[
https://issues.apache.org/jira/browse/KUDU-1587?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15677427#comment-15677427
]
Todd Lipcon edited comment on KUDU-1587 at 11/18/16 7:53 PM:
-------------------------------------------------------------
Seeing this same issue apparently with Impala workloads. The apply time on one
server is creeping up into the 10s of seconds and eventually causes a timeout.
!graph.png!
was (Author: tlipcon):
Seeing this same issue apparently with Impala workloads. The apply time on one
server is creeping up into the 10s of seconds and eventually causes a timeout.
> Memory-based backpressure is insufficient on seek-bound workloads
> -----------------------------------------------------------------
>
> Key: KUDU-1587
> URL: https://issues.apache.org/jira/browse/KUDU-1587
> Project: Kudu
> Issue Type: Bug
> Components: tserver
> Affects Versions: 0.10.0
> Reporter: Todd Lipcon
> Priority: Critical
> Attachments: graph.png, queue-time.png
>
>
> I pushed a uniform random insert workload from a bunch of clients to the
> point that the vast majority of bloom filters no longer fit in buffer cache,
> and the compaction had fallen way behind. Thus, every inserted row turns into
> 40+ seeks (due to non-compact data) and takes 400-500ms. In this kind of
> workload, the current backpressure (based on memory usage) is insufficient to
> prevent ridiculously long queues.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
