[
https://issues.apache.org/jira/browse/PARQUET-2149?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17694116#comment-17694116
]
ASF GitHub Bot commented on PARQUET-2149:
-----------------------------------------
parthchandra commented on PR #968:
URL: https://github.com/apache/parquet-mr/pull/968#issuecomment-1446796605
Also try a query like
```
select
SUM(length(IFNULL(ss_sold_date_sk, ' '))),
SUM(length(IFNULL(ss_sold_time_sk, ' '))),
SUM(length(IFNULL(ss_item_sk, ' '))),
SUM(length(IFNULL(ss_customer_sk, ' '))),
SUM(length(IFNULL(ss_cdemo_sk, ' '))),
SUM(length(IFNULL(ss_hdemo_sk, ' '))),
SUM(length(IFNULL(ss_addr_sk, ' '))),
SUM(length(IFNULL(ss_store_sk, ' '))),
SUM(length(IFNULL(ss_promo_sk, ' '))),
SUM(length(IFNULL(ss_ticket_number, ' '))),
SUM(ss_quantity),
SUM(ss_wholesale_Cost),
SUM(ss_list_price ),
SUM(ss_sales_price),
SUM(ss_ext_discount_amt),
SUM(ss_ext_sales_price),
SUM(ss_ext_wholesale_cost),
SUM(ss_ext_list_price),
SUM(ss_ext_tax),
SUM(ss_coupon_amt),
SUM(ss_net_paid),
SUM(ss_net_paid_inc_tax),
SUM(ss_net_profit)
from store_sales
```
which avoids the expensive sort
> 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)
