[Openstack-operators] Workload Management (post-instantiation)

Kris G. Lindgren klindgren at godaddy.com
Wed Mar 2 23:38:34 UTC 2016


We would love to have something like that as well.

However, to do it in openstack would mean that something would have to gather/monitor the health of the HV's and not only disable new provisions but kick off/monitor the migrations off the host and onto the new chosen destinations .  Also, due to the fact that some migration may never complete (dirtying pages faster than you can copy them) it would have to have some smarts to select the vm's that have the higher chance of being migrated.

___________________________________________________________________
Kris Lindgren
Senior Linux Systems Engineer
GoDaddy

From: Edgar Magana <edgar.magana at workday.com<mailto:edgar.magana at workday.com>>
Date: Wednesday, March 2, 2016 at 4:31 PM
To: Adam Lawson <alawson at aqorn.com<mailto:alawson at aqorn.com>>, "openstack-operators at lists.openstack.org<mailto:openstack-operators at lists.openstack.org>" <openstack-operators at lists.openstack.org<mailto:openstack-operators at lists.openstack.org>>
Subject: Re: [Openstack-operators] Workload Management (post-instantiation)

We have done it with nagios checks and customize ruby code.

Edgar

From: Adam Lawson <alawson at aqorn.com<mailto:alawson at aqorn.com>>
Date: Wednesday, March 2, 2016 at 1:48 PM
To: "openstack-operators at lists.openstack.org<mailto:openstack-operators at lists.openstack.org>" <openstack-operators at lists.openstack.org<mailto:openstack-operators at lists.openstack.org>>
Subject: [Openstack-operators] Workload Management (post-instantiation)

Hello fellow Ops-minded stackers!

I understand OpenStack uses scheduler logic to place a VM on a host to ensure the load is balanced across hosts. My 64 million dollar question is: Has anyone identified a way to monitor capacity across all hosts on an ongoing basis and automatically live migrate VM's as needed to ensure hosts resource consumption is balanced over time?

It seems the scheduler addresses capacity at the time of instantiation but there's nothing that addresses optimal usage AFTER the VM is initially placed.

Thoughts/experiences?

//adam

Adam Lawson

AQORN, Inc.
427 North Tatnall Street
Ste. 58461
Wilmington, Delaware 19801-2230
Toll-free: (844) 4-AQORN-NOW ext. 101
International: +1 302-387-4660
Direct: +1 916-246-2072
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openstack.org/pipermail/openstack-operators/attachments/20160302/8f6bbb89/attachment.html>


More information about the OpenStack-operators mailing list