Hi Marcelo: Dramatic improvement. The following is an example with kvm-75 and this patch. Without cpu affinity from a kvm perspective (vcpu-to-pcpu):
cpu 0: 1221107886.020298 cpu 1: 1221107886.020290 * cpu 2: 1221107886.020555 cpu 3: 1221107886.020549 * cpu 0: 1221107887.030244 cpu 1: 1221107887.030236 * cpu 2: 1221107887.030498 cpu 3: 1221107887.030493 * cpu 0: 1221107888.040248 cpu 1: 1221107888.040262 cpu 2: 1221107888.040314 cpu 3: 1221107888.040470 cpu 0: 1221107889.050305 cpu 1: 1221107889.050300 * cpu 2: 1221107889.050354 cpu 3: 1221107889.050394 cpu 0: 1221107890.060384 cpu 1: 1221107890.060489 cpu 2: 1221107890.060753 cpu 3: 1221107890.060918 cpu 0: 1221107891.083559 cpu 1: 1221107891.083558 * cpu 2: 1221107891.083614 cpu 3: 1221107891.083613 * cpu 0: 1221107892.091705 cpu 1: 1221107892.091699 * cpu 2: 1221107892.092998 cpu 3: 1221107892.093011 Setting vcpu-pcpu affinity well after guest startup, tracking is a bit better (fewer time travels). I do not believe there's a way to set affinity as kvm/qemu threads are spawned (short of modifying qemu). As before, RHEL3 guest. DL380G5 host. david Marcelo Tosatti wrote: > VMX initializes the TSC offset for each vcpu at different times, and > also reinitializes it for vcpus other than 0 on APIC SIPI message. > > This bug causes the TSC's to appear unsynchronized in the guest, even if > the host is good. > > Older Linux kernels don't handle the situation very well, so > gettimeofday is likely to go backwards in time: > > http://www.mail-archive.com/kvm@vger.kernel.org/msg02955.html > http://sourceforge.net/tracker/index.php?func=detail&aid=2025534&group_id=180599&atid=893831 > > Fix it by initializating the offset of each vcpu relative to vm creation > time, and moving it from vmx_vcpu_reset to vmx_vcpu_setup, out of the > APIC MP init path. > > > Signed-off-by: Marcelo Tosatti <[EMAIL PROTECTED]> > > > Index: kvm.tip/arch/x86/kvm/vmx.c > =================================================================== > --- kvm.tip.orig/arch/x86/kvm/vmx.c > +++ kvm.tip/arch/x86/kvm/vmx.c > @@ -850,11 +850,8 @@ static u64 guest_read_tsc(void) > * writes 'guest_tsc' into guest's timestamp counter "register" > * guest_tsc = host_tsc + tsc_offset ==> tsc_offset = guest_tsc - host_tsc > */ > -static void guest_write_tsc(u64 guest_tsc) > +static void guest_write_tsc(u64 guest_tsc, u64 host_tsc) > { > - u64 host_tsc; > - > - rdtscll(host_tsc); > vmcs_write64(TSC_OFFSET, guest_tsc - host_tsc); > } > > @@ -918,6 +915,7 @@ static int vmx_set_msr(struct kvm_vcpu * > { > struct vcpu_vmx *vmx = to_vmx(vcpu); > struct kvm_msr_entry *msr; > + u64 host_tsc; > int ret = 0; > > switch (msr_index) { > @@ -943,7 +941,8 @@ static int vmx_set_msr(struct kvm_vcpu * > vmcs_writel(GUEST_SYSENTER_ESP, data); > break; > case MSR_IA32_TIME_STAMP_COUNTER: > - guest_write_tsc(data); > + rdtscll(host_tsc); > + guest_write_tsc(data, host_tsc); > break; > case MSR_P6_PERFCTR0: > case MSR_P6_PERFCTR1: > @@ -2202,6 +2201,7 @@ static int vmx_vcpu_setup(struct vcpu_vm > vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL); > vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK); > > + guest_write_tsc(0, vmx->vcpu.kvm->arch.vm_init_tsc); > > return 0; > } > @@ -2292,8 +2292,6 @@ static int vmx_vcpu_reset(struct kvm_vcp > vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); > vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0); > > - guest_write_tsc(0); > - > /* Special registers */ > vmcs_write64(GUEST_IA32_DEBUGCTL, 0); > > Index: kvm.tip/arch/x86/kvm/x86.c > =================================================================== > --- kvm.tip.orig/arch/x86/kvm/x86.c > +++ kvm.tip/arch/x86/kvm/x86.c > @@ -4250,6 +4250,8 @@ struct kvm *kvm_arch_create_vm(void) > INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); > INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); > > + rdtscll(kvm->arch.vm_init_tsc); > + > return kvm; > } > > Index: kvm.tip/include/asm-x86/kvm_host.h > =================================================================== > --- kvm.tip.orig/include/asm-x86/kvm_host.h > +++ kvm.tip/include/asm-x86/kvm_host.h > @@ -377,6 +377,7 @@ struct kvm_arch{ > > struct page *ept_identity_pagetable; > bool ept_identity_pagetable_done; > + u64 vm_init_tsc; > }; > > struct kvm_vm_stat { > -- > To unsubscribe from this list: send the line "unsubscribe kvm" in > the body of a message to [EMAIL PROTECTED] > More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html