[GitHub] [incubator-yunikorn-core] TaoYang526 commented on issue #102: [YUNIKORN-34] Add document to explain benchmark result.

[GitBox <gi...@apache.org>]

TaoYang526 commented on issue #102: [YUNIKORN-34] Add document to explain benchmark result.
URL: https://github.com/apache/incubator-yunikorn-core/pull/102#issuecomment-599322572
 
 
   Thanks @yangwwei for this effort.
   This doc is very clear and easy to understand, just a small place need to be updated in the Scheduler Throughput section: "launching 50,000 pods with heterogeneous resource requests", 
    the prerequisite of this test is that all requests can be satisfied so that heterogeneous resource requests seem unnecessary,  even without heterogeneous requests, there may be different cases for this test, such as one app, many apps in a queue, many apps among several queues, and we just tested the simplest case that only have one app with 50,000 requests, and the results in other scenarios may be different but should be not much (since the most time-consuming phase is node sorting). So I think we can just leave "launching 50,000 pods" without detailed description, thoughts?

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscribe@yunikorn.apache.org
For additional commands, e-mail: dev-help@yunikorn.apache.org