[
https://issues.apache.org/jira/browse/BOOKKEEPER-336?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13412042#comment-13412042
]
Flavio Junqueira commented on BOOKKEEPER-336:
---------------------------------------------
bq. short timeout provided the mechanism to quick switch to try next bookie.
but it doesn't change read sequence, next read still started from same slow
bookie. same long latency needs for following read requests.
@sijie In general we have been taking an optimistic approach to reading. If
you're not happy with that approach, perhaps we should have a pessimistic
approach implemented in a different scheduler so that we can switch between the
two.
bq. The attached patch is based on the re-ordering mechanism and treated failed
bookies are unhealthy and kept last in the list.
@rakesh Could you post it on the review board, please, Rakesh? I haven't looked
at the patch yet, but I'm still wondering if we should have a separate
scheduler just so that we still have the option of using the approach we have
currently implemented.
> bookie readEntries is taking more time if the ensemble has failed bookie(s)
> ---------------------------------------------------------------------------
>
> Key: BOOKKEEPER-336
> URL: https://issues.apache.org/jira/browse/BOOKKEEPER-336
> Project: Bookkeeper
> Issue Type: Bug
> Affects Versions: 4.1.0
> Reporter: Brahma Reddy Battula
> Assignee: Rakesh R
> Attachments: BOOKKEEPER-336.patch
>
>
> Scenario:
> 1) Start three bookies. Create ledger with ensemblesize=3, quorumsize=2
> 2) Add 100 entries to this ledger
> 3) Make first bookie down and read the entries from 0-99
> Output: Each entry is going to fetch from the failed bookie and is waiting
> for the bookie connection timeout, only after failure going to next bookie.
> This is affecting the read entry performance.
> Impact: Namenode switching time will be affected by adding this failed bookie
> readTimeOut also.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
