[
https://issues.apache.org/jira/browse/PARQUET-2135?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17517681#comment-17517681
]
Miller, Tim commented on PARQUET-2135:
--------------------------------------
Hi,
I was wondering if anyone had any concerns or things they wanted to discuss
about this proposed patch. Would you like some benchmarking results? I'm
currently running the whole TPCDS quite in Trino, where I'm comparing with and
without this patch.
Also, are there any bugs in the JIRA that people would particularly like some
more eyes on?
Thanks.
On 4/1/22, 1:10 PM, "Timothy Miller (Jira)" <[email protected]> wrote:
CAUTION: This email originated from outside of the organization. Do not
click links or open attachments unless you can confirm the sender and know the
content is safe.
Timothy Miller created PARQUET-2135:
---------------------------------------
Summary: Performance optimizations: Merged all
LittleEndianDataInputStream functionality into ByteBufferInputStream
Key: PARQUET-2135
URL: https://issues.apache.org/jira/browse/PARQUET-2135
Project: Parquet
Issue Type: Improvement
Components: parquet-mr
Affects Versions: 1.12.2
Reporter: Timothy Miller
This PR is all performance optimization. In benchmarking with Trino, we
find query performance to improve from 5% to 15%, depending on the query, and
that includes all the I/O time from S3.
The main modification is to merge all of LittleEndianDataInputStream
functionality into ByteBufferInputStream, which yields the following benefits:
* Elimination of extra layers of abstraction and method call overhead
* Enable the use of intrinsics for readInt, readLong, etc.
* Availability of faster access methods like readFully and skipFully,
without the need for helper functions
* Reduces some object creation in the performance critical path
This also includes and enables performance optimizations to:
* ByteBitPackingValuesReader
* PlainValuesReader
* RunLengthBitPackingHybridDecoder
Context:
I've been working on improving Parquet reading performance in Trino, mostly
by profiling while running performance benchmarks and TPCDS queries. This PR is
a subset of the changes I made that have more than doubled the performance of a
lot of TPCDS queries (wall clock time, including the S3 access time). If you
are kind enough to accept these changes, I have more I would like to contribute.
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
> Performance optimizations: Merged all LittleEndianDataInputStream
> functionality into ByteBufferInputStream
> ----------------------------------------------------------------------------------------------------------
>
> Key: PARQUET-2135
> URL: https://issues.apache.org/jira/browse/PARQUET-2135
> Project: Parquet
> Issue Type: Improvement
> Components: parquet-mr
> Affects Versions: 1.12.2
> Reporter: Timothy Miller
> Priority: Major
>
> This PR is all performance optimization. In benchmarking with Trino, we find
> query performance to improve from 5% to 15%, depending on the query, and that
> includes all the I/O time from S3.
> The main modification is to merge all of LittleEndianDataInputStream
> functionality into ByteBufferInputStream, which yields the following benefits:
> * Elimination of extra layers of abstraction and method call overhead
> * Enable the use of intrinsics for readInt, readLong, etc.
> * Availability of faster access methods like readFully and skipFully,
> without the need for helper functions
> * Reduces some object creation in the performance critical path
> This also includes and enables performance optimizations to:
> * ByteBitPackingValuesReader
> * PlainValuesReader
> * RunLengthBitPackingHybridDecoder
> Context:
> I've been working on improving Parquet reading performance in Trino, mostly
> by profiling while running performance benchmarks and TPCDS queries. This PR
> is a subset of the changes I made that have more than doubled the performance
> of a lot of TPCDS queries (wall clock time, including the S3 access time). If
> you are kind enough to accept these changes, I have more I would like to
> contribute.
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
