Files
unkinben e24c35f534 feat: background syncer for github_rpm remotes (#108)
## Why

Builds on #107 (merged), which derives `github_rpm` RPM metadata lazily on the
client request path, single-flighted per replica. Two problems remain: the
derive still happens per replica, so across a multi-replica deployment the same
releases are scanned and re-derived N times, multiplying GitHub queries; and a
cold cache blocks the first request on a full derive. GitHub's rate limits are
low (~60/hr unauthenticated, ~5000/hr authenticated), so this needs a single
coordinated syncer with a shared rate limit and conditional requests.

## How

- Add a single per-process background syncer (started at boot, cleanly stopped
  on shutdown) that owns a deduped/coalescing work queue, a worker pool, and one
  global token-bucket rate limiter (`golang.org/x/time/rate`) bound onto the
  github provider so every GitHub call (releases list + each ranged asset GET)
  acquires a token first.
- Re-check each `github_rpm` remote for new/changed releases on its existing
  `mutable_ttl` cadence; derive only new/changed assets incrementally and prune
  assets that disappear upstream. Repodata is served from primed DB rows.
- Prime metadata in the background on remote creation; the create call returns
  immediately.
- Send the stored releases-list `ETag` as `If-None-Match`; a `304` derives
  nothing and is not counted against GitHub's rate limit, so an unchanged repo
  is nearly free.
- Coordinate replicas through a `github_rpm_sync_state` row (`last_synced_at`,
  `etag`, `sync_lease_owner`, `sync_lease_expires`): a periodic scan runs only
  for the replica that atomically claims the lease, bounding total GitHub load
  to ~once per `mutable_ttl` regardless of replica count; the ETag is shared
  through the same row.
- Keep the request path fast: serve current cache, enqueue a prime on an empty
  cache, and return a bounded wait then a retryable `503` rather than blocking
  on a cold derive.
- Add `GITHUB_SYNC_RATE` / `GITHUB_SYNC_BURST` / `GITHUB_SYNC_WORKERS` /
  `GITHUB_SYNC_POLL_INTERVAL` config with conservative defaults (1 req/s, burst
  5, 3 workers, 60s tick) and document the syncer in the README.

## Tests

- Unit (httptest, Range/ETag-aware fixture): `304` releases response derives
  nothing; incremental derive fetches only the newly added asset; the shared
  limiter caps request rate; work-queue enqueues coalesce to one job; prime
  enqueues a job; a held lease stops a second replica from scanning; cold-start
  serves `503` while warm cache serves `200`.
- DB integration (testcontainers postgres): the real lease SQL — one holder at a
  time, recency gate blocks a too-soon periodic re-claim, prime (freshness 0)
  bypasses recency but respects a live lease.
- Docker e2e re-run: `dnf install dotvault` works; prime-on-create derives in the
  background at ~1 req/s (global limiter); `dnf makecache` served fast from the
  priming cache (no cold block); clean shutdown mid-scan, no panics.

## Notes

- Reuses `mutable_ttl` as the check interval (no new per-remote field), per brief.

Reviewed-on: #108
Co-authored-by: Ben Vincent <ben@unkin.net>
Co-committed-by: Ben Vincent <ben@unkin.net>
2026-08-10 21:31:24 +10:00

96 lines
2.9 KiB
Go

package database
import (
"testing"
"time"
"git.unkin.net/unkin/artifactapi/pkg/models"
)
func seedGitHubRPMRemote(t *testing.T, name string) {
t.Helper()
if err := testDB.CreateRemote(ctx(), &models.Remote{
Name: name, PackageType: models.PackageGitHubRPM, RepoType: models.RepoTypeRemote,
BaseURL: "https://api.github.com/repos/acme/tools", ReleasesRemote: "github", MutableTTL: 3600,
}); err != nil {
t.Fatalf("seed github_rpm remote: %v", err)
}
}
// TestGitHubSyncLease exercises the real SQL: exactly one replica may hold the
// lease, the recency window blocks a too-soon periodic re-claim, and a prime
// (freshness 0) bypasses recency but still respects a live lease.
func TestGitHubSyncLease(t *testing.T) {
requireDB(t)
name := "gh-lease-" + time.Now().Format("150405.000000")
seedGitHubRPMRemote(t, name)
const lease = 15 * time.Minute
freshness := time.Hour
// First claim on a never-synced remote wins; etag starts empty.
claimed, etag, err := testDB.ClaimGitHubSyncLease(ctx(), name, "replica-1", freshness, lease)
if err != nil || !claimed {
t.Fatalf("replica-1 first claim: claimed=%v err=%v", claimed, err)
}
if etag != "" {
t.Fatalf("initial etag should be empty, got %q", etag)
}
// A second replica cannot claim while the lease is held.
claimed2, _, err := testDB.ClaimGitHubSyncLease(ctx(), name, "replica-2", freshness, lease)
if err != nil {
t.Fatalf("replica-2 claim err: %v", err)
}
if claimed2 {
t.Fatal("replica-2 claimed while replica-1 holds the lease")
}
// Replica 1 finishes: record the sync and persist an etag.
if err := testDB.ReleaseGitHubSyncLease(ctx(), name, "replica-1", `"etag-1"`, time.Now()); err != nil {
t.Fatalf("release: %v", err)
}
// A periodic re-claim inside the freshness window is blocked by recency.
claimed3, _, err := testDB.ClaimGitHubSyncLease(ctx(), name, "replica-2", freshness, lease)
if err != nil {
t.Fatalf("replica-2 recency claim err: %v", err)
}
if claimed3 {
t.Fatal("periodic claim succeeded inside the freshness window")
}
// A prime (freshness 0) bypasses recency and reads the persisted etag.
claimed4, etag4, err := testDB.ClaimGitHubSyncLease(ctx(), name, "replica-2", 0, lease)
if err != nil || !claimed4 {
t.Fatalf("prime claim: claimed=%v err=%v", claimed4, err)
}
if etag4 != `"etag-1"` {
t.Fatalf("prime claim etag = %q, want persisted \"etag-1\"", etag4)
}
}
func TestListGitHubRPMRemotes(t *testing.T) {
requireDB(t)
name := "gh-list-" + time.Now().Format("150405.000000")
seedGitHubRPMRemote(t, name)
seedRemote(t, "generic-"+time.Now().Format("150405.000000"))
remotes, err := testDB.ListGitHubRPMRemotes(ctx())
if err != nil {
t.Fatalf("list: %v", err)
}
found := false
for _, r := range remotes {
if r.PackageType != models.PackageGitHubRPM {
t.Fatalf("non-github_rpm remote returned: %s (%s)", r.Name, r.PackageType)
}
if r.Name == name {
found = true
}
}
if !found {
t.Fatalf("seeded remote %q not returned", name)
}
}