You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by GitBox <gi...@apache.org> on 2019/05/02 06:13:57 UTC
[GitHub] [flink] HuangZhenQiu commented on issue #8306: [FLINK-12342] Add
fast-heartbeat-delay yarn config for jobs with large number of containers
HuangZhenQiu commented on issue #8306: [FLINK-12342] Add fast-heartbeat-delay yarn config for jobs with large number of containers
URL: https://github.com/apache/flink/pull/8306#issuecomment-488563188
@tillrohrmann @rmetzger
As using the config and set it to 3000 milliseconds, the job with 256 containers can be successfully launched with only 1000+ total requested containers. The number can be further reduced by using larger number, such as 5000 or even higher. So, for small jobs with 32 containers, user should just default value for sending out request as soon as possible. For large jobs, user need to tune the parameter to trade-off the fast request and negative impact of repetitively as more containers.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services