| Message ID | 1403075722-11151-1-git-send-email-mihai.caraman@freescale.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Wed, 2014-06-18 at 10:15 +0300, Mihai Caraman wrote: > On vcpu schedule, the condition checked for tlb pollution is too loose. > The tlb entries of a vcpu become polluted (vs stale) only when a different > vcpu within the same logical partition runs in-between. Optimize the tlb > invalidation condition keeping last_vcpu per logical partition id. > > With the new invalidation condition, a guest shows 4% performance improvement > on P5020DS while running a memory stress application with the cpu oversubscribed, > the other guest running a cpu intensive workload. > > Guest - old invalidation condition > real 3.89 > user 3.87 > sys 0.01 > > Guest - enhanced invalidation condition > real 3.75 > user 3.73 > sys 0.01 > > Host > real 3.70 > user 1.85 > sys 0.00 > > The memory stress application accesses 4KB pages backed by 75% of available > TLB0 entries: > > char foo[ENTRIES][4096] __attribute__ ((aligned (4096))); > > int main() > { > char bar; > int i, j; > > for (i = 0; i < ITERATIONS; i++) > for (j = 0; j < ENTRIES; j++) > bar = foo[j][0]; > > return 0; > } > > Signed-off-by: Mihai Caraman <mihai.caraman@freescale.com> > Cc: Scott Wood <scottwood@freescale.com> > --- > v4: > - rename last_vcpu_on_cpu to last_vcpu_of_lpid > - use "*[" syntax despite checkpatch error > > v3: > - use existing logic while keeping last_cpu per lpid > > arch/powerpc/kvm/e500mc.c | 6 +++--- > 1 file changed, 3 insertions(+), 3 deletions(-) > > diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c > index 17e4562..690499d 100644 > --- a/arch/powerpc/kvm/e500mc.c > +++ b/arch/powerpc/kvm/e500mc.c > @@ -110,7 +110,7 @@ void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr) > { > } > > -static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu_on_cpu); > +static DEFINE_PER_CPU(struct kvm_vcpu *[KVMPPC_NR_LPIDS], last_vcpu_of_lpid); > > static void kvmppc_core_vcpu_load_e500mc(struct kvm_vcpu *vcpu, int cpu) > { > @@ -141,9 +141,9 @@ static void kvmppc_core_vcpu_load_e500mc(struct kvm_vcpu *vcpu, int cpu) > mtspr(SPRN_GESR, vcpu->arch.shared->esr); > > if (vcpu->arch.oldpir != mfspr(SPRN_PIR) || > - __get_cpu_var(last_vcpu_on_cpu) != vcpu) { > + __get_cpu_var(last_vcpu_of_lpid)[vcpu->kvm->arch.lpid] != vcpu) { > kvmppc_e500_tlbil_all(vcpu_e500); > - __get_cpu_var(last_vcpu_on_cpu) = vcpu; > + __get_cpu_var(last_vcpu_of_lpid)[vcpu->kvm->arch.lpid] = vcpu; > } > > kvmppc_load_guest_fp(vcpu); Reviewed-by: Scott Wood <scottwood@freescale.com> -Scott -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On 18.06.14 09:15, Mihai Caraman wrote: > On vcpu schedule, the condition checked for tlb pollution is too loose. > The tlb entries of a vcpu become polluted (vs stale) only when a different > vcpu within the same logical partition runs in-between. Optimize the tlb > invalidation condition keeping last_vcpu per logical partition id. > > With the new invalidation condition, a guest shows 4% performance improvement > on P5020DS while running a memory stress application with the cpu oversubscribed, > the other guest running a cpu intensive workload. > > Guest - old invalidation condition > real 3.89 > user 3.87 > sys 0.01 > > Guest - enhanced invalidation condition > real 3.75 > user 3.73 > sys 0.01 > > Host > real 3.70 > user 1.85 > sys 0.00 > > The memory stress application accesses 4KB pages backed by 75% of available > TLB0 entries: > > char foo[ENTRIES][4096] __attribute__ ((aligned (4096))); > > int main() > { > char bar; > int i, j; > > for (i = 0; i < ITERATIONS; i++) > for (j = 0; j < ENTRIES; j++) > bar = foo[j][0]; > > return 0; > } > > Signed-off-by: Mihai Caraman <mihai.caraman@freescale.com> > Cc: Scott Wood <scottwood@freescale.com> Thanks, applied to kvm-ppc-queue. Alex -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 17e4562..690499d 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -110,7 +110,7 @@ void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr) { } -static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu_on_cpu); +static DEFINE_PER_CPU(struct kvm_vcpu *[KVMPPC_NR_LPIDS], last_vcpu_of_lpid); static void kvmppc_core_vcpu_load_e500mc(struct kvm_vcpu *vcpu, int cpu) { @@ -141,9 +141,9 @@ static void kvmppc_core_vcpu_load_e500mc(struct kvm_vcpu *vcpu, int cpu) mtspr(SPRN_GESR, vcpu->arch.shared->esr); if (vcpu->arch.oldpir != mfspr(SPRN_PIR) || - __get_cpu_var(last_vcpu_on_cpu) != vcpu) { + __get_cpu_var(last_vcpu_of_lpid)[vcpu->kvm->arch.lpid] != vcpu) { kvmppc_e500_tlbil_all(vcpu_e500); - __get_cpu_var(last_vcpu_on_cpu) = vcpu; + __get_cpu_var(last_vcpu_of_lpid)[vcpu->kvm->arch.lpid] = vcpu; } kvmppc_load_guest_fp(vcpu);
On vcpu schedule, the condition checked for tlb pollution is too loose. The tlb entries of a vcpu become polluted (vs stale) only when a different vcpu within the same logical partition runs in-between. Optimize the tlb invalidation condition keeping last_vcpu per logical partition id. With the new invalidation condition, a guest shows 4% performance improvement on P5020DS while running a memory stress application with the cpu oversubscribed, the other guest running a cpu intensive workload. Guest - old invalidation condition real 3.89 user 3.87 sys 0.01 Guest - enhanced invalidation condition real 3.75 user 3.73 sys 0.01 Host real 3.70 user 1.85 sys 0.00 The memory stress application accesses 4KB pages backed by 75% of available TLB0 entries: char foo[ENTRIES][4096] __attribute__ ((aligned (4096))); int main() { char bar; int i, j; for (i = 0; i < ITERATIONS; i++) for (j = 0; j < ENTRIES; j++) bar = foo[j][0]; return 0; } Signed-off-by: Mihai Caraman <mihai.caraman@freescale.com> Cc: Scott Wood <scottwood@freescale.com> --- v4: - rename last_vcpu_on_cpu to last_vcpu_of_lpid - use "*[" syntax despite checkpatch error v3: - use existing logic while keeping last_cpu per lpid arch/powerpc/kvm/e500mc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)