[
https://issues.apache.org/jira/browse/STORM-3724?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Aaron Gresch resolved STORM-3724.
---------------------------------
Fix Version/s: 2.3.0
Resolution: Fixed
> Use blobstore dir modtime to avoid update lookups by HDFSBlobstore
> ------------------------------------------------------------------
>
> Key: STORM-3724
> URL: https://issues.apache.org/jira/browse/STORM-3724
> Project: Apache Storm
> Issue Type: Improvement
> Reporter: Aaron Gresch
> Assignee: Aaron Gresch
> Priority: Major
> Fix For: 2.3.0
>
> Time Spent: 4.5h
> Remaining Estimate: 0h
>
> We have multiple storm clusters with 100's of supervisors polling for blob
> updates. This causes high load on our Hadoop namenodes that are also used by
> multiple other clusters.
>
> An improvement would be for the AsyncLocalizer to check the remote blobstore
> last mod time once and then skip checking each individual blob if it was
> already checked for the same mod time.
>
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
