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>
`localDataRootPath` is used to init local chunk manager and has
`querynode` appended to it, thus is incorrect
#41435
Signed-off-by: Buqian Zheng <zhengbuqian@gmail.com>
issue: #43360
Enhance the partial result evaluation mechanism in delegator to use row
count based data ratio instead of simple segment count ratio for better
accuracy.
Key improvements:
- Introduce PartialResultEvaluator interface for flexible evaluation
strategy
- Implement NewRowCountBasedEvaluator using sealed segment row count
data
- Replace segment count based ratio with row count based data ratio
calculation
- Update PinReadableSegments to return sealedRowCount information
- Modify executeSubTasks to use configurable evaluator for partial
result decisions
- Add comprehensive unit tests for the new row count based evaluation
logic
This change provides more accurate partial result evaluation by
considering the actual data volume rather than just segment quantity,
leading to better query performance and consistency when some segments
are unavailable.
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
Ref https://github.com/milvus-io/milvus/issues/42148https://github.com/milvus-io/milvus/pull/42406 impls the segcore part of
storage for handling with VectorArray.
This PR:
1. impls the go part of storage for VectorArray
2. impls the collection creation with StructArrayField and VectorArray
3. insert and retrieve data from the collection.
---------
Signed-off-by: SpadeA <tangchenjie1210@gmail.com>
Signed-off-by: SpadeA-Tang <tangchenjie1210@gmail.com>
Signed-off-by: SpadeA-Tang <u6748471@anu.edu.au>
issue: #42884
Fixes an issue where delete records for a segment are lost from the
delete buffer if `load segment` execution on the delegator is too slow,
causing `syncTargetVersion` or other cleanup operations to clear them
prematurely.
Changes include:
- Introduced `Pin` and `Unpin` methods in `DeleteBuffer` interface and
its implementations (`doubleCacheBuffer`, `listDeleteBuffer`).
- Added a `pinnedTimestamps` map to track timestamps protected from
cleanup by specific segments.
- Modified `LoadSegments` in `shardDelegator` to `Pin` relevant segment
delete records before loading and `Unpin` them afterwards.
- Added `isPinned` check in `UnRegister` and `TryDiscard` methods of
`listDeleteBuffer` to skip cleanup if corresponding timestamps are
pinned.
- Added comprehensive unit tests for `Pin`, `Unpin`, and `isPinned`
functionality, covering basic, multiple pins, concurrent, and edge
cases.
This ensures the integrity of delete records by preventing their
premature removal from the delete buffer during segment loading.
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
issue: https://github.com/milvus-io/milvus/issues/41435
turns out we have per file binlog size in golang code, by passing it
into segcore we can support eviction in storage v1
Signed-off-by: Buqian Zheng <zhengbuqian@gmail.com>
issue: #41435
issue: https://github.com/milvus-io/milvus/issues/43038
This PR also:
1. removed ERROR state from ListNode
2. CacheSlot will do reserveMemory once for all requested cells after
updating the state to LOADING, so now we transit a cell to LOADING
before its resource reservation
3. reject resource reservation directly if size >= max_size
---------
Signed-off-by: Buqian Zheng <zhengbuqian@gmail.com>
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>
issue: #41570
Fix issue where growing and sealed segments could be searched
simultaneously, causing inflated count(*) results. This was caused by
logic introduced in PR #42009 that made sealed segments readable before
target version advancement.
Changes include:
- Fix conditional filtering logic in PinReadableSegments to prevent
sealed segments from becoming readable prematurely
- Use target version filter for full results (ratio=1.0) to ensure
sealed segments only become readable after target advancement
- Use query view segment list filter for partial results (ratio<1.0) to
maintain backward compatibility
- Simplify target version setting in AddDistributions to prevent
premature segment readability
- Add logging for redundant growing segments during sync
- Add comprehensive unit tests covering the duplicate segment scenario
This fix ensures count(*) queries return accurate results by preventing
the same segment from being counted in both growing and sealed states.
---------
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
issue: #42995
- The consuming lag at streaming node will be reported to coordinator.
- The consuming lag will trigger the write limit and deny by quota
center.
- Set the ttProtection by default.
---------
Signed-off-by: chyezh <chyezh@outlook.com>
Related to #39178
This PR add logs for segment schema change operations.
Also fixes the nit comments from PR #42490
---------
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
issue: #43040
This patch introduces a disk file writer that supports Direct IO.
Currently, it is exclusively utilized during the QueryNode load process.
Below is its parameters:
1. `common.diskWriteMode`
This parameter controls the write mode of the local disk, which is used
to write temporary data downloaded from remote storage.
Currently, only QueryNode uses 'common.diskWrite*' parameters. Support
for other components will be added in the future.
The options include 'direct' and 'buffered'. The default value is
'buffered'.
2. `common.diskWriteBufferSizeKb`
Disk write buffer size in KB, only used when disk write mode is
'direct', default is 64KB.
Current valid range is [4, 65536]. If the value is not aligned to 4KB,
it will be rounded up to the nearest multiple of 4KB.
3. `common.diskWriteNumThreads`
This parameter controls the number of writer threads used for disk write
operations. The valid range is [0, hardware_concurrency].
It is designed to limit the maximum concurrency of disk write operations
to reduce the impact on disk read performance.
For example, if you want to limit the maximum concurrency of disk write
operations to 1, you can set this parameter to 1.
The default value is 0, which means the caller will perform write
operations directly without using an additional writer thread pool.
In this case, the maximum concurrency of disk write operations is
determined by the caller's thread pool size.
Both parameters can be updated during runtime.
---------
Signed-off-by: Shawn Wang <shawn.wang@zilliz.com>
Related to #43028
This PR:
- Add mutex prevent concurrent load segment & schema change
- Add schema verison field in load meta
- Update schema in PutOrRef if schema verison is larger
---------
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
Ref #42053
This is the first PR for optimizing `LIKE` with ngram inverted index.
Now, only VARCHAR data type is supported and only InnerMatch LIKE
(%xxx%) query is supported.
How to use it:
```
milvus_client = MilvusClient("http://localhost:19530")
schema = milvus_client.create_schema()
...
schema.add_field("content_ngram", DataType.VARCHAR, max_length=10000)
...
index_params = milvus_client.prepare_index_params()
index_params.add_index(field_name="content_ngram", index_type="NGRAM", index_name="ngram_index", min_gram=2, max_gram=3)
milvus_client.create_collection(COLLECTION_NAME, ...)
```
min_gram and max_gram controls how we tokenize the documents. For
example, for min_gram=2 and max_gram=4, we will tokenize each document
with 2-gram, 3-gram and 4-gram.
---------
Signed-off-by: SpadeA <tangchenjie1210@gmail.com>
Signed-off-by: SpadeA-Tang <tangchenjie1210@gmail.com>
issue: #42404
Add syncedByCoord field to ensure delegator only becomes serviceable
after coordinator sync, preventing unreliable service state when memory
is insufficient.
Issue: When memory is low, delegator may become serviceable before
current target is ready, but segments can be released at any time,
making the serviceable state unreliable.
Changes include:
- Add syncedByCoord field to track coordinator sync status
- Update Serviceable() to require both data readiness and coord sync
- Set syncedByCoord=true in SyncTargetVersion
- Add comprehensive test coverage
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
Related to #39173
In storage v2, "narrow" column group could have group id not mapped
schema, which causing loading fails or resource estimation result
inaccurate.
This PR handles this case by mapping binlog from index instead of vice
versa.
---------
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
issue: #42098#42404
Fix critical issue where concurrent balance segment and balance channel
operations cause delegator view inconsistency. When shard leader
switches between load and release phases of segment balance, it results
in loading segments on old delegator but releasing on new delegator,
making the new delegator unserviceable.
The root cause is that balance segment modifies delegator views, and if
these modifications happen on different delegators due to leader change,
it corrupts the delegator state and affects query availability.
Changes include:
- Add shardLeaderID field to SegmentTask to track delegator for load
- Record shard leader ID during segment loading in move operations
- Skip release if shard leader changed from the one used for loading
- Add comprehensive unit tests for leader change scenarios
This ensures balance segment operations are atomic on single delegator,
preventing view corruption and maintaining delegator serviceability.
---------
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
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>
issue: #42661
Add NotStopped() and IsWorking() methods to shardDelegator for better
state management and error handling.
Changes include:
- Add instance state checking methods with proper error messages
- Replace lifetime package calls with delegator instance methods
- Add comprehensive unit tests for state transitions and error cases
- Improve error reporting with channel name for better debugging
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
issue: #42663
Fix panic issue when processing VchannelInfo messages from older
coordinator versions that don't have DeleteCheckpoint field.
Changes:
- Add null safety check for DeleteCheckpoint before accessing methods
- Maintain backward compatibility with legacy message formats
- Improve seek position selection logic for both old and new versions
---------
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
Related to #42640
The search/query plan holded a reference to schema, which could be
destructed after schema change. This PR make plan hold a shared ptr to
it fixing dangling reference problem under concurrent read & schema
change.
This PR also remove field binlog check for loading index for old segment
with old schema may have binlog lack.
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
issue: #42165
Implement dynamic task execution capacity calculation based on QueryNode
CPU core count instead of static configuration for better resource
utilization.
Changes include:
- Add CpuCoreNum() method and WithCpuCoreNum() option to NodeInfo
- Implement GetTaskExecutionCap() for dynamic capacity calculation
- Add QueryNodeTaskParallelismFactor parameter for tuning
- Update proto definition to include cpu_core_num field
- Add unit tests for new functionality
This allows QueryCoord to automatically adjust task parallelism based on
actual hardware resources.
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
issue: #39333#41570
Fix delete record missing issue introduced in PR #39552 L0 refactoring:
- Use delete checkpoint as consume start position when deleteCP <
channelCP
- Add logging when delete checkpoint is used instead of seek position
- Prevent delete record loss when deleteCP is earlier than default
channelCP
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
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>
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>
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>
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>
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>
