[jira] [Comment Edited] (MESOS-2197) Allow frameworks using Docker containerizer to prioritize resourceOffers with precached Docker images

["Timothy St. Clair (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/MESOS-2197?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14266217#comment-14266217 ] 

Timothy St. Clair edited comment on MESOS-2197 at 1/6/15 3:09 PM:
------------------------------------------------------------------

[~lcarstensen] You'll just need to be certain that whatever matching expression doesn't artificially leading to sub-optimal matches.  e.g. caching may not always lead to faster runs.  Especially in the case where throughput is the primary objective.  The startup time is finite, and offers don't have lifetimes likes claims so reuse could be infinite.  

Another way would be for a job/history server, which any framework could query.


was (Author: tstclair):
[~lcarstensen] You'll just need to be certain that whatever matching expression doesn't artificially leading to sub-optimal matches.  e.g. caching may not always lead to faster runs.  

Another way would be for a job/history server, which a framework could query.

> Allow frameworks using Docker containerizer to prioritize resourceOffers with precached Docker images
> -----------------------------------------------------------------------------------------------------
>
>                 Key: MESOS-2197
>                 URL: https://issues.apache.org/jira/browse/MESOS-2197
>             Project: Mesos
>          Issue Type: Improvement
>            Reporter: Lans Carstensen
>              Labels: mesosphere
>
> Docker container / task startup latency is significantly different on slaves that have already retrieved Docker images vs. those that haven't.  It would be desirable to give a framework the ability to sort/prioritize offers based on whether or not the Docker image is already present or not.
> Ideally this sort of signalling could also be leveraged to allow mesos slaves to pre-populate Docker images that frameworks are requesting.
> Keeping in mind that image tags are mutable.  Just because there is an "ubuntu:latest" image present on a slave doesn't mean that's the image that will be used (i.e. force_pull_image=true - https://reviews.apache.org/r/28190/ ).  This is especially true of continuous integration / deployment environments where "latest" could be changing frequently.  The framework may end up having to resolve an image tag to an image id first and use that for comparison with the slaves.



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