Commit Graph

478 Commits

Author SHA1 Message Date
Cai Yudong
b560602885
enhance: Store SparseFloatVector into parquet as JSON string (#33101)
Issue: #22837

Signed-off-by: Cai Yudong <yudong.cai@zilliz.com>
2024-05-17 15:01:37 +08:00
smellthemoon
225f4a6134
enhance: use the only MaxEtcdTxnNum (#33070)
#33071

Signed-off-by: lixinguo <xinguo.li@zilliz.com>
Co-authored-by: lixinguo <xinguo.li@zilliz.com>
2024-05-17 14:27:42 +08:00
Cai Yudong
4ef163fb70
enhance: Support readable JSON file import for Float16/BFloat16/SparseFloat (#33064)
Issue: #22837

Signed-off-by: Cai Yudong <yudong.cai@zilliz.com>
2024-05-16 14:47:35 +08:00
aoiasd
875ad88d84
enhance: Support access log use stdout with write cache and auto flush as time (#32213)
relate: https://github.com/milvus-io/milvus/issues/28948

Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
2024-05-16 10:05:34 +08:00
congqixia
8cf2cf5c94
enhance: Add go-deadlock as unittest only dependency (#33063)
See also #33062

This PR:

- Add `lock.RWMutex` & `lock.Mutex` alias to switch implementation based
  on build flags
- When build flags has `test` in it, use `go-deadlock` to detect
  possible deadlocks
- Replace all `sync.RWMutex` & `sync.Mutex` in datacoord pkg

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-05-15 16:33:34 +08:00
Cai Yudong
4fc7915c70
enhance: unify data generation test APIs (#32955)
Issue: #22837

Signed-off-by: Cai Yudong <yudong.cai@zilliz.com>
2024-05-14 14:33:33 +08:00
foxspy
f6777267e3
enhance: add score compute consistency config for knowhere (#32997)
issue: https://github.com/milvus-io/milvus/issues/32583
related: #32584

Signed-off-by: xianliang.li <xianliang.li@zilliz.com>
2024-05-13 14:21:31 +08:00
Bingyi Sun
4724779b3b
enhance: remove fallback keys for config generator (#32946)
Signed-off-by: sunby <sunbingyi1992@gmail.com>
2024-05-13 13:33:31 +08:00
chyezh
1c84a1c9b6
fix: lru related issue fixup patch (#32916)
issue: #32206, #32801

- search failure with some assertion, segment not loaded and resource
insufficient.

- segment leak when query segments

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2024-05-10 19:17:30 +08:00
wei liu
e2332bdc17
enhance: Enable channel exclusive balance policy (#32911)
issue: #32910  
* split replica's node list to channels when create replicas
 * balance nodes among channels when node change happens
 * implement channel level balance, let balance happens in channel level

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-05-10 17:27:31 +08:00
Bingyi Sun
1e1fba0588
enhance: add lazy load retry configurations (#32848)
Signed-off-by: sunby <sunbingyi1992@gmail.com>
2024-05-10 10:55:30 +08:00
aoiasd
54a51b1236
enhance: Support dynamic config for opentelemetry trace (#32169)
relate: https://github.com/milvus-io/milvus/issues/31940

---------

Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
2024-05-09 17:43:30 +08:00
Bingyi Sun
17a79f4ca9
enhance: The LRU cache evicts items and retries loading if the disk limit is reached. (#32819)
Signed-off-by: sunby <sunbingyi1992@gmail.com>
2024-05-08 14:45:30 +08:00
congqixia
40728ce83d
enhance: Add metautil.Channel to convert string compare to int (#32749)
See also #32748

This PR:

- Add `metautil.Channel` utiltiy which convert virtual name to physical
channel name, collectionID and shard idx
- Add channel mapper interface & implementation to convert limited
physical channel name into int index
- Apply `metautil.Channel` filter in querynode segment manager logic

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-05-07 19:13:35 +08:00
chyezh
641f702f64
fix: add request resource timeout for lazy load, refactor context usage in cache (#32709)
issue: #32663

- Use new param to control request resource timeout for lazy load.

- Remove the timeout parameter of `Do`, remove `DoWait`. use `context`
to control the timeout.

- Use `VersionedNotifier` to avoid notify event lost and broadcast,
remove the redundant goroutine in cache.

related dev pr: #32684

Signed-off-by: chyezh <chyezh@outlook.com>
2024-05-07 16:33:30 +08:00
yiwangdr
b1eacb2ae8
feat: datacoord/node watch based on rpc (#32036)
issue: https://github.com/milvus-io/milvus/issues/25309

Signed-off-by: yiwangdr <yiwangdr@gmail.com>
2024-05-07 15:49:30 +08:00
SimFG
0ea08b008a
enhance: add the config to control the way when fail to init plugin (#32680)
issue: #32679

Signed-off-by: SimFG <bang.fu@zilliz.com>
2024-05-07 11:01:31 +08:00
cai.zhang
a5d1135512
fix: Fix scalar auto index config incorrect version (#32795)
issue: #29309

Signed-off-by: Cai Zhang <cai.zhang@zilliz.com>
2024-05-07 10:13:00 +08:00
congqixia
02bf47f295
fix: Validate num of rows for insert field data with schema (#32770)
See also #32769

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-05-07 10:07:29 +08:00
Bingyi Sun
fecd9c21ba
feat: LRU cache implementation (#32567)
issue: https://github.com/milvus-io/milvus/issues/32783
This pr is the implementation of lru cache on branch lru-dev.

Signed-off-by: sunby <sunbingyi1992@gmail.com>
Co-authored-by: chyezh <chyezh@outlook.com>
Co-authored-by: MrPresent-Han <chun.han@zilliz.com>
Co-authored-by: Ted Xu <ted.xu@zilliz.com>
Co-authored-by: jaime <yun.zhang@zilliz.com>
Co-authored-by: wayblink <anyang.wang@zilliz.com>
2024-05-06 20:29:30 +08:00
SimFG
09cd56d44f
enhance: add the skip auto id and partition key check config (#32592)
/kind improvement
issue: #32591

Signed-off-by: SimFG <bang.fu@zilliz.com>
2024-04-29 10:29:26 +08:00
congqixia
967cfb3133
enhance: Add WithBlock option for etcd client creation (#32641)
Related to #32598

Use `WithBlock` may fail fast when create etcd client to some invalid
etcd endpoints and make it easier to check problem.

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-04-28 14:45:25 +08:00
Xiaofan
02ace25c68
enhance: reduce the cpu usage when collection number is high (#32245)
related to #32165
1. for all the manager, support collection level index
2. remove collection level filter to avoid extra cpu usage when
collection number increases

Signed-off-by: xiaofanluan <xiaofan.luan@zilliz.com>
2024-04-26 11:49:25 +08:00
chyezh
2586c2f1b3
enhance: use WalkWithPrefix api for oss, enable piplined file gc (#31740)
issue: #19095,#29655,#31718

- Change `ListWithPrefix` to `WalkWithPrefix` of OOS into a pipeline
mode.

- File garbage collection is performed in other goroutine.

- Segment Index Recycle clean index file too.

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2024-04-25 20:41:27 +08:00
Buqian Zheng
8a1017a152
enhance: add helpers to parse sparse float vector in JSON (#32543)
issue: #29419

added helper functions to parse JSON representation of sparse float
vectors, will be used by both the restful server and the import utils.

Signed-off-by: Buqian Zheng <zhengbuqian@gmail.com>
2024-04-25 14:47:24 +08:00
chyezh
b287fbaa2e
fix: return collection on recovering but not collection not loaded when target is not recovered (#32447)
issue: #32398

Signed-off-by: chyezh <chyezh@outlook.com>
2024-04-25 11:21:26 +08:00
Cai Yudong
5fc439c600
feat: Bulk insert support fp16/bf16 (#32157)
Issue: #22837

Signed-off-by: Cai Yudong <yudong.cai@zilliz.com>
2024-04-22 10:05:22 +08:00
SimFG
8594b55ad5
enhance: add max insert request size and must use partition key configs (#32433)
issue: https://github.com/milvus-io/milvus/issues/30577
/kind improvement

Signed-off-by: SimFG <bang.fu@zilliz.com>
2024-04-19 10:31:20 +08:00
SimFG
31a29a2451
enhance: avoid the repeated metric info in the proxy (#32380)
issue: #30577

Signed-off-by: SimFG <bang.fu@zilliz.com>
2024-04-19 10:21:20 +08:00
madogar
919df4cd02
enhance: changes to propagate traceid from client (#32264)
https://github.com/milvus-io/milvus/issues/32321

Issue Description:
Tracing is an important means of identifying bottleneck points in a
system and is crucial for debugging production issues. Milvus(or any DB)
is generally the most downstream system for an user call -- a user call
can originate from UI and pass through multiple components, in
micro-services architecture, before reaching Milvus.
So, when an user experiences a glitch, one would debug the call trace
via logs using a common trace id. As of now, Milvus generates a new
trace id for every call and this request is to make sure client can pass
the trace id which will be used for all the logs across the Milvus
sub-components so that one can fetch logs for a user call across the
components -- including Milvus.

Signed-off-by: Shreesha Srinath Madogaran <smadogaran@salesforce.com>
Co-authored-by: Shreesha Srinath Madogaran <smadogaran@salesforce.com>
2024-04-17 01:13:20 +08:00
SimFG
84f05ba66e
enhance: make the auth error message more suitable (#32253)
/issue: #32252
/kind improvement

Signed-off-by: SimFG <bang.fu@zilliz.com>
2024-04-16 16:47:19 +08:00
Ted Xu
78d32bd8b2
enhance: update milvus.yaml (#31832)
See #32168

---------

Signed-off-by: Ted Xu <ted.xu@zilliz.com>
2024-04-16 16:17:19 +08:00
smellthemoon
ae8f46f431
fix: panic when get empty ids (#32220)
#32223

Signed-off-by: lixinguo <xinguo.li@zilliz.com>
Co-authored-by: lixinguo <xinguo.li@zilliz.com>
2024-04-15 16:53:23 +08:00
Buqian Zheng
c93ae72d92
fix: more comprehensive check on sparse index and value (#32250)
issue: #29419

Signed-off-by: Buqian Zheng <zhengbuqian@gmail.com>
2024-04-15 16:51:24 +08:00
chyezh
48fe977a9d
enhance: declarative resource group api (#31930)
issue: #30647

- Add declarative resource group api

- Add config for resource group management

- Resource group recovery enhancement

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2024-04-15 08:13:19 +08:00
SimFG
c012e6786f
feat: support rate limiter based on db and partition levels (#31070)
issue: https://github.com/milvus-io/milvus/issues/30577
co-author: @jaime0815

---------

Signed-off-by: Patrick Weizhi Xu <weizhi.xu@zilliz.com>
Signed-off-by: SimFG <bang.fu@zilliz.com>
Co-authored-by: Patrick Weizhi Xu <weizhi.xu@zilliz.com>
2024-04-12 16:01:19 +08:00
Buqian Zheng
33801c32c4
fix: in milvus check sparse index to be less than uint32 max (#32199)
issue: #29419

Signed-off-by: Buqian Zheng <zhengbuqian@gmail.com>
2024-04-12 14:25:19 +08:00
aoiasd
43a9be2cce
enhance: support access log dynamic config and prepare for support resutful interface access log (#29638)
relate: https://github.com/milvus-io/milvus/issues/29637
https://github.com/milvus-io/milvus/issues/31823

---------

Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
2024-04-12 10:37:27 +08:00
jaime
371e6d2c1a
enhance: refine sync memory watermark configuration (#32140)
Signed-off-by: jaime <yun.zhang@zilliz.com>
2024-04-11 20:07:24 +08:00
Ted Xu
3d5fe7b45c
feat: adding cache stats support (#32068)
See #32067

---------

Signed-off-by: Ted Xu <ted.xu@zilliz.com>
2024-04-11 19:19:18 +08:00
Patrick Weizhi Xu
52ae47c850
enhance: gather materialized view search info once per request (#31996)
issue: #29892 

This PR:
1. Move the process of gathering materialized search info to when the
search plan is created, before it goes to each segment, to avoid
repeated work and access the plan node under multi-threaded
circumstances.
2. Enforce the supported MV type to `VARCHAR`
3. Add integration test

Signed-off-by: Patrick Weizhi Xu <weizhi.xu@zilliz.com>
2024-04-11 15:21:19 +08:00
Xiaofan
dbab9c5096
fix: reduce didn't handle offset without limit and reduceStopForBest correctly (#32089)
fix https://github.com/milvus-io/milvus/issues/32059

this pr fix two issues:

offset is not handled correctly without specify a limit
reduceStopForBest doesn't guarantee to return limit result even if there
are more result when there is small segment

Signed-off-by: xiaofanluan <xiaofan.luan@zilliz.com>
2024-04-10 16:01:18 +08:00
SimFG
90bed1caf9
enhance: add the related data size for the read apis (#31816)
issue: #30436
origin pr: #30438
related pr: #31772

---------

Signed-off-by: SimFG <bang.fu@zilliz.com>
2024-04-10 15:07:17 +08:00
chyezh
c9faa6d936
enhance: add more metrics for cache and search (#31777)
issue: #30931

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2024-04-10 10:55:17 +08:00
SimFG
420baacb6d
enhance: use the rate log in the privilege interceptor (#32037)
/kind improvement

Signed-off-by: SimFG <bang.fu@zilliz.com>
2024-04-09 16:19:17 +08:00
cqy123456
8fda3cbeda
enhance: check fp16/bf16 nan or inf value (#31840)
issue:https://github.com/milvus-io/milvus/issues/22837

Signed-off-by: cqy123456 <qianya.cheng@zilliz.com>
2024-04-09 14:19:27 +08:00
cai.zhang
1b767669a4
enhance: Throw error instead of crash when index cannot be built (#31844)
issue: #27589

---------

Signed-off-by: Cai Zhang <cai.zhang@zilliz.com>
2024-04-09 11:51:18 +08:00
yihao.dai
49d109de18
enhance: Use an individual buffer size parameter for imports (#31833)
Use an individual buffer size parameter for imports and set buffer size
to 64MB.

issue: https://github.com/milvus-io/milvus/issues/28521

---------

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2024-04-08 21:07:18 +08:00
Ted Xu
9901958288
fix: deadlock in cache concurrent visit (#31938)
See #31944

There is deadlock in concurrent invocation on `cache.DoWait()`. Suppose
2 callers are calling `DoWait` concurrently, the notification for cache
wait queue may be limited to just 1 caller's occupation instead of them
combined.

To fix this issue, this patch is trying to notify all waiters in queue.

Signed-off-by: Ted Xu <ted.xu@zilliz.com>
2024-04-08 18:55:16 +08:00
chyezh
7b400252ff
fix: add configuration disk capacity config for lru and fix some bug (#31977)
issue: #30361

- Add configurable disk capacity limit

- fix bitset reset logic

- make insert record reinsert after clear

Signed-off-by: chyezh <chyezh@outlook.com>
2024-04-08 15:55:16 +08:00