10655 Commits

Author SHA1 Message Date
cqy123456
c9680a5b56
fix: avoid load index or create interim index in ChunkedSegmentSealedImpl::HasRawData() (#42622)
issue: https://github.com/milvus-io/milvus/issues/42526

Signed-off-by: cqy123456 <qianya.cheng@zilliz.com>
2025-06-10 14:54:34 +08:00
Zhen Ye
af0881ee5d
fix: timetick cannot push forward when upgrading (#42567)
issue #42492

- streamingcoord start before old rootcoord.
- streaming balancer will check the node session synchronously to avoid
redundant operation when cluster startup.
- ddl operation will check if streaming enabled, if the streaming is not
enabled, it will use msgstream.
- msgstream will initialize if streaming is not enabled, and stop when
streaming is enabled.

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2025-06-10 14:52:42 +08:00
cqy123456
317bbfbf81
enhance: milvus support minhash vector and mhjaccard metric (#42036)
issue:
https://github.com/issues/assigned?issue=milvus-io%7Cmilvus%7C41746

Signed-off-by: cqy123456 <qianya.cheng@zilliz.com>
2025-06-10 14:38:34 +08:00
Bingyi Sun
b3ecf77a66
fix: Fix the bug of valid data write corruption (#42556)
issue: https://github.com/milvus-io/milvus/issues/42554

---------

Signed-off-by: sunby <sunbingyi1992@gmail.com>
2025-06-10 14:22:34 +08:00
zhagnlu
2861096734
fix: Add explicit move semantics to get_batch_view interface (#42403)
#42401

Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2025-06-10 13:06:35 +08:00
sthuang
9439eaef52
fix: [StorageV2] sync with int8 vector data type core dumped (#42616)
related: https://github.com/milvus-io/milvus/issues/42613, #39173

Signed-off-by: shaoting-huang <shaoting.huang@zilliz.com>
2025-06-10 11:42:35 +08:00
aoiasd
13330bd466
fix: add concurrency and close protect for bm25 function (#42597)
relate: https://github.com/milvus-io/milvus/issues/42576

Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
2025-06-10 11:36:34 +08:00
sthuang
89c3afb12e
fix: [StorageV2] index/stats task level storage v2 fs (#42191)
related: #39173

---------

Signed-off-by: shaoting-huang <shaoting.huang@zilliz.com>
2025-06-10 11:06:35 +08:00
aoiasd
fd6e2b52ff
enhance: use english name as language name for all type language identifier (#42600)
Set whatlang detect return language name as english name.
Make sure same with lingua.

Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
2025-06-10 10:24:35 +08:00
congqixia
a9aaa86193
enhance: [StorageV2] Pass bucket name for compaction readers (#42607)
Related to #39173

Like logic in #41919, storage v2 fs shall use complete paths with
bucketName prefix to be compatible with its definition. This PR fills
bucket name from config when creating reader for compaction tasks.

NOTE: the bucket name shall be read from task params config for
compaction task pooling.

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-06-10 10:20:35 +08:00
congqixia
118684afbb
enhance: [storageV2] Pass nullable converting insertMsg fieldData (#42584)
Related to #39173

`nullable` flag is crucial for serde logic of v2 writer, missing this
flag causes logic bug for v2 nullalbe data.

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-06-10 10:06:34 +08:00
Bingyi Sun
ffb2877992
enhance: support auto index type for json index (#42071)
issue: https://github.com/milvus-io/milvus/issues/42070

---------

Signed-off-by: sunby <sunbingyi1992@gmail.com>
2025-06-09 21:22:34 +08:00
wei liu
317e7999da
fix: ReleasePartition cause delegator unserviceable. (#42423)
issue: #42098 #42404
related to: ##42009 #41937

Implement new method to handle partition removal from next target
without directly modifying current target.

Changes include:
- Add RemovePartitionFromNextTarget method and deprecate RemovePartition
- Update target_observer to use new method for ReleasePartition
operations
- Add unit tests and mock methods for new functionality

This ensures that all changes to next target will propagates to
delegator's query view.

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2025-06-09 19:02:34 +08:00
Bingyi Sun
6404e02d99
fix: Check cast type is array for json contains expr (#42184)
issue: https://github.com/milvus-io/milvus/issues/42181

Signed-off-by: sunby <sunbingyi1992@gmail.com>
2025-06-09 17:04:33 +08:00
congqixia
f1188b6781
enhance: [storagev2] Support partition key isolation index (#42574)
Related to #39173

This patch make storage v2 support partition key isolation index feature

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-06-09 14:02:33 +08:00
yihao.dai
837349dead
enhance: Adjust default import buffer size (#42541)
Increase insert buffer size from 16MB to 64MB, while keeping delete
buffer size at 16MB.

issue: https://github.com/milvus-io/milvus/issues/42518

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2025-06-09 13:02:33 +08:00
sthuang
b136f85ca0
fix: storage v2 write mmap file per field per cell (#42180)
Each cell of a field should be written to its own mmap file, rather than
writing all cells of the field into a single mmap file.
related: #39173

---------

Signed-off-by: shaoting-huang <shaoting.huang@zilliz.com>
2025-06-09 11:48:33 +08:00
aoiasd
6e16653597
fix: update tantivy commit version to fix stemmer panic (#42171)
relate: https://github.com/milvus-io/milvus/issues/42168

Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
2025-06-09 10:34:33 +08:00
Xianhui Lin
7e46fc6618
feat: implement batch commit for JSON Stats (#42494)
implement batch commit for JSON Stats
issue:https://github.com/milvus-io/milvus/issues/41616

Signed-off-by: Xianhui.Lin <xianhui.lin@zilliz.com>
2025-06-08 19:58:33 +08:00
Buqian Zheng
b4d549d96a
fix: pipeline/delegator leak (#42582)
the manager's logging lambda should not capture the pipeline object

this creates a circular reference between the manager and the pipeline
object, making it impossible for both to be GC-ed.

issue: https://github.com/milvus-io/milvus/issues/42581

Signed-off-by: Buqian Zheng <buqianzheng@Buqians-MacBook-Air.local>
Co-authored-by: Buqian Zheng <buqianzheng@Buqians-MacBook-Air.local>
2025-06-06 22:00:32 +08:00
wei liu
8511881d3f
enhance: Increase search/query retry times on proxy before timeout (#40438)
issue: #39379

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2025-06-06 18:12:32 +08:00
congqixia
b50c4a7973
enhance: Make segcore thread name set correctly (#42497)
Previous PR: #42017 did not work due to following updated points by this
PR:

- Initialize the `name_map`, which not touched at all before
- Trim the thread name under 15 characters to fit syscall limit

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-06-06 16:26:32 +08:00
Bingyi Sun
cc5ac1c220
enhance: Support cast function for json index (#41949)
issue: #41948

---------

Signed-off-by: sunby <sunbingyi1992@gmail.com>
2025-06-05 19:42:32 +08:00
zhagnlu
0c4b12565e
fix: fix is null bug for marisa index (#42420)
#42255

Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2025-06-05 16:40:32 +08:00
cai.zhang
e299c533be
fix: Just trigger stats task for Flushed segment (#42424)
issue: #42419

---------

Signed-off-by: Cai Zhang <cai.zhang@zilliz.com>
2025-06-05 15:42:32 +08:00
aoiasd
b1f86f6556
enhance: run analyzer should get database name from grpc context (#42398)
Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
2025-06-05 14:26:31 +08:00
aoiasd
2eb24fbe7c
fix: analyzer memory leak because function runner not close (#41839)
relate: https://github.com/milvus-io/milvus/issues/41213

---------

Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
2025-06-05 14:24:40 +08:00
congqixia
373deba0bd
fix: Pass cluster id tranforming drop task to drop job request (#42531)
Related to #42530

The cluster id is missing when drop worker drop causing redoing task on
report duplicated task error.

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-06-05 13:20:32 +08:00
Zhen Ye
0567f512b3
fix: streamingnode get stucked when stop (#42501)
issue: #42498

- fix: sealed segment cannot be flushed after upgrading
- fix: get mvcc panic when upgrading
- ignore the L0 segment when graceful stop of querynode.

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2025-06-05 12:22:31 +08:00
Ted Xu
35c17523de
feat: limit search result entries (#42522)
See: #42521

Signed-off-by: Ted Xu <ted.xu@zilliz.com>
2025-06-05 12:08:33 +08:00
cai.zhang
43c99a2c49
fix: Only mark segment compacting for sort stats task (#42516)
issue: #42506

---------

Signed-off-by: Cai Zhang <cai.zhang@zilliz.com>
2025-06-04 22:46:32 +08:00
yihao.dai
6fda1f69c8
fix: Fix duplicate autoID between import and insert (#42519)
Remove the unlimited logID mechanism and switch to redundantly
allocating a large number of IDs.

issue: https://github.com/milvus-io/milvus/issues/42518

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2025-06-04 19:58:31 +08:00
cai.zhang
5566a85bcc
enhance: Add proxy task queue metrics (#42156)
issue: #42155

Signed-off-by: Cai Zhang <cai.zhang@zilliz.com>
2025-06-04 11:26:32 +08:00
Chun Han
e9b5d9e8bc
enhance: refine compaction trigger to reduce read/write amplifaction(#41336) (#41728)
related: #41336

Signed-off-by: MrPresent-Han <chun.han@gmail.com>
Co-authored-by: MrPresent-Han <chun.han@gmail.com>
2025-06-04 11:24:38 +08:00
Zhen Ye
508264f953
fix: querynode upgrade from 2.5 get stucked (#42502)
issue: #42492

- consider the old RO query node (not streaming node) when balancing
channel.
- querynode graceful stop can be done if there's only L0 segment exists.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-06-04 11:20:30 +08:00
congqixia
b76478378a
feat: [Tiered] Make load list work as warmup hint (#42490)
Related to #42489
See also #41435

This PR's main target is to make partial load field list work as caching
layer warmup policy hint. If user specify load field list, the fields
not included in the list shall use `disabled` warmup policy and be able
to lazily loaded if any read op uses them.

The major changes are listed here:
- Pass load list to segcore and creating collection&schema
- Add util functions to check field shall be proactively loaded
- Adapt storage v2 column group, which may lead to hint fail if columns
share same group

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-06-04 10:28:32 +08:00
Zhen Ye
fc010e44a8
fix: release memory after pop from heap (#42482)
issue: #42481

Signed-off-by: chyezh <chyezh@outlook.com>
2025-06-04 10:00:32 +08:00
sthuang
490827974d
enhance: avoid shutdown sdk api in minio cm destructor (#42459)
related: #39173

---------

Signed-off-by: shaoting-huang <shaoting.huang@zilliz.com>
2025-06-04 09:58:39 +08:00
yihao.dai
e0113b375e
fix: Fix sort stats generates large binlogs (#42456)
Remove the hardcoded batchSize of 100,000 and instead trigger a write
every 64MB based on actual data size. This prevents sort stats from
generating excessively large binlog files.

issue: https://github.com/milvus-io/milvus/issues/42400

---------

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2025-06-04 09:56:39 +08:00
wei liu
aa66072a1c
enhance: Remove inadvertently introduced goccy/go-json dependency (#42146)
Remove the 'goccy/go-json' library, which was inadvertently introduced,
and revert to using the standard internal JSON handling.

Changes include:
- Removed dependency on 'github.com/goccy/go-json' in go.mod and go.sum.
- Replaced import of 'goccy/go-json' with 'internal/json' in
'internal/querycoordv2/task/scheduler.go'.

This correction ensures the project continues to use the intended JSON
processing libraries and avoids unnecessary external dependencies.

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2025-06-03 17:38:32 +08:00
cqy123456
727f4ec24b
enhance:mmapchunkmanager allocates MmapChunkDescriptor itself (#42150)
issue: https://github.com/milvus-io/milvus/issues/42157

Signed-off-by: cqy123456 <qianya.cheng@zilliz.com>
2025-06-03 14:42:31 +08:00
wei liu
5a355d1e57
fix: Fix data race in global scheduler test using atomic counters (#42454)
issue: #42457

Replace unsafe ExpectedCalls modification with atomic.Int32 state
tracking to avoid race conditions in concurrent test execution. Changes
include:
- Use atomic counters instead of direct mock ExpectedCalls manipulation
- Add RunAndReturn with atomic state transitions for thread safety
- Remove github.com/samber/lo dependency

This prevents data race when mock framework and test goroutines access
ExpectedCalls concurrently.

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2025-06-03 14:18:30 +08:00
Zhen Ye
e479467582
fix: panic when upgrading from old arch (#42422)
issue: #42405

- add delete rows into header when upsert.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-31 22:56:29 +08:00
congqixia
cc42d49769
fix: [StorageV2][AddField] Handle lack binlog rows in storage v2 (#42186)
Related to #39173 #39718

In storage v2, the `lack_bin_rows` cannot be used since field id is not
column group id, which will not be matched forever.

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-05-31 02:44:30 +08:00
yihao.dai
297331b2cc
enhance: Add slot and tasks num metrics (#42141)
issue: https://github.com/milvus-io/milvus/issues/41123

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2025-05-30 21:52:30 +08:00
wei liu
2669d14ba0
refactor: Remove balance constraints between channel and segment tasks (#42177)
issue: #42176

Remove the mutual exclusion constraints between channel and segment
balance tasks to allow them to run concurrently.

Changes include:
- Remove permitBalanceChannel() and permitBalanceSegment() methods from
RoundRobinBalancer
- Update ChannelLevelScoreBalancer, MultiTargetBalancer,
RowCountBasedBalancer, and ScoreBasedBalancer to remove constraint
checks
- Allow segment balance tasks to proceed even when channel balance tasks
are running
- Update test cases to reflect new behavior where balance tasks no
longer block each other

This change improves the efficiency of load balancing by removing
unnecessary coordination overhead between different types of balance
operations.

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2025-05-30 18:14:25 +08:00
congqixia
6d2ad519b1
enhance:[StorageV2] Adapt local storage & other minor issue (#42167)
Related to #39173

This PR
- Handle storage v2 log path in local storage mode on querynode
- Ignore field info check when append index for loaded sealed segment
when using storage v2

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-05-30 10:22:29 +08:00
Xiaowei Shi
729d0b666e
enhance: use parsed physical timestamp in metrics (#41784)
issue: https://github.com/milvus-io/milvus/issues/38809
pr: https://github.com/milvus-io/milvus/pull/38810 failed to reopen

Signed-off-by: Xiaowei Shi <shallwe.shih@gmail.com>
2025-05-30 10:20:37 +08:00
Chun Han
ed0df38605
enhance: resize high priority wqthreadpool dynamically(#40838) (#41549) (#41929)
related: #40838
pr: https://github.com/milvus-io/milvus/pull/41549

Signed-off-by: MrPresent-Han <chun.han@gmail.com>
2025-05-30 10:18:36 +08:00
Zhen Ye
66cc194ab2
enhance: add partition gc at streaming arch (#42179)
issue: #41976

- make drop partition message as a broadcast message.
- add gc when drop partition message is acked.
- add a call back to handle the broadcast message when ack.
- the ack operation of broadcast message will retry until success.

Signed-off-by: chyezh <chyezh@outlook.com>
2025-05-29 23:20:30 +08:00