issue: #33744
This PR includes the following changes:
1. Added a new task type to the task scheduler in datacoord: stats task,
which sorts segments by primary key.
2. Implemented segment sorting in indexnode.
3. Added a new field `FieldStatsLog` to SegmentInfo to store token index
information.
---------
Signed-off-by: Cai Zhang <cai.zhang@zilliz.com>
issue: #33285
- using streaming service in insert/upsert/flush/delete/querynode
- fixup flusher bugs and refactor the flush operation
- enable streaming service for dml and ddl
- pass the e2e when enabling streaming service
- pass the integration tst when enabling streaming service
---------
Signed-off-by: chyezh <chyezh@outlook.com>
Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
L0 segments now do not contain insert data and may cause confusion for
query hook optimizer if counted as sealed segment number.
This PR add segment level flag in segment entry and exclude L0 segments
while get readable segment snaphsot
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
issue: #35087
after qc restarts, and target is not ready yet, if dist_handler try to
update segment dist, it will set legacy level to l0 segment, which may
cause l0 segment be moved to other node, cause search/query failed.
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
At most cases, data in each channel is almost evenly distributed, we
could utilize the channel num info to optimize searh param in queryHook
Signed-off-by: chasingegg <chao.gao@zilliz.com>
Grow slice & map.growWork may cause a lot when segment number is large
for big K query. This PR pre-allocate space for reduce methods to avoid
this cost.
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
Related to #33235
THe querynode pipeline will make map & call ProcessInsert when there is
no write messages. So querynodes will have high CPU usage even when
there is no workload.
This PR check msg length before composing data struct and calling method
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
github.com/gogo/protobuf is deprecated and could be error prune after
upgrade protobuf message to v2.
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
issue: #34500
cause the sort in `GetLevel0Deletions` will broken the corresponed order
between pks and tss, then the pks and tss will be sorted in
segment.Delete() interface.
This PR remove this uncessary and incorrect sort progress to avoid query
may return deleted records.
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
related: #30376
fix: paritionIDs lost when no setting paritions
enhance: refine metrics for segment prune
Signed-off-by: MrPresent-Han <chun.han@zilliz.com>
related: #30376
1. support more complex expr
2. add more ut test for unrelated fields
Signed-off-by: MrPresent-Han <chun.han@gmail.com>
Co-authored-by: MrPresent-Han <chun.han@gmail.com>
issue: #32252
This PR try to pre-allocate FieldData for Reduce operations in the Query
chain using typeutil.PrepareResultFieldData to avoid the overhead of
dynamically growing the slice during appendFieldData process.
---------
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
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>
issue: #31479#31797
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>
related: #31959
1. reset segment index status after evicting to lazyload=true
2. reset num_rows to null_opt
Signed-off-by: MrPresent-Han <chun.han@zilliz.com>
issue: #31468
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>
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>
"-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>
use retry.handle when request is not able to service but don't throw
unrecoverable erros
fix#31323
Signed-off-by: xiaofanluan <xiaofan.luan@zilliz.com>
/kind improvement
fix: #31272
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>
issue: #30931
- 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>
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>
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>
Chun Han
XuanYang-cn
congqixia
jaime
cai.zhang
Zhen Ye
aoiasd
yihao.dai
Gao
SimFG
Ted Xu
zhagnlu
Bingyi Sun
wei liu
zhenshan.cao
wayblink
smellthemoon
cqy123456
Jiquan Long
Xiaofan
Cai Yudong
foxspy
John
groot
Buqian Zheng