You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@uniffle.apache.org by GitBox <gi...@apache.org> on 2022/09/01 09:12:17 UTC

[GitHub] [incubator-uniffle] zuston commented on pull request #192: [ISSUE-186][Feature] Use I/O cost time to select storage paths

zuston commented on PR #192:
URL: https://github.com/apache/incubator-uniffle/pull/192#issuecomment-1233991602

   Thanks for your reply @smallzhongfeng 
   > At present, we want to support multiple clusters, but the pressure of each cluster is different. We want to select the cluster with the least pressure to write data, instead of writing data to each cluster evenly. In fact, our understanding of configuring multiple HDFS paths can play a certain role in disaster recovery.
   
   Got your thought. In our internal company, we have a router filesystem to support fault tolerance between namespaces. So there is no such requirement.
   
   > Moreover, for HDFS metrics, there seems to be no metric that can directly reflect the pressure of the cluster.
   
   Can we implement a HDFS checker to check the w/r time whether to exceed the threshold?
   


-- 
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.

To unsubscribe, e-mail: issues-unsubscribe@uniffle.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


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