| Message ID | 1402995739-23756-1-git-send-email-mihai.caraman@freescale.com (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
On Tue, 2014-06-17 at 12:02 +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 taking into account the 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. See https://lists.ozlabs.org/pipermail/linuxppc-dev/2014-June/118547.html -Scott
> -----Original Message----- > From: Wood Scott-B07421 > Sent: Tuesday, June 17, 2014 6:36 PM > To: Caraman Mihai Claudiu-B02008 > Cc: kvm-ppc@vger.kernel.org; kvm@vger.kernel.org; linuxppc- > dev@lists.ozlabs.org > Subject: Re: [PATCH v2] KVM: PPC: e500mc: Enhance tlb invalidation > condition on vcpu schedule > > On Tue, 2014-06-17 at 12:02 +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 taking into account the 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. > > See > https://lists.ozlabs.org/pipermail/linuxppc-dev/2014-June/118547.html Thanks. The original code needs just a simple adjustment to benefit from this optimization, please review v3. - Mike
On Tue, 2014-06-17 at 14:04 -0500, Caraman Mihai Claudiu-B02008 wrote: > > -----Original Message----- > > From: Wood Scott-B07421 > > Sent: Tuesday, June 17, 2014 6:36 PM > > To: Caraman Mihai Claudiu-B02008 > > Cc: kvm-ppc@vger.kernel.org; kvm@vger.kernel.org; linuxppc- > > dev@lists.ozlabs.org > > Subject: Re: [PATCH v2] KVM: PPC: e500mc: Enhance tlb invalidation > > condition on vcpu schedule > > > > On Tue, 2014-06-17 at 12:02 +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 taking into account the 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. > > > > See > > https://lists.ozlabs.org/pipermail/linuxppc-dev/2014-June/118547.html > > Thanks. The original code needs just a simple adjustment to benefit from > this optimization, please review v3. Where is v3? Or is it forthcoming? -Scott
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 17e4562..d3b814b0 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -111,10 +111,12 @@ 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(int, last_lpid_on_cpu); static void kvmppc_core_vcpu_load_e500mc(struct kvm_vcpu *vcpu, int cpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); + bool update_last = false, inval_tlb = false; kvmppc_booke_vcpu_load(vcpu, cpu); @@ -140,12 +142,24 @@ static void kvmppc_core_vcpu_load_e500mc(struct kvm_vcpu *vcpu, int cpu) mtspr(SPRN_GDEAR, vcpu->arch.shared->dar); mtspr(SPRN_GESR, vcpu->arch.shared->esr); - if (vcpu->arch.oldpir != mfspr(SPRN_PIR) || - __get_cpu_var(last_vcpu_on_cpu) != vcpu) { - kvmppc_e500_tlbil_all(vcpu_e500); + if (vcpu->arch.oldpir != mfspr(SPRN_PIR)) { + /* stale tlb entries */ + inval_tlb = update_last = true; + } else if (__get_cpu_var(last_vcpu_on_cpu) != vcpu) { + update_last = true; + /* polluted tlb entries */ + inval_tlb = __get_cpu_var(last_lpid_on_cpu) == + vcpu->kvm->arch.lpid; + } + + if (update_last) { __get_cpu_var(last_vcpu_on_cpu) = vcpu; + __get_cpu_var(last_lpid_on_cpu) = vcpu->kvm->arch.lpid; } + if (inval_tlb) + kvmppc_e500_tlbil_all(vcpu_e500); + 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 taking into account the 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> --- v2: - improve patch name and description - add performance results arch/powerpc/kvm/e500mc.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-)