[
https://issues.apache.org/jira/browse/PHOENIX-5082?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16730416#comment-16730416
]
Lars Hofhansl edited comment on PHOENIX-5082 at 12/28/18 7:24 PM:
------------------------------------------------------------------
Thanks [~yonigo]! This is interesting and in fact the behavior I'd like.
Awesome!
I'll give it a try.
I guess other thing to check is that the shadow cell updates are parallelized
by Phoenix (just the initial upserts are).
(Note: Even when it is async, the work is still done by the region server,
right?)
Part of the perf issue is that we're updating column in the memstore, where all
the other data was also just written into the memstore, and that's pretty slow.
(But it doesn't explain all of it)
was (Author: lhofhansl):
Thanks [~yonigo]! This is interesting and in fact the behavior I'd like.
Awesome!
I'll give it a try.
I guess other thing to check is that the shadow cell updates are parallelized
by Phoenix (just the initial upserts are).
(Note: Even when it is async, the work is still done by the region server,
right?)
> Observations about the Phoenix-Omid integration
> -----------------------------------------------
>
> Key: PHOENIX-5082
> URL: https://issues.apache.org/jira/browse/PHOENIX-5082
> Project: Phoenix
> Issue Type: Task
> Reporter: Lars Hofhansl
> Assignee: Yonatan Gottesman
> Priority: Major
> Attachments: CommitTS-Sample.png, Omid-profile.png, Omid-sample.png
>
>
> Filing this issue to track my observations and perhaps some fixes.
> [~ohads]
> [~jamestaylor]
> [~yonigo]
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
