[
https://issues.apache.org/jira/browse/KUDU-2162?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16979695#comment-16979695
]
ASF subversion and git services commented on KUDU-2162:
-------------------------------------------------------
Commit b58b37a1ffe359f8237e1ff7a834080cab111339 in kudu's branch
refs/heads/master from Thomas D'Silva
[ https://gitbox.apache.org/repos/asf?p=kudu.git;h=b58b37a ]
KUDU-2162 Expose stats about scan filters
This patch adds the following resource metrics to scanners.
- bytes read, from disk or cache
- scan rpc wait and total duration scanner was open in nanoseconds
- cpu time and system time in nanoseconds
These metrics can be used to roughly compare the amount of work done by
scan operations, and could be useful for runtime optimizations in query
planners like Impala or Spark.
Change-Id: Id30a7e82357fe2fc28f6d316378a612af43d8c96
Reviewed-on: http://gerrit.cloudera.org:8080/8375
Reviewed-by: Adar Dembo <a...@cloudera.com>
Tested-by: Adar Dembo <a...@cloudera.com>
> Expose stats about scan filters
> -------------------------------
>
> Key: KUDU-2162
> URL: https://issues.apache.org/jira/browse/KUDU-2162
> Project: Kudu
> Issue Type: Improvement
> Components: client
> Reporter: Thomas Tauber-Marshall
> Assignee: Thomas D'Silva
> Priority: Major
> Fix For: 1.12.0
>
>
> Impala is working on implementing runtime filters that get pushed down into
> Kudu using KuduScanner::AddConjunctPredicate()
> It would be useful for perf analysis and debugging to be able to include info
> in Impala's runtime profile about the effectiveness of the filters, eg.
> number of rows that are filtered.
> This would probably require at least two counters:
> - # of blocks that are entirely skipped
> - # of rows that are filtered from blocks that aren't entirely skipped
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
