[
https://issues.apache.org/jira/browse/BOOKKEEPER-968?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15658844#comment-15658844
]
ASF GitHub Bot commented on BOOKKEEPER-968:
-------------------------------------------
Github user merlimat commented on the issue:
https://github.com/apache/bookkeeper/pull/77
@dlg99 Have you considered the approach of using a rate limiter (eg: guava
`RateLimiter`) with a configurable max number of MBytes/s to write when
flushing?
It might be a bit inconvenient to properly tune for one's system, but
setting the rate slightly below the disk write capacity should do the trick.
> Entry log flushes happen on log rotation and cause long spikes in IO
> utilization
> --------------------------------------------------------------------------------
>
> Key: BOOKKEEPER-968
> URL: https://issues.apache.org/jira/browse/BOOKKEEPER-968
> Project: Bookkeeper
> Issue Type: Improvement
> Components: bookkeeper-server
> Affects Versions: 4.5.0
> Reporter: Andrey Yegorov
> Assignee: Andrey Yegorov
> Priority: Minor
>
> Caught this issue on the servers with 128G of RAM. This is probably not an
> issue on servers/VMs with less RAM.
> With current implementation we end up with single entry log flush during log
> rotation.
> OS tries to flush everything as fast as possible and saturates disk. This
> results in long periods of high latency (reads and writes).
>
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
