[infinispan-issues] [JBoss JIRA] (ISPN-2750) Uneven request balancing via hotrod

[Dan Berindei (JIRA)]

     [ https://issues.jboss.org/browse/ISPN-2750?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Dan Berindei resolved ISPN-2750.
--------------------------------

    Resolution: Won't Fix


Looks like a configuration problem again: numSegments is only 40, and there are 32 nodes, which means the segments are not evenly divided between the cache members.

Here's an ASCII "graph" to that shows how many segments are owned by each node in a sample consistent hash ('=' means it's a primary owner, '+' means it's a backup owner):

{noformat}
+ +       +     + + +     +             +                       
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 
= + + = = = = + = + + + + = + + + + + + + + = + + + + + + + + + 
= = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = 
{noformat}

You can see from the graph that before the ISPN-2643 fix, when the HotRod client would contact a random owner, the load was balanced more evenly. After that fix however, the HotRod client only contacts the primary owner, and there is a clear difference in load between the nodes who primary-own 2 segments and the nodes who primary-own only 1 segment.
                
> Uneven request balancing via hotrod
> -----------------------------------
>
>                 Key: ISPN-2750
>                 URL: https://issues.jboss.org/browse/ISPN-2750
>             Project: Infinispan
>          Issue Type: Bug
>          Components: Server
>    Affects Versions: 5.2.0.CR2
>            Reporter: Michal Linhard
>            Assignee: Dan Berindei
>             Fix For: 5.2.0.Final
>
>
> The load sent to servers in the cluster isn't balanced
> tried in 32 node resilience tests:
> http://dev39.mw.lab.eng.bos.redhat.com/~mlinhard/hyperion3/run0035-resi-32-28-32-ER9/report/stats-throughput.png
> http://dev39.mw.lab.eng.bos.redhat.com/~mlinhard/hyperion3/run0036-resi-32-31-32-ER9/report/stats-throughput.png
> this differs from ISPN-2632 in that the load is unbalanced from the beginning of the test.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira