Hold every kept archive by a manifest so the store's collector keeps it (hq issue 253)

The store's garbage-collect marks only from manifests, and archives were
published as bare blobs, so the first real collection would delete every
archive the mesh keeps. PublishArchive now puts a deterministic OCI holder
manifest (empty config, one layer) beside each archive; the sweep holds every
kept archive before it lets anything go, which backfills existing bare blobs,
and lets go of an archive holder-first. A forgotten module no longer keeps its
five recent builds (ADR 0189). `collection [--json]` reports kept archives
held/unheld and what may be let go, so the dry run can be lifted on evidence.
This commit is contained in:
jochen
2026-10-05 18:13:23 +02:00
parent bb3cd6437b
commit 01c5ab2aab
13 changed files with 1252 additions and 32 deletions
+53 -1
View File
@@ -31,7 +31,12 @@ func collect(ctx context.Context, inv *inventory.Inventory) {
fmt.Fprintf(os.Stderr, "could not work out what the artifact store may let go of: %v\n", err)
return
}
if len(references) == 0 {
kept, err := inv.KeptArchives(ctx)
if err != nil {
fmt.Fprintf(os.Stderr, "could not work out which archives the artifact store keeps: %v\n", err)
return
}
if len(references) == 0 && len(kept) == 0 {
return
}
shelf, err := inv.Catalogue(ctx)
@@ -59,6 +64,25 @@ func collect(ctx context.Context, inv *inventory.Inventory) {
defer stop()
store := artifacts.Store{Address: address}
// **Hold before letting go** (novox/hq issue 253). The store's collector keeps only what a
// manifest names, and archives were published as bare blobs, so every kept archive is first
// held by its manifest — which backfills the ones published before holders, a few at a time
// as builds come, and is two HEADs each once done. A kept archive that could not be held stops
// the sweep before it deletes anything: "everything kept is held" is the precondition the
// collector's safety rests on, and a store refusing a hold would refuse the deletes too.
wrote, missing, err := holdKept(within, store, kept)
if wrote > 0 {
fmt.Fprintf(os.Stderr, "the artifact store now holds %d more kept archive(s) by a manifest\n", wrote)
}
if missing > 0 {
fmt.Fprintf(os.Stderr, "%d archive(s) the mesh keeps are not in the artifact store at all; "+
"`collection` lists them\n", missing)
}
if err != nil {
fmt.Fprintf(os.Stderr, "not every kept archive could be held, so nothing was let go: %v\n", err)
return
}
var done []string
var left, skipped int
for i, reference := range references {
@@ -114,6 +138,34 @@ func collect(ctx context.Context, inv *inventory.Inventory) {
}
}
// holdKept holds every kept archive by its manifest, stopping at the first refusal by the store.
// Answers how many holders it wrote and how many kept archives the store does not have.
//
// A missing archive is counted rather than fatal: there is nothing to hold, and that is a fact
// for an operator to read (`collection`), not a reason to stop collecting what is not kept. A
// reference the store cannot be asked about is skipped as the deletion loop skips one
// (novox/hq issue 226).
func holdKept(ctx context.Context, store artifacts.Store, kept []string) (wrote, missing int, err error) {
for _, reference := range kept {
if err := ctx.Err(); err != nil {
return wrote, missing, fmt.Errorf("ran out of time before %s: %w", reference, err)
}
did, err := store.Hold(ctx, reference)
switch {
case err == nil:
if did {
wrote++
}
case errors.Is(err, artifacts.Gone):
missing++
case errors.Is(err, artifacts.ErrNotOurs):
default:
return wrote, missing, fmt.Errorf("holding %s: %w", reference, err)
}
}
return wrote, missing, nil
}
// mostPerSweep is how many artifacts one sweep will ask about. Enough that a mesh building
// several times a day converges within days of this landing; small enough that no single build
// waits on the whole backlog.