[
https://issues.apache.org/jira/browse/SAMZA-548?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14311787#comment-14311787
]
Jay Kreps commented on SAMZA-548:
---------------------------------
Nice. A couple things:
1. It would be good to write this up when we have more realistic results (not
from your laptop). People definitely care about performance. For a more
realistic test you probably need more data. If you are running at 200k/sec then
1m records is just 5 seconds, right? But JVM perf can be kind of squirrelly for
the first 10-30 secs so it would be good to try with more.
2. It would be good to know if this is producer bound, consumer bound, or samza
bound.
3. If producer or consumer I can help.
4. For code optimization purposes your laptop is probably ideal since it is
just running over localhost it ends up stressing everything else more since it
has infinite bandwidth with no latency.
> Add performance test for container Kafka performance
> ----------------------------------------------------
>
> Key: SAMZA-548
> URL: https://issues.apache.org/jira/browse/SAMZA-548
> Project: Samza
> Issue Type: Bug
> Components: kafka, test
> Affects Versions: 0.9.0
> Reporter: Chris Riccomini
> Assignee: Chris Riccomini
> Fix For: 0.9.0
>
> Attachments: SAMZA-548-0.patch
>
>
> There was [some
> discussion|http://mail-archives.apache.org/mod_mbox/samza-dev/201502.mbox/%3CCANFmfeNfdGCRsj66-76prLy%3DreK7_q3bfKLNP5iKfX7G1X2sNg%40mail.gmail.com%3E]
> on the mailing list about Samza's read/write performance with Kafka. We
> don't currently have a performance test that measures a Samza container's
> read/write performance when using Kafka. We should write one.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
