[SPARK-2650][SQL] Try to partially fix SPARK-2650 by adjusting initial buffer size and reducing memory allocation #1769
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
QA tests have started for PR 1769. This patch merges cleanly. |
|
QA tests have started for PR 1769. This patch merges cleanly. |
|
QA results for PR 1769: |
|
QA results for PR 1769: |
|
Thanks, merged into master and 1.1. |
asfgit
pushed a commit
that referenced
this pull request
Aug 6, 2014
…l buffer size and reducing memory allocation JIRA issue: [SPARK-2650](https://issues.apache.org/jira/browse/SPARK-2650) Please refer to [comments](https://issues.apache.org/jira/browse/SPARK-2650?focusedCommentId=14084397&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-14084397) of SPARK-2650 for some other details. This PR adjusts the initial in-memory columnar buffer size to 1MB, same as the default value of Shark's `shark.column.partitionSize.mb` property when running in local mode. Will add Shark style partition size estimation in another PR. Also, before this PR, `NullableColumnBuilder` copies the whole buffer to add the null positions section, and then `CompressibleColumnBuilder` copies and compresses the buffer again, even if compression is disabled (`PassThrough` compression scheme is used to disable compression). In this PR the first buffer copy is eliminated to reduce memory consumption. Author: Cheng Lian <lian.cs.zju@gmail.com> Closes #1769 from liancheng/spark-2650 and squashes the following commits: 88a042e [Cheng Lian] Fixed method visibility and removed dead code 001f2e5 [Cheng Lian] Try fixing SPARK-2650 by adjusting initial buffer size and reducing memory allocation (cherry picked from commit d0ae3f3) Signed-off-by: Michael Armbrust <michael@databricks.com>
xiliu82
pushed a commit
to xiliu82/spark
that referenced
this pull request
Sep 4, 2014
…l buffer size and reducing memory allocation JIRA issue: [SPARK-2650](https://issues.apache.org/jira/browse/SPARK-2650) Please refer to [comments](https://issues.apache.org/jira/browse/SPARK-2650?focusedCommentId=14084397&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-14084397) of SPARK-2650 for some other details. This PR adjusts the initial in-memory columnar buffer size to 1MB, same as the default value of Shark's `shark.column.partitionSize.mb` property when running in local mode. Will add Shark style partition size estimation in another PR. Also, before this PR, `NullableColumnBuilder` copies the whole buffer to add the null positions section, and then `CompressibleColumnBuilder` copies and compresses the buffer again, even if compression is disabled (`PassThrough` compression scheme is used to disable compression). In this PR the first buffer copy is eliminated to reduce memory consumption. Author: Cheng Lian <lian.cs.zju@gmail.com> Closes apache#1769 from liancheng/spark-2650 and squashes the following commits: 88a042e [Cheng Lian] Fixed method visibility and removed dead code 001f2e5 [Cheng Lian] Try fixing SPARK-2650 by adjusting initial buffer size and reducing memory allocation
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
JIRA issue: SPARK-2650
Please refer to comments of SPARK-2650 for some other details.
This PR adjusts the initial in-memory columnar buffer size to 1MB, same as the default value of Shark's
shark.column.partitionSize.mbproperty when running in local mode. Will add Shark style partition size estimation in another PR.Also, before this PR,
NullableColumnBuildercopies the whole buffer to add the null positions section, and thenCompressibleColumnBuildercopies and compresses the buffer again, even if compression is disabled (PassThroughcompression scheme is used to disable compression). In this PR the first buffer copy is eliminated to reduce memory consumption.