You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@aurora.apache.org by "Maxim Khutornenko (JIRA)" <ji...@apache.org> on 2014/04/25 17:10:21 UTC
[jira] [Reopened] (AURORA-290) Expose basic SLA job stats from
scheduler
[ https://issues.apache.org/jira/browse/AURORA-290?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Maxim Khutornenko reopened AURORA-290:
--------------------------------------
> Expose basic SLA job stats from scheduler
> -----------------------------------------
>
> Key: AURORA-290
> URL: https://issues.apache.org/jira/browse/AURORA-290
> Project: Aurora
> Issue Type: Epic
> Components: Scheduler
> Reporter: Maxim Khutornenko
> Assignee: Maxim Khutornenko
>
> Be able to collect and monitor Aurora job SLA (Service Level Agreements) metrics that define the contractual relationship between the Aurora/Mesos platform and hosted services. Specifically, collect the following stats:
> ARD (Aggregate Regrettable Downtime) stat:
> Per job
> Per cluster
> MTTA (Mean Time To Assigned) and MTTR (Mean Time To Running) stats:
> Per job
> Per cluster
> Per instance size (small, medium, large, x-large)
> By CPU
> By RAM
> By DISK
> Job uptime stats (see V1 for more) at 99, 95, 90 and 75 percentiles (to be refined)
--
This message was sent by Atlassian JIRA
(v6.2#6252)