Commit Graph

35 Commits (master)

Author SHA1 Message Date
sthuang a2c7ed2780
fix: [StorageV2] sort field binlogs paths for packed reader and writer (#43585)
key changes:
* fix unstable storage v2 compaction unit test by guaranteeing the order
of paths during sync.
* bump milvus-storage version, include
https://github.com/milvus-io/milvus-storage/pull/222
https://github.com/milvus-io/milvus-storage/pull/223
https://github.com/milvus-io/milvus-storage/pull/224
https://github.com/milvus-io/milvus-storage/pull/225
https://github.com/milvus-io/milvus-storage/pull/226
* Also fix the below related oom issue.
related: https://github.com/milvus-io/milvus/issues/43310

Signed-off-by: shaoting-huang <shaoting.huang@zilliz.com>
2025-07-30 08:09:36 +08:00
sthuang a0c9f499ee
fix: [StorageV2] sync panic with nullable add field (#43142)
related: https://github.com/milvus-io/milvus/pull/42932
fix: https://github.com/milvus-io/milvus/issues/43072

Signed-off-by: shaoting-huang <shaoting.huang@zilliz.com>
2025-07-25 10:08:53 +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
congqixia b8d7045539
enhance: [Add Field] Use consistent schema for single buffer (#41891)
Related to #41873

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-05-17 19:46:22 +08:00
congqixia a6d09ff4cd
enhance: [StorageV2] fix issues integrating basic RW operations (#41834)
Related to #39173

This PR:
- Upgrade milvus-storage commit to fix filesystem finalized issue
- Add bucket-name as prefix for all fs style access io
- Initial arrow fs on querynodes startup
- Fix timestamp access when loading sealed segment

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-05-15 09:52:23 +08:00
congqixia 476984c53e
fix: [AddField] Use latest schema instead of cached one (#41757)
Related to #41713 #41710

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-05-12 16:24:56 +08:00
Ted Xu 1bcea2a775
fix: assigning the correct storage version in sync and index tasks (#41093)
See #39663 #40667

---------

Signed-off-by: Ted Xu <ted.xu@zilliz.com>
2025-04-08 10:14:25 +08:00
sthuang 63a7c4570e
feat: storage v2 sync (#39663)
related: #39173

Signed-off-by: shaoting-huang <shaoting.huang@zilliz.com>
2025-03-05 11:22:15 +08:00
congqixia cb7f2fa6fd
enhance: Use v2 package name for pkg module (#39990)
Related to #39095

https://go.dev/doc/modules/version-numbers

Update pkg version according to golang dep version convention

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-02-22 23:15:58 +08:00
Ted Xu 56659bacbb
enhance: make serialization be part of sync task to support file format change (#38946)
See #38945

---------

Signed-off-by: Ted Xu <ted.xu@zilliz.com>
2025-01-23 15:49:05 +08:00
yihao.dai ec2e77b5d7
enhance: Reduce memory usage of BF in DataNode and QueryNode (#38129)
1. DataNode: Skip generating BF during the insert phase (BF will be
regenerated during the sync phase).
2. QueryNode: Skip generating or maintaining BF for growing segments;
deletion checks will be handled in the segcore.

issue: https://github.com/milvus-io/milvus/issues/37630

---------

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2025-01-15 01:59:01 +08:00
Zhen Ye bb8d1ab3bf
enhance: make new go package to manage proto (#39114)
issue: #39095

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2025-01-10 10:49:01 +08:00
jaime 29e620fa6d
fix: sync task still running after DataNode has stopped (#38377)
issue: #38319

Signed-off-by: jaime <yun.zhang@zilliz.com>
2024-12-17 18:06:44 +08:00
wei liu 2035575941
fix: Datanode stop progress stuck at writer buffer memory check (#38274)
issue: #38273

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-12-06 18:20:39 +08:00
XuanYang-cn 70e6a00ba1
fix: Replace outer lock with concurrent map (#37817)
See also: #37493

---------

Signed-off-by: yangxuan <xuan.yang@zilliz.com>
2024-11-21 16:08:33 +08:00
XuanYang-cn 5a23c80f20
fix: Change memoryCheck write lock to read lock (#37525)
See also: milvus-io#37493

Signed-off-by: yangxuan <xuan.yang@zilliz.com>

Signed-off-by: yangxuan <xuan.yang@zilliz.com>
2024-11-15 10:44:31 +08:00
XuanYang-cn 31a8d08bdd
fix: Correct varchar primarykey size calculation (#37617)
See also: #37582

---------

Signed-off-by: yangxuan <xuan.yang@zilliz.com>
2024-11-14 14:16:38 +08:00
Zhen Ye 49657c4690
enhance: add create segment message, enable empty segment flush (#37407)
issue: #37172

- add redo interceptor to implement append context refresh. (make new
timetick)
- add create segment handler for flusher.
- make empty segment flushable and directly change it into dropped.
- add create segment message into wal when creating new growing segment.
- make the insert operation into following seq: createSegment -> insert
-> insert -> flushSegment.
- make manual flush into following seq: flushTs -> flushsegment ->
flushsegment -> manualflush.

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2024-11-08 10:16:34 +08:00
yihao.dai 81879425e1
enhance: Optimize the performance of stats task (#37374)
1. Increase the writer's `batchSize` to avoid multiple serialization
operations.
2. Perform asynchronous upload of binlog files to prevent blocking the
data processing flow.
3. Reduce multiple calls to `writer.Flush()`.

issue: https://github.com/milvus-io/milvus/issues/37373

---------

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2024-11-08 10:08:27 +08:00
jaime 9d16b972ea
feat: add tasks page into management WebUI (#37002)
issue: #36621

1. Add API to access task runtime metrics, including:
  - build index task
  - compaction task
  - import task
- balance (including load/release of segments/channels and some leader
tasks on querycoord)
  - sync task
2. Add a debug model to the webpage by using debug=true or debug=false
in the URL query parameters to enable or disable debug mode.

Signed-off-by: jaime <yun.zhang@zilliz.com>
2024-10-28 10:13:29 +08:00
XuanYang-cn b172ea1093
fix: Remove enableLevelZeroSegment config (#36535)
See also: #36504

---------

Signed-off-by: yangxuan <xuan.yang@zilliz.com>
2024-10-17 11:59:24 +08:00
Zhen Ye 8905b042f1
fix: add proportion for capacity seal policy in streaming flusher (#36761)
issue: #36760

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2024-10-14 14:47:22 +08:00
XuanYang-cn 794e3ab7e5
fix: fail to init fg clears flushTs so that slows flush (#36740)
See also: #36709

Signed-off-by: yangxuan <xuan.yang@zilliz.com>
2024-10-11 17:37:04 +08:00
yihao.dai 80f25d497f
enhance: Add metrics to monitor import throughput and imported rows (#36519)
issue: https://github.com/milvus-io/milvus/issues/36518

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2024-09-28 17:31:15 +08:00
yihao.dai 9e8cafcbe2
enhance: Skip loading bf in datanode (#36367)
Skip loading bf in datanode:
1. When watching vchannels, skip loading bloom filters for segments.
2. Bypass bloom filter checks for delete messages, directly writing to
L0 segments.
3. Remove flushed segments proactively after flush.

issue: https://github.com/milvus-io/milvus/issues/34585

---------

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2024-09-26 10:11:15 +08:00
aoiasd 139787371e
feat: support embedding bm25 sparse vector and flush bm25 stats log (#36036)
relate: https://github.com/milvus-io/milvus/issues/35853

---------

Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
2024-09-19 10:57:12 +08:00
congqixia c6eb6c7cb2
enhance: Add error handler for write buffer (#36216)
Related to #36215

This PR add error handler setting option providing the possibility to
change error handling behavior other than panicking.

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-09-13 10:11:09 +08:00
yihao.dai 6130a85444
enhance: Remove bf from streaming node (#35902)
Remove bf from streaming node:
1. When watching vchannels, skip loading bloom filters for segments.
2. Bypass bloom filter checks for delete messages, directly writing to
L0 segments.
3. Remove flushed segments proactively after flush.

issue: https://github.com/milvus-io/milvus/issues/33285,
https://github.com/milvus-io/milvus/issues/34585

---------

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2024-09-03 14:17:02 +08:00
congqixia ab532ae199
enhance: Add back BF lazy load logic for datanode watch channel (#35646)
Add back lazy loading statslog when watch dml channel on datanode.

Related to #22994 #27675

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-08-22 19:42:57 +08:00
smellthemoon 80a7c78f28
enhance: import supports null in parquet and json formats (#35558)
#31728

---------

Signed-off-by: lixinguo <xinguo.li@zilliz.com>
Co-authored-by: lixinguo <xinguo.li@zilliz.com>
2024-08-20 16:50:55 +08:00
yihao.dai a4439cc911
enhance: Implement flusher in streamingNode (#34942)
- Implement flusher to:
  - Manage the pipelines (creation, deletion, etc.)
  - Manage the segment write buffer
  - Manage sync operation (including receive flushMsg and execute flush)
- Add a new `GetChannelRecoveryInfo` RPC in DataCoord.
- Reorganize packages: `flushcommon` and `datanode`.

issue: https://github.com/milvus-io/milvus/issues/33285

---------

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2024-08-02 18:30:23 +08:00
zhenshan.cao aa247f192d
enhance: remove unused code for StorageV2 (#35132)
issue: https://github.com/milvus-io/milvus/issues/34168

Signed-off-by: zhenshan.cao <zhenshan.cao@zilliz.com>
2024-08-01 12:08:13 +08:00
congqixia de8a266d8a
enhance: Enable linux code checker (#35084)
See also #34483

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-07-30 15:53:51 +08:00
chyezh 39c7e06bc5
enhance: add message and msgstream msgpack adaptor (#34874)
issue: #33285

- make message builder and message conversion type safe
- add adaptor type and function to adapt old msgstream msgpack and
message interface

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2024-07-22 20:59:42 +08:00
yihao.dai 8aab6cbfac
enhance: Organize the common modules of streamingNode and dataNode (#34773)
1. Move the common modules of streamingNode and dataNode to flushcommon
2. Add new GetVChannels interface for rootcoord

issue: https://github.com/milvus-io/milvus/issues/33285

---------

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2024-07-22 11:33:51 +08:00