[
https://issues.apache.org/jira/browse/KUDU-749?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16415717#comment-16415717
]
Paul Brannan commented on KUDU-749:
-----------------------------------
We have observed the same behavior for an update-heavy workload; according to
perf, the MaintenangeMgr thread is spending most of its time in these two
functions:
{noformat}
68.20% kudu-tserver [.] kudu::tablet::DeltaMemStore::CheckRowDeleted(u
17.42% kudu-tserver [.] kudu::GetMemcmpableVarint64(kudu::Slice*, unsi
{noformat}
> Improve performance for zipfian update
> --------------------------------------
>
> Key: KUDU-749
> URL: https://issues.apache.org/jira/browse/KUDU-749
> Project: Kudu
> Issue Type: Improvement
> Components: perf, tablet
> Affects Versions: Private Beta
> Reporter: Todd Lipcon
> Priority: Major
> Attachments: screenshot-1.png, screenshot-2.png
>
>
> A zipfian 50/50 update/read workload on YCSB gets slower and slower until
> it's pretty intolerable (random reads taking 100+ms of CPU). It seems like
> all the CPU is spent in DMSIterator::PrepareBatch. We're probably doing
> something dumb here - let's look for some low hanging fruit to fix this.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
