Retry failed GitHub release scans with backoff (#133)
ci/woodpecker/tag/docker Pipeline was successful

Releasing a GitHub sync lease always advanced `last_synced_at`, even after a failed scan (e.g. a rate-limit 403). A remote that failed once waited a full `mutable_ttl` before retrying, and a cold remote kept returning 503 until then.

- record scan outcomes in one shared lease helper for github_rpm/deb/alpine
- keep `last_synced_at` and the ETag on failure; retry from 60s with exponential backoff, capped at min(10m, ttl/4)
- honour `Retry-After` / `X-RateLimit-Reset`, clamped to `mutable_ttl`
- add `sync_failures` / `next_retry_at` columns (migration 0002)

Reviewed-on: #133
Co-authored-by: unkin-agent <unkin-agent@unkin.net>
Co-committed-by: unkin-agent <unkin-agent@unkin.net>
This commit was merged in pull request #133.
This commit is contained in:
2026-10-09 23:15:55 +11:00
committed by BenVincent
parent 1780b3d77c
commit 492607a164
18 changed files with 477 additions and 134 deletions
+1 -1
View File
@@ -470,7 +470,7 @@ func (p *GitHubProvider) fetchReleases(ctx context.Context, remote models.Remote
return nil, "", false, err
}
if resp.StatusCode != http.StatusOK {
return nil, "", false, fmt.Errorf("github releases API %s: status %d", u, resp.StatusCode)
return nil, "", false, provider.NewUpstreamStatusError("github releases API "+u, resp)
}
if page == 1 {
newEtag = respEtag
+7 -9
View File
@@ -28,7 +28,7 @@ type SyncStore interface {
provider.RemoteMetadataStore
ListGitHubAlpineRemotes(ctx context.Context) ([]models.Remote, error)
ClaimGitHubAlpineSyncLease(ctx context.Context, remoteName, owner string, freshness, lease time.Duration) (claimed bool, etag string, err error)
ReleaseGitHubAlpineSyncLease(ctx context.Context, remoteName, owner, etag string, syncedAt time.Time) error
ReleaseGitHubAlpineSyncLease(ctx context.Context, remoteName, owner string, res provider.SyncResult) error
}
// SyncConfig tunes the shared syncer. Zero values fall back to safe defaults.
@@ -189,10 +189,11 @@ func (s *Syncer) process(ctx context.Context, job syncJob) {
s.mu.Unlock()
}()
freshness := time.Duration(job.remote.MutableTTL) * time.Second
if freshness <= 0 {
freshness = defaultSyncFreshness
ttl := time.Duration(job.remote.MutableTTL) * time.Second
if ttl <= 0 {
ttl = defaultSyncFreshness
}
freshness := ttl
if job.prime {
freshness = 0
}
@@ -210,16 +211,13 @@ func (s *Syncer) process(ctx context.Context, job syncJob) {
defer cancel()
newEtag, changed, scanErr := s.prov.scanWithState(scanCtx, job.remote, s.store, etag)
releaseEtag := etag
if scanErr == nil {
releaseEtag = newEtag
} else {
if scanErr != nil {
slog.Error("github_alpine syncer: scan failed", "remote", job.remote.Name, "error", scanErr)
}
relCtx, relCancel := context.WithTimeout(context.WithoutCancel(ctx), 10*time.Second)
defer relCancel()
if err := s.store.ReleaseGitHubAlpineSyncLease(relCtx, job.remote.Name, s.owner, releaseEtag, time.Now()); err != nil {
if err := s.store.ReleaseGitHubAlpineSyncLease(relCtx, job.remote.Name, s.owner, provider.NewSyncResult(newEtag, scanErr, ttl)); err != nil {
slog.Warn("github_alpine syncer: release lease", "remote", job.remote.Name, "error", err)
}
+13 -3
View File
@@ -27,6 +27,7 @@ type fakeSyncStore struct {
leaseExp map[string]time.Time
lastSynced map[string]time.Time
etags map[string]string
retryAt map[string]time.Time
}
func newFakeSyncStore() *fakeSyncStore {
@@ -36,6 +37,7 @@ func newFakeSyncStore() *fakeSyncStore {
leaseExp: map[string]time.Time{},
lastSynced: map[string]time.Time{},
etags: map[string]string{},
retryAt: map[string]time.Time{},
}
}
@@ -52,6 +54,9 @@ func (f *fakeSyncStore) ClaimGitHubAlpineSyncLease(_ context.Context, name, owne
ls, hasLS := f.lastSynced[name]
exp, hasExp := f.leaseExp[name]
freshOK := !hasLS || now.Sub(ls) >= freshness
if ra, pending := f.retryAt[name]; pending {
freshOK = !now.Before(ra)
}
leaseOK := !hasExp || exp.Before(now)
if freshOK && leaseOK {
f.leaseOwner[name] = owner
@@ -61,14 +66,19 @@ func (f *fakeSyncStore) ClaimGitHubAlpineSyncLease(_ context.Context, name, owne
return false, "", nil
}
func (f *fakeSyncStore) ReleaseGitHubAlpineSyncLease(_ context.Context, name, owner, etag string, syncedAt time.Time) error {
func (f *fakeSyncStore) ReleaseGitHubAlpineSyncLease(_ context.Context, name, owner string, res provider.SyncResult) error {
f.mu.Lock()
defer f.mu.Unlock()
if f.leaseOwner[name] != owner {
return nil
}
f.lastSynced[name] = syncedAt
f.etags[name] = etag
if res.Failed {
f.retryAt[name] = time.Now().Add(res.Backoff)
} else {
f.lastSynced[name] = time.Now()
f.etags[name] = res.Etag
delete(f.retryAt, name)
}
delete(f.leaseOwner, name)
delete(f.leaseExp, name)
return nil