Merge pull request #236 from clown15/fix-cleanup-stale-uploads-modtime

Parse native multipart directory timestamps before the Base64 compatibility path. Cover ambiguous plaintext IDs, cleanup metadata reads, expiration, and conservative legacy fallback. Signed-off-by: Feng Ruohang <rh@vonng.com>
2026-10-16 22:55:58 +03:00 · 2026-10-15 18:31:35 +08:00
parent a592d69f45 bfc7906064
commit a7370aa9ac
2 changed files with 196 additions and 10 deletions
@@ -0,0 +1,177 @@
+// Copyright (c) 2026 clown15
+//
+// This file is part of Silo Object Storage stack
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"context"
+	"encoding/base64"
+	"fmt"
+	"net/url"
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+)
+
+func TestExtractModTimeFromUploadIDDir(t *testing.T) {
+	now := time.Unix(1792056747, 123456789).UTC()
+	nano := now.UnixNano()
+	uuid := "d16ad42a-6fe5-4a3b-8092-69983142238f"
+
+	testCases := []struct {
+		name        string
+		dirName     string
+		expectedMod time.Time
+		wantZero    bool
+	}{
+		{
+			name:        "Modern Plaintext Format (<UUID>x<UnixNano>)",
+			dirName:     fmt.Sprintf("%sx%d", uuid, nano),
+			expectedMod: time.Unix(0, nano),
+			wantZero:    false,
+		},
+		{
+			// This valid UUID decodes to bytes containing 'x'. Checking
+			// for that byte before parsing plaintext loses the timestamp.
+			name:        "Plaintext Also Decodes To Base64 Containing x",
+			dirName:     fmt.Sprintf("4eacd477-e733-4851-b821-6fd42785ff87x%d", nano),
+			expectedMod: now,
+		},
+		{
+			name:        "Legacy Format Without Timestamp (<UUID>)",
+			dirName:     uuid,
+			expectedMod: time.Time{},
+			wantZero:    true,
+		},
+		{
+			name:        "Base64 Encoded Format",
+			dirName:     base64.RawURLEncoding.EncodeToString([]byte(fmt.Sprintf("%sx%d", uuid, nano))),
+			expectedMod: time.Unix(0, nano),
+			wantZero:    false,
+		},
+		{
+			name:        "Encoded Format With Deployment Prefix",
+			dirName:     base64.RawURLEncoding.EncodeToString([]byte(fmt.Sprintf("%s.%sx%d", uuid, uuid, nano))),
+			expectedMod: now,
+		},
+		{
+			name:        "Malformed Suffix (<UUID>xinvalid)",
+			dirName:     fmt.Sprintf("%sxnotanumber", uuid),
+			expectedMod: time.Time{},
+			wantZero:    true,
+		},
+		{
+			name:     "Timestamp Overflow",
+			dirName:  uuid + "x9223372036854775808",
+			wantZero: true,
+		},
+		{
+			name:     "Malformed Plaintext UUID",
+			dirName:  fmt.Sprintf("not-a-uuidx%d", nano),
+			wantZero: true,
+		},
+		{
+			name:        "Empty Directory Name",
+			dirName:     "",
+			expectedMod: time.Time{},
+			wantZero:    true,
+		},
+	}
+
+	for _, tc := range testCases {
+		t.Run(tc.name, func(t *testing.T) {
+			got := extractModTimeFromUploadIDDir(tc.dirName)
+			if tc.wantZero {
+				if !got.IsZero() {
+					t.Fatalf("expected zero time for %q, got %v", tc.dirName, got)
+				}
+				return
+			}
+			if !got.Equal(tc.expectedMod) {
+				t.Fatalf("extractModTimeFromUploadIDDir(%q) = %v; want %v", tc.dirName, got, tc.expectedMod)
+			}
+		})
+	}
+}
+
+type multipartCleanupDisk struct {
+	StorageAPI
+	root    string
+	modTime time.Time
+	readErr error
+	reads   int
+}
+
+func (d *multipartCleanupDisk) Endpoint() Endpoint {
+	return Endpoint{URL: &url.URL{Path: d.root}}
+}
+
+func (d *multipartCleanupDisk) ReadVersion(context.Context, string, string, string, string, ReadOptions) (FileInfo, error) {
+	d.reads++
+	return FileInfo{ModTime: d.modTime}, d.readErr
+}
+
+func (d *multipartCleanupDisk) StatVol(context.Context, string) (VolInfo, error) {
+	return VolInfo{Created: time.Now()}, nil
+}
+
+func TestCleanupStaleUploadsOnDisk(t *testing.T) {
+	const uuid = "d16ad42a-6fe5-4a3b-8092-69983142238f"
+	expiry := globalAPIConfig.getStaleUploadsExpiry()
+	for _, tc := range []struct {
+		name, prefix string
+		age          time.Duration
+		legacy       bool
+		readErr      error
+		wantReads    int
+		wantDeleted  bool
+	}{
+		{name: "recent", prefix: uuid, age: expiry / 2, readErr: errFileNotFound},
+		{name: "plaintext_base64_collision", prefix: "4eacd477-e733-4851-b821-6fd42785ff87", age: expiry / 2, readErr: errFileNotFound},
+		{name: "expired", prefix: uuid, age: 2 * expiry, readErr: errFileNotFound, wantDeleted: true},
+		{name: "legacy_recent", prefix: uuid, age: expiry / 2, legacy: true, wantReads: 1},
+		{name: "legacy_expired", prefix: uuid, age: 2 * expiry, legacy: true, wantReads: 1, wantDeleted: true},
+		{name: "legacy_metadata_missing", prefix: uuid, age: 2 * expiry, legacy: true, readErr: errFileNotFound, wantReads: 1},
+		{name: "malformed_metadata_missing", prefix: "not-a-uuid", age: 2 * expiry, readErr: errFileNotFound, wantReads: 1},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			modTime := time.Now().Add(-tc.age)
+			id := tc.prefix
+			if !tc.legacy {
+				id = fmt.Sprintf("%sx%d", tc.prefix, modTime.UnixNano())
+			}
+			disk := &multipartCleanupDisk{root: t.TempDir(), modTime: modTime, readErr: tc.readErr}
+			uploadDir := filepath.Join(disk.root, minioMetaMultipartBucket, "sha", id)
+			if err := os.MkdirAll(uploadDir, 0o755); err != nil {
+				t.Fatal(err)
+			}
+			erasureObjects{}.cleanupStaleUploadsOnDisk(t.Context(), disk)
+			if disk.reads != tc.wantReads {
+				t.Errorf("ReadVersion calls = %d, want %d", disk.reads, tc.wantReads)
+			}
+			_, err := os.Stat(uploadDir)
+			if tc.wantDeleted {
+				if !os.IsNotExist(err) {
+					t.Errorf("expired upload must be removed: %v", err)
+				}
+			} else if err != nil {
+				t.Errorf("upload must be preserved: %v", err)
+			}
+		})
+	}
+}
@@ -174,6 +174,24 @@ func (er erasureObjects) deleteAll(ctx context.Context, bucket, prefix string) {
 	wg.Wait()
 }

+// extractModTimeFromUploadIDDir extracts creation time from the upload ID directory on disk.
+// On-disk directory names are of the form <UUID>x<UnixNano>.
+// Parse the native format first: plaintext UUIDs can also be valid Base64.
+// Preserve the previous encoded-format parser for compatibility.
+func extractModTimeFromUploadIDDir(uploadIDDir string) time.Time {
+	if modTime, ok := multipartUploadTime(uploadIDDir); ok {
+		return modTime
+	}
+	if b64, err := base64.RawURLEncoding.DecodeString(uploadIDDir); err == nil {
+		if split := strings.Split(string(b64), "x"); len(split) == 2 {
+			if t, err := strconv.ParseInt(split[1], 10, 64); err == nil {
+				return time.Unix(0, t)
+			}
+		}
+	}
+	return time.Time{}
+}
+
 // Remove the old multipart uploads on the given disk.
 func (er erasureObjects) cleanupStaleUploadsOnDisk(ctx context.Context, disk StorageAPI) {
 	drivePath := disk.Endpoint().Path
@@ -181,16 +199,7 @@ func (er erasureObjects) cleanupStaleUploadsOnDisk(ctx context.Context, disk Sto
 	readDirFn(pathJoin(drivePath, minioMetaMultipartBucket), func(shaDir string, typ os.FileMode) error {
 		readDirFn(pathJoin(drivePath, minioMetaMultipartBucket, shaDir), func(uploadIDDir string, typ os.FileMode) error {
 			uploadIDPath := pathJoin(shaDir, uploadIDDir)
-			var modTime time.Time
-			// Upload IDs are of the form base64_url(<UUID>x<UnixNano>), we can extract the time from the UUID.
-			if b64, err := base64.RawURLEncoding.DecodeString(uploadIDDir); err == nil {
-				if split := strings.Split(string(b64), "x"); len(split) == 2 {
-					t, err := strconv.ParseInt(split[1], 10, 64)
-					if err == nil {
-						modTime = time.Unix(0, t)
-					}
-				}
-			}
+			modTime := extractModTimeFromUploadIDDir(uploadIDDir)
 			// Fallback for older uploads without time in the ID.
 			if modTime.IsZero() {
 				wait := deleteMultipartCleanupSleeper.Timer(ctx)