[jira] [Commented] (PARQUET-2149) Implement async IO for Parquet file reader

["ASF GitHub Bot (Jira)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/PARQUET-2149?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17711388#comment-17711388 ] 

ASF GitHub Bot commented on PARQUET-2149:
-----------------------------------------

steveloughran commented on PR #968:
URL: https://github.com/apache/parquet-mr/pull/968#issuecomment-1505269164

   @hazelnutsgz hadoop 3.3.5 supports vector IO on an s3 stream; async parallel fetch of blocks, which also works on local fs (and with gcs, abfs TODO items). we see significant performance increases there. There's a PR for it, though as it is 3.3.5+ only, not merged in to asf parquet branches unless the move or we finish a shim library to offer (serialized) support for the api on older releases.




> 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
(v8.20.10#820010)