unkinben
deabda9895
Complete rewrite of ArtifactAPI from Python/FastAPI to Go as a single binary. Core engine: - 10 package providers: generic, docker, helm, pypi, npm, rpm, alpine, puppet, terraform, goproxy — each with built-in mutable patterns - Content-addressable storage (SHA256 dedup across all remotes) - Three-tier caching: Redis (TTL/locks) → S3/MinIO (blobs) → upstream - Classifier with allowlist/blocklist per-remote (empty = allow all) - Circuit breaker, conditional revalidation, stale-on-error - Background garbage collection for orphaned blobs - Access logging to PostgreSQL API: - v1 proxy endpoints (backwards compatible) - v2 management API: CRUD remotes/virtuals, object browser, stats, health, SSE events, probe/test endpoint - Virtual repos with index merging (Helm YAML + PyPI HTML) Frontend (React + Vite, separate Dockerfile): - Dashboard with stats, health indicators, top remotes - Remotes list with type filter, remote detail with config/patterns - Object browser with pagination and evict - Test Remote page: probe any remote path, see headers/size/timing - Virtuals page with expandable member lists TUI (Bubble Tea): - Dashboard, remotes list/detail, object browser, virtuals - Vim-style navigation, artifactapi tui --endpoint <url> Infrastructure: - S3 client supports MinIO, Ceph RGW, AWS S3 (minio-go) - PostgreSQL schema with migrations - Docker Compose: API + UI + Postgres 17 + Redis 7 + MinIO - Makefile with Go version check, build/test/lint/fmt/e2e targets - Distroless Docker image (~15MB) Testing: - Unit tests for models, classifier, providers, mergers - E2E tests with testcontainers-go (real Postgres/Redis/MinIO) Terraform config: - All 40 production remotes + helm virtual as HCL - Provider repo: terraform-provider-artifactapi v0.0.1 (separate)
68 lines
1.4 KiB
Go
68 lines
1.4 KiB
Go
package gc
|
|
|
|
import (
|
|
"context"
|
|
"log/slog"
|
|
"time"
|
|
|
|
"git.unkin.net/unkin/artifactapi/internal/database"
|
|
"git.unkin.net/unkin/artifactapi/internal/storage"
|
|
)
|
|
|
|
type Collector struct {
|
|
db *database.DB
|
|
store *storage.S3
|
|
interval time.Duration
|
|
}
|
|
|
|
func New(db *database.DB, store *storage.S3, interval time.Duration) *Collector {
|
|
return &Collector{db: db, store: store, interval: interval}
|
|
}
|
|
|
|
func (c *Collector) Run(ctx context.Context) {
|
|
slog.Info("gc started", "interval", c.interval)
|
|
ticker := time.NewTicker(c.interval)
|
|
defer ticker.Stop()
|
|
|
|
for {
|
|
select {
|
|
case <-ctx.Done():
|
|
slog.Info("gc stopped")
|
|
return
|
|
case <-ticker.C:
|
|
c.sweep(ctx)
|
|
}
|
|
}
|
|
}
|
|
|
|
func (c *Collector) sweep(ctx context.Context) {
|
|
start := time.Now()
|
|
|
|
orphaned, err := c.db.FindOrphanedBlobs(ctx)
|
|
if err != nil {
|
|
slog.Error("gc: find orphaned blobs", "error", err)
|
|
return
|
|
}
|
|
|
|
deleted := 0
|
|
for _, blob := range orphaned {
|
|
if err := c.store.Delete(ctx, blob.S3Key); err != nil {
|
|
slog.Warn("gc: delete s3 object", "key", blob.S3Key, "error", err)
|
|
continue
|
|
}
|
|
if err := c.db.DeleteBlob(ctx, blob.ContentHash); err != nil {
|
|
slog.Warn("gc: delete blob row", "hash", blob.ContentHash, "error", err)
|
|
continue
|
|
}
|
|
deleted++
|
|
}
|
|
|
|
if deleted > 0 || len(orphaned) > 0 {
|
|
slog.Info("gc sweep complete",
|
|
"orphaned_found", len(orphaned),
|
|
"deleted", deleted,
|
|
"duration_ms", time.Since(start).Milliseconds(),
|
|
)
|
|
}
|
|
}
|