mirror of
https://github.com/pgsty/minio.git
synced 2026-11-10 17:45:32 +03:00
7f38bf6282
A native restore (POST ?restore, issue #281) marks the version ongoing, and a background worker rehydrates it from the tier. The worker, its upload and every status write could be reached or confused by other callers. A public client could write into or complete the restore upload. POST copied a whole metadata snapshot over newer protection changes. An old or failed attempt could act on a newer one. Restore, expiry and heal decided on whichever drive's metadata they read. Each POST that starts a rehydration now writes an attempt ID into the version's internal metadata, with the identity it resolved: version ID, ETag, size and ModTime. The worker, its upload, its part writes and its completion carry the attempt. A worker whose attempt no longer owns the version stops without writing, completing or resetting. Every write uses the versioning state and explicit version ID captured by POST, so a null target stays null. The restore upload carries an internal marker, decided over all drives. Public multipart calls answer NoSuchUpload and listings hide it. An unknown marker fails closed. A completion holds a commit lock from staging its commit in the upload until the commit ends. Stale cleanup decides on every upload past the stale age under that lock, and keeps it until its rename ends, also past the drive deadline. Abort of a committing upload takes the lock and removes a failed commit's leftover only when every copy is staged and older than one hour. POST, the worker, the reset, the ExpireRestored recheck and heal all decide on the authoritative revision of the exact version. That is the revision held by max(n/2+1, read quorum) drives, identified by the version header and the normalized metadata digest. Status writes patch only the restore fields of that revision. They write only the drives that hold it, and put the old revision back on failure. Heal copies restore fields only when a quorum holds the same fields. A failed attempt resets itself with bounded in-memory retries. A later POST takes over a stranded marker when no attempt runs. Otherwise it answers RestoreAlreadyInProgress within a few seconds. Older nodes do not know the marker. A new grid capability handler lets the serving node ask every peer. POST answers 503 ServiceUnavailable and writes nothing until all peers support native restore, and a queued worker asks again before it creates its upload. The single-pool lock-domain split between DELETE/CopyObject and restore is closed by its own fix, which this change depends on. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Signed-off-by: Feng Ruohang <rh@vonng.com>
249 lines
8.4 KiB
Go
249 lines
8.4 KiB
Go
// 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++
|
|
if d.readErr != nil {
|
|
return FileInfo{}, d.readErr
|
|
}
|
|
fi := newFileInfo("obj", 1, 0)
|
|
fi.Erasure.Index, fi.ModTime = 1, d.modTime
|
|
return fi, nil
|
|
}
|
|
|
|
// multipartCleanupSet is a set of one drive, which also answers the
|
|
// metadata reads that establish the restore marker of an expired upload.
|
|
// Its locks are local: stale cleanup decides a removal under the upload's
|
|
// commit lock.
|
|
func multipartCleanupSet(disk StorageAPI) erasureObjects {
|
|
return erasureObjects{getDisks: func() []StorageAPI { return []StorageAPI{disk} }, nsMutex: newNSLock(false)}
|
|
}
|
|
|
|
func (d *multipartCleanupDisk) StatVol(ctx context.Context, volume string) (VolInfo, error) {
|
|
return (&xlStorage{drivePath: d.root}).StatVol(ctx, volume)
|
|
}
|
|
|
|
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},
|
|
// Only an expired upload is read on every drive, for its restore marker.
|
|
{name: "expired", prefix: uuid, age: 2 * expiry, readErr: errFileNotFound, wantReads: 1, 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: 2, 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)
|
|
for _, dir := range []string{uploadDir, filepath.Join(disk.root, minioMetaTmpDeletedBucket)} {
|
|
if err := os.MkdirAll(dir, 0o755); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
}
|
|
// An old parent must not bypass a skipped upload's age or read error.
|
|
if err := os.Chtimes(filepath.Dir(uploadDir), modTime, modTime); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
multipartCleanupSet(disk).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)
|
|
}
|
|
if _, err := os.Stat(filepath.Dir(uploadDir)); !os.IsNotExist(err) {
|
|
t.Errorf("empty hash directory must be removed in the same pass: %v", err)
|
|
}
|
|
} else if err != nil {
|
|
t.Errorf("upload must be preserved: %v", err)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestCleanupStaleUploadsEmptyHashDirectory(t *testing.T) {
|
|
for _, age := range []time.Duration{0, 2 * globalAPIConfig.getStaleUploadsExpiry()} {
|
|
t.Run(age.String(), func(t *testing.T) {
|
|
disk := &multipartCleanupDisk{root: t.TempDir()}
|
|
shaDir := filepath.Join(disk.root, minioMetaMultipartBucket, "sha")
|
|
for _, dir := range []string{shaDir, filepath.Join(disk.root, minioMetaTmpDeletedBucket)} {
|
|
if err := os.MkdirAll(dir, 0o755); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
}
|
|
modTime := time.Now().Add(-age)
|
|
if err := os.Chtimes(shaDir, modTime, modTime); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
multipartCleanupSet(disk).cleanupStaleUploadsOnDisk(t.Context(), disk)
|
|
if _, err := os.Stat(shaDir); !os.IsNotExist(err) {
|
|
t.Fatalf("empty hash directory must be removed regardless of age: %v", err)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestCleanupStaleUploadsSharedHashDirectory(t *testing.T) {
|
|
disk := &multipartCleanupDisk{root: t.TempDir(), readErr: errFileNotFound}
|
|
shaDir := filepath.Join(disk.root, minioMetaMultipartBucket, "sha")
|
|
now := time.Now()
|
|
expiredID := fmt.Sprintf("d16ad42a-6fe5-4a3b-8092-69983142238fx%d", now.Add(-2*globalAPIConfig.getStaleUploadsExpiry()).UnixNano())
|
|
recentID := fmt.Sprintf("4eacd477-e733-4851-b821-6fd42785ff87x%d", now.UnixNano())
|
|
for _, id := range []string{expiredID, recentID} {
|
|
if err := os.MkdirAll(filepath.Join(shaDir, id), 0o755); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
}
|
|
partPath := filepath.Join(shaDir, recentID, "part.1")
|
|
const part = "recent upload part"
|
|
if err := os.WriteFile(partPath, []byte(part), 0o600); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
|
|
multipartCleanupSet(disk).cleanupStaleUploadsOnDisk(t.Context(), disk)
|
|
if _, err := os.Stat(filepath.Join(shaDir, expiredID)); !os.IsNotExist(err) {
|
|
t.Errorf("expired upload must be removed: %v", err)
|
|
}
|
|
if got, err := os.ReadFile(partPath); err != nil || string(got) != part {
|
|
t.Errorf("recent upload must remain intact: got %q, err %v", got, err)
|
|
}
|
|
}
|