You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@parquet.apache.org by GitBox <gi...@apache.org> on 2022/04/28 14:10:11 UTC
[GitHub] [parquet-mr] theosib-amazon opened a new pull request, #962: Performance optimization to ByteBitPackingValuesReader
theosib-amazon opened a new pull request, #962:
URL: https://github.com/apache/parquet-mr/pull/962
Minor performance improvements for ByteBitPackingValuesReader:
- Move object creation (temporary byte array) out of frequently used code by retaining small temporary buffer as class member.
- Move less frequently used code (readMore) into separate function to encourage JIT to inline more frequently used code (readInteger)
- Avoid use of unpack8Values that takes ByteBuffer, because it's slower.
--
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: dev-unsubscribe@parquet.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [parquet-mr] shangxinli merged pull request #962: Performance optimization to ByteBitPackingValuesReader
Posted by GitBox <gi...@apache.org>.
shangxinli merged PR #962:
URL: https://github.com/apache/parquet-mr/pull/962
--
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: dev-unsubscribe@parquet.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [parquet-mr] shangxinli commented on pull request #962: Performance optimization to ByteBitPackingValuesReader
Posted by GitBox <gi...@apache.org>.
shangxinli commented on PR #962:
URL: https://github.com/apache/parquet-mr/pull/962#issuecomment-1124443439
Can you add tests?
--
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: dev-unsubscribe@parquet.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [parquet-mr] theosib-amazon commented on pull request #962: Performance optimization to ByteBitPackingValuesReader
Posted by GitBox <gi...@apache.org>.
theosib-amazon commented on PR #962:
URL: https://github.com/apache/parquet-mr/pull/962#issuecomment-1128059990
There is no new functionality here. There is just a performance optimization. It looks like the following tests should already handle this: BitPackingPerfTest, TestBitPackingColumn. There are also a bunch of other tests that use it indirectly, because they test classes that instantiate ByteBitPackingValuesReader.
--
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: dev-unsubscribe@parquet.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [parquet-mr] ggershinsky commented on pull request #962: Performance optimization to ByteBitPackingValuesReader
Posted by GitBox <gi...@apache.org>.
ggershinsky commented on PR #962:
URL: https://github.com/apache/parquet-mr/pull/962#issuecomment-1262142129
Optimizations like using byte arrays instead of byte buffers, and allocating the byte array once only, instead of per operation. Done in a concise manner, without unnecessary code changes. LGTM.
--
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: dev-unsubscribe@parquet.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org