[
https://issues.apache.org/jira/browse/FLINK-1725?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14724019#comment-14724019
]
ASF GitHub Bot commented on FLINK-1725:
---------------------------------------
Github user anisnasir commented on the pull request:
https://github.com/apache/flink/pull/1069#issuecomment-136496310
@tillrohrmann Yes, we can design a system that adapts to the load imbalance
and increases the number of partitions per key in real time. However, this
comes with few other questions that are:
1. When to increases the choices?
2. How much to increase the choices?
3. Should we increase the choices for all the keys?
A simple solution for the datasets that cannot be handled using our
solution is to use ShufflePartitioner.
> New Partitioner for better load balancing for skewed data
> ---------------------------------------------------------
>
> Key: FLINK-1725
> URL: https://issues.apache.org/jira/browse/FLINK-1725
> Project: Flink
> Issue Type: Improvement
> Components: New Components
> Affects Versions: 0.8.1
> Reporter: Anis Nasir
> Assignee: Anis Nasir
> Labels: LoadBalancing, Partitioner
> Original Estimate: 336h
> Remaining Estimate: 336h
>
> Hi,
> We have recently studied the problem of load balancing in Storm [1].
> In particular, we focused on key distribution of the stream for skewed data.
> We developed a new stream partitioning scheme (which we call Partial Key
> Grouping). It achieves better load balancing than key grouping while being
> more scalable than shuffle grouping in terms of memory.
> In the paper we show a number of mining algorithms that are easy to implement
> with partial key grouping, and whose performance can benefit from it. We
> think that it might also be useful for a larger class of algorithms.
> Partial key grouping is very easy to implement: it requires just a few lines
> of code in Java when implemented as a custom grouping in Storm [2].
> For all these reasons, we believe it will be a nice addition to the standard
> Partitioners available in Flink. If the community thinks it's a good idea, we
> will be happy to offer support in the porting.
> References:
> [1].
> https://melmeric.files.wordpress.com/2014/11/the-power-of-both-choices-practical-load-balancing-for-distributed-stream-processing-engines.pdf
> [2]. https://github.com/gdfm/partial-key-grouping
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
