[openstack-dev] [nova] State of NUMA live migration

2018-10-03 Thread Artom Lifshitz
open+project:openstack/nova+branch:master+topic:bp/numa-aware-live-migration > [3] https://review.openstack.org/#/c/576602/ > [4] https://review.openstack.org/#/c/574871/6 -- -- Artom Lifshitz Software Engineer, OpenStack Compute DFG

[openstack-dev] State of NUMA live migration

2018-10-03 Thread Artom Lifshitz
Yes, this is still happening. Mea culpa for not carrying the ball and maintaining visibility. There's work in nova to actually get it working, and in intel-nfv-ci to lay down the groundwork for eventual CI. In nova, the spec has been re-proposed for Stein [1]. There are some differences from the

Re: [openstack-dev] [placement] The "intended purpose" of traits

2018-10-01 Thread Artom Lifshitz
https://anticdent.org/ > freenode: cdent tw: > @anticdent__ > OpenStack Development Mailing List (not for usage q

Re: [openstack-dev] [infra][nova] Running NFV tests in CI

2018-07-24 Thread Artom Lifshitz
On Tue, Jul 24, 2018 at 12:30 PM, Clark Boylan wrote: > On Tue, Jul 24, 2018, at 9:23 AM, Artom Lifshitz wrote: >> Hey all, >> >> tl;dr Humbly requesting a handful of nodes to run NFV tests in CI >> >> Intel has their NFV tests tempest plugin [1] and manages

[openstack-dev] [infra][nova] Running NFV tests in CI

2018-07-24 Thread Artom Lifshitz
Hey all, tl;dr Humbly requesting a handful of nodes to run NFV tests in CI Intel has their NFV tests tempest plugin [1] and manages a third party CI for Nova. Two of the cores on that project (Stephen Finucane and Sean Mooney) have now moved to Red Hat, but the point still stands that there's a

Re: [openstack-dev] [Nova][Cinder][Tempest] Help with tempest.api.compute.servers.test_device_tagging.TaggedAttachmentsTest.test_tagged_attachment needed

2018-07-19 Thread Artom Lifshitz
I've proposed [1] to add extra logging on the Nova side. Let's see if that helps us catch the root cause of this. [1] https://review.openstack.org/584032 On Thu, Jul 19, 2018 at 12:50 PM, Artom Lifshitz wrote: > Because we're waiting for the volume to become available before we > co

Re: [openstack-dev] [Nova][Cinder][Tempest] Help with tempest.api.compute.servers.test_device_tagging.TaggedAttachmentsTest.test_tagged_attachment needed

2018-07-19 Thread Artom Lifshitz
-19_10_06_09_273919 > > — > Slawek Kaplonski > Senior software engineer > Red Hat > > > __ > OpenStack Development Mailing List (not for usage questions) > Unsubscribe: openstack-dev-requ...@lists.openstack.org?subject:unsubscribe > http:

Re: [openstack-dev] [nova] NUMA-aware live migration: easy but incomplete vs complete but hard

2018-06-21 Thread Artom Lifshitz
> Side question... does either approach touch PCI device management during > live migration? Nope. I'd need to do some research to see what, if anything, is needed at the lower levels (kernel, libvirt) to enable this. > I ask because the only workloads I've ever seen that pin guest vCPU threads

Re: [openstack-dev] [nova] NUMA-aware live migration: easy but incomplete vs complete but hard

2018-06-21 Thread Artom Lifshitz
> > As I understand it, Artom is proposing to have a larger race window, > essentially > from when the scheduler selects a node until the resource audit runs on > that node. > Exactly. When writing the spec I thought we could just call the resource tracker to claim the resources when the

Re: [openstack-dev] [nova] NUMA-aware live migration: easy but incomplete vs complete but hard

2018-06-19 Thread Artom Lifshitz
> Adding > claims support later on wouldn't change any on-the-wire messaging, it would > just make things work more robustly. I'm not even sure about that. Assuming [1] has at least the right idea, it looks like it's an either-or kind of thing: either we use resource tracker claims and get the

Re: [openstack-dev] [nova] NUMA-aware live migration: easy but incomplete vs complete but hard

2018-06-18 Thread Artom Lifshitz
> For what it's worth, I think the previous patch languished for a number of > reasons other than the complexity of the code...the original author left, > the coding style was a bit odd, there was an attempt to make it work even if > the source was an earlier version, etc. I think a fresh

[openstack-dev] [nova] NUMA-aware live migration: easy but incomplete vs complete but hard

2018-06-18 Thread Artom Lifshitz
Hey all, For Rocky I'm trying to get live migration to work properly for instances that have a NUMA topology [1]. A question that came up on one of patches [2] is how to handle resources claims on the destination, or indeed whether to handle that at all. The previous attempt's approach [3]

Re: [openstack-dev] [nova][cinder] Update (swap) of multiattach volume should not be allowed

2018-06-06 Thread Artom Lifshitz
ttach volume to server 2 >> >> Combined with a patch to nova to disallow swap_volume on any >> multiattach volume, this would then be possible if inconvenient. >> >> Regardless of any other changes, though, I think it's urgent that we >> disable the ability to swap_volume a multiattach volume because we >> don't

Re: [openstack-dev] [tc][all] A culture change (nitpicking)

2018-05-29 Thread Artom Lifshitz
> On Tue, May 29, 2018 at 10:52:04AM -0400, Mohammed Naser wrote: > > :On Tue, May 29, 2018 at 10:43 AM, Artom Lifshitz wrote: > :> One idea would be that, once the meat of the patch > :> has passed multiple rounds of reviews and looks good, and what remains > :>

Re: [openstack-dev] [tc][all] A culture change (nitpicking)

2018-05-29 Thread Artom Lifshitz
> -Julia > - > [1]: https://review.openstack.org/570940 > > __ > OpenStack Development Mailing List (not for usage questions) > Unsubscribe: openstack-dev-requ...@lists.openstack.org?subject:unsubscribe > http://lists.openstack.org/cgi-bin/mailman/l

Re: [openstack-dev] [nova] Default scheduler filters survey

2018-04-29 Thread Artom Lifshitz
ecsFilter > ImagePropertiesFilter > ServerGroupAntiAffinityFilter > SameHostFilter > > Cheers, > Lingxian Kong > > > On Sat, Apr 28, 2018 at 3:04 AM Jim Rollenhagen <j...@jimrollenhagen.com> > wrote: >> >> On Wed, Apr 18, 2018 at 11:17 AM, Artom Lifshitz <alifs...@redhat.c

[openstack-dev] [nova] Default scheduler filters survey

2018-04-18 Thread Artom Lifshitz
Hi all, A CI issue [1] caused by tempest thinking some filters are enabled when they're really not, and a proposed patch [2] to add (Same|Different)HostFilter to the default filters as a workaround, has led to a discussion about what filters should be enabled by default in nova. The default

Re: [openstack-dev] [nova] EC2 cleanup ?

2018-03-26 Thread Artom Lifshitz
> That is easier said than done. There have been a couple of related attempts > in the past: > > https://review.openstack.org/#/c/266425/ > > https://review.openstack.org/#/c/282872/ > > I don't remember exactly where those fell down, but it's worth looking at > this first before trying to do this

Re: [openstack-dev] [nova] Device tagging: rebuild config drive upon instance reboot to refresh metadata on it

2017-02-27 Thread Artom Lifshitz
> - virtio-vsock - think of this as UNIX domain sockets between the host and >guest. This is to deal with the valid use case of people wanting to use >a network protocol, but not wanting an real NIC exposed to the guest/host >for security concerns. As such I think it'd be useful to

Re: [openstack-dev] [nova] Device tagging: rebuild config drive upon instance reboot to refresh metadata on it

2017-02-20 Thread Artom Lifshitz
> But before doing that though, I think it'd be worth understanding whether > metadata-over-vsock support would be acceptable to people who refuse > to deploy metadata-over-TCPIP today. I wrote a thing [1], let's see what happens. [1]

Re: [openstack-dev] [nova] Device tagging: rebuild config drive upon instance reboot to refresh metadata on it

2017-02-20 Thread Artom Lifshitz
>> But before doing that though, I think it'd be worth understanding whether >> metadata-over-vsock support would be acceptable to people who refuse >> to deploy metadata-over-TCPIP today. > > Sure, although I'm still concerned that it'll effectively make tagged > hotplug libvirt-only. Upon

Re: [openstack-dev] [nova] Device tagging: rebuild config drive upon instance reboot to refresh metadata on it

2017-02-20 Thread Artom Lifshitz
> But before doing that though, I think it'd be worth understanding whether > metadata-over-vsock support would be acceptable to people who refuse > to deploy metadata-over-TCPIP today. Sure, although I'm still concerned that it'll effectively make tagged hotplug libvirt-only.

Re: [openstack-dev] [nova] Device tagging: rebuild config drive upon instance reboot to refresh metadata on it

2017-02-20 Thread Artom Lifshitz
to be more deployable, both in terms of security, and IPv6 support? [1] https://review.openstack.org/#/c/333781/ On Mon, Feb 20, 2017 at 10:35 AM, Clint Byrum <cl...@fewbar.com> wrote: > Excerpts from Jay Pipes's message of 2017-02-20 10:00:06 -0500: >> On 02/17/2017 02:28 PM, Artom

Re: [openstack-dev] [nova] Device tagging: rebuild config drive upon instance reboot to refresh metadata on it

2017-02-20 Thread Artom Lifshitz
19, 2017 at 6:12 AM, Steve Gordon <sgor...@redhat.com> wrote: > - Original Message - > > From: "Artom Lifshitz" <alifs...@redhat.com> > > To: "OpenStack Development Mailing List (not for usage questions)" < > openstack-dev@lists.opensta

Re: [openstack-dev] [nova] Device tagging: rebuild config drive upon instance reboot to refresh metadata on it

2017-02-18 Thread Artom Lifshitz
m > > __ > OpenStack Development Mailing List (not for usage questions) > Unsubscribe: openstack-dev-requ...@lists.openstack.org?subject:unsubscribe > http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-dev

Re: [openstack-dev] [nova] Device tagging: rebuild config drive upon instance reboot to refresh metadata on it

2017-02-18 Thread Artom Lifshitz
In reply to Michael: > We have had this discussion several times in the past for other reasons. The > reality is that some people will never deploy the metadata API, so I feel > like we need a better solution than what we have now. Aha, that's definitely a good reason to continue making the

[openstack-dev] [nova] Device tagging: rebuild config drive upon instance reboot to refresh metadata on it

2017-02-17 Thread Artom Lifshitz
houghts into writing, and will be able to refer to them later on :) [1] https://review.openstack.org/#/q/status:open+topic:bp/virt-device-tagged-attach-detach [2] https://github.com/openstack/nova/blob/master/nova/virt/libvirt/driver.py#L2667-L267

Re: [openstack-dev] [nova] Device tag in the API breaks in the old microversion

2017-01-31 Thread Artom Lifshitz
7 8:32 PM, Artom Lifshitz wrote: >> >> Since the consensus is to fix this with a new microversion, I've >> submitted some patches: >> >> * https://review.openstack.org/#/c/426030/ >> A spec for the new microversion in case folks want one. > > > Mer

Re: [openstack-dev] [nova] Device tag in the API breaks in the old microversion

2017-01-26 Thread Artom Lifshitz
: openstack-dev-requ...@lists.openstack.org?subject:unsubscribe > http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-dev -- -- Artom Lifshitz __ OpenStack Development Mailing List (not for usage questions) Unsubs

Re: [openstack-dev] [nova] Device tag in the API breaks in the old microversion

2017-01-24 Thread Artom Lifshitz
> So the current API behavior is as below: > > 2.32: BDM tag and network device tag added. > 2.33 - 2.36: 'tag' in the BDM disappeared. The network device tag still > works. > 2.37: The network device tag disappeared also. Thanks for the summary. For the visual minded like me, I made some ASCII

Re: [openstack-dev] [nova][libvirt] Lets make libvirt's domain XML canonical

2016-09-27 Thread Artom Lifshitz
n issue > alone is enough of a reason todo this. > > Regards, > Daniel > -- > |: http://berrange.com -o-http://www.flickr.com/photos/dberrange/ :| > |: http://libvirt.org -o-

Re: [openstack-dev] [nova] Non-priority feature freeze and FFEs

2016-07-05 Thread Artom Lifshitz
> The Hyper-V implementation of the bp virt-device-role-tagging is mergeable > [1]. The patch is quite simple, it got some reviews, and the tempest test > test_device_tagging [2] passed. [3] > > [1] https://review.openstack.org/#/c/331889/ > [2] https://review.openstack.org/#/c/305120/ > [3]

[openstack-dev] [Nova] Virt device role tagging for other virt drivers

2016-06-15 Thread Artom Lifshitz
/327920/ -- Artom Lifshitz __ OpenStack Development Mailing List (not for usage questions) Unsubscribe: openstack-dev-requ...@lists.openstack.org?subject:unsubscribe http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack

[openstack-dev] [Nova] Virtual device role tagging

2015-07-14 Thread Artom Lifshitz
Hello, I'd like to get the conversation started around a spec that my colleague Dan Berrange has proposed to the backlog. The spec [1] solves the problem of passing information about virtual devices into an instance. For example, in an instance with multiple network interfaces, each connected

[openstack-dev] [Nova] Add config option for real deletes instead of soft-deletes

2015-04-21 Thread Artom Lifshitz
Hello, I'd like to gauge acceptance of introducing a feature that would give operators a config option to perform real database deletes instead of soft deletes. There's definitely a need for *something* that cleans up the database. There have been a few attempts at a DB purge engine