zenoyang opened a new pull request, #19313:
URL: https://github.com/apache/doris/pull/19313
# Proposed changes
Issue Number: close #xxx
Avoid copying when bitmap deserialization.
## Problem summary
Tested based on version 1.1.5
test sql:
```sql
set enable_vectorized_engine=true;
set parallel_fragment_exec_instance_num = 1;
SELECT flow_key
, bitmap_union_count(user_id)
FROM db1.tbl1
WHERE partition_date BETWEEN '2022-06-20' AND '2022-07-25'
group by flow_key
```
before:
```
SegmentIterator:
- Id: 0
- Table Name: tbl1
- BitmapIndexFilterTimer: 58.477us
- BlockLoadTime: 14s123ms
- BlockSeekCount: 95
- BlockSeekTime: 15.566ms
- BlocksLoad: 966
- CachedPagesNum: 0
- CompressedBytesRead: 304.42 MB
- DecompressorTimer: 429.259ms
- IOTimer: 193.780ms
- IndexLoadTime_V1: 0ns
- NumSegmentFiltered: 0
- NumSegmentTotal: 95
- RawRowsRead: 3.371003M (3371003)
- RowsBitmapIndexFiltered: 0
- RowsBloomFilterFiltered: 0
- RowsConditionsFiltered: 0
- RowsKeyRangeFiltered: 0
- RowsStatsFiltered: 0
- RowsVectorPredFiltered: 0
- TotalPagesNum: 6.774K (6774)
- UncompressedBytesRead: 399.61 MB
- VectorPredEvalTime: 0ns
```
after:
```
SegmentIterator:
- Id: 0
- Table Name: tbl1
- BitmapIndexFilterTimer: 63.642us
- BlockLoadTime: 6s572ms
- BlockSeekCount: 94
- BlockSeekTime: 12.363ms
- BlocksLoad: 933
- CachedPagesNum: 0
- CompressedBytesRead: 297.09 MB
- DecompressorTimer: 260.559ms
- IOTimer: 142.114ms
- IndexLoadTime_V1: 0ns
- NumSegmentFiltered: 0
- NumSegmentTotal: 94
- RawRowsRead: 3.249427M (3249427)
- RowsBitmapIndexFiltered: 0
- RowsBloomFilterFiltered: 0
- RowsConditionsFiltered: 0
- RowsKeyRangeFiltered: 0
- RowsStatsFiltered: 0
- RowsVectorPredFiltered: 0
- TotalPagesNum: 6.625K (6625)
- UncompressedBytesRead: 389.85 MB
- VectorPredEvalTime: 0ns
```
BlockLoadTime dropped from 14s123ms to 6s572ms
## Checklist(Required)
* [ ] Does it affect the original behavior
* [ ] Has unit tests been added
* [ ] Has document been added or modified
* [ ] Does it need to update dependencies
* [ ] Is this PR support rollback (If NO, please explain WHY)
## Further comments
If this is a relatively large or complex change, kick off the discussion at
[[email protected]](mailto:[email protected]) by explaining why you
chose the solution you did and what alternatives you considered, etc...
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
