query coord send load request to delegator, delegator load bf first,
then forward load request to qn worker. but when qn worker has no more
memory, it will return load failed immediatelly. then delegator roll
back the loaded bf. query coord wil retry the load request, and
delegator will load and roll back bf again and again.
this PR delay the loading bf step until load segment succeed in worker.
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
issue: #32995
To speed up the construction and querying of Bloom filters, we chose a
blocked Bloom filter instead of a basic Bloom filter implementation.
WARN: This PR is compatible with old version bf impl, but if fall back
to old milvus version, it may causes bloom filter deserialize failed.
In single Bloom filter test cases with a capacity of 1,000,000 and a
false positive rate (FPR) of 0.001, the blocked Bloom filter is 5 times
faster than the basic Bloom filter in both querying and construction, at
the cost of a 30% increase in memory usage.
- Block BF construct time {"time": "54.128131ms"}
- Block BF size {"size": 3021578}
- Block BF Test cost {"time": "55.407352ms"}
- Basic BF construct time {"time": "210.262183ms"}
- Basic BF size {"size": 2396308}
- Basic BF Test cost {"time": "192.596229ms"}
In multi Bloom filter test cases with a capacity of 100,000, an FPR of
0.001, and 100 Bloom filters, we reuse the primary key locations for all
Bloom filters to avoid repeated hash computations. As a result, the
blocked Bloom filter is also 5 times faster than the basic Bloom filter
in querying.
- Block BF TestLocation cost {"time": "529.97183ms"}
- Basic BF TestLocation cost {"time": "3.197430181s"}
---------
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
related: #33137
adding has_more_result_tag for various level's reduce to rectify
reduce_stop_for_best
Signed-off-by: MrPresent-Han <chun.han@zilliz.com>
1. use a small warmup pool to reduce the impact of warmup
2. change the warmup pool to nonblocking mode
3. disable warmup by default
4. remove the maximum size limit of 16 for the load pool
issue: https://github.com/milvus-io/milvus/issues/32772
---------
Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
Co-authored-by: xiaofanluan <xiaofan.luan@zilliz.com>
issue: #32530
cause ProcessDelete need to check whether pk exist in bloom filter, and
ProcessInsert need to update pk to bloom filter, when execute
ProcessInsert and ProcessDelete in parallel, it will cause race
condition in segment's bloom filter
This PR execute ProcessInsert and ProcessDelete in serial to avoid block
each other
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
fix#32979
remove l0 cache and build delete pk and ts everytime. this reduce the
memory and also increase the code readability
Signed-off-by: xiaofanluan <xiaofan.luan@zilliz.com>
issue: #33005
1. add `MemorySize` field for insert binlog.
2. `LogSize` means the file size in the storage object.
3. `MemorySize` means the size of the data in the memory.
---------
Signed-off-by: Cai Zhang <cai.zhang@zilliz.com>
Signed-off-by: cai.zhang <cai.zhang@zilliz.com>
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>
issue:#32899
This PR fix the wrong metric value of load index, which introduced by
pr#32567, use wrong time unit for load index metrics
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
issue: #32530
when try to match segment bloom filter with pk, we can reuse the hash
locations. This PR maintain the max hash Func, and compute hash location
once for all segment, reuse hash location can speed up bf access
---------
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
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>
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>
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>
`applyDelete` used to be serial for delete entries on each segments.
This PR make it work in parallel with errgroup to improve performance
---------
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
issue: #30361
- Delete may be lost when segment is not data-loaded status in lru
cache. skip filtering to fix it.
- `stats_` and `variable_fields_avg_size_` should be reset when
`ReleaseData`
- Remove repeat load delta log operation in lru.
---------
Signed-off-by: chyezh <chyezh@outlook.com>
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>
jaime
wei liu
Jiquan Long
Chun Han
aoiasd
SimFG
yihao.dai
Bingyi Sun
Xiaofan
cai.zhang
Cai Yudong
chyezh
foxspy
congqixia
Gao