408 Commits

Author SHA1 Message Date
jaime
bb2ffd47f6
enhance: Add db label for some usual metrics (#32024)
issue: https://github.com/milvus-io/milvus/issues/31782
pr: #30956
cherry pick: #30956 #32003 #31715

---------

Signed-off-by: jaime <yun.zhang@zilliz.com>
Signed-off-by: chyezh <chyezh@outlook.com>
Co-authored-by: chyezh <chyezh@outlook.com>
2024-04-10 20:59:20 +08:00
wei liu
fcef1c54da
fix: Check exclude segment before add new growing segment (#31803) (#32115)
issue: #31479 #31797
pr: #31803

milvus will add released segment to excluded info, and filter out it's
stream data in filter_node. but for data buffered in insert_node's
channel, if it belongs to growing segment which already be released,
then it will all the growing segment back again.

This PR maintain `excluded segments` in delegator, and check excluded
segment before new growing segment.

---------

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-04-10 19:03:20 +08:00
congqixia
c85cd01557
fix: [2.4] Validate PlaceholderGroups before combine them (#32016) (#32042)
Cherry-pick from master
pr: #32016
See also #32015

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-04-10 16:57:26 +08:00
aoiasd
4d7ae52d62
fix: [Cherry-Pick] delegator filter out all partition's delete msg when loading segment (#31588)
May cause deleted data queryable a period of time.
relate: https://github.com/milvus-io/milvus/issues/31484
pr: https://github.com/milvus-io/milvus/pull/31585

---------

Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
2024-04-09 15:21:24 +08:00
zhenshan.cao
4c07304790
enhance: Refactor hybrid search (#31742)
issue: https://github.com/milvus-io/milvus/issues/25639
https://github.com/milvus-io/milvus/issues/31368
pr :https://github.com/milvus-io/milvus/pull/32020

Signed-off-by: zhenshan.cao <zhenshan.cao@zilliz.com>
2024-04-09 10:15:18 +08:00
Jiquan Long
b2a79a0570
enhance: add more metrics (#31271) (#31861)
/kind improvement
fix: #31272 
pr: #31271 

This pr add more metrics, which are:
- Slow query count, which the duration considered as slow can be
configurable;
- Number of deleted entities;
- Number of entities imported;
- Number of entities per collection;
- Number of loaded entities per collection;
- Number of indexed entities;
- Number of indexed entities, per collection, per index and whether it's
a vetor index;
- Quota states (LongTimeTickDelay, MemoryExhuasted, DiskQuotaExhuasted)
per database;

---------

Signed-off-by: longjiquan <jiquan.long@zilliz.com>
2024-04-05 10:09:22 +08:00
congqixia
732f0ace11
enhance: [Cherry-pick] Add back unit test for compactor and fix some TODOs (#31829) (#31876)
Cherry-pick from master
pr: #31829
This PR adds back compactor "Unhandled" data type unit test and fixes
some TODOs behvaior

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-04-03 17:19:15 +08:00
wei liu
12d2f4b39b
fix: Update segment's version in leader task (#31643) (#31774)
issue: #31468
pr: #31643

1. when segment's version in leader view doesn't match segment's version
in dist, should update leader view
2. after call loadDeltalog, should update segment's load version with
latest ts
3. change leader task's priority from high to low, to avoid leader task
replace segment task and balance task

---------

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-04-01 21:09:18 +08:00
cqy123456
d4d0c6be8b
fix: [cherry-pick]fix fp16/bf16 some code missing and add more fp16/bf16 test (#31677)
issue: https://github.com/milvus-io/milvus/issues/31534
pr: https://github.com/milvus-io/milvus/pull/31612

Signed-off-by: cqy123456 <qianya.cheng@zilliz.com>
2024-04-01 20:53:13 +08:00
wei liu
609674c0ea
fix: Remove segment from leader view can't be executed (#31663) (#31775)
issue: #31664
pr: #31663

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-04-01 16:55:19 +08:00
Jiquan Long
d37e1fdd9f
fix: predict inverted index resource usage more reasonably (#31615) (#31641)
/kind improvement
issue: https://github.com/milvus-io/milvus/issues/31617
pr: #31615

Signed-off-by: longjiquan <jiquan.long@zilliz.com>
2024-03-27 21:07:11 +08:00
Bingyi Sun
875887244b
fix: fix mmap enabled check in resource estimation (#31536) (#31574)
issue: https://github.com/milvus-io/milvus/issues/31569

related pr: https://github.com/milvus-io/milvus/pull/31536

Signed-off-by: sunby <sunbingyi1992@gmail.com>
2024-03-27 16:37:11 +08:00
Bingyi Sun
5d8bbea5e4
fix: fix mmap enable log (#31439) (#31573)
issue: https://github.com/milvus-io/milvus/issues/31443

related pr: https://github.com/milvus-io/milvus/pull/31439

Signed-off-by: sunby <sunbingyi1992@gmail.com>
2024-03-27 16:33:10 +08:00
chyezh
96cec7871d
enhance: transfer resource group and dbname to querynode when load (#31322)
issue: #30931
pr: #30936

Signed-off-by: chyezh <chyezh@outlook.com>
2024-03-27 10:37:09 +08:00
congqixia
6e0baa47e2
enhance: [Cherry-pick] Release level zero segments when channel unsub (#31486) (#31509)
Cherry-pick from master
pr: #31486
Related to #27349
See also #30816

Level zero is not allowed to balance among delegators, they shall always
serve current delegator. This PR releases all level zero segments after
channel is unsubscribed and preventing level zero segment blocking
graceful stop.

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-03-25 10:21:08 +08:00
congqixia
99774548f2
enhance: [Cherry-pick] Add AllPartitionsID const to replace InvalidPartitionID (#31438) (#31515)
Cherry-pick from master
pr: #31438

"-1" as `InvalidPartitionID` previously used as All partition place
holder in delete cases. It's confusing and hard to maintain when a const
var has more than one meaning.

This PR add `AllPartitionsID` to replace these usages in delete
scenarios.

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-03-22 16:37:08 +08:00
congqixia
b8d8805c87
fix: [Cherry-pick] Use mutex protection when accessing pks of l0 segments (#31505) (#31517)
Cherry-pick from master
pr: #31505
See also #31504

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-03-22 16:07:08 +08:00
groot
a0535edb67
enhance: Support MinIO TLS connection (#31396)
issue: https://github.com/milvus-io/milvus/issues/30709
pr: https://github.com/milvus-io/milvus/pull/31292

Signed-off-by: yhmo <yihua.mo@zilliz.com>
Co-authored-by: Chen Rao <chenrao317328@163.com>
2024-03-21 11:15:20 +08:00
chyezh
775129bd4e
enhance: add resource usage estimate for segment interface (#31309)
issue: #30931
pr: #31050

- move resource estimate function outside from segment loader.
- add load info and collection to base segment.
- add resource usage method for sealed segment.

Signed-off-by: chyezh <chyezh@outlook.com>
2024-03-21 09:27:07 +08:00
Bingyi Sun
e7b053817d
feat: Add global mmap enable configuration (#31267) (#31373)
https://github.com/milvus-io/milvus/issues/31279
related pr: #31267

Signed-off-by: sunby <sunbingyi1992@gmail.com>
2024-03-18 21:57:05 +08:00
congqixia
4e83ca46bc
fix: [cherry-pick] Report offline info in GetDataDistribition (#31349)
Cherry pick from master
pr: #31347
See also #31345

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-03-18 17:05:05 +08:00
congqixia
08aba2e05f
fix: Remove QueryNodeEntitiesSize after segment/collection released (#31290)
See also #31289

This PR:
- Set collection level `QueryNodeEntitiesSize` to zero if all segment
released
- Delete `QueryNodeEntitiesSize` metrics value after collection ref is
zero

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-03-15 15:43:04 +08:00
jaime
db79be3ae0
fix: ctx cancel should be the last step while stopping server (#31220)
issue: #31219

Signed-off-by: jaime <yun.zhang@zilliz.com>
2024-03-15 10:33:05 +08:00
congqixia
b1ff8e2749
fix: Fix data race on loadSealedSegmentFields opts (#31230)
See also #31229

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-03-14 10:43:04 +08:00
Buqian Zheng
3c80083f51
feat: [Sparse Float Vector] add sparse vector support to milvus components (#30630)
add sparse float vector support to different milvus components,
including proxy, data node to receive and write sparse float vectors to
binlog, query node to handle search requests, index node to build index
for sparse float column, etc.

https://github.com/milvus-io/milvus/issues/29419

---------

Signed-off-by: Buqian Zheng <zhengbuqian@gmail.com>
2024-03-13 14:32:54 -07:00
congqixia
57a5e44b88
enhance: Add id,type filter shortcut for QueryNode segment manager (#31179)
See also #31143

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-03-13 20:15:03 +08:00
Bingyi Sun
7b7187b465
fix: fix mmap load (#31171)
issue: https://github.com/milvus-io/milvus/issues/31101

---------

Signed-off-by: sunby <sunbingyi1992@gmail.com>
2024-03-13 10:49:04 +08:00
congqixia
1d96239137
enhance: Add ctx trace for segment load prepare (#31203)
Add ctx paramter to `prepare` and add trace id in underline logs.

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-03-13 10:01:07 +08:00
Chun Han
3298e64bd3
enhance: cache config values for saving cpu cycles to parse config item (#30947)
related: #30958

Signed-off-by: MrPresent-Han <chun.han@zilliz.com>
2024-03-12 11:09:04 +08:00
wei liu
9cfe183253
enhance: remove duplicated target node id check (#31087)
issue: #31109
This PR remove duplicate target node id check, due to server id has
already been checked in rpc's interceptor

---------

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-03-11 15:31:02 +08:00
wei liu
5016031dc7
enhance: add metrics for load segment progress (#31005)
This PR add metrics for load segment progress:
1. add metrics for load segment/index concurrency
2. add metrics for load index latency
3. change load segment latency's time unit to ms

---------

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-03-08 15:39:02 +08:00
zhagnlu
a65a9ce8a5
fix: fix oom because of wrong load mode for index's raw data (#31130)
#30962

Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2024-03-07 12:14:26 -08:00
congqixia
ba8197fafb
fix: Filter channel level zero segments when build level delete cache (#31129)
See also #31125

Delegator shall build level zero delete cache from l0 segments belongs
to it. Previously it build cache from all existing level zero segments
in the querynode which may lead to high memory usage and even panicking
when pk types are not matched

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-03-07 23:01:02 +08:00
Bingyi Sun
fd17a5f050
fix: check collection lazy load prop using schema (#30992)
issue: https://github.com/milvus-io/milvus/issues/30361

---------

Signed-off-by: sunby <sunbingyi1992@gmail.com>
2024-03-06 16:19:01 +08:00
congqixia
30398d4b71
enhance: Fix misleading log content & possible nil panic (#31021)
- Change load field log from "dy pool" to "load pool"
- Also defer delete when there is no error

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-03-05 16:33:00 +08:00
congqixia
52540fecb2
enhance: Add back load memory factor when esitmating memory resource (#30994)
Segment load memory usage is underestimated due to removing the load
memroy factor. This PR adds it back to protect querynode OOM during some
extreme memory cases.

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-03-04 19:54:59 +08:00
SimFG
ee8d6f236c
enhance: make the watch dm channel request better compatibility (#30952)
issue: #30938

Signed-off-by: SimFG <bang.fu@zilliz.com>
2024-03-01 16:07:37 +08:00
chyezh
dd957cf9e3
enhance: add configurable memory index load predict memory usage factor (#30561)
related pr: https://github.com/milvus-io/milvus/pull/30475

Signed-off-by: chyezh <chyezh@outlook.com>
2024-03-01 15:23:00 +08:00
wei liu
cc46d6bafc
fix: segment version doesn't update as expected (#30951)
issue: #30950

due to segment version doesn't update as expected.
This PR will update segment version until segment become loaded

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-03-01 14:21:10 +08:00
congqixia
385dec3b69
fix: index attr caches wrong result variable (#30960)
See also #30757 #30756

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-03-01 13:17:00 +08:00
aoiasd
3633923bb7
enhance: clean invalid pipline excluded segment info (#30429)
relate: https://github.com/milvus-io/milvus/issues/30281

---------

Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
2024-03-01 10:43:01 +08:00
MrPresent-Han
17a2fd048e
feat: support set up knowhere-build-pool-size on querynode(#29650) (#30922)
related: #29650

Signed-off-by: MrPresent-Han <chun.han@zilliz.com>
2024-02-29 18:15:00 +08:00
chyezh
0c7474d7e8
enhance: add graceful stop timeout to avoid node stop hang under extreme cases (#30317)
1. add coordinator graceful stop timeout to 5s
2. change the order of datacoord component while stop
3. change querynode grace stop timeout to 900s, and we should
potentially change this to 600s when graceful stop is smooth

issue: #30310
also see pr: #30306

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2024-02-29 17:01:50 +08:00
congqixia
4082315bd0
enhance: Add ParseCTraceContext util function for tracing (#30883)
See also #29803

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-02-28 18:59:00 +08:00
wei liu
382b7485a6
enhance: Correct misleading nodeID in GetComponentStates's log (#30731)
This PR corrects the misleading nodeId in GetComponentStates's log

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-02-28 13:13:12 +08:00
Cai Yudong
8a219e0102
feat: Support knowhere trace using OpenTelemetry (#30750)
Issue: #21508

Signed-off-by: Yudong Cai <yudong.cai@zilliz.com>
2024-02-28 12:29:00 +08:00
smellthemoon
a4f3e01a3a
fix: add the range search params check in proxy (#30423)
if check in Segcore, will not do the it when not insert data.
so, check "radius" and "range_filter" in proxy.
related with #30365

Signed-off-by: lixinguo <xinguo.li@zilliz.com>
Co-authored-by: lixinguo <xinguo.li@zilliz.com>
2024-02-28 11:24:58 +08:00
chyezh
77477d6340
fix: wrong context passing into NewClient, error handling lost in session_util (#30817)
issue: #30799

Signed-off-by: chyezh <chyezh@outlook.com>
2024-02-28 10:40:09 +08:00
yah01
57397b1307
enhance: add new LRU cache impl (#30360)
- remove  the unused LRU cache
- add new LRU cache impl which wraps github.com/karlseguin/ccache

related #30361

---------

Signed-off-by: yah01 <yang.cen@zilliz.com>
2024-02-27 20:58:40 +08:00
Xiaofan
0661d33879
enhance: change frequent log to debug (#30782)
change the "pipeline fetch insert msg" log to debug

Signed-off-by: xiaofanluan <xiaofan.luan@zilliz.com>
2024-02-27 10:30:56 +08:00