159 Commits

Author SHA1 Message Date
congqixia
0a208d7224
enhance: Move segment loading logic from Go layer to segcore for self-managed loading (#45488)
Related to #45060

Refactor segment loading architecture to make segments autonomously
manage their own loading process, moving the orchestration logic from Go
(segment_loader.go) to C++ (segcore).

**C++ Layer (segcore):**
- Added `SetLoadInfo()` and `Load()` methods to `SegmentInterface` and
implementations
- Implemented `ChunkedSegmentSealedImpl::Load()` with parallel loading
strategy:
  - Separates indexed fields from non-indexed fields
  - Loads indexes concurrently using thread pools
  - Loads field data for non-indexed fields in parallel
- Implemented `SegmentGrowingImpl::Load()` to convert and load field
data
- Extracted `LoadIndexData()` as a reusable utility function in
`Utils.cpp`
- Added `SegmentLoad()` C binding in `segment_c.cpp`

**Go Layer:**
- Added `Load()` method to segment interfaces
- Updated mock implementations and test interfaces
- Integrated new C++ `SegmentLoad()` binding in Go segment wrapper

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-11-14 11:21:37 +08:00
congqixia
36a887b38b
enhance: add NewSegmentWithLoadInfo API to support segment self-managed loading (#45061)
This commit introduces the foundation for enabling segments to manage
their own loading process by passing load information during segment
creation.

Changes:

C++ Layer:
- Add NewSegmentWithLoadInfo() C API to create segments with serialized
load info
- Add SetLoadInfo() method to SegmentInterface for storing load
information
- Refactor segment creation logic into shared CreateSegment() helper
function
- Add comprehensive documentation for the new API

Go Layer:
- Extend CreateCSegmentRequest to support optional LoadInfo field
- Update segment creation in querynode to pass SegmentLoadInfo when
available
- Add ConvertToSegcoreSegmentLoadInfo() and helper converters for proto
translation

Proto Definitions:
- Add segcorepb.SegmentLoadInfo message with essential loading metadata
- Add supporting messages: Binlog, FieldBinlog, FieldIndexInfo,
TextIndexStats, JsonKeyStats
- Remove dependency on data_coord.proto by creating segcore-specific
definitions

Testing:
- Add comprehensive unit tests for proto conversion functions
- Test edge cases including nil inputs, empty data, and nil array/map
elements

This is the first step toward issue #45060 - enabling segments to
autonomously manage their loading process, which will:
- Clarify responsibilities between Go and C++ layers
- Reduce cross-language call overhead
- Enable precise resource management at the C++ level
- Support better integration with caching layer
- Enable proactive schema evolution handling

Related to #45060

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-10-27 15:28:12 +08:00
sparknack
935160840c
enhance: add a disk quota for the loaded binlog size to prevent load failure of querynode (#44893)
issue: #41435

---------

Signed-off-by: Shawn Wang <shawn.wang@zilliz.com>
2025-10-19 19:44:01 +08:00
sparknack
c8a4d6e2ef
enhance: add cachinglayer management for TextMatchIndex (#44741)
issue: #41435, #44502

Signed-off-by: Shawn Wang <shawn.wang@zilliz.com>
2025-10-13 14:37:58 +08:00
sparknack
6d5b41644b
enhance: remove logical usage checks during segment loading (#44743)
issue: #41435

Signed-off-by: Shawn Wang <shawn.wang@zilliz.com>
2025-10-13 14:21:58 +08:00
zhagnlu
eac16a577c
enhance:support cachelayer for json stats (#44446)
#42533

Signed-off-by: zhagnlu <lu.zhang@zilliz.com>
2025-09-24 15:30:04 +08:00
jiaqizho
338ed2fed4
enhance: Introduce sparse filter in query (#44347)
issue: #44373

The current commit implements sparse filtering in query tasks using the
statistical information (Bloom filter/MinMax) of the Primary Key (PK).

The statistical information of the PK is bound to the segment during the
segment loading phase. A new filter has been added to the segment filter
to enable the sparse filtering functionality.

Signed-off-by: jiaqizho <jiaqi.zhou@zilliz.com>
2025-09-23 09:58:09 +08:00
Gao
2e98cb0103
enhance: load resource estimation for tiered index (#44171)
issue: https://github.com/milvus-io/milvus/issues/42032

- Use bytes to estimate load resource in the whole estimation procedure
- Add num_rows and dim info for vector index to better estimate
- Disable eviction for tiered index's meta

---------

Signed-off-by: chasingegg <chao.gao@zilliz.com>
2025-09-04 19:41:53 +08:00
Bingyi Sun
0c0630cc38
feat: support dropping index without releasing collection (#42941)
issue: #42942

This pr includes the following changes:
1. Added checks for index checker in querycoord to generate drop index
tasks
2. Added drop index interface to querynode
3. To avoid search failure after dropping the index, the querynode
allows the use of lazy mode (warmup=disable) to load raw data even when
indexes contain raw data.
4. In segcore, loading the index no longer deletes raw data; instead, it
evicts it.
5. In expr, the index is pinned to prevent concurrent errors.

---------

Signed-off-by: sunby <sunbingyi1992@gmail.com>
2025-09-02 16:17:52 +08:00
congqixia
7721edf32a
enhance: Add mutex and range check preventing concurrent del (#44128)
This PR adds a mutex prevent concurrent applying delete on same segment
and check latestDeltaTimestamp to skip overlapping delete range

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-09-01 14:29:52 +08:00
zhagnlu
fc876639cf
enhance: support json stats with shredding design (#42534)
#42533

Co-authored-by: luzhang <luzhang@zilliz.com>
2025-09-01 10:49:52 +08:00
sparknack
70c8114e85
enhance: cachinglayer: resource management for segment loading (#43846)
issue: #41435

---------

Signed-off-by: Shawn Wang <shawn.wang@zilliz.com>
2025-08-29 11:37:50 +08:00
Chun Han
da156981c6
feat: milvus support posix-compatible mode(milvus-io#43942) (#43944)
related: #43942

Signed-off-by: MrPresent-Han <chun.han@gmail.com>
Co-authored-by: MrPresent-Han <chun.han@gmail.com>
2025-08-27 16:29:50 +08:00
zhagnlu
8934c18792
enhance: support cache result cache for expr (#43923)
issue: #43878

Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2025-08-26 10:55:52 +08:00
Xianhui Lin
c7d8dc100a
fix: add segment lock in LoadTextIndex and LoadJSONKeyIndex (#43811)
fix: add segment lock in LoadTextIndex and LoadJSONKeyIndex
issue:https://github.com/milvus-io/milvus/issues/43572

Signed-off-by: Xianhui.Lin <xianhui.lin@zilliz.com>
2025-08-18 01:17:52 +08:00
sparknack
544c7c0600
enhance: update cachinglayer default cache ratio to 0.3 (#43723)
issue: #41435

---------

Signed-off-by: Shawn Wang <shawn.wang@zilliz.com>
2025-08-05 01:35:39 +08:00
Chun Han
d826d6ac91
fix: try to get span raw data for variable length data type(#43544) (#43705)
related: #43544

Signed-off-by: MrPresent-Han <chun.han@gmail.com>
Co-authored-by: MrPresent-Han <chun.han@gmail.com>
2025-08-04 11:15:38 +08:00
sparknack
bdd65871ea
enhance: tiered storage: estimate segment loading resource usage while considering eviction (#43323)
issue: #41435 

After introducing the caching layer's lazy loading and eviction
mechanisms, most parts of a segment won't be loaded into memory or disk
immediately, even if the segment is marked as LOADED. This means
physical resource usage may be very low. However, we still need to
reserve enough resources for the segments marked as LOADED. Thus, the
logic of resource usage estimation during segment loading, which based
on physcial resource usage only for now, should be changed.

To address this issue, we introduced the concept of logical resource
usage in this patch. This can be thought of as the base reserved
resource for each LOADED segment.

A segment’s logical resource usage is derived from its final evictable
and inevictable resource usage and calculated as follows:

```
SLR = SFPIER + evitable_cache_ratio * SFPER
```

it also equals to

```
SLR = (SFPIER + SFPER) - (1.0 - evitable_cache_ratio) * SFPER
```

`SLR`: The logical resource usage of a segment.
`SFPIER`: The final physical inevictable resource usage of a segment.
`SFPER`: The final physical evictable resource usage of a segment.
`evitable_cache_ratio`: The ratio of a segment's evictable resources
that can be cached locally. The higher the ratio, the more physical
memory is reserved for evictable memory.

When loading a segment, two types of resource usage are taken into
account.

First is the estimated maximum physical resource usage:

```
PPR = HPR + CPR + SMPR - SFPER
```

`PPR`: The predicted physical resource usage after the current segment
is allowed to load.
`HPR`: The physical resource usage obtained from hardware information.  
`CPR`: The total physical resource usage of segments that have been
committed but not yet loaded. When one new segment is allow to load,
`CPR' = CPR + (SMR - SER)`. When one of the committed segments is
loaded, `CPR' = CPR - (SMR - SER)`.
`SMPR`: The maximum physical resource usage of the current segment.
`SFPER`: The final physical evictable resource usage of the current
segment.

Second is the estimated logical resource usage, this check is only valid
when eviction is enabled:

```
PLR = LLR + CLR + SLR
```

`PLR`: The predicted logical resource usage after the current segment is
allowed to load.
`LLR`: The total logical resource usage of all loaded segments. When a
new segment is loaded, `LLR` should be updated to `LLR' = LLR + SLR`.
`CLR`: The total logical resource usage of segments that have been
committed but not yet loaded. When one new segment is allow to load,
`CLR' = CLR + SLR`. When one of the committed segments is loaded, `CLR'
= CLR - SLR`.
`SLR`: The logical resource usage of the current segment.

Only when `PPR < PRL && PLR < PRL` (`PRL`: Physical resource limit of
the querynode), the segment is allowed to be loaded.

---------

Signed-off-by: Shawn Wang <shawn.wang@zilliz.com>
2025-08-01 21:31:37 +08:00
Zhen Ye
3aacd179f7
fix: balance channel before balance segment when upgrading (#43346)
issue: #43117, #42966, #43373

- also fix channel balance may not work at 2.6.
- fix error lost at delete path
- add mvcc into s/q log
- change the log level for TestCoordDownSearch

Signed-off-by: chyezh <chyezh@outlook.com>
2025-07-17 20:16:52 +08:00
sthuang
0d57acb13a
enhance: [StorageV2] field id as meta path for wide column when load (#42863)
related: #42862 #39173

Signed-off-by: shaoting-huang <shaoting.huang@zilliz.com>
2025-06-25 11:08:48 +08:00
Spade A
e2c85eec81
fix: load stats index based on mmap config (#42788)
ref https://github.com/milvus-io/milvus/issues/42626

This PR makes text match index and json key stats index be loaded based
on mmap config.

---------

Signed-off-by: SpadeA <tangchenjie1210@gmail.com>
2025-06-19 10:10:39 +08:00
Chun Han
001619aef9
feat: supporing load priority for loading (#42413)
related: #40781

Signed-off-by: MrPresent-Han <chun.han@gmail.com>
Co-authored-by: MrPresent-Han <chun.han@gmail.com>
2025-06-17 15:22:38 +08:00
cqy123456
5fe7015f63
enhance: InterimIndex support more index type and data type (#41021)
issue: https://github.com/milvus-io/milvus/issues/27678
cherry pick from : https://github.com/milvus-io/milvus/pull/39180,
https://github.com/milvus-io/milvus/pull/40429

Signed-off-by: cqy123456 <qianya.cheng@zilliz.com>
2025-05-28 08:40:28 +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
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
Buqian Zheng
ff5c2770e5
feat: cachinglayer: various improvements (#41546)
issue: https://github.com/milvus-io/milvus/issues/41435

this PR is based on https://github.com/milvus-io/milvus/pull/41436. 

Improvements include:

- Lazy Load support for Storage v1
- Use Low/High watermark to control eviction
- Caching Layer related config changes
- Removed ChunkCache related configs and code in golang
- Add `PinAllCells` helper method to CacheSlot class
- Modified ValueAt, RawAt, PrimitiveRawAt to Bulk version, to reduce
caching layer overhead
- Removed some unclear templated bulk_subscript methods
- CachedSearchIterator to store PinWrapper when searching on
ChunkedColumn, and removed unused contrustor.

---------

Signed-off-by: Buqian Zheng <zhengbuqian@gmail.com>
2025-05-10 09:19:16 +08:00
Buqian Zheng
3de904c7ea
feat: add cachinglayer to sealed segment (#41436)
issue: https://github.com/milvus-io/milvus/issues/41435

---------

Signed-off-by: Buqian Zheng <zhengbuqian@gmail.com>
2025-04-28 10:52:40 +08:00
congqixia
b5443ddbd0
enhance: [AddField] Reopen loaded segments after AddField (#41529)
Related to #39718

This PR:
- Add reopen logic for growing & sealed segments
- Lazy reopen when schema version increases
- Add FinishLoad api for loading progress

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-04-26 08:48:39 +08:00
SimFG
91d40fa558
fix: Update logging context and upgrade dependencies (#41318)
- issue: #41291

---------

Signed-off-by: SimFG <bang.fu@zilliz.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-04-23 10:52:38 +08:00
Bingyi Sun
bf617115ca
enhance: Remove single chunk segment related codes (#39249)
https://github.com/milvus-io/milvus/issues/39112

---------

Signed-off-by: sunby <sunbingyi1992@gmail.com>
2025-04-11 18:56:29 +08:00
Xianhui Lin
3bc24c264f
enhance: Add json key inverted index in stats for optimization (#38039)
Add json key inverted index in stats for optimization
https://github.com/milvus-io/milvus/issues/36995

---------

Signed-off-by: Xianhui.Lin <xianhui.lin@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2025-04-10 15:20:28 +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
Bingyi Sun
b59555057d
feat: support json index (#36750)
https://github.com/milvus-io/milvus/issues/35528

This PR adds json index support for json and dynamic fields. Now you can
only do unary query like 'a["b"] > 1' using this index. We will support
more filter type later.

basic usage:
```
collection.create_index("json_field", {"index_type": "INVERTED",
    "params": {"json_cast_type": DataType.STRING, "json_path":
'json_field["a"]["b"]'}})
```

There are some limits to use this index:
1. If a record does not have the json path you specify, it will be
ignored and there will not be an error.
2. If a value of the json path fails to be cast to the type you specify,
it will be ignored and there will not be an error.
3. A specific json path can have only one json index.
4. If you try to create more than one json indexes for one json field,
sdk(pymilvus<=2.4.7) may return immediately because of internal
implementation. This will be fixed in a later version.

---------

Signed-off-by: sunby <sunbingyi1992@gmail.com>
2025-02-15 14:06:15 +08:00
congqixia
b2d6dbf836
fix: Return early when skip load pk index (#39762)
Previous PR #39437 only print log and add index while load operation is
still executed. This PR return early when segment decides not to load PK
index.

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-02-11 11:04:50 +08:00
aoiasd
74890dabc9
enhance: skip load bm25 sparse row data (#39078)
Skip load row data of bm25 sparse field, because it's forbidden to
return.

---------

Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
2025-02-06 18:40:44 +08:00
congqixia
fb5761af8d
enhance: Skip loading pk index for sorted segment in loader (#39437)
Related to #39339
Previous PR #39389 only skips append index into segment

Also related to #39428

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-01-20 18:17:10 +08:00
congqixia
57e5652f1a
enhance: Log error instead of panicking if load lock wait timeout (#39308)
Related to #39205
Previous PR #39206

This PR change wait timeout behavior to log error and return to avoid
making other collection read failure in only some collections have
deadlock

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-01-16 02:31:02 +08:00
yihao.dai
ce41778fe6
enhance: Optimize GetLocalDiskSize and segment loader mutex (#38599)
1. Make the segment loader lock protect only the resource.
2. Optimize GetDiskUsage to avoid excessive overhead.

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

---------

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2025-01-15 15:45:01 +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
congqixia
d89768f9e0
enhance: Unify LoadStateLock RLock & PinIf (#39206)
Related to #39205

This PR merge `RLock` & `PinIfNotReleased` into `PinIf` function
preventing segment being released before any Read operation finished.

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-01-14 18:38:59 +08:00
Zhen Ye
3e788f0fbd
enhance: record memory size (uncompressed) item for index (#38770)
issue: #38715

- Current milvus use a serialized index size(compressed) for estimate
resource for loading.
- Add a new field `MemSize` (before compressing) for index to estimate
resource.

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2025-01-14 10:33:06 +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
Bingyi Sun
c6a7f48123
enhance: Fix using wrong pool for warmup (#38941)
Signed-off-by: sunby <sunbingyi1992@gmail.com>
2025-01-03 17:50:54 +08:00
Bingyi Sun
aa0a87eda7
fix: Block warmup submit if pool full in sync mode (#38690)
https://github.com/milvus-io/milvus/issues/38692

---------

Signed-off-by: sunby <sunbingyi1992@gmail.com>
2025-01-02 15:04:58 +08:00
Zhen Ye
5395ec19ad
enhance: add mem size for index file and fallback to multiply with serialized size (#38716)
issue: #38715

Signed-off-by: chyezh <chyezh@outlook.com>
2024-12-25 14:46:49 +08:00
congqixia
618f0cb728
enhance: Put release segment and other misc cgo call into pool (#38186)
Related to #30273

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-12-05 11:04:40 +08:00
Zhen Ye
c6dcef7b84
enhance: move segcore codes of segment into one package (#37722)
issue: #33285

- move most cgo opeartions related to search/query into segcore package
for reusing for streamingnode.
- add go unittest for segcore operations.

Signed-off-by: chyezh <chyezh@outlook.com>
2024-11-29 10:22:36 +08:00
congqixia
1ed686783f
enhance: Use PrimaryKeys to replace interface slice for segment delete (#37880)
Related to #35303

Reduce temporary memory usage for PK interface for segment delete.

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-11-22 11:52:33 +08:00
congqixia
92e6ee6285
enhance: Use load pool for CreateTextIndex (#37898)
Related to #37895

Only resolves the starving issue which caused goroutine leakage

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-11-22 10:06:33 +08:00
congqixia
ee54a98578
enhance: Add cgo call metrics for load/write API (#37405)
Cgo API cost is not observerable since not metrics is related to them.
This PR add metrics for some sync cgo call related to load & write

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-11-07 10:06:25 +08:00