mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-09-08 15:41:15 +02:00
filer: route exclusive and conditional creates to the entry's ring owner (#11109)
* proto: resync the java copy of filer.proto The Makefile keeps other/java/client/src/main/proto/filer.proto a verbatim copy, but AssignVolumeResponse.fsync and SubscribeMetadataResponse.flushed_ts_ns landed without it. Copy them over; no behaviour change. Claude-Session: https://claude.ai/code/session_01Fx1Hx8RqsJqHpbfbgTf4WJ * filer: route exclusive and conditional creates to the entry's ring owner CreateEntry with o_excl is a FindEntry-then-Insert. The per-path lock added for it makes that atomic only on the filer running it, and the store's insert is an upsert on every backend, so two filers both pass the existence check and both report success. mkdir(2) then succeeds twice for the same path. The same hole sits under the condition precondition, whose comment already told callers to route the key's writes to the owner filer themselves. Do it on the server instead, with the mechanism ObjectTransaction already uses: resolve the entry's ring owner and forward one hop, bounded by is_moved. The ring's membership comes from the master, so it tolerates a stale view and reassigns when a filer dies, neither of which a client's configured filer list can do. Every creator gets this — mount, S3, the filer's own HTTP surface, the Java client — not only the ones that opted in. Plain creates are upserts whoever applies them, so they stay local and pay nothing. The route key shares the S3 gateway's namespace so an object's ObjectTransaction and its CreateEntry land on the same filer's per-path lock. Claude-Session: https://claude.ai/code/session_01Fx1Hx8RqsJqHpbfbgTf4WJ
This commit is contained in:
@@ -1014,6 +1014,16 @@ func (m *CreateEntryRequest) MarshalToSizedBufferVT(dAtA []byte) (int, error) {
|
||||
i -= len(m.unknownFields)
|
||||
copy(dAtA[i:], m.unknownFields)
|
||||
}
|
||||
if m.IsMoved {
|
||||
i--
|
||||
if m.IsMoved {
|
||||
dAtA[i] = 1
|
||||
} else {
|
||||
dAtA[i] = 0
|
||||
}
|
||||
i--
|
||||
dAtA[i] = 0x40
|
||||
}
|
||||
if m.Condition != nil {
|
||||
size, err := m.Condition.MarshalToSizedBufferVT(dAtA[:i])
|
||||
if err != nil {
|
||||
@@ -6687,6 +6697,9 @@ func (m *CreateEntryRequest) SizeVT() (n int) {
|
||||
l = m.Condition.SizeVT()
|
||||
n += 1 + l + protohelpers.SizeOfVarint(uint64(l))
|
||||
}
|
||||
if m.IsMoved {
|
||||
n += 2
|
||||
}
|
||||
n += len(m.unknownFields)
|
||||
return n
|
||||
}
|
||||
@@ -11746,6 +11759,26 @@ func (m *CreateEntryRequest) UnmarshalVT(dAtA []byte) error {
|
||||
return err
|
||||
}
|
||||
iNdEx = postIndex
|
||||
case 8:
|
||||
if wireType != 0 {
|
||||
return fmt.Errorf("proto: wrong wireType = %d for field IsMoved", wireType)
|
||||
}
|
||||
var v int
|
||||
for shift := uint(0); ; shift += 7 {
|
||||
if shift >= 64 {
|
||||
return protohelpers.ErrIntOverflow
|
||||
}
|
||||
if iNdEx >= l {
|
||||
return io.ErrUnexpectedEOF
|
||||
}
|
||||
b := dAtA[iNdEx]
|
||||
iNdEx++
|
||||
v |= int(b&0x7F) << shift
|
||||
if b < 0x80 {
|
||||
break
|
||||
}
|
||||
}
|
||||
m.IsMoved = bool(v != 0)
|
||||
default:
|
||||
iNdEx = preIndex
|
||||
skippy, err := protohelpers.Skip(dAtA[iNdEx:])
|
||||
|
||||
Reference in New Issue
Block a user