2015-02-03 17:07:43 |
Chris Friesen |
bug |
|
|
added bug |
2015-02-04 16:23:23 |
Bart Wensley |
bug |
|
|
added subscriber Bart Wensley |
2015-02-12 20:13:54 |
Ian Jolliffe |
bug |
|
|
added subscriber Ian Jolliffe |
2015-02-13 20:10:25 |
melanie witt |
nova: importance |
Undecided |
Medium |
|
2015-02-13 20:10:25 |
melanie witt |
nova: status |
New |
Confirmed |
|
2015-02-17 17:33:37 |
Nikola Đipanov |
marked as duplicate |
|
1370390 |
|
2015-02-20 18:45:28 |
Chris Friesen |
removed duplicate marker |
1370390 |
|
|
2015-02-25 14:43:06 |
John Haller |
bug |
|
|
added subscriber John Haller |
2015-02-26 14:53:59 |
Chris Friesen |
nova: assignee |
|
Chris Friesen (cbf123) |
|
2015-03-02 13:20:54 |
Bart Wensley |
nova: assignee |
Chris Friesen (cbf123) |
Bart Wensley (bartwensley) |
|
2015-03-11 13:52:32 |
OpenStack Infra |
nova: status |
Confirmed |
In Progress |
|
2015-03-13 13:03:45 |
Abhijeet Malawade |
bug |
|
|
added subscriber Abhijeet Malawade |
2015-03-16 03:11:32 |
gustavo panizzo |
bug |
|
|
added subscriber gustavo panizzo |
2015-04-17 12:32:20 |
Markus Zoeller (markus_z) |
bug |
|
|
added subscriber Markus Zoeller |
2015-06-01 09:45:20 |
Pawel Koniszewski |
tags |
compute |
compute live-migrate |
|
2015-06-02 06:32:14 |
andrew xu |
bug |
|
|
added subscriber andrew xu |
2015-06-03 14:42:16 |
Pawel Koniszewski |
bug |
|
|
added subscriber Pawel Koniszewski |
2015-08-28 16:35:25 |
OpenStack Infra |
nova: assignee |
Bart Wensley (bartwensley) |
Nikola Đipanov (ndipanov) |
|
2015-09-15 08:18:16 |
John Garbutt |
tags |
compute live-migrate |
compute liberty-rc-potential live-migrate |
|
2015-09-21 09:21:28 |
John Garbutt |
nova: milestone |
|
liberty-rc1 |
|
2015-09-23 09:25:18 |
John Garbutt |
nova: milestone |
liberty-rc1 |
|
|
2015-09-23 15:36:07 |
Matt Riedemann |
tags |
compute liberty-rc-potential live-migrate |
compute live-migrate |
|
2015-11-06 17:06:39 |
Paul Murray |
tags |
compute live-migrate |
compute live-migration |
|
2016-05-12 16:02:24 |
OpenStack Infra |
tags |
compute live-migration |
compute in-stable-liberty live-migration |
|
2016-06-01 12:55:08 |
OpenStack Infra |
nova: assignee |
Nikola Đipanov (ndipanov) |
Sylvain Bauza (sylvain-bauza) |
|
2016-06-13 13:14:25 |
OpenStack Infra |
nova: assignee |
Sylvain Bauza (sylvain-bauza) |
sahid (sahid-ferdjaoui) |
|
2016-07-05 14:27:35 |
OpenStack Infra |
nova: assignee |
sahid (sahid-ferdjaoui) |
Sylvain Bauza (sylvain-bauza) |
|
2016-07-06 08:28:01 |
OpenStack Infra |
nova: assignee |
Sylvain Bauza (sylvain-bauza) |
sahid (sahid-ferdjaoui) |
|
2016-07-27 01:23:33 |
Chris Stone |
bug |
|
|
added subscriber Chris Stone |
2016-10-06 13:57:30 |
OpenStack Infra |
nova: assignee |
sahid (sahid-ferdjaoui) |
Stephen Finucane (stephenfinucane) |
|
2016-10-20 12:37:37 |
OpenStack Infra |
nova: assignee |
Stephen Finucane (stephenfinucane) |
Pawel Koniszewski (pawel-koniszewski) |
|
2016-11-01 02:10:12 |
Seamanhanshan |
bug |
|
|
added subscriber Seamanhanshan |
2016-11-01 21:05:27 |
Jesse Keating |
bug |
|
|
added subscriber Jesse Keating |
2016-11-02 14:07:55 |
OpenStack Infra |
nova: assignee |
Pawel Koniszewski (pawel-koniszewski) |
sahid (sahid-ferdjaoui) |
|
2016-11-07 11:15:36 |
OpenStack Infra |
nova: assignee |
sahid (sahid-ferdjaoui) |
Pawel Koniszewski (pawel-koniszewski) |
|
2016-12-09 16:43:15 |
Stephen Finucane |
summary |
migration/evacuation/rebuild/resize of instance with dedicated cpus needs to recalculate cpus on destination |
migration/evacuation/rebuild/resize of instance with NUMA topology needs to recalculate NUMA topology |
|
2017-02-09 15:56:26 |
OpenStack Infra |
nova: assignee |
Pawel Koniszewski (pawel-koniszewski) |
Andrey Volkov (avolkov) |
|
2017-07-11 11:30:40 |
Lukasz Sobota |
bug |
|
|
added subscriber Lukasz Sobota |
2017-07-17 07:29:19 |
Hua Zhang |
bug |
|
|
added subscriber Hua Zhang |
2017-07-18 09:06:40 |
Andrey Volkov |
nova: assignee |
Andrey Volkov (avolkov) |
|
|
2017-07-19 10:03:09 |
Dominique Poulain |
bug |
|
|
added subscriber Dominique Poulain |
2017-07-26 10:15:17 |
Emil Muratov |
bug |
|
|
added subscriber Emil Muratov |
2017-09-07 12:57:33 |
Gayathri Devi |
nova: assignee |
|
Gayathri Devi (gayathrik) |
|
2017-09-11 09:41:36 |
Gayathri Devi |
nova: assignee |
Gayathri Devi (gayathrik) |
|
|
2017-10-19 20:36:46 |
Erik Olof Gunnar Andersson |
bug |
|
|
added subscriber Erik Olof Gunnar Andersson |
2017-11-23 15:38:12 |
OpenStack Infra |
nova: assignee |
|
Stephen Finucane (stephenfinucane) |
|
2018-01-17 10:53:37 |
OpenStack Infra |
nova: assignee |
Stephen Finucane (stephenfinucane) |
sahid (sahid-ferdjaoui) |
|
2018-01-17 16:32:15 |
Ken Young |
bug |
|
|
added subscriber Ken Young |
2018-02-13 11:00:35 |
Sylvain Bauza |
summary |
migration/evacuation/rebuild/resize of instance with NUMA topology needs to recalculate NUMA topology |
migration/evacuation/rebuild/resize/shelve of instance with NUMA topology needs to recalculate NUMA topology |
|
2018-02-13 15:34:00 |
Chris Friesen |
summary |
migration/evacuation/rebuild/resize/shelve of instance with NUMA topology needs to recalculate NUMA topology |
migration/evacuation/rebuild/resize/unshelve of instance with NUMA topology needs to recalculate NUMA topology |
|
2018-03-20 15:17:14 |
Radoslaw Poplawski |
removed subscriber Radoslaw Poplawski |
|
|
|
2018-03-20 15:17:33 |
Radoslaw Poplawski |
bug |
|
|
added subscriber Radoslaw Poplawski |
2018-04-05 20:19:44 |
Matt Riedemann |
summary |
migration/evacuation/rebuild/resize/unshelve of instance with NUMA topology needs to recalculate NUMA topology |
migration/evacuation/resize/unshelve of instance with NUMA topology needs to recalculate NUMA topology |
|
2018-04-05 21:11:38 |
Chris Friesen |
description |
I'm running nova trunk, commit 752954a.
I configured a flavor with two vcpus and extra specs "hw:cpu_policy=dedicated" in order to enable vcpu pinning.
I booted up a number of instances such that there was one instance affined to host cpus 12 and 13 on compute-0, and another instance affined to cpus 12 and 13 on compute-2. (As reported by "virsh vcpupin" and "virsh dumpxml".)
I then triggered a live migration of one instance from compute-0 to compute-2. This resulted in both instances being affined to host cpus 12 and 13 on compute-2.
The "hw:cpu_policy=dedicated" extra spec is intended to provide dedicated host cpus for the instance. In order to provide this, on a live migration (or cold migration, or rebuild, or evacuation, or resize, etc.) nova needs to ensure that the instance is affined to host cpus that are not currently being used by other instances. |
I'm running nova trunk, commit 752954a.
I configured a flavor with two vcpus and extra specs "hw:cpu_policy=dedicated" in order to enable vcpu pinning.
I booted up a number of instances such that there was one instance affined to host cpus 12 and 13 on compute-0, and another instance affined to cpus 12 and 13 on compute-2. (As reported by "virsh vcpupin" and "virsh dumpxml".)
I then triggered a live migration of one instance from compute-0 to compute-2. This resulted in both instances being affined to host cpus 12 and 13 on compute-2.
The "hw:cpu_policy=dedicated" extra spec is intended to provide dedicated host cpus for the instance. In order to provide this, on a live migration (or cold migration, or evacuation, or resize, etc.) nova needs to ensure that the instance is affined to host cpus that are not currently being used by other instances. |
|
2018-04-05 23:04:58 |
Matt Riedemann |
nova: status |
In Progress |
Fix Released |
|
2018-04-05 23:05:03 |
Matt Riedemann |
nova: assignee |
sahid (sahid-ferdjaoui) |
Nikola Đipanov (ndipanov) |
|
2018-08-22 09:15:56 |
Hu Zhou |
bug |
|
|
added subscriber Hu Zhou |
2018-10-16 16:22:56 |
Stephen Finucane |
nova: assignee |
Nikola Đipanov (ndipanov) |
Artom Lifshitz (notartom) |
|
2018-10-16 16:23:01 |
Stephen Finucane |
nova: assignee |
Artom Lifshitz (notartom) |
|
|
2018-10-16 16:25:31 |
Stephen Finucane |
summary |
migration/evacuation/resize/unshelve of instance with NUMA topology needs to recalculate NUMA topology |
cold migration/evacuation/resize/unshelve of instance with NUMA topology needs to recalculate NUMA topology |
|
2018-10-16 16:26:04 |
Stephen Finucane |
summary |
cold migration/evacuation/resize/unshelve of instance with NUMA topology needs to recalculate NUMA topology |
Move operations need to recalculate NUMA topology |
|
2018-10-16 16:27:23 |
Stephen Finucane |
description |
I'm running nova trunk, commit 752954a.
I configured a flavor with two vcpus and extra specs "hw:cpu_policy=dedicated" in order to enable vcpu pinning.
I booted up a number of instances such that there was one instance affined to host cpus 12 and 13 on compute-0, and another instance affined to cpus 12 and 13 on compute-2. (As reported by "virsh vcpupin" and "virsh dumpxml".)
I then triggered a live migration of one instance from compute-0 to compute-2. This resulted in both instances being affined to host cpus 12 and 13 on compute-2.
The "hw:cpu_policy=dedicated" extra spec is intended to provide dedicated host cpus for the instance. In order to provide this, on a live migration (or cold migration, or evacuation, or resize, etc.) nova needs to ensure that the instance is affined to host cpus that are not currently being used by other instances. |
**Important:** This bug only covers cold migration, evacuation, resize and unshelve operation. Live migration is covered by bug 1289064.
I'm running nova trunk, commit 752954a.
I configured a flavor with two vcpus and extra specs "hw:cpu_policy=dedicated" in order to enable vcpu pinning.
I booted up a number of instances such that there was one instance affined to host cpus 12 and 13 on compute-0, and another instance affined to cpus 12 and 13 on compute-2. (As reported by "virsh vcpupin" and "virsh dumpxml".)
I then triggered a live migration of one instance from compute-0 to compute-2. This resulted in both instances being affined to host cpus 12 and 13 on compute-2.
The "hw:cpu_policy=dedicated" extra spec is intended to provide dedicated host cpus for the instance. In order to provide this, on a live migration (or cold migration, or evacuation, or resize, etc.) nova needs to ensure that the instance is affined to host cpus that are not currently being used by other instances. |
|