mirror of
https://github.com/pgsty/minio.git
synced 2026-11-09 17:21:51 +03:00
fix(heal): send the dry-run flag to remote bucket heal
remotePeerS3Client.HealBucket sent only the bucket name and the remove flag, and HealBucketHandler built its heal options from those two values. During a dry-run bucket heal every remote node therefore ran a real one: it created the bucket directory on drives that lacked it, or removed empty bucket directories when the bucket was missing from every pool. Only the coordinating node honored DryRun. Add a "dry-run" key to the peer message and read it into HealOpts.DryRun on the receiving side, so healBucketLocal returns before MakeVol and DeleteVol on every node. The message is a string map: an older node ignores the key, and a missing key reads as false, so a mixed-version cluster behaves as before until every node is upgraded. The regression calls the real client over a test grid connection to the real handler. It fails on main, and it fails if either side of the change is removed. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Signed-off-by: Feng Ruohang <rh@vonng.com>
This commit is contained in:
@@ -1291,8 +1291,10 @@ func (s *peerRESTServer) HealBucketHandler(mss *grid.MSS) (np *grid.JSON[madmin.
|
||||
}
|
||||
|
||||
bucketDeleted := mss.Get(peerS3BucketDeleted) == "true"
|
||||
dryRun := mss.Get(peerS3BucketDryRun) == "true"
|
||||
res, err := healBucketLocal(context.Background(), bucket, madmin.HealOpts{
|
||||
Remove: bucketDeleted,
|
||||
DryRun: dryRun,
|
||||
})
|
||||
if err != nil {
|
||||
return np, grid.NewRemoteErr(err)
|
||||
|
||||
+11
-4
@@ -354,10 +354,7 @@ func (client *remotePeerS3Client) HealBucket(ctx context.Context, bucket string,
|
||||
return madmin.HealResultItem{}, nil
|
||||
}
|
||||
|
||||
mss := grid.NewMSSWith(map[string]string{
|
||||
peerS3Bucket: bucket,
|
||||
peerS3BucketDeleted: strconv.FormatBool(opts.Remove),
|
||||
})
|
||||
mss := healBucketPeerMSS(bucket, opts)
|
||||
|
||||
ctx, cancel := context.WithTimeout(ctx, globalDriveConfig.GetMaxTimeout())
|
||||
defer cancel()
|
||||
@@ -366,6 +363,16 @@ func (client *remotePeerS3Client) HealBucket(ctx context.Context, bucket string,
|
||||
return resp.ValueOrZero(), toStorageErr(err)
|
||||
}
|
||||
|
||||
// healBucketPeerMSS encodes the bucket heal options a peer applies to its
|
||||
// local drives. Peers that predate the dry-run key ignore it.
|
||||
func healBucketPeerMSS(bucket string, opts madmin.HealOpts) *grid.MSS {
|
||||
return grid.NewMSSWith(map[string]string{
|
||||
peerS3Bucket: bucket,
|
||||
peerS3BucketDeleted: strconv.FormatBool(opts.Remove),
|
||||
peerS3BucketDryRun: strconv.FormatBool(opts.DryRun),
|
||||
})
|
||||
}
|
||||
|
||||
// GetBucketInfo returns bucket stat info from a peer
|
||||
func (client *remotePeerS3Client) GetBucketInfo(ctx context.Context, bucket string, opts BucketOptions) (BucketInfo, error) {
|
||||
conn := client.gridConn()
|
||||
|
||||
@@ -0,0 +1,107 @@
|
||||
// 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 (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
|
||||
"github.com/minio/madmin-go/v3"
|
||||
"github.com/minio/minio/internal/grid"
|
||||
)
|
||||
|
||||
// A remote node must apply the caller's dry run to its local bucket heal.
|
||||
// The request goes from remotePeerS3Client.HealBucket over a grid connection
|
||||
// to the peer handler, as it does between the nodes of a deployment.
|
||||
func TestPeerHealBucketDryRun(t *testing.T) {
|
||||
obj, roots, err := prepareErasure(t.Context(), 4)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
setObjectLayer(obj)
|
||||
defer removeRoots(roots)
|
||||
defer obj.Shutdown(t.Context())
|
||||
|
||||
tg, err := grid.SetupTestGrid(2)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
defer tg.Cleanup()
|
||||
if err = healBucketRPC.Register(tg.Managers[1], (&peerRESTServer{}).HealBucketHandler); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
conn := func() *grid.Connection { return tg.Managers[0].Connection(tg.Hosts[1]) }
|
||||
client := &remotePeerS3Client{gridConn: conn}
|
||||
|
||||
const bucket = "peer-heal-dry-run"
|
||||
if err = obj.MakeBucket(t.Context(), bucket, MakeBucketOptions{}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
dirs := make([]string, len(roots))
|
||||
for i, root := range roots {
|
||||
dirs[i] = filepath.Join(root, bucket)
|
||||
}
|
||||
if err = os.Remove(dirs[0]); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
exists := func(dir string) bool {
|
||||
_, err := os.Stat(dir)
|
||||
return err == nil
|
||||
}
|
||||
heal := func(opts madmin.HealOpts) {
|
||||
t.Helper()
|
||||
if _, err := client.HealBucket(t.Context(), bucket, opts); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
|
||||
// Dry run must not recreate the missing bucket directory.
|
||||
heal(madmin.HealOpts{DryRun: true})
|
||||
if exists(dirs[0]) {
|
||||
t.Fatal("dry-run peer bucket heal created a missing bucket directory")
|
||||
}
|
||||
|
||||
// Dry run must not remove the empty bucket directories.
|
||||
heal(madmin.HealOpts{DryRun: true, Remove: true})
|
||||
for _, dir := range dirs[1:] {
|
||||
if !exists(dir) {
|
||||
t.Fatalf("dry-run peer bucket heal removed %s", dir)
|
||||
}
|
||||
}
|
||||
|
||||
// Controls. A message without the dry-run key, as sent by an older node,
|
||||
// still heals: the fixture reaches MakeVol.
|
||||
if _, err = healBucketRPC.Call(t.Context(), conn(), grid.NewMSSWith(map[string]string{
|
||||
peerS3Bucket: bucket,
|
||||
peerS3BucketDeleted: "false",
|
||||
})); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if !exists(dirs[0]) {
|
||||
t.Fatal("control: peer bucket heal did not recreate the missing directory")
|
||||
}
|
||||
|
||||
// A real heal with Remove reaches DeleteVol for the empty directories.
|
||||
heal(madmin.HealOpts{Remove: true})
|
||||
for _, dir := range dirs {
|
||||
if exists(dir) {
|
||||
t.Fatalf("control: peer bucket heal kept empty directory %s", dir)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -29,6 +29,7 @@ import (
|
||||
const (
|
||||
peerS3Bucket = "bucket"
|
||||
peerS3BucketDeleted = "bucket-deleted"
|
||||
peerS3BucketDryRun = "dry-run"
|
||||
peerS3BucketForceCreate = "force-create"
|
||||
peerS3BucketForceDelete = "force-delete"
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user