22784 Commits

Author SHA1 Message Date
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
presburger
e878fe588e
enhance: Set the default GPU version autoindex to use the CAgra index (#41906)
issue:  #41907

Signed-off-by: yusheng.ma <yusheng.ma@zilliz.com>
2025-05-23 01:20:28 +08:00
yihao.dai
e04e5b41ca
enhance: Add task version monitoring (#42023)
issue: https://github.com/milvus-io/milvus/issues/41123

---------

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2025-05-22 23:24:28 +08:00
congqixia
244aa30076
fix: Lock before reading flusher cp sampling truncate cp (#42019)
Related to #42018

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-05-22 21:38:28 +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
congqixia
9fb0257bfa
enhance: Set thread name for segcore thread pool (#42017)
Thread name could be helpful when debugging thread explosion issues

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-05-22 19:06:27 +08:00
zhuwenxing
c937da5234
test: add multi analyzer test (#41578)
/kind improvement

Signed-off-by: zhuwenxing <wenxing.zhu@zilliz.com>
2025-05-22 17:46:24 +08:00
congqixia
22ef03b040
fix: [AddField] Expire metacache with rc task timestamp (#42010)
Related to #39718 #41681

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-05-22 17:20:25 +08:00
binbin
804b175771
test: add test cases for rerank (#42012)
Signed-off-by: binbin lv <binbin.lv@zilliz.com>
2025-05-22 17:04:25 +08:00
Zhen Ye
458ab86894
fix: stop retry if collection not found too much when get recovery from coord (#41980)
issue: #41966

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-22 16:22:24 +08:00
Buqian Zheng
2e3539319d
feat: vector field raw data to mmap by default (#41975)
issue: https://github.com/milvus-io/milvus/issues/41435

should address https://github.com/milvus-io/milvus/issues/41774

this PR also: 
* added caching layer memory overhead metric
* re-enable TextMatch.GrowingLoadData test

Signed-off-by: Buqian Zheng <zhengbuqian@gmail.com>
2025-05-22 11:56:25 +08:00
wei liu
78010262f0
enhance: Optimize shard serviceable mechanism (#41937)
issue: https://github.com/milvus-io/milvus/issues/41690
- Merge leader view and channel management into ChannelDistManager,
allowing a channel to have multiple delegators.
- Improve shard leader switching to ensure a single replica only has one
shard leader per channel. The shard leader handles all resource loading
and query requests.
- Refine the serviceable mechanism: after QC completes loading, sync the
query view to the delegator. The delegator then determines its
serviceable status based on the query view.
- When a delegator encounters forwarding query or deletion failures,
mark the corresponding segment as offline and transition it to an
unserviceable state.

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2025-05-22 11:38:24 +08:00
congqixia
f021b3f26a
fix: [AddField] Add protection logic inserting old data into new schema (#41978)
Related to #39718

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-05-22 11:30:24 +08:00
wei liu
dad43a3894
fix: cost metrics collection logic for replica selection (#41965)
issue: #41621
- Deprecate EnableWorkerSQCostMetrics parameter
- Always collect cost metrics from all search and retrieve results
- Update code with comments explaining the changes rationale

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2025-05-22 10:20:25 +08:00
Buqian Zheng
8a85bc4213
fix: fixes async warmup deadlock (#41995)
issue: https://github.com/milvus-io/milvus/issues/41993

also updated cachinglayer metrics

Signed-off-by: Buqian Zheng <zhengbuqian@gmail.com>
2025-05-22 09:54:24 +08:00
yanliang567
f20e085b22
test: Update ivf_rabitq error msg and groupby support nullable field (#41997)
related issue: #41898

Signed-off-by: yanliang567 <yanliang.qiao@zilliz.com>
2025-05-21 22:20:25 +08:00
wei liu
4e1208f4f6
enhance: support balancing multiple collections in single trigger (#41875)
issue: #41874
- Optimize balance_checker to support balancing multiple collections
simultaneously
- Add new parameters for segment and channel balancing batch sizes
- Add enableBalanceOnMultipleCollections parameter
- Update tests for balance checker

This change improves resource utilization by allowing the system to
balance multiple collections in a single trigger with configurable batch
sizes.

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2025-05-21 21:38:25 +08:00
SimFG
9f866dd7c3
enhance: add privilege group message types and corresponding tests (#41939)
- issue: #41938

Signed-off-by: SimFG <bang.fu@zilliz.com>
2025-05-21 11:12:28 +08:00
yihao.dai
3f85d376dd
fix: Fix ineffective log level setting in ThreadWatcher (#41886)
issue: https://github.com/milvus-io/milvus/issues/41781

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2025-05-20 21:22:24 +08:00
yihao.dai
142bd2fc05
enhance: Pooling for data tasks (#41256)
1. Add global scheduler for datacoord.
2. Define and implement new CreateTask, QueryTask, DropTask interfaces.
3. Refine Import, Compaction, Stats, Index task.

issue: https://github.com/milvus-io/milvus/issues/41123

Co-authored-by: Cai Zhang <cai.zhang@zilliz.com>
2025-05-20 21:06:24 +08:00
yanliang567
d475d93a3d
test: Add ivf_rabitq index tests (#41914)
related issue: #41760

---------

Signed-off-by: yanliang567 <yanliang.qiao@zilliz.com>
2025-05-20 19:28:24 +08:00
Zhen Ye
59ab274dbe
fix: use flusher and recovery checkpoint together to determine the truncate position (#41934)
issue: #41544

- unify the log field of message
- use the minimum one of flusher and recovery storage checkpoint as the
truncate position

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-20 16:10:24 +08:00
congqixia
b099926f24
fix: Read group by field in sparse format in it (#41943)
Related to #41942

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-05-20 16:02:23 +08:00
junjiejiangjjj
1cc5fa8be9
fix: Fix rrf score (#41857)
https://github.com/milvus-io/milvus/issues/41835

Signed-off-by: junjie.jiang <junjie.jiang@zilliz.com>
2025-05-20 15:24:24 +08:00
junjiejiangjjj
0bbbf98a5b
enhance: refactor decay rerank (#41778)
https://github.com/milvus-io/milvus/issues/35856
1. Optimizing decay function
2. Since the decay function is larger, the more similar it is, the
smaller the L2/JACCARD/HAMMING metrics scores the more similar they are.
For these metrics, the decay function regenerates new scores.

Signed-off-by: junjie.jiang <junjie.jiang@zilliz.com>
2025-05-20 15:22:24 +08:00
foxspy
3dbad0306a
fix: Add bypass thread pool mode to avoid growing indexes blocking insert/load (#41012)
issue: #40825

Signed-off-by: xianliang.li <xianliang.li@zilliz.com>
2025-05-20 14:30:24 +08:00
aoiasd
b6f251718c
enhance: support print nq and params for search and query (#41802)
relate: https://github.com/milvus-io/milvus/issues/41801

Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
2025-05-20 14:10:23 +08:00
congqixia
f2a8330f87
fix: [StorageV2] Use correct group building index (#41925)
Related to #39173 #41534

This pr fixes an issue that building mem index may report datatype not
match error when collection split fields into multiple groups

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-05-20 13:26:23 +08:00
congqixia
a22088a380
enhance: [StorageV2] Make packed reader use correct path (#41919)
Related to #39173

This PR
- Use updated path with bucketName for packedReader
- Update milvus-storage commit to report reader/writer initialization
failure, see also milvus-io/milvus-storage#192

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-05-20 10:36:23 +08:00
Zhen Ye
e4f04fd692
fix: vchannel count of wal balancer is wrong after recovering (#41922)
issue: #40638

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-19 22:14:23 +08:00
yihao.dai
65dd3982d8
fix: Fix ants.Pool goroutine leak (#41892)
1. Release the pool after it is no longer in use.
2. Upgrade ants.Pool to fix the goroutine leak issue (see [PR
#287](https://github.com/panjf2000/ants/pull/287)).

issue: https://github.com/milvus-io/milvus/issues/41838

---------

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2025-05-19 17:56:22 +08:00
sre-ci-robot
b932e03448
[automated] Bump milvus version to v2.5.12 (#41926)
Bump milvus version to v2.5.12
Signed-off-by: sre-ci-robot sre-ci-robot@users.noreply.github.com

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-05-19 17:28:23 +08:00
sre-ci-robot
28a0d1adc0
[automated] Bump milvus version to v2.5.12 (#41923)
Bump milvus version to v2.5.12
Signed-off-by: sre-ci-robot sre-ci-robot@users.noreply.github.com

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-05-19 16:58:27 +08:00
tinswzy
3d8629de3e
fix memory reuse in woodpecker to prevent streamingNode OOM (#41918)
#41846 
Reduce woodpecker memory allocation frequency through recycled memory
pools, allowing GC to keep up with collection.
related [woodpecker issue 24
](https://github.com/zilliztech/woodpecker/issues/24)

Signed-off-by: tinswzy <zhenyuan.wei@zilliz.com>
2025-05-19 15:22:22 +08:00
cai.zhang
38ded7364f
fix: Don't create index for unsorted importing segment when enable stats (#41864)
issue: #41863

---------

Signed-off-by: Cai Zhang <cai.zhang@zilliz.com>
2025-05-19 10:52:23 +08:00
Ted Xu
7660be0993
feat: bulk insert support storage v2 (#41843)
See #39173

---------

Signed-off-by: Ted Xu <ted.xu@zilliz.com>
2025-05-19 10:34:24 +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
Ted Xu
ae32203d3a
fix: support group by with nullable grouping keys (#41797)
See #36264

In this PR:
- Enhanced error handling in parse of grouping field.
- Fixed null handling in reduce tasks in proxy nodes. 
- Updated tests to reflect changes in error handling and data processing
logic.

---------

Signed-off-by: Ted Xu <ted.xu@zilliz.com>
2025-05-17 20:54:22 +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
Zhen Ye
a3d5ad135e
fix: recover a dropped collection from wal if create collection message can be seen (#41902)
issue: #41654

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-17 07:38:21 +08:00
congqixia
3bbc0fa560
enhance: [StorageV2] update storage to pass endpoint as-is (#41889)
Related to milvus-io/milvus-storage#190

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-05-16 18:06:21 +08:00
Bingyi Sun
b006d738b2
fix: Fix skip much more rows when moving cursor (#41862)
issue: https://github.com/milvus-io/milvus/issues/41790

---------

Signed-off-by: sunby <sunbingyi1992@gmail.com>
2025-05-16 16:46:22 +08:00
Buqian Zheng
b0260d8676
feat: manual evict cache after built interim index (#41836)
issue: https://github.com/milvus-io/milvus/issues/41435

this PR also makes HasRawData of ChunkedSegmentSealedImpl to return
based on metadata, without needing to load the cache just to answer this
simple question.

---------

Signed-off-by: Buqian Zheng <zhengbuqian@gmail.com>
2025-05-16 16:34:23 +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
d3fff1769e
fix: streaming node panic with when binary size is set as zero (#41879)
issue: #41853

- persist the estimated binary size for insert message into wal.
- add metric to record the total growing rows of channel.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-16 11:12:22 +08:00
yanliang567
83cdd6b121
test: set specific mq for standalone e2e (#41859)
related issue: https://github.com/milvus-io/milvus/issues/41819
1. remove useless distributed config
2. set specific mq for standalone e2e

---------

Signed-off-by: yanliang567 <yanliang.qiao@zilliz.com>
2025-05-16 10:30:23 +08:00
yihao.dai
6c1a37fca1
fix: Fix import reader goroutine leak (#41869)
Close the chunk manager's reader after the import completes to prevent
goroutine leaks.

issues: https://github.com/milvus-io/milvus/issues/41868

---------

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2025-05-16 10:18:35 +08:00
Zhen Ye
ae43230703
enhance: set jemalloc prof disable by default (#41850)
issue: #40730

- add assertion for insert message
- add more buffer for seal notifier

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-15 20:10:23 +08:00
congqixia
ba8f62a3b2
enhance: Bump x/net fixing CVE-2025-22872 (#41861)
Related to #41291
Related to CVE-2025-22872

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-05-15 19:04:23 +08:00
SimFG
9fa50e0b1a
enhance: implement authorization checks for DescribeCollection and DescribeDatabase tasks (#41798)
- issue: #41694

---------

Signed-off-by: SimFG <bang.fu@zilliz.com>
2025-05-15 17:52:23 +08:00