Advance lapic timer tries to hidden the hypervisor overhead between the
host emulated timer fires and the guest awares the timer is fired. However,
it just hidden the time between apic_timer_fn/handle_preemption_timer ->
wait_lapic_expire, instead of the real position of vmentry which is
mentioned in the orignial commit d0659d946be0 ("KVM: x86: add option to
advance tscdeadline hrtimer expiration"). There is 700+ cpu cycles between
the end of wait_lapic_expire and before world switch on my haswell desktop,
it will be 2400+ cycles if vmentry_l1d_flush is tuned to always.
This patchset tries to narrow the last gap(wait_lapic_expire -> world switch),
it takes the real overhead time between apic_timer_fn/handle_preemption_timer
and before world switch into consideration when adaptively tuning timer
advancement. The patchset can reduce 40% latency (~1600+ cycles to ~1000+
cycles on a haswell desktop) for kvm-unit-tests/tscdeadline_latency when
testing busy waits.
v1 -> v2:
* fix indent in patch 1/4
* remove the wait_lapic_expire() tracepoint and expose by debugfs
* move the call to wait_lapic_expire() into vmx.c and svm.c
Wanpeng Li (4):
KVM: LAPIC: Extract adaptive tune timer advancement logic
KVM: LAPIC: Fix lapic_timer_advance_ns parameter overflow
KVM: LAPIC: Expose per-vCPU timer adavance information to userspace
KVM: LAPIC: Optimize timer latency further
arch/x86/kvm/debugfs.c | 16 +++++++++++++
arch/x86/kvm/lapic.c | 62 +++++++++++++++++++++++++++++---------------------
arch/x86/kvm/lapic.h | 3 ++-
arch/x86/kvm/svm.c | 4 ++++
arch/x86/kvm/trace.h | 20 ----------------
arch/x86/kvm/vmx/vmx.c | 4 ++++
arch/x86/kvm/x86.c | 5 +---
7 files changed, 63 insertions(+), 51 deletions(-)
--
2.7.4
