|
||||
// Read chunk data
|
||||
chunkData := make([]byte, length)
|
||||
if _, err := io.ReadFull(decompressor, chunkData); err != nil {
|
||||
return fmt.Errorf("failed to read chunk at offset %d: %w", offset, err)
|
||||
}
|
||||
totalRead += length
|
||||
|
||||
// Verify chunk hash
|
||||
hasher := sha256.New()
|
||||
hasher.Write(chunkData)
|
||||
calculatedHash := hex.EncodeToString(hasher.Sum(nil))
|
||||
|
||||
if calculatedHash != chunkHash {
|
||||
return fmt.Errorf("chunk hash mismatch at offset %d: calculated %s, expected %s",
|
||||
offset, calculatedHash, chunkHash)
|
||||
}
|
||||
|
||||
chunkCount++
|
||||
}
|
||||
|
||||
if err := rows.Err(); err != nil {
|
||||
return fmt.Errorf("error iterating blob chunks: %w", err)
|
||||
}
|
||||
|
||||
log.Debug("Blob verified",
|
||||
"hash", blobInfo.Hash,
|
||||
"chunks", chunkCount,
|
||||
"size", humanize.Bytes(uint64(blobInfo.CompressedSize)),
|
||||
)
|
||||
|
||||
return nil
|
||||
}
|
||||
Reference in New Issue
Block a user