You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@parquet.apache.org by "Ryan Blue (JIRA)" <ji...@apache.org> on 2015/06/09 23:45:01 UTC
[jira] [Commented] (PARQUET-306) Improve alignment between row
groups and HDFS blocks
[ https://issues.apache.org/jira/browse/PARQUET-306?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14579618#comment-14579618 ]
Ryan Blue commented on PARQUET-306:
-----------------------------------
The PR implements #1 and #3. HDFS-3689 isn't available yet.
> Improve alignment between row groups and HDFS blocks
> ----------------------------------------------------
>
> Key: PARQUET-306
> URL: https://issues.apache.org/jira/browse/PARQUET-306
> Project: Parquet
> Issue Type: Improvement
> Components: parquet-mr
> Reporter: Ryan Blue
> Assignee: Ryan Blue
>
> Row groups should not span HDFS blocks to avoid remote reads. There are 3 things we can use to avoid this:
> 1. Set the next row group's size to the remaining bytes in the current HDFS block
> 2. Use HDFS-3689, variable-length HDFS blocks, when available
> 3. Pad after row groups close to the block boundary to start the next row group at the start of the next block
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)