search for: pcpus

...4 1,3,5,7 VM6 4 0,2,4,6 VM7 4 0,2,4,6 VM8 4 0,2,4,6 I do not set the CPU affinity in the configuration file, and I cannot find when the hypervisor set the CPU affinity in the source code. In this situation, 4 VCPUs of each VM are binding to 4 PCPUs permanently, and 5 VMs run on a set of PCPUs, and others run on the other set of PCPUs. It is unfair to these VMs. -- Like Zhou _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel

I''ve just pushed some changes to hg that seem to speed things up a bit for me. On one machine with 2 x dual core 2.4Ghz AMD cpu''s, testing with iperf from DomU to Dom0 I get: Windows (vcpus = 2) - ~500MBits/sec - ~66% cpu utilization (eg 100% on one, and 33% on the second cpu) Linux (vcpus = 1) - ~2200MBits/sec On another machine with 1 x dual core 1.8Ghz AMD cpu, testing as

On Mon, 2012-01-23 at 18:21 +0000, Dario Faggioli wrote: > Allow for "^<cpuid>" syntax while specifying the pCPUs list > during a vcpu-pin. This enables doing the following: > > xl vcpu-pin 1 1 0-4,^2 > > and achieving: > > xl vcpu-list > Name ID VCPU CPU State Time(s) CPU Affinity > ... > Squeeze_pv 1 1...

On Wed, 2012-01-25 at 14:35 +0000, Dario Faggioli wrote: > Allow for "^<cpuid>" syntax while specifying the pCPUs list > during a vcpu-pin. This enables doing the following: > > xl vcpu-pin 1 1 0-4,^2 > > and achieving: > > xl vcpu-list > Name ID VCPU CPU State Time(s) CPU Affinity > ... > Squeeze_pv 1 1...

Hi all, I am working with libvirt and I am trying to set cpu affinity. Now I can always use      virsh vcpupin <domain_name> <vcpu> <pcpu> to pin vcpus to pcpus. I want to do it using Python API. Now, there is function pinVcpu which is supposed to do that. But this is not working. For example I gave      dom.pinVcpu(0,1) but still my vcpu affinity is for all the pcpus. The function returns 0 (success). Any idea what am I doing wrong? Thanks.   ~Peeyush...

On Fri, Sep 18, 2020 at 10:44:03AM +0100, Richard W.M. Jones wrote: > So it didn't make any noticable difference in my test. I wonder if > the test guest I'm using (Fedora 32 using dracut) doesn't use parallel > compression? Do you do anything special to optimize storage ? If the thing using parallel CPUs in the guest is doing I/O you'd likely want to tune storage at

This helps mkinitrd which runs pigz (parallel gzip). Thanks Jean-Louis Dupond for suggesting this change. --- common | 2 +- v2v/v2v.ml | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/common b/common index c840f2e39..ea5278bba 160000 --- a/common +++ b/common @@ -1 +1 @@ -Subproject commit c840f2e39d0bb637a98b224c89f6df011e1d4414 +Subproject commit

On Friday, 18 September 2020 11:44:04 CEST Richard W.M. Jones wrote: > let g = open_guestfs ~identifier:"v2v" () in > g#set_memsize (g#get_memsize () * 14 / 5); > + (* Setting the number of vCPUs allows parallel mkinitrd. *) > + g#set_smp (Sysconf.nr_processors_online ()); IMHO this is not a good idea, for few reasons: a) it unconditionally uses all the available

On Fri, Sep 18, 2020 at 10:52:58AM +0100, Daniel P. Berrangé wrote: > On Fri, Sep 18, 2020 at 10:44:03AM +0100, Richard W.M. Jones wrote: > > So it didn't make any noticable difference in my test. I wonder if > > the test guest I'm using (Fedora 32 using dracut) doesn't use parallel > > compression? > > Do you do anything special to optimize storage ? If

So it didn't make any noticable difference in my test. I wonder if the test guest I'm using (Fedora 32 using dracut) doesn't use parallel compression? However I don't think it can cause a problem and it seems obvious that it could benefit some cases. Rich.

Hello, I observed that a configuration where dom0 vcpus were pinned to a set of pcpus in the host using dom0_vcpus_pin and the guests were prevented from running on the dom0 pcpus (here called "exclusively-pinned dom0 vcpus", or xpin) caused the general performance of the guests in a host with around 24 pcpus or more to increase during bootstorms and high density of gu...

Hi all, This is the second take of a patch that I submitted some time ago for allowing specifying vcpu pinning taking NUMA nodes into account. IOW, something like this: * "nodes:0-3": all pCPUs of nodes 0,1,2,3;  * "nodes:0-3,^node:2": all pCPUS of nodes 0,1,3;  * "1,nodes:1-2,^6": pCPU 1 plus all pCPUs of nodes 1,2    but not pCPU 6; v1 was a single patch, this is a small series. It become necessary to do that while coping with the review comments I got from IanJ. Wh...

...] On Fri, Jul 19, 2013 at 11:45 AM, Peeyush Gupta <gpeeyush@ymail.com> wrote: > Hi all, > > I am working with libvirt and I am trying to set cpu affinity. Now I can > always use > > virsh vcpupin <domain_name> <vcpu> <pcpu> > > to pin vcpus to pcpus. I want to do it using Python API. Now, there is > function pinVcpu which is supposed to do that. But this is not working. For > example I gave > > dom.pinVcpu(0,1) > > but still my vcpu affinity is for all the pcpus. The function returns 0 > (success). > Any idea what a...

...pu is never planning to execute a sysret back to a pv vcpu, the update is safe from a security point of view. * Swap the NMI trap handlers. The crashing pcpu gets the nop handler, to prevent it getting stuck in an NMI context, causing a hang instead of crash. The non-crashing pcpus all get the nmi_crash handler which is designed never to return. do_nmi_crash() will: * Save the crash notes and shut the pcpu down. There is now an extra per-cpu variable to prevent us from executing this multiple times. In the case where we reenter midway through, attempt the...

Hello, This small series deals with some weirdness in the mechanism with which the credit scheduler choses what PCPU to tickle upon a VCPU wake-up. Details are available in the changelog of the first patch. The new approach has been extensively benchmarked and proved itself either beneficial or harmless. That means it does not introduce any significant amount of overhead and/or performances

Hi All, I am new to Xen, and would like to know if anyone can help with a problem I have. I have a dual - Quad Core Intel 5535 VT 2.66 server, with 24G ram running CentOS5 dom0 and domU (both 64 bit). Everything works great and I am SUPER impressed with the efficiency of Xen (i have always been a UML man). I would however, like to run a single domU domain, with a single VCPU, but get the power

...ombination with the `low_crashinfo` command line option. ### crashkernel ### credit2\_balance\_over @@ -211,7 +262,8 @@ Specify the bit width of the DMA heap. ### dom0\_max\_vcpus > `= <integer>` -Specifiy the maximum number of vcpus to give to dom0. This defaults to the number of pcpus on the host. +Specifiy the maximum number of vcpus to give to dom0. This defaults +to the number of pcpus on the host. ### dom0\_mem (ia64) > `= <size>` @@ -260,7 +312,8 @@ Pin dom0 vcpus to their respective pcpus > Default: `guest_loglvl=none/warning` -Set the logging level f...

Hello, I have noticed that when I use xen-create-image to generate an domU, the whole server (dom0 and domU''s) basically hangs until it is finished. This happens primarily during the creation of the ext3 filesystem on an LVM partition. This creation of the file system can take up to 4 or 5 minutes. At which point, any other domU''s are basically paused... tcp connections time

An over-committed guest with more vCPUs than pCPUs has a heavy overload in osq_lock(). This is because vCPU A hold the osq lock and yield out, vCPU B wait per_cpu node->locked to be set. IOW, vCPU B wait vCPU A to run and unlock the osq lock. Kernel has an interface bool vcpu_is_preempted(int cpu) to see if a vCPU is currently running or not....

...t;/vcpu> ... </domain> I have seen that virsh vcpupin and virsh emulatorpin can be used to query and set the cpusets of the <vcpupin> and <emulatorpin> children elements of <cputune> which override the cpuset of <vcpu>. If i did not have to pin to different PCPUs, I would execute just one command for the whole domain rather than one command per VCPU + one per the emulator threads. Thanks! -------------------------------------------------- regards, Edoardo Comar WebSphere Application Service Platform for Networks (ASPN) ecomar@uk.ibm.com IBM UK Ltd, Hursl...