fix: add a grace period before GC deletes orphaned blobs

FindOrphanedBlobs returned any unreferenced blob, so a concurrent dedup
upload (which inserts the blob row before its artifact/local_files row)
could have its S3 object deleted mid-flight. Restrict collection to blobs
older than a 1h grace period.

Refs #71

.woodpecker/docker.yaml

@@ -8,6 +8,8 @@ steps:
     settings:
       registry: git.unkin.net
       repo: git.unkin.net/unkin/artifactapi
+      build_args:
+        VERSION: ${CI_COMMIT_TAG}
       username: droneci
       password:
         from_secret: DRONECI_PASSWORD
@@ -22,6 +24,8 @@ steps:
       repo: git.unkin.net/unkin/artifactapi-ui
       dockerfile: ui/Dockerfile.ui
       context: ui
+      build_args:
+        BASE_PATH: /ui
       username: droneci
       password:
         from_secret: DRONECI_PASSWORD

Dockerfile

@@ -9,7 +9,8 @@ RUN go mod download
 
 COPY . .
 
-RUN CGO_ENABLED=0 go build -ldflags="-s -w" -o artifactapi ./cmd/artifactapi
+ARG VERSION=dev
+RUN CGO_ENABLED=0 go build -ldflags="-s -w -X main.version=${VERSION}" -o artifactapi ./cmd/artifactapi
 
 FROM gcr.io/distroless/static-debian12:nonroot
 

Makefile

@@ -12,7 +12,7 @@ check-go:
 	fi
 
 build: check-go tidy
-	go build -ldflags="-s -w" -o $(BINARY) ./cmd/artifactapi
+	go build -ldflags="-s -w -X main.version=$(VERSION)" -o $(BINARY) ./cmd/artifactapi
 
 test: check-go
 	go test -race -count=1 ./pkg/... ./internal/...

cmd/artifactapi/main.go

@@ -13,6 +13,8 @@ import (
 	"git.unkin.net/unkin/artifactapi/internal/tui"
 )
 
+var version = "dev"
+
 func main() {
 	if len(os.Args) > 1 && os.Args[1] == "tui" {
 		endpoint := os.Getenv("ARTIFACTAPI_ENDPOINT")
@@ -42,7 +44,7 @@ func main() {
 	ctx, cancel := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM)
 	defer cancel()
 
-	srv, err := server.New(cfg)
+	srv, err := server.New(cfg, version)
 	if err != nil {
 		slog.Error("failed to create server", "error", err)
 		os.Exit(1)

internal/api/v1/proxy.go

@@ -37,6 +37,20 @@ func (h *ProxyHandler) Routes() chi.Router {
 	return r
 }
 
+func (h *ProxyHandler) DockerV2Routes() chi.Router {
+	r := chi.NewRouter()
+	r.Get("/", h.handleDockerPing)
+	r.Head("/", h.handleDockerPing)
+	r.Get("/{remoteName}/*", h.handleProxy)
+	r.Head("/{remoteName}/*", h.handleProxy)
+	return r
+}
+
+func (h *ProxyHandler) handleDockerPing(w http.ResponseWriter, r *http.Request) {
+	w.Header().Set("Docker-Distribution-Api-Version", "registry/2.0")
+	w.WriteHeader(http.StatusOK)
+}
+
 func (h *ProxyHandler) handleProxy(w http.ResponseWriter, r *http.Request) {
 	remoteName := chi.URLParam(r, "remoteName")
 	path := chi.URLParam(r, "*")
@@ -53,7 +67,7 @@ func (h *ProxyHandler) handleProxy(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	result, err := h.engine.Fetch(r.Context(), *remote, path, prov)
+	result, err := h.engine.Fetch(r.Context(), *remote, path, prov, r.Header)
 	if err != nil {
 		var proxyErr *proxy.ProxyError
 		if errors.As(err, &proxyErr) {

internal/database/artifacts.go

@@ -109,16 +109,22 @@ func (db *DB) InsertAccessLog(ctx context.Context, remoteName, path string, cach
 	return err
 }
 
-func (db *DB) FindOrphanedBlobs(ctx context.Context) ([]models.Blob, error) {
+// FindOrphanedBlobs returns blobs no longer referenced by any artifact or
+// local file, restricted to those created before now()-minAge. The age cutoff
+// is a grace period that avoids a TOCTOU race with in-flight dedup uploads,
+// which insert the blob row before the referencing artifact/local_files row.
+func (db *DB) FindOrphanedBlobs(ctx context.Context, minAge time.Duration) ([]models.Blob, error) {
+	cutoff := time.Now().Add(-minAge)
 	rows, err := db.Pool.Query(ctx, `
 		SELECT b.content_hash, b.s3_key, b.size_bytes, b.content_type, b.created_at
 		FROM blobs b
-		WHERE b.content_hash NOT IN (
+		WHERE b.created_at < $1
+		  AND b.content_hash NOT IN (
 			SELECT content_hash FROM artifacts
 			UNION
 			SELECT content_hash FROM local_files
 		)
-	`)
+	`, cutoff)
 	if err != nil {
 		return nil, err
 	}

internal/database/stats.go

@@ -30,6 +30,15 @@ func (db *DB) GetOverviewStats(ctx context.Context) (*models.OverviewStats, erro
 		return nil, err
 	}
 
+	err = db.Pool.QueryRow(ctx, `
+		SELECT COALESCE(SUM(size_bytes), 0)
+		FROM access_log
+		WHERE cache_hit = TRUE AND created_at > NOW() - INTERVAL '30 days'
+	`).Scan(&stats.BandwidthSaved30d)
+	if err != nil {
+		return nil, err
+	}
+
 	return &stats, nil
 }
 

internal/gc/gc.go

@@ -9,6 +9,11 @@ import (
 	"git.unkin.net/unkin/artifactapi/internal/storage"
 )
 
+// blobGracePeriod is how old an orphaned blob must be before GC will delete
+// it. This avoids racing in-flight dedup uploads that insert the blob row
+// before the referencing artifact/local_files row exists.
+const blobGracePeriod = 1 * time.Hour
+
 type Collector struct {
 	db       *database.DB
 	store    *storage.S3
@@ -38,7 +43,7 @@ func (c *Collector) Run(ctx context.Context) {
 func (c *Collector) sweep(ctx context.Context) {
 	start := time.Now()
 
-	orphaned, err := c.db.FindOrphanedBlobs(ctx)
+	orphaned, err := c.db.FindOrphanedBlobs(ctx, blobGracePeriod)
 	if err != nil {
 		slog.Error("gc: find orphaned blobs", "error", err)
 		return

internal/proxy/engine.go

@@ -4,10 +4,12 @@ import (
 	"context"
 	"crypto/sha256"
 	"encoding/hex"
+	"encoding/json"
 	"fmt"
 	"io"
 	"log/slog"
 	"net/http"
+	"strings"
 	"time"
 
 	"git.unkin.net/unkin/artifactapi/internal/cache"
@@ -42,7 +44,7 @@ type FetchResult struct {
 	Source      string // "cache" or "remote"
 }
 
-func (e *Engine) Fetch(ctx context.Context, remote models.Remote, path string, prov provider.Provider) (*FetchResult, error) {
+func (e *Engine) Fetch(ctx context.Context, remote models.Remote, path string, prov provider.Provider, clientHeaders ...http.Header) (*FetchResult, error) {
 	classifier := NewClassifier(prov)
 	class := classifier.Classify(remote, path)
 
@@ -103,8 +105,13 @@ func (e *Engine) Fetch(ctx context.Context, remote models.Remote, path string, p
 		}
 	}
 
+	var fwdHeaders http.Header
+	if len(clientHeaders) > 0 && clientHeaders[0] != nil {
+		fwdHeaders = clientHeaders[0]
+	}
+
 	start := time.Now()
-	result, err := e.fetchFromUpstream(ctx, remote, path, prov, class, ttl)
+	result, err := e.fetchFromUpstream(ctx, remote, path, prov, class, ttl, fwdHeaders)
 	upstreamMS := int(time.Since(start).Milliseconds())
 	if err != nil {
 		if remote.StaleOnError && isNetworkError(err) {
@@ -124,7 +131,7 @@ func (e *Engine) Fetch(ctx context.Context, remote models.Remote, path string, p
 	return result, nil
 }
 
-func (e *Engine) fetchFromUpstream(ctx context.Context, remote models.Remote, path string, prov provider.Provider, class Classification, ttl time.Duration) (*FetchResult, error) {
+func (e *Engine) fetchFromUpstream(ctx context.Context, remote models.Remote, path string, prov provider.Provider, class Classification, ttl time.Duration, clientHeaders http.Header) (*FetchResult, error) {
 	url := prov.UpstreamURL(remote, path)
 
 	authHeaders, err := prov.AuthHeaders(ctx, remote)
@@ -141,12 +148,37 @@ func (e *Engine) fetchFromUpstream(ctx context.Context, remote models.Remote, pa
 			req.Header.Add(k, v)
 		}
 	}
+	if clientHeaders != nil {
+		if accept := clientHeaders.Get("Accept"); accept != "" {
+			req.Header.Set("Accept", accept)
+		}
+	}
 
 	resp, err := http.DefaultClient.Do(req)
 	if err != nil {
 		return nil, &UpstreamError{Err: err}
 	}
 
+	if resp.StatusCode == http.StatusUnauthorized {
+		resp.Body.Close()
+		token, err := fetchBearerToken(ctx, resp.Header.Get("Www-Authenticate"), remote)
+		if err == nil && token != "" {
+			req2, _ := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
+			req2.Header.Set("Authorization", "Bearer "+token)
+			if clientHeaders != nil {
+				if accept := clientHeaders.Get("Accept"); accept != "" {
+					req2.Header.Set("Accept", accept)
+				}
+			}
+			resp, err = http.DefaultClient.Do(req2)
+			if err != nil {
+				return nil, &UpstreamError{Err: err}
+			}
+		} else {
+			return nil, &ProxyError{Status: http.StatusUnauthorized, Message: "upstream returned 401"}
+		}
+	}
+
 	if resp.StatusCode != http.StatusOK {
 		resp.Body.Close()
 		return nil, &ProxyError{Status: resp.StatusCode, Message: fmt.Sprintf("upstream returned %d", resp.StatusCode)}
@@ -167,7 +199,7 @@ func (e *Engine) fetchFromUpstream(ctx context.Context, remote models.Remote, pa
 	}
 
 	contentType := prov.ContentType(path)
-	if ct := resp.Header.Get("Content-Type"); ct != "" && contentType == "application/octet-stream" {
+	if ct := resp.Header.Get("Content-Type"); ct != "" {
 		contentType = ct
 	}
 
@@ -319,6 +351,71 @@ func (r readerAt) ReadAt(p []byte, off int64) (n int, err error) {
 	return
 }
 
+func fetchBearerToken(ctx context.Context, wwwAuth string, remote models.Remote) (string, error) {
+	if !strings.HasPrefix(wwwAuth, "Bearer ") {
+		return "", fmt.Errorf("not a Bearer challenge")
+	}
+
+	params := map[string]string{}
+	for _, part := range strings.Split(wwwAuth[7:], ",") {
+		part = strings.TrimSpace(part)
+		eq := strings.Index(part, "=")
+		if eq < 0 {
+			continue
+		}
+		key := part[:eq]
+		val := strings.Trim(part[eq+1:], `"`)
+		params[key] = val
+	}
+
+	realm := params["realm"]
+	if realm == "" {
+		return "", fmt.Errorf("no realm in Bearer challenge")
+	}
+
+	tokenURL := realm
+	sep := "?"
+	if s, ok := params["service"]; ok {
+		tokenURL += sep + "service=" + s
+		sep = "&"
+	}
+	if s, ok := params["scope"]; ok {
+		tokenURL += sep + "scope=" + s
+	}
+
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, tokenURL, nil)
+	if err != nil {
+		return "", err
+	}
+
+	if remote.Username != "" && remote.Password != "" {
+		req.SetBasicAuth(remote.Username, remote.Password)
+	}
+
+	resp, err := http.DefaultClient.Do(req)
+	if err != nil {
+		return "", err
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode != http.StatusOK {
+		return "", fmt.Errorf("token endpoint returned %d", resp.StatusCode)
+	}
+
+	var tokenResp struct {
+		Token       string `json:"token"`
+		AccessToken string `json:"access_token"`
+	}
+	if err := json.NewDecoder(resp.Body).Decode(&tokenResp); err != nil {
+		return "", err
+	}
+
+	if tokenResp.Token != "" {
+		return tokenResp.Token, nil
+	}
+	return tokenResp.AccessToken, nil
+}
+
 type ProxyError struct {
 	Status  int
 	Message string

internal/server/server.go

@@ -35,6 +35,7 @@ import (
 
 type Server struct {
 	cfg          *config.Config
+	version      string
 	router       chi.Router
 	db           *database.DB
 	cache        *cache.Redis
@@ -45,7 +46,7 @@ type Server struct {
 	gc           *gc.Collector
 }
 
-func New(cfg *config.Config) (*Server, error) {
+func New(cfg *config.Config, version string) (*Server, error) {
 	db, err := database.New(cfg.DatabaseDSN())
 	if err != nil {
 		return nil, fmt.Errorf("database: %w", err)
@@ -68,6 +69,7 @@ func New(cfg *config.Config) (*Server, error) {
 
 	s := &Server{
 		cfg:          cfg,
+		version:      version,
 		db:           db,
 		cache:        redis,
 		store:        s3,
@@ -96,6 +98,7 @@ func (s *Server) routes() chi.Router {
 
 	proxyHandler := v1.NewProxyHandler(s.engine, s.virtEngine, s.db, s.store, s.localHandler)
 	r.Mount("/api/v1", proxyHandler.Routes())
+	r.Mount("/v2", proxyHandler.DockerV2Routes())
 
 	remotesHandler := v2.NewRemotesHandler(s.db)
 	virtualsHandler := v2.NewVirtualsHandler(s.db)
@@ -137,7 +140,7 @@ func (s *Server) handleHealth(w http.ResponseWriter, r *http.Request) {
 func (s *Server) handleRoot(w http.ResponseWriter, r *http.Request) {
 	w.Header().Set("Content-Type", "application/json")
 	w.WriteHeader(http.StatusOK)
-	fmt.Fprint(w, `{"name":"artifactapi","version":"3.0.0-dev"}`)
+	fmt.Fprintf(w, `{"name":"artifactapi","version":"%s"}`, s.version)
 }
 
 func (s *Server) newHTTPServer() *http.Server {

internal/virtual/engine.go

@@ -79,7 +79,7 @@ func (e *Engine) fetchMemberIndexes(ctx context.Context, virt models.Virtual, pa
 					results[idx] = result{err: fmt.Errorf("local index %q: %w", name, err)}
 					return
 				}
-				results[idx] = result{index: MemberIndex{RemoteName: name, RepoType: remote.RepoType, Body: body}}
+				results[idx] = result{index: MemberIndex{RemoteName: name, RepoType: remote.RepoType, BaseURL: remote.BaseURL, Body: body}}
 				return
 			}
 
@@ -102,7 +102,7 @@ func (e *Engine) fetchMemberIndexes(ctx context.Context, virt models.Virtual, pa
 				return
 			}
 
-			results[idx] = result{index: MemberIndex{RemoteName: name, RepoType: remote.RepoType, Body: body}}
+			results[idx] = result{index: MemberIndex{RemoteName: name, RepoType: remote.RepoType, BaseURL: remote.BaseURL, Body: body}}
 		}(i, memberName)
 	}
 

internal/virtual/helm_merger.go

@@ -54,15 +54,27 @@ func (m *HelmMerger) MergeIndexes(members []MemberIndex, proxyBaseURL string) ([
 				seen[chart][ver.Version] = true
 
 				if proxyBaseURL != "" {
+					routePrefix := "remote"
+					if member.RepoType == "local" {
+						routePrefix = "local"
+					}
+					baseHost := extractHost(member.BaseURL)
+
 					for i, u := range ver.URLs {
 						if strings.HasPrefix(u, "http://") || strings.HasPrefix(u, "https://") {
-							ver.URLs[i] = fmt.Sprintf("%s/api/v1/remote/%s/%s",
+							if baseHost != "" && extractHost(u) != baseHost {
+								continue
+							}
+							relPath := extractPathRelativeToBase(u, member.BaseURL)
+							ver.URLs[i] = fmt.Sprintf("%s/api/v1/%s/%s/%s",
 								strings.TrimRight(proxyBaseURL, "/"),
+								routePrefix,
 								member.RemoteName,
-								extractPath(u))
+								relPath)
 						} else {
-							ver.URLs[i] = fmt.Sprintf("%s/api/v1/remote/%s/%s",
+							ver.URLs[i] = fmt.Sprintf("%s/api/v1/%s/%s/%s",
 								strings.TrimRight(proxyBaseURL, "/"),
+								routePrefix,
 								member.RemoteName,
 								u)
 						}
@@ -78,6 +90,31 @@ func (m *HelmMerger) MergeIndexes(members []MemberIndex, proxyBaseURL string) ([
 	return yaml.Marshal(merged)
 }
 
+func extractHost(rawURL string) string {
+	idx := strings.Index(rawURL, "://")
+	if idx == -1 {
+		return ""
+	}
+	rest := rawURL[idx+3:]
+	slashIdx := strings.Index(rest, "/")
+	if slashIdx == -1 {
+		return rest
+	}
+	return rest[:slashIdx]
+}
+
+func extractPathRelativeToBase(rawURL, baseURL string) string {
+	fullPath := extractPath(rawURL)
+	basePath := extractPath(baseURL)
+	if basePath != "" {
+		basePath = strings.TrimRight(basePath, "/") + "/"
+		if strings.HasPrefix(fullPath, basePath) {
+			return fullPath[len(basePath):]
+		}
+	}
+	return fullPath
+}
+
 func extractPath(rawURL string) string {
 	idx := strings.Index(rawURL, "://")
 	if idx == -1 {

internal/virtual/merger.go

@@ -9,6 +9,7 @@ import (
 type MemberIndex struct {
 	RemoteName string
 	RepoType   models.RepoType
+	BaseURL    string
 	Body       []byte
 }
 

ui/Dockerfile.ui

@@ -6,13 +6,20 @@ COPY package.json package-lock.json* ./
 RUN npm ci
 
 COPY . .
+
+ARG BASE_PATH=/
+ENV BASE_PATH=${BASE_PATH}
 RUN npm run build
 
 FROM nginx:alpine
 
+ARG BASE_PATH=/
+
 COPY --from=builder /app/dist /usr/share/nginx/html
 COPY nginx.conf /etc/nginx/conf.d/default.conf
 
+RUN sed -i "s|\${BASE_PATH}|${BASE_PATH}|g" /etc/nginx/conf.d/default.conf
+
 EXPOSE 80
 
 CMD ["nginx", "-g", "daemon off;"]

ui/nginx.conf

@@ -5,33 +5,12 @@ server {
     root /usr/share/nginx/html;
     index index.html;
 
-    location /api/ {
-        proxy_pass http://artifactapi:8000;
-        proxy_set_header Host $host;
-        proxy_set_header X-Real-IP $remote_addr;
-        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-        proxy_set_header X-Forwarded-Proto $scheme;
-        proxy_buffering off;
-    }
-
-    location /v2/ {
-        proxy_pass http://artifactapi:8000;
-        proxy_set_header Host $host;
-        proxy_set_header X-Real-IP $remote_addr;
-        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-        proxy_set_header X-Forwarded-Proto $scheme;
-        proxy_buffering off;
-    }
-
-    location /health {
-        proxy_pass http://artifactapi:8000;
-    }
-
-    location /metrics {
-        proxy_pass http://artifactapi:8000;
-    }
-
-    location / {
+    location ${BASE_PATH}/ {
+        rewrite ^${BASE_PATH}(/.*)$ $1 break;
         try_files $uri $uri/ /index.html;
     }
+
+    location = ${BASE_PATH} {
+        return 301 ${BASE_PATH}/;
+    }
 }

ui/src/main.tsx

@@ -4,9 +4,13 @@ import { BrowserRouter } from 'react-router-dom';
 import { App } from './App';
 import './index.css';
 
+declare const __BASE_PATH__: string;
+
+const basename = __BASE_PATH__.replace(/\/+$/, '') || '/';
+
 createRoot(document.getElementById('root')!).render(
   <StrictMode>
-    <BrowserRouter>
+    <BrowserRouter basename={basename}>
       <App />
     </BrowserRouter>
   </StrictMode>,

ui/src/pages/Dashboard.tsx

@@ -50,6 +50,11 @@ export function Dashboard() {
           value={formatNumber(stats.total_blobs_deduped)}
           sub="shared blobs"
         />
+        <StatsCard
+          label="Bandwidth Saved"
+          value={formatBytes(stats.bandwidth_saved_30d)}
+          sub="last 30 days"
+        />
       </div>
 
       {health && (

ui/vite.config.ts

@@ -1,7 +1,10 @@
 import { defineConfig } from 'vite'
 import react from '@vitejs/plugin-react'
 
+const basePath = process.env.BASE_PATH || '/'
+
 export default defineConfig({
+  base: basePath,
   plugins: [react()],
   server: {
     proxy: {
@@ -11,4 +14,7 @@ export default defineConfig({
       '/metrics': 'http://localhost:8000',
     },
   },
+  define: {
+    '__BASE_PATH__': JSON.stringify(basePath),
+  },
 })