ramkrishna.s.vasudevan updated HBASE-15536:
    Attachment: latesttrunk_defaultWAL_50threads_10cols.jfr

>From the profile it can be seen that the checkSumCalculation though done by 
>different thread now overall the profile shows same % of time. 
But what you can see additionally in the AsyncWAL case is those netty based 
internal thread map that clears and allocates the buffers. Those add to the 
thread contention report.
The jfr reports are quite big in size since I have taken them for a 3 min 

> Make AsyncFSWAL as our default WAL
> ----------------------------------
>                 Key: HBASE-15536
>                 URL: https://issues.apache.org/jira/browse/HBASE-15536
>             Project: HBase
>          Issue Type: Sub-task
>          Components: wal
>    Affects Versions: 2.0.0
>            Reporter: Duo Zhang
>            Assignee: Duo Zhang
>            Priority: Critical
>             Fix For: 2.0.0
>         Attachments: HBASE-15536-v1.patch, HBASE-15536-v2.patch, 
> HBASE-15536-v3.patch, HBASE-15536-v4.patch, HBASE-15536-v5.patch, 
> HBASE-15536.patch, latesttrunk_asyncWAL_50threads_10cols.jfr, 
> latesttrunk_defaultWAL_50threads_10cols.jfr
> As it should be predicated on passing basic cluster ITBLL

This message was sent by Atlassian JIRA

Reply via email to