[
https://issues.apache.org/jira/browse/HBASE-10047?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13834013#comment-13834013
]
Lars Hofhansl commented on HBASE-10047:
---------------------------------------
I think the costly part is the instanceof. So if a coprocessor could make its
type and the methods it overloads (as you said) explicit that could save some
cycles.
However, coprocessors are not on the superhot code paths. The one mentioned
here being an exception as it could called a lot when we filter a lot of rows
at the server. So I am not sure it is actually worth it.
> postScannerFilterRow consumes a lot of CPU in tall table scans
> --------------------------------------------------------------
>
> Key: HBASE-10047
> URL: https://issues.apache.org/jira/browse/HBASE-10047
> Project: HBase
> Issue Type: Bug
> Reporter: Lars Hofhansl
> Attachments: postScannerFilterRow.png
>
>
> Continuing my profiling quest, I find that in scanning tall table (and
> filtering everything on the server) a quarter of the time is now spent in the
> postScannerFilterRow coprocessor hook.
--
This message was sent by Atlassian JIRA
(v6.1#6144)
