gc: add a policy to skip garbage collecting new blobs

We perform inline garbage collection of orphan blobs. However, the
dist-spec poses a problem because blobs begin their life as orphan blobs
and then a manifest is add which refers to these blobs.

We use umoci's GC() to perform garbage collection and policy support
has been added recently which can control whether a blob can be skipped
for GC.

In this patch, we use a time-based policy to skip blobs.

pkg/api/BUILD.bazel

@@ -33,7 +33,7 @@ go_library(
 
 go_test(
     name = "go_default_test",
-    timeout = "short",
+    timeout = "moderate",
     srcs = ["controller_test.go"],
     data = [
         "//:exported_testdata",

pkg/storage/BUILD.bazel

@@ -11,10 +11,12 @@ go_library(
     deps = [
         "//errors:go_default_library",
         "//pkg/log:go_default_library",
+        "@com_github_apex_log//:go_default_library",
         "@com_github_gofrs_uuid//:go_default_library",
         "@com_github_opencontainers_go_digest//:go_default_library",
         "@com_github_opencontainers_image_spec//specs-go/v1:go_default_library",
         "@com_github_opencontainers_umoci//:go_default_library",
+        "@com_github_opencontainers_umoci//oci/casext:go_default_library",
         "@com_github_rs_zerolog//:go_default_library",
         "@io_etcd_go_bbolt//:go_default_library",
     ],

pkg/storage/storage.go

@@ -11,13 +11,16 @@ import (
 	"path"
 	"path/filepath"
 	"sync"
+	"time"
 
 	"github.com/anuvu/zot/errors"
 	zlog "github.com/anuvu/zot/pkg/log"
+	apexlog "github.com/apex/log"
 	guuid "github.com/gofrs/uuid"
 	godigest "github.com/opencontainers/go-digest"
 	ispec "github.com/opencontainers/image-spec/specs-go/v1"
 	"github.com/opencontainers/umoci"
+	"github.com/opencontainers/umoci/oci/casext"
 	"github.com/rs/zerolog"
 )
 
@@ -25,6 +28,7 @@ const (
 	// BlobUploadDir defines the upload directory for blob uploads.
 	BlobUploadDir = ".uploads"
 	schemaVersion = 2
+	gcDelay       = 1 * time.Hour
 )
 
 // BlobUpload models and upload request.
@@ -66,6 +70,20 @@ func NewImageStore(rootDir string, gc bool, dedupe bool, log zlog.Logger) *Image
 		is.cache = NewCache(rootDir, "cache", log)
 	}
 
+	if gc {
+		// we use umoci GC to perform garbage-collection, but it uses its own logger
+		// - so capture those logs, could be useful
+		apexlog.SetLevel(apexlog.DebugLevel)
+		apexlog.SetHandler(apexlog.HandlerFunc(func(entry *apexlog.Entry) error {
+			e := log.Debug()
+			for k, v := range entry.Fields {
+				e = e.Interface(k, v)
+			}
+			e.Msg(entry.Message)
+			return nil
+		}))
+	}
+
 	return is
 }
 
@@ -492,7 +510,7 @@ func (is *ImageStore) PutImageManifest(repo string, reference string, mediaType
 		}
 		defer oci.Close()
 
-		if err := oci.GC(context.Background()); err != nil {
+		if err := oci.GC(context.Background(), ifOlderThan(is, repo, gcDelay)); err != nil {
 			return "", err
 		}
 	}
@@ -568,7 +586,7 @@ func (is *ImageStore) DeleteImageManifest(repo string, reference string) error {
 		}
 		defer oci.Close()
 
-		if err := oci.GC(context.Background()); err != nil {
+		if err := oci.GC(context.Background(), ifOlderThan(is, repo, gcDelay)); err != nil {
 			return err
 		}
 	}
@@ -1025,3 +1043,22 @@ func ensureDir(dir string, log zerolog.Logger) {
 		log.Panic().Err(err).Str("dir", dir).Msg("unable to create dir")
 	}
 }
+
+func ifOlderThan(is *ImageStore, repo string, delay time.Duration) casext.GCPolicy {
+	return func(ctx context.Context, digest godigest.Digest) (bool, error) {
+		blobPath := is.BlobPath(repo, digest)
+		fi, err := os.Stat(blobPath)
+
+		if err != nil {
+			return false, err
+		}
+
+		if fi.ModTime().Add(delay).After(time.Now()) {
+			return false, nil
+		}
+
+		is.log.Info().Str("digest", digest.String()).Str("blobPath", blobPath).Msg("perform GC on blob")
+
+		return true, nil
+	}
+}