[
https://issues.apache.org/jira/browse/SPARK-23529?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16427650#comment-16427650
]
Adit Madan commented on SPARK-23529:
------------------------------------
Hi [~foxish], I also have a use case for using hostpath volumes and would be
happy to contribute the implementation.
Summary: Enable short-circuit writes to distributed storage on k8s.
The Alluxio File System uses domain sockets to enable short-circuit writes from
the client to worker memory when co-located on the same host machine. A
directory, lets say /tmp/domain on the host, is mounted on the Alluxio worker
container as well as the Alluxio client ( = Spark executor) container. The
worker creates a domain socket /tmp/domain/d and if the client container mounts
the same directory, it can write directory to the Alluxio worker w/o passing
through network stack. The end result is faster data access when data is local.
Appreciate your thoughts on this!. I have an implementation ready exposing a
new property spark.kubernetes.executor.volumes taking the value of the form
hostPath:containerPath[:ro|rw].
> Specify hostpath volume and mount the volume in Spark driver and executor
> pods in Kubernetes
> --------------------------------------------------------------------------------------------
>
> Key: SPARK-23529
> URL: https://issues.apache.org/jira/browse/SPARK-23529
> Project: Spark
> Issue Type: Improvement
> Components: Kubernetes
> Affects Versions: 2.3.0
> Reporter: Suman Somasundar
> Assignee: Anirudh Ramanathan
> Priority: Minor
>
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
