unkinben
6dc72920da
Lazy per-replica scans re-derived RPM metadata on the client request path and, run independently on every replica, multiplied GitHub queries by the replica count. A single background syncer with a shared rate limit, ETag conditional checks, and a DB lease keeps metadata fresh off the request path while bounding GitHub load to ~once per mutable_ttl across the fleet. - Add a single per-process syncer (started at boot, stopped on shutdown) that owns a deduped/coalescing work queue, a worker pool, and one global token-bucket rate limiter bound onto the github provider so every GitHub call (releases list + each ranged asset GET) acquires a token first. - Check each github_rpm remote for new/changed releases on its mutable_ttl cadence; derive only new/changed assets incrementally and prune assets that disappear upstream, so repodata is served from primed DB rows. - Prime metadata in the background on remote creation; the create call never blocks on a derive. - Send the stored releases-list ETag as If-None-Match; a 304 derives nothing (and does not count against GitHub's rate limit), making an unchanged repo 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. - 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/BURST/WORKERS/POLL_INTERVAL config (conservative defaults) and document the syncer in the README.
96 lines
2.9 KiB
Go
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)
|
|
}
|
|
}
|