similar to: Live Migration and how exactly it works

On 03/20/2014 10:05 AM, Faizul Bari wrote: > ​Hello, > > I have been trying to track different phases of a live migration process. I > am using libvirt ​with qemu-kvm. I am issuing migration commands using > virsh. > > Now, I want to measure the time spent in each phase of live migration, > e.g., pre-copy and stop-copy. I stumbled upon the file qemu_driver.c. It > has

Thanks Eric. So, I need to look at QEMU. Do you know which files/functions should I look at? ​-- Faiz​ On Thu, Mar 20, 2014 at 12:41 PM, Eric Blake <eblake@redhat.com> wrote: > On 03/20/2014 10:05 AM, Faizul Bari wrote: > > ​Hello, > > > > I have been trying to track different phases of a live migration > process. I > > am using libvirt ​with qemu-kvm. I am

​Hello, I have been trying to track different phases of a live migration process. I am using libvirt ​with qemu-kvm. I am issuing migration commands using virsh. Now, I want to measure the time spent in each phase of live migration, e.g., pre-copy and stop-copy. I stumbled upon the file qemu_driver.c. It has functions like qemudDomainMigratePrepare2 qemudDomainMigratePerform

Yeah, I was just puzzled :D No worries. Cheers, Sebastian 2014-12-16 11:09 GMT+01:00 Daniel Sanders <Daniel.Sanders at imgtec.com>: > It looks like I missed that email completely, I started out replying to > Nikola and Hans which is why I was talking about Windows rather than OS X. > > > > I've just found your first email in my llvmdev folder and I think I see what

It looks like I missed that email completely, I started out replying to Nikola and Hans which is why I was talking about Windows rather than OS X. I've just found your first email in my llvmdev folder and I think I see what happened. My mail rules deliver llvmdev messages to a folder named llvmdev unless I'm directly addressed in which case it delivers to my inbox. It looks like you

Hi, I''m running a two node xen-Cluster with CentOS 5.3. I''m using gfs2 for the cluster filesystem and kernel 2.6.18-128.1.6.el5xen #1 SMP for Dom0 (xen 3.0.3). Live migration works fine as long as the DomU guest is running CentOS 5.3 or SLC 4.7 with kernel version 2.6.9-55.EL.cern. But if the SLC 4.7 guest is running the current 2.6.9-78.0.17.EL.cern kernel, the migration

> On Mon, Mar 14, 2016 at 05:03:34PM +0000, Dr. David Alan Gilbert wrote: > > * Li, Liang Z (liang.z.li at intel.com) wrote: > > > > > > > > Hi, > > > > I'm just catching back up on this thread; so without reference > > > > to any particular previous mail in the thread. > > > > > > > > 1) How many of the free

> On Thu, Mar 03, 2016 at 05:46:15PM +0000, Dr. David Alan Gilbert wrote: > > * Liang Li (liang.z.li at intel.com) wrote: > > > The current QEMU live migration implementation mark the all the > > > guest's RAM pages as dirtied in the ram bulk stage, all these pages > > > will be processed and that takes quit a lot of CPU cycles. > > > > > >

> > > * Liang Li (liang.z.li at intel.com) wrote: > > > > The current QEMU live migration implementation mark the all the > > > > guest's RAM pages as dirtied in the ram bulk stage, all these > > > > pages will be processed and that takes quit a lot of CPU cycles. > > > > > > > > From guest's point of view, it doesn't

On (Thu) 03 Mar 2016 [18:44:24], Liang Li wrote: > The current QEMU live migration implementation mark the all the > guest's RAM pages as dirtied in the ram bulk stage, all these pages > will be processed and that takes quit a lot of CPU cycles. > > From guest's point of view, it doesn't care about the content in free > pages. We can make use of this fact and skip

On Thu, Mar 03, 2016 at 06:44:24PM +0800, Liang Li wrote: > The current QEMU live migration implementation mark the all the > guest's RAM pages as dirtied in the ram bulk stage, all these pages > will be processed and that takes quit a lot of CPU cycles. > > From guest's point of view, it doesn't care about the content in free > pages. We can make use of this fact

* Li, Liang Z (liang.z.li at intel.com) wrote: > > On Mon, Mar 14, 2016 at 05:03:34PM +0000, Dr. David Alan Gilbert wrote: > > > * Li, Liang Z (liang.z.li at intel.com) wrote: > > > > > > > > > > Hi, > > > > > I'm just catching back up on this thread; so without reference > > > > > to any particular previous mail in

* Li, Liang Z (liang.z.li at intel.com) wrote: > > On Mon, Mar 14, 2016 at 05:03:34PM +0000, Dr. David Alan Gilbert wrote: > > > * Li, Liang Z (liang.z.li at intel.com) wrote: > > > > > > > > > > Hi, > > > > > I'm just catching back up on this thread; so without reference > > > > > to any particular previous mail in

* Roman Kagan (rkagan at virtuozzo.com) wrote: > On Fri, Mar 04, 2016 at 08:23:09AM +0000, Li, Liang Z wrote: > > > On Thu, Mar 03, 2016 at 05:46:15PM +0000, Dr. David Alan Gilbert wrote: > > > > * Liang Li (liang.z.li at intel.com) wrote: > > > > > The current QEMU live migration implementation mark the all the > > > > > guest's RAM pages

* Liang Li (liang.z.li at intel.com) wrote: > The current QEMU live migration implementation mark the all the > guest's RAM pages as dirtied in the ram bulk stage, all these pages > will be processed and that takes quit a lot of CPU cycles. > > From guest's point of view, it doesn't care about the content in free > pages. We can make use of this fact and skip

* Li, Liang Z (liang.z.li at intel.com) wrote: > > > > Hi, > > I'm just catching back up on this thread; so without reference to any > > particular previous mail in the thread. > > > > 1) How many of the free pages do we tell the host about? > > Your main change is telling the host about all the > > free pages. > > Yes, all

Hi Qin, On Mon, Aug 26, 2013 at 10:32 PM, Qin Chuanyu <qinchuanyu@huawei.com> wrote: > Hi all > > I am participating in a project which try to port vhost_net on Xen。 Neat! > By change the memory copy and notify mechanism ，currently virtio-net with > vhost_net could run on Xen with good performance。 I think the key in doing this would be to implement a property ioeventfd

On 08/31/2013 12:45 PM, Qin Chuanyu wrote: > On 2013/8/30 0:08, Anthony Liguori wrote: >> Hi Qin, > >>> By change the memory copy and notify mechanism ，currently >>> virtio-net with >>> vhost_net could run on Xen with good performance。 >> >> I think the key in doing this would be to implement a property >> ioeventfd and irqfd interface in

> > > > * Liang Li (liang.z.li at intel.com) wrote: > > > The current QEMU live migration implementation mark the all the > > > guest's RAM pages as dirtied in the ram bulk stage, all these pages > > > will be processed and that takes quit a lot of CPU cycles. > > > > > > From guest's point of view, it doesn't care about the

> > > > * Liang Li (liang.z.li at intel.com) wrote: > > > The current QEMU live migration implementation mark the all the > > > guest's RAM pages as dirtied in the ram bulk stage, all these pages > > > will be processed and that takes quit a lot of CPU cycles. > > > > > > From guest's point of view, it doesn't care about the