Files
minio/cmd/metacache-listing-locks_test.go
T
Feng Ruohang e90cb2067d fix(listing): preserve readable keys across pool and metadata disagreements
Continue PR #221 while retaining its original commits and authorship.
Route latest-only fallback reads through the namespace lock used by normal
writes, propagate terminal scan errors before cache completion, and retain
delete markers until the cross-pool merge has resolved them.

Recount narrowly eligible latest null-version metadata when mixed erasure
layouts prevent selection. Keep each EC group separate and preserve the
requested quorum, strict resolution, and version-listing behavior.

Add regression coverage for locking, terminal errors, cache completion,
delete markers, mixed EC layouts, and HTTP behavior; run focused race tests
in CI. Verified with make test, focused race tests, and local distributed
single- and multi-pool rolling-restart workloads with exact final oracles.

Refs: https://github.com/pgsty/silo/issues/218
Refs: https://github.com/pgsty/silo/pull/221
Signed-off-by: Feng Ruohang <rh@vonng.com>
2026-10-16 00:58:46 +08:00

138 lines
4.1 KiB
Go

// Copyright (c) 2026 Feng Ruohang
//
// 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 (
"bytes"
"context"
"net/http"
"testing"
"time"
)
// The fallback on pool 1 must contend with the
// pools-layer lock used by ordinary multi-pool writers (anchored at pool 0).
func TestListFallbackMultiPoolReadLock(t *testing.T) {
z, bucket, _ := listingPoolsBackend(t)
ctx := t.Context()
set := z.serverPools[1].sets[0]
disks := set.getDisks()
const object = "object"
body := bytes.Repeat([]byte{'a'}, 8192)
mtime := time.Now().UTC().Add(-time.Hour)
put := func(tm time.Time) {
_, err := set.PutObject(ctx, bucket, object, mustGetPutObjReader(t, bytes.NewReader(body), int64(len(body)), "", ""), ObjectOptions{MTime: tm})
if err != nil {
t.Fatal(err)
}
}
put(mtime)
old := make([][]byte, len(disks))
for i := range old {
old[i] = mustReadNullQuorumMeta(t, disks[i], bucket, object)
}
put(mtime.Add(time.Minute))
entries := make(metaCacheEntries, len(disks))
errs := make([]error, len(disks))
for i := range 3 {
entries[i] = metaCacheEntry{name: object, metadata: old[i]}
}
for i := 3; i < 8; i++ {
entries[i] = metaCacheEntry{name: object, metadata: mustReadNullQuorumMeta(t, disks[i], bucket, object)}
}
for i := 8; i < len(disks); i++ {
errs[i] = errDiskNotFound
}
resolver := metadataResolutionParams{dirQuorum: 8, objQuorum: 8, bucket: bucket, requestedVersions: 1}
lock := z.NewNSLock(bucket, object)
lkctx, err := lock.GetLock(ctx, globalOperationTimeout)
if err != nil {
t.Fatal(err)
}
locked := true
defer func() {
if locked {
lock.Unlock(lkctx)
}
}()
done := make(chan struct{})
var entry *metaCacheEntry
var readErr error
go func() {
defer close(done)
entry, readErr = set.resolveListEntry(ctx, bucket, entries, errs, &resolver, z.listingNSLock(set))
}()
waitForListingReadLock(t, z.serverPools[0].sets[0].nsMutex, bucket, object, done)
lock.Unlock(lkctx)
locked = false
<-done
if readErr != nil || entry == nil || entry.name != object {
t.Fatalf("fallback after writer unlock: entry=%v err=%v", entry, readErr)
}
}
// Observe the reader registered on the writer's actual namespace lock before
// releasing the writer. This tests mutual exclusion without a timed sleep.
func waitForListingReadLock(t *testing.T, mutex *nsLockMap, bucket, object string, done <-chan struct{}) {
t.Helper()
timer := time.NewTimer(5 * time.Second)
defer timer.Stop()
tick := time.NewTicker(time.Millisecond)
defer tick.Stop()
for {
mutex.lockMapMutex.Lock()
lock := mutex.lockMap[pathJoin(bucket, object)]
waiting := lock != nil && lock.ref > 1
mutex.lockMapMutex.Unlock()
if waiting {
return
}
select {
case <-done:
t.Fatal("listing completed while the writer held its namespace lock")
case <-timer.C:
t.Fatal("listing did not wait on the writer's namespace lock")
case <-tick.C:
}
}
}
func listingPoolsBackend(t *testing.T) (*erasureServerPools, string, http.Handler) {
t.Helper()
ctx, cancel := context.WithCancel(t.Context())
obj, dirs, err := prepareErasurePoolsWithContext(ctx)
if err != nil {
cancel()
t.Fatal(err)
}
z := obj.(*erasureServerPools)
previous := newObjectLayerFn()
setObjectLayer(z)
t.Cleanup(func() {
cancel()
z.Shutdown(context.Background())
removeRoots(dirs)
setObjectLayer(previous)
})
bucket, router, err := initAPIHandlerTest(ctx, z, nil, MakeBucketOptions{})
if err != nil {
t.Fatal(err)
}
return z, bucket, router
}