97 Commits

Author SHA1 Message Date
Zhen Ye
c171280f63
enhance: support replicate message in wal. (#44456)
issue: #44123

- support replicate message  in wal of milvus.
- support CDC-replicate recovery from wal.
- fix some CDC replicator bugs

Signed-off-by: chyezh <chyezh@outlook.com>
2025-09-22 17:06:11 +08:00
tinswzy
c7f21d5a06
enhance: purge small files right after wp segment compaction (#44473)
#43638 
improve wp log output
[wp#43](https://github.com/zilliztech/woodpecker/issues/43)
intro purge small files right after segment compaction
[wp#47](https://github.com/zilliztech/woodpecker/issues/47)
The rootpath configured by milvus is uniformly used as the base for wp
local fs storage.
update to v0.1.5

Signed-off-by: tinswzy <zhenyuan.wei@zilliz.com>
2025-09-21 16:32:01 +08:00
Zhen Ye
ba289891c0
enhance: add all ddl message into messages (#44407)
issue: #43897

- add ddl messages proto and add some message utilities.
- support shard/exclusive resource-key-lock.
- add all ddl callbacks future into broadcast registry.

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2025-09-18 10:08:00 +08:00
yihao.dai
51f69f32d0
feat: Add CDC support (#44124)
This PR implements a new CDC service for Milvus 2.6, providing log-based
cross-cluster replication.

issue: https://github.com/milvus-io/milvus/issues/44123

---------

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
Signed-off-by: chyezh <chyezh@outlook.com>
Co-authored-by: chyezh <chyezh@outlook.com>
2025-09-16 16:32:01 +08:00
Zhen Ye
cbe4c3d231
enhance: get cchannel before build message (#44229)
issue: #43897

- support never expire txn message.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-09-10 11:09:57 +08:00
Zhen Ye
9e2d1963d4
enhance: support cchannel for streaming service (#44143)
issue: #43897

- add cchannel as a special vchannel to hold some ddl and dcl.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-09-02 10:05:52 +08:00
Zhen Ye
3327df72e4
enhance: make immutable message as the param of ack operation for cdc (#43900)
issue: #43897

- The original broadcast ack operation need to recover message from
etcd, which can not support cdc.
- immutable message will set as the ack parameter to fix it.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-09-01 10:21:52 +08:00
XuanYang-cn
37a447d166
feat: Add CMEK cipher plugin (#43722)
1. Enable Milvus to read cipher configs
2. Enable cipher plugin in binlog reader and writer
3. Add a testCipher for unittests
4. Support pooling for datanode
5. Add encryption in storagev2

See also: #40321 
Signed-off-by: yangxuan <xuan.yang@zilliz.com>

---------

Signed-off-by: yangxuan <xuan.yang@zilliz.com>
2025-08-27 11:15:52 +08:00
Zhen Ye
5bdc593b8a
enhance: use v0.15.1 official pulsar client and add logging for pulsar client (#43913)
issue: #43785

- pulsar client will print log into milvus logger now.
- pulsar client open the metric by default.
- upgrade the pulsar client to v0.15.1, and use offical repo.
- the fixing of milvus-io/pulsar-client-go is already covered by
official v0.15.1.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-08-26 16:45:53 +08:00
Zhen Ye
d0e3a33c37
enhance: add IsRebalanceSuspended interface for wal balancer (#44026)
issue: #43968

Signed-off-by: chyezh <chyezh@outlook.com>
2025-08-24 09:19:47 +08:00
Zhen Ye
082ca62ec1
enhance: support balancer interface for streaming client to fetch streaming node information (#43969)
issue: #43968

- Add ListStreamingNode/GetWALDistribution to  fetch streaming node info
- Add SuspendRebalance/ResumeRebalance to enable or stop balance
- Add FreezeNodeIDs/DefreezeNodeIDs to freeze target node

Signed-off-by: chyezh <chyezh@outlook.com>
2025-08-21 15:55:47 +08:00
Zhen Ye
f5cee0012a
fix: remove panic for message type in recovery storage and marshal log (#43976)
issue: #43897

Signed-off-by: chyezh <chyezh@outlook.com>
2025-08-21 14:23:47 +08:00
tinswzy
6a342edc5a
fix: empty error returned on append timeout when MinIO is unavailable (#43926)
#43810 
Fixed the issue where the result err returned by append timeout was
empty when objectstorage was unavailable, causing the client to
mistakenly believe that the write was successful.

Signed-off-by: tinswzy <zhenyuan.wei@zilliz.com>
2025-08-19 10:47:45 +08:00
Zhen Ye
a86b6f2a54
enhance: extend the stats manage at streaming shard manager for L0 (#43371)
issue: #42416

- Rename the InsertMetric into ModifiedMetric.
- Add L0 control configuration.
- Add some L0 current state collect.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-08-18 20:41:46 +08:00
Zhen Ye
7b005c48bf
enhance: support util template generation for messages (#43881)
issue: #43880

Signed-off-by: chyezh <chyezh@outlook.com>
2025-08-18 01:19:44 +08:00
tinswzy
084f777552
enhance: use wp internal writer without lock (#43775)
#43638  #43810 
add internal writer without session lock;
refactor and unify read state and log entry
refactor data reading related methods;
fix bug where a closed writer is reused for finalize;

Signed-off-by: tinswzy <zhenyuan.wei@zilliz.com>
2025-08-18 01:15:44 +08:00
Zhen Ye
8ff118a9ff
fix: call IntoMessageProto instead of Payload when rpc (#43678)
issue: #43677

Signed-off-by: chyezh <chyezh@outlook.com>
2025-08-06 14:45:40 +08:00
Zhen Ye
3e3775fb81
fix: panics when describe collection internal failure (#43630)
issue: #43629

- also fix the scanner_switchable panic underlying wal scanner return
context error.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-07-29 20:33:36 +08:00
tinswzy
173efe2b98
enhance: wp metrics and update deps to v0.1.0 (#43569)
#43574   #43604 #43431  #43603 
Fix wp metrics not registered bug;
Update the version dependent on wp to v0.1.2-rc1;
improve advanced reader with concurrent prefetch blks;
add the segment rolling policy based on the number of blocks;
improve concurrent compaction
release lock failed bug

Signed-off-by: tinswzy <zhenyuan.wei@zilliz.com>
2025-07-29 14:51:35 +08:00
Zhen Ye
648994182f
fix: pulsar use more memory for queue (#43565)
issue: #43564

Signed-off-by: chyezh <chyezh@outlook.com>
2025-07-28 14:00:56 +08:00
Zhen Ye
070aabd27e
enhance: fix remove flushing state of segment (#43560)
issue: #43559, #42884

- also fix the data lost when streaming resuming from old arch message.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-07-25 18:08:54 +08:00
Zhen Ye
e9ab73e93d
enhance: add schema version at recovery storage (#43500)
issue: #43072, #43289

- manage the schema version at recovery storage.
- update the schema when creating collection or alter schema.
- get schema at write buffer based on version.
- recover the schema when upgrading from 2.5.

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2025-07-23 21:38:54 +08:00
Zhen Ye
07fa2cbdd3
enhance: wal balance consider the wal status on streamingnode (#43265)
issue: #42995

- don't balance the wal if the producing-consuming lag is too long.
- don't balance if the rebalance is set as false.
- don't balance if the wal is balanced recently.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-07-18 11:10:51 +08:00
tinswzy
7da62698e0
enhance: improve WP parallel sync mechanism and fencing logic (#42892)
related: #42595 
improve WP parallel sync mechanism and fencing logic; remove redundant
metrics and labels

Signed-off-by: tinswzy <zhenyuan.wei@zilliz.com>
2025-07-13 23:04:49 +08:00
Zhen Ye
15a6631147
enhance: add quota limit based on sn consuming lag (#43105)
issue: #42995

- The consuming lag at streaming node will be reported to coordinator.
- The consuming lag will trigger the write limit and deny by quota
center.
- Set the ttProtection by default.

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2025-07-11 14:10:49 +08:00
Zhen Ye
f598ca2b4e
fix: block at msgpack adaptor and wrong metrics (#43235)
issue: #43018

Signed-off-by: chyezh <chyezh@outlook.com>
2025-07-11 10:14:49 +08:00
Zhen Ye
490c5d5088
fix: lost message version after compatible message modification (#43217)
issue: #43018

Signed-off-by: chyezh <chyezh@outlook.com>
2025-07-10 10:36:48 +08:00
Zhen Ye
6798fdc3b3
fix: rocksmq cannot graceful stop (#42841)
issue: #40532

Signed-off-by: chyezh <chyezh@outlook.com>
2025-06-19 19:38:39 +08:00
Zhen Ye
593662970b
fix: reuse consumer for backlog clear and use shared consumer (#42822)
issue: #42820

- fix that ro pulsar cannot be closed when upgrading milvus.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-06-19 19:36:48 +08:00
Zhen Ye
4f5409e1fe
fix: panic when schema change (#42727)
issue: #42723

Signed-off-by: chyezh <chyezh@outlook.com>
2025-06-13 17:43:07 +08:00
Zhen Ye
1f66b650e9
fix: pulsar cannot work properly if backlog exceed (#42653)
issue: #42649

- the sync operation of different pchannel is concurrent now.
- add a option to notify the backlog clear automatically.
- make pulsar walimpls can be recovered from backlog exceed.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-06-13 14:28:37 +08:00
yihao.dai
e6da4a64b5
fix: Pre-check import message to prevent pipeline block indefinitely (#42415)
Pre-check import message to prevent pipeline block indefinitely.

issue: https://github.com/milvus-io/milvus/issues/42414

---------

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
Co-authored-by: chyezh <chyezh@outlook.com>
2025-06-11 13:40:38 +08:00
tinswzy
36a4b74fc0
enhance: Adjust the default parameters of WP according to performance tests (#42598)
#42595

Signed-off-by: tinswzy <zhenyuan.wei@zilliz.com>
2025-06-10 16:30:35 +08:00
tinswzy
f55f900c85
fix insert hang caused by WAL writer writing to a closing logfile (#42078)
related issue #42049 
wp commit
[94de4](94de4cbc60)

Signed-off-by: tinswzy <zhenyuan.wei@zilliz.com>
2025-06-03 09:58:36 +08:00
Zhen Ye
4bad293655
enhance: make upgrading from 2.5.x less down time (#42082)
issue: #40532

- start timeticksync at rootcoord if the streaming service is not
available
- stop timeticksync if the streaming service is available
- open a read-only wal if some nodes in cluster is not upgrading to 2.6
- allow to open read-write wal after all nodes in cluster is upgrading
to 2.6

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-29 23:02:29 +08:00
Zhen Ye
b94cee2413
fix: growing segment from old arch is not flushed after upgrading (#42164)
issue: #42162

- enhance: add read ahead buffer size issue #42129
- fix: rocksmq consumer's close operation may get stucked
- fix: growing segment from old arch is not flushed after upgrading

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-29 23:00:28 +08:00
tinswzy
1735f557ca
fix sn oom issue during small file loading in wp (#41946)
#41846  #41894 
Resolve SN OOM issue during small file loading in Woodpecker; 
Correct WP fence/close execution order;

Signed-off-by: tinswzy <zhenyuan.wei@zilliz.com>
2025-05-23 01:30:28 +08:00
Zhen Ye
c9b0748ff9
enhance: add delete rows into delete msg header and more metric (#41952)
issue: #41544

- add delete rows into delete messsage header
- add more insert/delete metrics
- fix non-broadcast message has broadcast header

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-22 20:28:26 +08:00
Zhen Ye
59dff668dc
enhance: schema change without manual flush (#41882)
issue: #39718

- remove the manual flush message from schema change operation
- add flush segment id handle into schema change processes

Signed-off-by: chyezh <chyezh@outlook.com>
Co-authored-by: congqixia <congqi.xia@zilliz.com>
2025-05-19 10:14:22 +08:00
tinswzy
4edb1bc6f1
fix: resolve wp WALImpls concurrent read/write bug (#41763)
#41563 #41579 #41842 #41846 #41758
Upgraded the wp dependency to incorporate recent fixes addressing
multiple concurrency bugs in WALImpls.

Signed-off-by: tinswzy <zhenyuan.wei@zilliz.com>
2025-05-16 12:02:27 +08:00
Zhen Ye
0a465bb5b7
enhance: use recovery+shardmanager, remove segment assignment interceptor (#41824)
issue: #41544

- add lock interceptor into wal.
- use recovery and shardmanager to replace the original implementation
of segment assignment.
- remove redundant implementation and unittest.
- remove redundant proto definition.
- use 2 streamingnode in e2e.

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-14 23:00:23 +08:00
Zhen Ye
21d6d1669e
fix: wal should be reopen if wal append receive the fence error (#41807)
issue: #41544

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-14 01:02:56 +08:00
Zhen Ye
7beafe99a7
enhance: implement wal garbage collector with truncate api (#41770)
issue: #41544

- add a truncator implementation into wal recovery storage.
- add metrics for recovery storage.

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-13 22:08:56 +08:00
Zhen Ye
52950ce392
enhance: add pulsar truncate api to protect pulsar unconsumed message (#41724)
issue: #41465

- implement truncate api for pulsar based on durable subscription.
- truncate api can only be called if wal is read-write.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-11 20:50:55 +08:00
Zhen Ye
e675da76e4
enhance: simplify the proto message, make segment assignment code more clean (#41671)
issue: #41544

- simplify the proto message for flush and create segment.
- simplify the msg handler for flowgraph.

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-11 20:49:00 +08:00
Zhen Ye
f62a2e281e
enhance: add MustAsMutable... function, cooldown notifier, hardware listener (#41637)
issue: #41544

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-06 01:16:52 +08:00
Zhen Ye
de8f0af20d
enhance: use dispatcher at delegator when enable streaming (#41266)
issue: #38399

- add an adaptor type to adapt the streaming service client and
msgstream client to reuse the msgdispatcher.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-06 01:12:53 +08:00
XuanYang-cn
b6f3fd0de1
enhance: Update to the latest CipherPlugin API (#41599)
See also: #41585

Signed-off-by: yangxuan <xuan.yang@zilliz.com>
2025-04-29 14:50:50 +08:00
tinswzy
b36ed03141
enhance: Add Truncate Interface to WALImpls for Log Retention Control (#41517)
#41465 Add Truncate Interface to WALImpls for Proactive Log Retention
Management

Signed-off-by: tinswzy <zhenyuan.wei@zilliz.com>
2025-04-29 14:36:49 +08:00
Zhen Ye
dfbb02a5f7
enhance: make streaming message as a log field for easier coding (#41545)
issue: #41544

- implement message can be logged as a field by zap.
- fix too many slow log for woodpecker.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-04-28 14:38:42 +08:00