spark-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Rafael RENAUDIN-AVINO (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (SPARK-26881) Scaling issue with Gramian computation for RowMatrix: too many results sent to driver
Date Thu, 14 Feb 2019 18:47:00 GMT

     [ https://issues.apache.org/jira/browse/SPARK-26881?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Rafael RENAUDIN-AVINO updated SPARK-26881:
------------------------------------------
    Description: 
This issue hit me when running PCA (the one from spark.ml) on large dataset (~1Billion rows,
~30k columns).

Computing Gramian of a big RowMatrix allows to reproduce the issue.

 

The problem arises in the treeAggregate phase of the gramian matrix computation: results sent
to driver are enormous.

A potential solution to this could be to replace the hard coded depth (2) of the tree aggregation
by a heuristic computed based on the number of partitions, driver max result size, and memory
size of the dense vectors that are being aggregated, cf below for more detail:

(nb_partitions)^(1/depth) * dense_vector_size <= driver_max_result_size

I have a potential fix ready (currently testing it at scale), but I'd like to hear the community
opinion about such a fix to know if it's worth investing my time into a clean pull request.

 

Note that I only faced this issue with spark 2.2 but I suspect it affects later versions
aswell. 

 

  was:
This issue hit me when running PCA on large dataset (~1Billion rows, ~30k columns).

Computing Gramian of a big RowMatrix allows to reproduce the issue. 

 

The problem arises in the treeAggregate phase of the gramian matrix computation: results sent
to driver are enormous.

A potential solution to this could be to replace the hard coded depth (2) of the tree aggregation
by a heuristic computed based on the number of partitions, driver max result size, and memory
size of the dense vectors that are being aggregated, cf below for more detail:

(nb_partitions)^(1/depth) * dense_vector_size <= driver_max_result_size

I have a potential fix ready (currently testing it at scale), but I'd like to hear the community
opinion about such a fix to know if it's worth investing my time into a clean pull request.

 

Note that I only faced this issue with spark 2.2 but I suspect it affects later versions
aswell. 

 


> Scaling issue with Gramian computation for RowMatrix: too many results sent to driver
> -------------------------------------------------------------------------------------
>
>                 Key: SPARK-26881
>                 URL: https://issues.apache.org/jira/browse/SPARK-26881
>             Project: Spark
>          Issue Type: Improvement
>          Components: MLlib
>    Affects Versions: 2.2.0
>            Reporter: Rafael RENAUDIN-AVINO
>            Priority: Minor
>
> This issue hit me when running PCA (the one from spark.ml) on large dataset (~1Billion
rows, ~30k columns).
> Computing Gramian of a big RowMatrix allows to reproduce the issue.
>  
> The problem arises in the treeAggregate phase of the gramian matrix computation: results
sent to driver are enormous.
> A potential solution to this could be to replace the hard coded depth (2) of the tree
aggregation by a heuristic computed based on the number of partitions, driver max result size,
and memory size of the dense vectors that are being aggregated, cf below for more detail:
> (nb_partitions)^(1/depth) * dense_vector_size <= driver_max_result_size
> I have a potential fix ready (currently testing it at scale), but I'd like to hear the
community opinion about such a fix to know if it's worth investing my time into a clean pull
request.
>  
> Note that I only faced this issue with spark 2.2 but I suspect it affects later versions
aswell. 
>  



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org


Mime
View raw message