| Message ID | 1562915435-8818-1-git-send-email-wanpengli@tencent.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | KVM: Boosting vCPUs that are delivering interrupts | expand |
On 12.07.19 09:10, Wanpeng Li wrote: > From: Wanpeng Li <wanpengli@tencent.com> > > Inspired by commit 9cac38dd5d (KVM/s390: Set preempted flag during vcpu wakeup > and interrupt delivery), except the lock holder, we want to also boost vCPUs > that are delivering interrupts. Actually most smp_call_function_many calls are > synchronous ipi calls, the ipi target vCPUs are also good yield candidates. > This patch sets preempted flag during wakeup and interrupt delivery time. > > Testing on 80 HT 2 socket Xeon Skylake server, with 80 vCPUs VM 80GB RAM: > ebizzy -M > > vanilla boosting improved > 1VM 23000 21232 -9% > 2VM 2800 8000 180% > 3VM 1800 3100 72% > > Testing on my Haswell desktop 8 HT, with 8 vCPUs VM 8GB RAM, two VMs, > one running ebizzy -M, the other running 'stress --cpu 2': > > w/ boosting + w/o pv sched yield(vanilla) > > vanilla boosting improved > 1570 4000 55% > > w/ boosting + w/ pv sched yield(vanilla) > > vanilla boosting improved > 1844 5157 79% > > w/o boosting, perf top in VM: > > 72.33% [kernel] [k] smp_call_function_many > 4.22% [kernel] [k] call_function_i > 3.71% [kernel] [k] async_page_fault > > w/ boosting, perf top in VM: > > 38.43% [kernel] [k] smp_call_function_many > 6.31% [kernel] [k] async_page_fault > 6.13% libc-2.23.so [.] __memcpy_avx_unaligned > 4.88% [kernel] [k] call_function_interrupt This certainly made sense for s390 so I guess that this also makes sense for others. Nnote we (s390) do not use kvm_vcpu_kick, so this should not cause any issue for s390. > > Cc: Paolo Bonzini <pbonzini@redhat.com> > Cc: Radim Krčmář <rkrcmar@redhat.com> > Cc: Christian Borntraeger <borntraeger@de.ibm.com> > Signed-off-by: Wanpeng Li <wanpengli@tencent.com> > --- > virt/kvm/kvm_main.c | 4 +++- > 1 file changed, 3 insertions(+), 1 deletion(-) > > diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c > index b4ab59d..2c46705 100644 > --- a/virt/kvm/kvm_main.c > +++ b/virt/kvm/kvm_main.c > @@ -2404,8 +2404,10 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) > int me; > int cpu = vcpu->cpu; > > - if (kvm_vcpu_wake_up(vcpu)) > + if (kvm_vcpu_wake_up(vcpu)) { > + vcpu->preempted = true; > return; > + } > > me = get_cpu(); > if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) >
Cc arm and powerpc people, On Mon, 15 Jul 2019 at 18:53, Christian Borntraeger <borntraeger@de.ibm.com> wrote: > > > > On 12.07.19 09:10, Wanpeng Li wrote: > > From: Wanpeng Li <wanpengli@tencent.com> > > > > Inspired by commit 9cac38dd5d (KVM/s390: Set preempted flag during vcpu wakeup > > and interrupt delivery), except the lock holder, we want to also boost vCPUs > > that are delivering interrupts. Actually most smp_call_function_many calls are > > synchronous ipi calls, the ipi target vCPUs are also good yield candidates. > > This patch sets preempted flag during wakeup and interrupt delivery time. > > > > Testing on 80 HT 2 socket Xeon Skylake server, with 80 vCPUs VM 80GB RAM: > > ebizzy -M > > > > vanilla boosting improved > > 1VM 23000 21232 -9% > > 2VM 2800 8000 180% > > 3VM 1800 3100 72% > > > > Testing on my Haswell desktop 8 HT, with 8 vCPUs VM 8GB RAM, two VMs, > > one running ebizzy -M, the other running 'stress --cpu 2': > > > > w/ boosting + w/o pv sched yield(vanilla) > > > > vanilla boosting improved > > 1570 4000 55% > > > > w/ boosting + w/ pv sched yield(vanilla) > > > > vanilla boosting improved > > 1844 5157 79% > > > > w/o boosting, perf top in VM: > > > > 72.33% [kernel] [k] smp_call_function_many > > 4.22% [kernel] [k] call_function_i > > 3.71% [kernel] [k] async_page_fault > > > > w/ boosting, perf top in VM: > > > > 38.43% [kernel] [k] smp_call_function_many > > 6.31% [kernel] [k] async_page_fault > > 6.13% libc-2.23.so [.] __memcpy_avx_unaligned > > 4.88% [kernel] [k] call_function_interrupt > This certainly made sense for s390 so I guess that this also makes sense > for others. > Nnote we (s390) do not use kvm_vcpu_kick, so this should not cause > any issue for s390. > > > > > > Cc: Paolo Bonzini <pbonzini@redhat.com> > > Cc: Radim Krčmář <rkrcmar@redhat.com> > > Cc: Christian Borntraeger <borntraeger@de.ibm.com> > > Signed-off-by: Wanpeng Li <wanpengli@tencent.com> > > --- > > virt/kvm/kvm_main.c | 4 +++- > > 1 file changed, 3 insertions(+), 1 deletion(-) > > > > diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c > > index b4ab59d..2c46705 100644 > > --- a/virt/kvm/kvm_main.c > > +++ b/virt/kvm/kvm_main.c > > @@ -2404,8 +2404,10 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) > > int me; > > int cpu = vcpu->cpu; > > > > - if (kvm_vcpu_wake_up(vcpu)) > > + if (kvm_vcpu_wake_up(vcpu)) { > > + vcpu->preempted = true; > > return; > > + } > > > > me = get_cpu(); > > if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) > > >
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index b4ab59d..2c46705 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2404,8 +2404,10 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) int me; int cpu = vcpu->cpu; - if (kvm_vcpu_wake_up(vcpu)) + if (kvm_vcpu_wake_up(vcpu)) { + vcpu->preempted = true; return; + } me = get_cpu(); if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))