astelm/minio
1
0
Fork 0
mirror of https://github.com/pgsty/minio.git synced 2026-10-30 20:41:03 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix: retain maintenance read compatibility with write safety fixes

Browse Source 
Signed-off-by: Feng Ruohang <rh@vonng.com>
This commit is contained in:
Feng Ruohang
2026-10-25 18:39:31 +08:00
parent 9449e6a4a8
commit 2a04d5f485
18 changed files with 639 additions and 360 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cmd/metacache-null-quorum_test.go
+11 -35
View File
@@ -701,13 +701,9 @@ func TestSingleNullQuorumReadAndConsumers(t *testing.T) {
}
}
put(newBody, oldTime.Add(time.Minute))
newMeta := make([][]byte, len(disks))
for i, disk := range disks {
newMeta[i] = mustReadNullQuorumMeta(t, disk, bucket, object)
}
newMinorityMeta := mustReadNullQuorumMeta(t, disks[14], bucket, object)
// Model an incomplete overwrite using real inline shards: fifteen old
// copies retain a read quorum; the final disk contains the newer minority.
// The old quorum does not prove that the newer overwrite was uncommitted.
for i := range 15 {
if err := disks[i].WriteAll(t.Context(), bucket, object+"/"+xlStorageFormatFile, oldMeta[i]); err != nil {
t.Fatal(err)
@@ -725,38 +721,18 @@ func TestSingleNullQuorumReadAndConsumers(t *testing.T) {
t.Fatalf("wrong readable generation: %v, %v", oi.ModTime, err)
}
}
for _, method := range []string{http.MethodGet, http.MethodHead} {
rec := nullQuorumRequest(t, router, method, getGetObjectURL("", bucket, object))
if rec.Code != http.StatusServiceUnavailable {
t.Fatalf("%s exposed an unresolved old quorum: %d", method, rec.Code)
}
}
if _, err := z.HealObject(t.Context(), bucket, object, "", madmin.HealOpts{Remove: true}); !isErrReadQuorum(err) {
t.Fatalf("heal accepted an unresolved old quorum: %v", err)
}
checkRead(oldBody, oldTime)
// Reading must not reinterpret the minority as absent or delete it.
minority, err := disks[15].ReadVersion(t.Context(), "", bucket, object, "", ReadOptions{})
if err != nil || !minority.ModTime.Equal(oldTime.Add(time.Minute)) {
t.Fatalf("read mutated the minority: %+v, %v", minority, err)
}
// Now model the safe direction: the latest generation has the quorum.
// Keep the migration, Walk and scanner assertions on that readable state.
for i := range 15 {
if err := disks[i].WriteAll(t.Context(), bucket, object+"/"+xlStorageFormatFile, newMeta[i]); err != nil {
t.Fatal(err)
}
}
if err := disks[15].WriteAll(t.Context(), bucket, object+"/"+xlStorageFormatFile, oldMeta[15]); err != nil {
t.Fatal(err)
}
newTime := oldTime.Add(time.Minute)
checkRead(newBody, newTime)
for _, kind := range []string{"rebalance", "decommission"} {
t.Run(kind, func(t *testing.T) {
var names []string
consume := func(entry metaCacheEntry) {
versions, err := entry.fileInfoVersions(bucket)
if err != nil || len(versions.Versions) != 1 || !versions.Versions[0].ModTime.Equal(newTime) {
if err != nil || len(versions.Versions) != 1 || !versions.Versions[0].ModTime.Equal(oldTime) {
t.Errorf("invalid migration metadata: %+v, %v", versions, err)
return
}
@@ -769,7 +745,7 @@ func TestSingleNullQuorumReadAndConsumers(t *testing.T) {
}
body, err := io.ReadAll(reader)
reader.Close()
if err != nil || !bytes.Equal(body, newBody) {
if err != nil || !bytes.Equal(body, oldBody) {
t.Errorf("migration could not read selected object data: %v", err)
}
names = append(names, entry.name)
@@ -792,7 +768,7 @@ func TestSingleNullQuorumReadAndConsumers(t *testing.T) {
}
var names []string
for result := range results {
if result.Err != nil || !result.Item.ModTime.Equal(newTime) {
if result.Err != nil || !result.Item.ModTime.Equal(oldTime) {
t.Fatalf("Walk returned invalid metadata: %+v", result)
}
names = append(names, result.Item.Name)
@@ -803,22 +779,22 @@ func TestSingleNullQuorumReadAndConsumers(t *testing.T) {
}
// Exercise the scanner's actual abandoned-child path. Make the scan drive
// miss the object, while keeping the latest quorum and an older minority on
// miss the object, while keeping an older quorum and a newer minority on
// the remaining disks. Its queued heal must read all disks and repair both.
if err := disks[14].WriteAll(t.Context(), bucket, object+"/"+xlStorageFormatFile, oldMeta[14]); err != nil {
if err := disks[14].WriteAll(t.Context(), bucket, object+"/"+xlStorageFormatFile, newMinorityMeta); err != nil {
t.Fatal(err)
}
if err := os.RemoveAll(filepath.Join(disks[15].Endpoint().Path, bucket, object)); err != nil {
t.Fatal(err)
}
scanNullQuorumAbandoned(t, z, bucket, object, newTime)
scanNullQuorumAbandoned(t, z, bucket, object, oldTime)
for i, disk := range disks {
fi, err := disk.ReadVersion(t.Context(), "", bucket, object, "", ReadOptions{Healing: true})
if err != nil || !fi.ModTime.Equal(newTime) {
if err != nil || !fi.ModTime.Equal(oldTime) {
t.Fatalf("scanner heal did not reconcile disk %d: %v, %v", i, fi.ModTime, err)
}
}
checkRead(newBody, newTime)
checkRead(oldBody, oldTime)
put(newBody, oldTime.Add(2*time.Minute))
checkRead(newBody, oldTime.Add(2*time.Minute))
}
@@ -914,5 +890,5 @@ func scanNullQuorumAbandoned(t *testing.T, z *erasureServerPools, bucket, object
if flat == nil || flat.Objects != 1 || flat.Size != 8192 {
t.Fatalf("scanner lost the healed object from usage: %+v", flat)
}
t.Logf("scanner queued %v; healed latest quorum, repaired minority/missing copies, and retained one 8192-byte object", healed)
t.Logf("scanner queued %v; healed old quorum, repaired minority/missing copies, and retained one 8192-byte object", healed)
}