[
https://issues.apache.org/jira/browse/FLINK-4175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15388545#comment-15388545
]
Felix Neutatz commented on FLINK-4175:
--------------------------------------
I started a design document here:
https://docs.google.com/document/d/1odYIvmQt4feonQF9q-btBnGvrzzN3lX0Os6rzHcCOjA/edit?usp=sharing
I highly appreciate any idea or comment and I am looking forward to the
discussion
> Broadcast data sent increases with # slots per TM
> -------------------------------------------------
>
> Key: FLINK-4175
> URL: https://issues.apache.org/jira/browse/FLINK-4175
> Project: Flink
> Issue Type: Improvement
> Components: Core, TaskManager
> Affects Versions: 1.0.3
> Reporter: Felix Neutatz
> Assignee: Felix Neutatz
> Labels: performance
>
> Problem:
> we experience some unexpected increase of data sent over the network for
> broadcasts with increasing number of slots per Taskmanager.
> We provided a benchmark [1]. It not only increases the size of data sent over
> the network but also hurts performance as seen in the preliminary results
> below. In this results cloud-11 has 25 nodes and ibm-power has 8 nodes with
> scaling the number of slots per node from 1 - 16.
> +-----------------------+--------------+-------------+
> | suite | name | median_time |
> +=======================+==============+=============+
> | broadcast.cloud-11 | broadcast.01 | 8796 |
> | broadcast.cloud-11 | broadcast.02 | 14802 |
> | broadcast.cloud-11 | broadcast.04 | 30173 |
> | broadcast.cloud-11 | broadcast.08 | 56936 |
> | broadcast.cloud-11 | broadcast.16 | 117507 |
> | broadcast.ibm-power-1 | broadcast.01 | 6807 |
> | broadcast.ibm-power-1 | broadcast.02 | 8443 |
> | broadcast.ibm-power-1 | broadcast.04 | 11823 |
> | broadcast.ibm-power-1 | broadcast.08 | 21655 |
> | broadcast.ibm-power-1 | broadcast.16 | 37426 |
> +-----------------------+--------------+-------------+
> After looking into the code base it, it seems that the data is de-serialized
> only once per TM, but the actual data is sent for all slots running the
> operator with broadcast vars and just gets discarded in case its already
> de-serialized.
> We do not see a reason the data can't be shared among the slots of a TM and
> therefore just sent once.
> [1] https://github.com/TU-Berlin-DIMA/flink-broadcast
> This Jira will continue the discussion started here:
> https://mail-archives.apache.org/mod_mbox/flink-dev/201606.mbox/%3c1465386300767.94...@tu-berlin.de%3E
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
