You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by "Oleksandr Nitavskyi (JIRA)" <ji...@apache.org> on 2019/01/19 09:52:00 UTC
[jira] [Updated] (FLINK-11396) MetricStore creates significant GC
pressure
[ https://issues.apache.org/jira/browse/FLINK-11396?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Oleksandr Nitavskyi updated FLINK-11396:
----------------------------------------
Description:
On Flink version 1.6.x we observe a significant increase of the latency in UI.
After performance profiling, we have concluded that during UI rendering back-end spends 50% of the time on GC pauses, which means that Flink 1.6.x is not friendly with G1 GC ergonomics configurations.
On Flink side, MetricStore creates a huge amount of short living objects for our job, which provokes a lot of Young GC pauses for a non-small job, with around 50 operators and 120 parallelisms.
Samples of GC logs are in attach.
was:
On Flink version 1.6.x we observe a significant increase of the latency in UI.
After performance profiling, we have concluded that during UI rendering back-end spends 50% of the time on GC pauses, which means that Flink 1.6.x is not friendly with G1 GC ergonomics configurations.
On Flink side, MetricStore creates a huge amount of short living objects for our job, which provokes a lot of Young GC pauses for a non-small job, with around 50 operators and 120 parallelisms.
> MetricStore creates significant GC pressure
> -------------------------------------------
>
> Key: FLINK-11396
> URL: https://issues.apache.org/jira/browse/FLINK-11396
> Project: Flink
> Issue Type: Bug
> Reporter: Oleksandr Nitavskyi
> Priority: Major
>
> On Flink version 1.6.x we observe a significant increase of the latency in UI.
> After performance profiling, we have concluded that during UI rendering back-end spends 50% of the time on GC pauses, which means that Flink 1.6.x is not friendly with G1 GC ergonomics configurations.
> On Flink side, MetricStore creates a huge amount of short living objects for our job, which provokes a lot of Young GC pauses for a non-small job, with around 50 operators and 120 parallelisms.
> Samples of GC logs are in attach.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)