You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@arrow.apache.org by "Philipp Moritz (JIRA)" <ji...@apache.org> on 2019/07/26 03:04:00 UTC
[jira] [Resolved] (ARROW-5955) [Plasma] Support setting memory
quotas per plasma client for better isolation
[ https://issues.apache.org/jira/browse/ARROW-5955?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Philipp Moritz resolved ARROW-5955.
-----------------------------------
Resolution: Fixed
Fix Version/s: 1.0.0
Issue resolved by pull request 4885
[https://github.com/apache/arrow/pull/4885]
> [Plasma] Support setting memory quotas per plasma client for better isolation
> -----------------------------------------------------------------------------
>
> Key: ARROW-5955
> URL: https://issues.apache.org/jira/browse/ARROW-5955
> Project: Apache Arrow
> Issue Type: Improvement
> Reporter: Eric Liang
> Priority: Major
> Labels: pull-request-available
> Fix For: 1.0.0
>
> Time Spent: 2h 20m
> Remaining Estimate: 0h
>
> Currently, plasma evicts objects according a global LRU queue. In Ray, this often causes memory-intensive workloads to fail unpredictably, since a client that creates objects at a high rate can evict objects created by clients at lower rates. This is despite the fact that the true working set of both clients may be quite small.
> cc [~pcmoritz]
--
This message was sent by Atlassian JIRA
(v7.6.14#76016)