You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@kafka.apache.org by "Ashish K Singh (JIRA)" <ji...@apache.org> on 2015/03/02 06:22:04 UTC

[jira] [Commented] (KAFKA-1994) Evaluate performance effect of chroot check on Topic creation

    [ https://issues.apache.org/jira/browse/KAFKA-1994?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14342769#comment-14342769 ] 

Ashish K Singh commented on KAFKA-1994:
---------------------------------------

Ran quick test of creating a topic with 1000 partitions with and without KAFKA-1664's patch. Results are averaged over 100 iterations.

W/o patch (100 iterations):
real	2m4.689s
user	1m45.213s
sys	0m6.893s

user + sys = 1121.06 ms for each topic creation

W patch (100 iterations):
real	2m4.327s
user	1m45.497s
sys	0m7.004s
user + sys = 1125.01 ms for each topic creation

Effect due to the patch is ~0.35%. Below is the simple test I ran. Let me know if you have a better test in mind.

{code}
time for i in `seq 1 100`; do bin/kafka-topics.sh --zookeeper localhost:2181 --create --topic topic$i --partitions 2000 --replication-factor 1; done
{code}

> Evaluate performance effect of chroot check on Topic creation
> -------------------------------------------------------------
>
>                 Key: KAFKA-1994
>                 URL: https://issues.apache.org/jira/browse/KAFKA-1994
>             Project: Kafka
>          Issue Type: Improvement
>            Reporter: Ashish K Singh
>            Assignee: Ashish K Singh
>
> KAFKA-1664 adds check for chroot while creating a node in ZK. ZkPath checks if namespace exists before trying to create a path in ZK. This raises a concern that checking namespace for each path creation might be unnecessary and can potentially make creations expensive.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)