[
https://issues.apache.org/jira/browse/HADOOP-2960?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12576214#action_12576214
]
Runping Qi commented on HADOOP-2960:
------------------------------------
Uniq key counting can be done as a part of sort. YOu don't need extra computing
at all.
I don't think the overhead of calling combiner can be dismissed.
It does not make sense to call it most keys are unique, which is very common if
the number of reducers is large.
> A mapper should use some heuristics to decide whether to run the combiner
> during spills
> ---------------------------------------------------------------------------------------
>
> Key: HADOOP-2960
> URL: https://issues.apache.org/jira/browse/HADOOP-2960
> Project: Hadoop Core
> Issue Type: Bug
> Reporter: Runping Qi
>
> Right now, the combiner, if set, will be called for each spill, no mapper
> whether the combiner can actually reduce the values.
> The mapper should use some heuristics to decide whether to run the combiner
> during spills.
> One of such heuristics is to check the the ratio of the nymber of keys to
> the number of unique keys in the spill.
> The combiner will be called only if that ration exceeds certain threshold
> (say 2).
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
