You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@storm.apache.org by "Rick Kellogg (JIRA)" <ji...@apache.org> on 2015/10/05 03:23:27 UTC

[jira] [Updated] (STORM-892) Worker Metrics Collection Improvements

     [ https://issues.apache.org/jira/browse/STORM-892?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Rick Kellogg updated STORM-892:
-------------------------------
    Component/s: storm-core

> Worker Metrics Collection Improvements
> --------------------------------------
>
>                 Key: STORM-892
>                 URL: https://issues.apache.org/jira/browse/STORM-892
>             Project: Apache Storm
>          Issue Type: Improvement
>          Components: storm-core
>            Reporter: Robert Joseph Evans
>
> Heron has a dedicated metrics collection process per host/topology.  In our current setup metrics collection is not always consistent, especially on systems  and bolts that are overloaded.  We should explore if the benefits of collecting the metrics differently and decide if there is a better way to do it.  Especially after STORM-885, we could potentially use it as a starting point for this process and have it pre-aggregate the metrics/heartbeats that are sent to nimbus for scheduling purposes, while forwarding on other metrics to different systems for alerting and monitoring.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)