[
https://issues.apache.org/jira/browse/JENA-703?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14221009#comment-14221009
]
Bala Kolla commented on JENA-703:
---------------------------------
This experiment is yielding very good results and it seems like the "committed
but not yet flushed transactions" could have significant impact on CPU. We will
take a look at our code to batch up the writes as much we could but we can't
eliminate the possibility of high volume of reads at the higher user load and
essentially blocking the writes forever. These pending transactions would add
additional load on CPU and hence make the queries to even take longer and hence
increase the likely hood of even more pending queries. This explains the
behavior we mentioned in Jena 801 and once the system reaches this stage of
100% CPU it never recovers until we stop the use load.
> TDB - Ensure readers don't block writeback forever.
> ---------------------------------------------------
>
> Key: JENA-703
> URL: https://issues.apache.org/jira/browse/JENA-703
> Project: Apache Jena
> Issue Type: Improvement
> Components: TDB
> Affects Versions: Jena 2.11.1
> Reporter: Andy Seaborne
>
> The commit queue can only be flushed when the main storage is quiet. A
> stream of readers can lead to the main storage never being quiet.
> One possibility is to place a maximum (quite high) on the number of readers
> allowed after the decision to flush the journal to main storage. If exceeded,
> then lock readers for a while, flush and resume.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
