[
https://issues.apache.org/jira/browse/BEAM-5521?focusedWorklogId=155685&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-155685
]
ASF GitHub Bot logged work on BEAM-5521:
----------------------------------------
Author: ASF GitHub Bot
Created on: 18/Oct/18 03:28
Start Date: 18/Oct/18 03:28
Worklog Time Spent: 10m
Work Description: tweise commented on issue #6717: [BEAM-5521] Re-use
bundle processors across bundles.
URL: https://github.com/apache/beam/pull/6717#issuecomment-430863234
I see CPU reduction by 50% when running locally with parallelism 1. The
throughput increases are much more visible when combined with
https://github.com/apache/beam/pull/6723. Will take it to the cluster with both
changes, the gains will be visible more clearly when running with high
parallelism. @mwylde fyi
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
Issue Time Tracking
-------------------
Worklog Id: (was: 155685)
Time Spent: 0.5h (was: 20m)
> Cache execution trees in SDK worker
> -----------------------------------
>
> Key: BEAM-5521
> URL: https://issues.apache.org/jira/browse/BEAM-5521
> Project: Beam
> Issue Type: Improvement
> Components: sdk-py-harness
> Reporter: Robert Bradshaw
> Assignee: Robert Bradshaw
> Priority: Major
> Labels: portability-flink
> Time Spent: 0.5h
> Remaining Estimate: 0h
>
> Currently they are re-constructed from the protos for every bundle, which is
> expensive (especially for 1-element bundles in streaming flink).
> Care should be taken to ensure the objects can be re-usued.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
