[ 
https://issues.apache.org/jira/browse/MESOS-4392?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15106093#comment-15106093
 ] 

Guangya Liu commented on MESOS-4392:
------------------------------------

When we do the design for Optimistic offer phase 1 (MESOS-1607), we already 
considered this case, we can call this as {{Quota Slack}} which means the 
difference between the amount of {{quotaed resources}} and the amount of 
{{allocated resources}}. 

But before we proceed for this, I think that we need to consider how does the 
{{Quota Slack}} works if we introduced {{Quota Limit}}, at least need to 
clarify in the design document for this.

{quota}
With this solution, seems the Quota Limit does not make much sense: The admin 
can set a large Quota Guaranteed and lend out current role's resources to other 
roles.
{quota}

Personally, for an ideal design, if we have both {{Quota Guarantee}} and 
{{Quota Limit}}, we should document to tell end user guarantee less resources 
and make the resources between  {{Quota Guarantee}} and {{Quota Limit}} as 
revocable which is the {{Quota Slack}} in my thinking.

> Balance quota frameworks with non-quota, greedy frameworks.
> -----------------------------------------------------------
>
>                 Key: MESOS-4392
>                 URL: https://issues.apache.org/jira/browse/MESOS-4392
>             Project: Mesos
>          Issue Type: Epic
>          Components: allocation, master
>            Reporter: Bernd Mathiske
>            Assignee: Alexander Rukletsov
>              Labels: mesosphere
>
> Maximize resource utilization and minimize starvation risk for both quota 
> frameworks and non-quota, greedy frameworks when competing with each other.
> A greedy analytics batch system wants to use as much of the cluster as 
> possible to maximize computational throughput. When a competing web service 
> with fixed task size starts up, there must be sufficient resources to run it 
> immediately. The operator can reserve these resources by setting quota. 
> However, if these resources are kept idle until the service is in use, this 
> is wasteful from the analytics job's point of view. On the other hand, the 
> analytics job should hand back reserved resources to the service when needed 
> to avoid starvation of the latter.
> We can assume that often, the resources needed by the service will be of the 
> non-revocable variety. Here we need to introduce clearer distinctions between 
> oversubscribed and revocable resources that are not oversubscribed. An 
> oversubscribed resource cannot be converted into a non-revocable resource, 
> not even by preemption. In contrast, a non-oversubscribed, revocable resource 
> can be converted into a non-revocable resource.
> Another related topic is optimistic offers. The pertinent aspect in this 
> context is again whether resources are oversubscribed or not.



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

Reply via email to