[infinispan-issues] [JBoss JIRA] (ISPN-4372) Map/Reduce performance is dependent on cache value size

[Alan Field (JIRA)]

    [ https://issues.jboss.org/browse/ISPN-4372?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12974657#comment-12974657 ] 

Alan Field commented on ISPN-4372:
----------------------------------

I was comparing the performance in Infinispan 6 and 7 which has much different performance characteristics when using the same input data and {{WordCountMapperEmitPerValue}} code. In Infinispan 6, the performance is unaffected by cache value size, and the throughput increases as more nodes are added. The throughput in Infinispan 7 is affected when the value size is changed. Whether this is due to the input cache value size or intermediate values is to be determined. I can rerun the tests using the {{WordCountMapper}}, but I suspect that it will fail in Infinispan 6 due to the number of intermediate values emitted by the mapper.

> Map/Reduce performance is dependent on cache value size
> -------------------------------------------------------
>
>                 Key: ISPN-4372
>                 URL: https://issues.jboss.org/browse/ISPN-4372
>             Project: Infinispan
>          Issue Type: Feature Request
>          Components: Distributed Execution and Map/Reduce
>    Affects Versions: 7.0.0.Alpha4
>            Reporter: Alan Field
>            Assignee: Vladimir Blagojevic
>              Labels: performance
>
> Performance testing the Map/Reduce changes has shown that the performance improvements vary based on the size of the values in the cache. [1] Using values from 8kB to 128kB shows a large performance increase over Infinispan 6, but smaller and larger values are the same or slower than Infinispan 6.
> http://blog.infinispan.org/2014/06/mapreduce-performance-improvements.html



--
This message was sent by Atlassian JIRA
(v6.2.3#6260)