[
https://issues.apache.org/jira/browse/PARQUET-2149?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17542147#comment-17542147
]
ASF GitHub Bot commented on PARQUET-2149:
-----------------------------------------
theosib-amazon commented on PR #968:
URL: https://github.com/apache/parquet-mr/pull/968#issuecomment-1137610598
That batch reader in Presto reminds me of some of the experimental changes I
made in Trino. I modified PrimitiveColumnReader to work out how many of each
data item it needs to read from the data source and requests all of them at
once in an array. This doubled the performance of some TPCDS queries. This is
why I have array access methods planned for ParquetMR.
(https://docs.google.com/document/d/1fBGpF_LgtfaeHnPD5CFEIpA2Ga_lTITmFdFIcO9Af-g/edit?usp=sharing)
Requesting data in bulk saves a lot on function call overhead for each data
item.
> Implement async IO for Parquet file reader
> ------------------------------------------
>
> Key: PARQUET-2149
> URL: https://issues.apache.org/jira/browse/PARQUET-2149
> Project: Parquet
> Issue Type: Improvement
> Components: parquet-mr
> Reporter: Parth Chandra
> Priority: Major
>
> ParquetFileReader's implementation has the following flow (simplified) -
> - For every column -> Read from storage in 8MB blocks -> Read all
> uncompressed pages into output queue
> - From output queues -> (downstream ) decompression + decoding
> This flow is serialized, which means that downstream threads are blocked
> until the data has been read. Because a large part of the time spent is
> waiting for data from storage, threads are idle and CPU utilization is really
> low.
> There is no reason why this cannot be made asynchronous _and_ parallel. So
> For Column _i_ -> reading one chunk until end, from storage -> intermediate
> output queue -> read one uncompressed page until end -> output queue ->
> (downstream ) decompression + decoding
> Note that this can be made completely self contained in ParquetFileReader and
> downstream implementations like Iceberg and Spark will automatically be able
> to take advantage without code change as long as the ParquetFileReader apis
> are not changed.
> In past work with async io [Drill - async page reader
> |https://github.com/apache/drill/blob/master/exec/java-exec/src/main/java/org/apache/drill/exec/store/parquet/columnreaders/AsyncPageReader.java]
> , I have seen 2x-3x improvement in reading speed for Parquet files.
--
This message was sent by Atlassian Jira
(v8.20.7#820007)
