metadb: add optional fast restart path that skips storage walk when (version + commit + storage config) matches metaDB stamp (#4026)

* chore(metadb): add writer version to interface Signed-off-by: Jacob McSwain <jacob@mcswain.dev> * chore(metadb): add writer version to db mock Signed-off-by: Jacob McSwain <jacob@mcswain.dev> * chore(metadb): implement writer version for bolt, redis, and dynamodb Signed-off-by: Jacob McSwain <jacob@mcswain.dev> * feat(metadb): add optional fast restart path that skips storage walk when binary identity matches metaDB stamp binary identity is determined by the current release tag/commit and stored in metaDB after a successful storage parse. When fast restart is enabled, the next startup will skip the parse if the stored identity matches the current binary Signed-off-by: Jacob McSwain <jacob@mcswain.dev> * chore(cli): serve: add a way to force reparse storage Signed-off-by: Jacob McSwain <jacob@mcswain.dev> * refactor(meta): version: split to avoid global state mutation in tests Signed-off-by: Jacob McSwain <jacob@mcswain.dev> * fix(meta): version: include commit in writerVersion to distinguish retags Signed-off-by: Jacob McSwain <jacob@mcswain.dev> * chore(config): add IsFastRestartEnabled() test Signed-off-by: Jacob McSwain <jacob@mcswain.dev> * fix(meta): skip writer-version stamp when storage parse is incomplete ParseStorage returns nil even when individual repos fail to parse or are only partially parsed (a missing manifest blob), so MaybeParseStorage would stamp a partially-populated metaDB as good. On the next restart fastRestart trusts the stamp, skips the storage walk, and never recovers. Track per-repo outcomes via parseStats and stamp only when the walk fully populated the metaDB, otherwise log and continue so the next restart reparses Signed-off-by: Jacob McSwain <jacob@mcswain.dev> * fix(docs): readme: remove trailing comma from JSON config Signed-off-by: Jacob McSwain <jacob@mcswain.dev> * fix(meta): dynamodb: use context.Background instead of context.TODO Signed-off-by: Jacob McSwain <jacob@mcswain.dev> * fix(meta): invalidate fast restart on storage config changes Signed-off-by: Jacob McSwain <jacob@mcswain.dev> * chore(meta): dynamodb: use context.Background() instead of context.TODO() Signed-off-by: Jacob McSwain <jacob@mcswain.dev> * docs(meta): dynamodb: add comment about nil AttributeValue handling in GetWriterVersion Signed-off-by: Jacob McSwain <jacob@mcswain.dev> * chore: rename writer-version stamp to fast-restart stamp also replaces the version/commit tracking to use BinaryVersion instead of WriterVersion This should make things more clear Signed-off-by: Jacob McSwain <jacob@mcswain.dev> * fix(config): ensure FastRestart is on GlobalStorageConfig This is not a per-subpath setting Signed-off-by: Jacob McSwain <jacob@mcswain.dev> * fix(metadb): redis: tests: ensure clients are closed Signed-off-by: Jacob McSwain <jacob@mcswain.dev> --------- Signed-off-by: Jacob McSwain <jacob@mcswain.dev>
2026-06-18 05:28:07 +08:00 · 2026-06-09 12:47:20 -05:00
parent d480380ef7
commit 273b15364b
19 changed files with 1103 additions and 44 deletions
@@ -0,0 +1,141 @@
+package meta
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"testing"
+	"time"
+
+	godigest "github.com/opencontainers/go-digest"
+	ispec "github.com/opencontainers/image-spec/specs-go/v1"
+	. "github.com/smartystreets/goconvey/convey"
+
+	zerr "zotregistry.dev/zot/v2/errors"
+	"zotregistry.dev/zot/v2/pkg/log"
+	mTypes "zotregistry.dev/zot/v2/pkg/meta/types"
+	"zotregistry.dev/zot/v2/pkg/storage"
+	testimage "zotregistry.dev/zot/v2/pkg/test/image-utils"
+	"zotregistry.dev/zot/v2/pkg/test/mocks"
+)
+
+var errParseInternal = errors.New("parse internal test error")
+
+func indexBlobFor(digest godigest.Digest, tag string) []byte {
+	blob, err := json.Marshal(ispec.Index{
+		MediaType: ispec.MediaTypeImageIndex,
+		Manifests: []ispec.Descriptor{{
+			MediaType:   ispec.MediaTypeImageManifest,
+			Digest:      digest,
+			Annotations: map[string]string{ispec.AnnotationRefName: tag},
+		}},
+	})
+	if err != nil {
+		panic("image index should always be marshable")
+	}
+
+	return blob
+}
+
+func TestParseStatsComplete(t *testing.T) {
+	Convey("parseStats.complete is true only with no failed or partial repos", t, func() {
+		So(parseStats{}.complete(), ShouldBeTrue)
+		So(parseStats{failedRepos: 1}.complete(), ShouldBeFalse)
+		So(parseStats{partialRepos: 1}.complete(), ShouldBeFalse)
+		So(parseStats{failedRepos: 2, partialRepos: 3}.complete(), ShouldBeFalse)
+	})
+}
+
+func TestFastRestartStamp(t *testing.T) {
+	Convey("FastRestartStamp joins the binary version and storage fingerprint", t, func() {
+		So(FastRestartStamp("v2.3.4+abc123", "deadbeef"), ShouldEqual, "v2.3.4+abc123|deadbeef")
+	})
+
+	Convey("FastRestartStamp returns empty when the binary version is empty", t, func() {
+		So(FastRestartStamp("", "deadbeef"), ShouldEqual, "")
+	})
+
+	Convey("FastRestartStamp returns empty when the storage fingerprint is empty", t, func() {
+		So(FastRestartStamp("v2.3.4+abc123", ""), ShouldEqual, "")
+	})
+}
+
+func TestParseStorageStats(t *testing.T) {
+	logger := log.NewTestLogger()
+
+	// A valid image whose manifest + config blobs parse cleanly through ParseRepo.
+	validImage := testimage.CreateRandomImage()
+
+	manifestBlob, err := json.Marshal(validImage.Manifest)
+	if err != nil {
+		t.Fatalf("marshal manifest: %v", err)
+	}
+
+	configBlob, err := json.Marshal(validImage.Config)
+	if err != nil {
+		t.Fatalf("marshal config: %v", err)
+	}
+
+	goodDigest := godigest.FromString("good-manifest")
+	missingDigest := godigest.FromString("missing-manifest")
+
+	// blobFor maps the descriptor digests our mocked index references back to the
+	// valid image blobs, anything else is reported as a missing blob.
+	blobFor := func(_ string, digest godigest.Digest) ([]byte, error) {
+		switch digest {
+		case goodDigest:
+			return manifestBlob, nil
+		case validImage.ConfigDescriptor.Digest:
+			return configBlob, nil
+		default:
+			return nil, zerr.ErrBlobNotFound
+		}
+	}
+
+	metaDB := mocks.MetaDBMock{
+		SetRepoReferenceFn: func(context.Context, string, string, mTypes.ImageMeta) error { return nil },
+	}
+
+	Convey("a fully-parsed repo yields a complete parseStats", t, func() {
+		store := storage.StoreController{DefaultStore: mocks.MockedImageStore{
+			GetRepositoriesFn: func() ([]string, error) { return []string{"goodrepo"}, nil },
+			GetIndexContentFn: func(string) ([]byte, error) { return indexBlobFor(goodDigest, "gtag"), nil },
+			GetBlobContentFn:  blobFor,
+		}}
+
+		stats, err := parseStorage(metaDB, store, logger)
+		So(err, ShouldBeNil)
+		So(stats.failedRepos, ShouldEqual, 0)
+		So(stats.partialRepos, ShouldEqual, 0)
+		So(stats.complete(), ShouldBeTrue)
+	})
+
+	Convey("failed and partial repos are counted independently", t, func() {
+		store := storage.StoreController{DefaultStore: mocks.MockedImageStore{
+			GetRepositoriesFn: func() ([]string, error) {
+				return []string{"failrepo", "partialrepo", "goodrepo"}, nil
+			},
+			StatIndexFn: func(repo string) (bool, int64, time.Time, error) {
+				if repo == "failrepo" {
+					return false, 0, time.Time{}, errParseInternal
+				}
+
+				return true, 0, time.Time{}, nil
+			},
+			GetIndexContentFn: func(repo string) ([]byte, error) {
+				if repo == "partialrepo" {
+					return indexBlobFor(missingDigest, "ptag"), nil
+				}
+
+				return indexBlobFor(goodDigest, "gtag"), nil
+			},
+			GetBlobContentFn: blobFor,
+		}}
+
+		stats, err := parseStorage(metaDB, store, logger)
+		So(err, ShouldBeNil)
+		So(stats.failedRepos, ShouldEqual, 1)
+		So(stats.partialRepos, ShouldEqual, 1)
+		So(stats.complete(), ShouldBeFalse)
+	})
+}