On 10/12/2012 04:16 PM, Martin Kletzander wrote: > On 10/12/2012 11:50 AM, Osier Yang wrote: >> If the vcpu placement is "static", it's just fine to ignore the >> def->cpumask if emulatorpin is specified. See more details in >> PATCH 1/7. >> --- >> src/qemu/qemu_process.c | 3 ++- >> 1 files changed, 2 insertions(+), 1 deletions(-) >> >> diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c >> index f8a2bfd..63a51c4 100644 >> --- a/src/qemu/qemu_process.c >> +++ b/src/qemu/qemu_process.c >> @@ -2618,7 +2618,8 @@ static int qemuProcessHook(void *data) >> >> /* This must be done after cgroup placement to avoid resetting CPU >> * affinity */ >> - if (qemuProcessInitCpuAffinity(h->driver, h->vm, h->nodemask) < 0) >> + if (!def->cputune.emulatorpin && >> + qemuProcessInitCpuAffinity(h->driver, h->vm, h->nodemask) < 0) >> goto cleanup; >> >> if (qemuProcessInitNumaMemoryPolicy(h->vm, h->nodemask) < 0) >> > > I think it is more readable in qemuProcessInitCpuAffinity, makes more > sense to me, what do you think? > But anyway, no problem here, so ACK, because we are sure that if there is emulatorpin specified, then there is no placement='auto' as well as no need for checking cpumask (handled with cgroups already. Martin -- libvir-list mailing list libvir-list@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/libvir-list