Re: [PATCH v7 0/2] KVM: LAPIC: Implement Exitless Timer

[Wanpeng Li]

On Sat, 6 Jul 2019 at 09:26, Wanpeng Li <kernellwp@xxxxxxxxx> wrote:
>
> Dedicated instances are currently disturbed by unnecessary jitter due
> to the emulated lapic timers fire on the same pCPUs which vCPUs resident.
> There is no hardware virtual timer on Intel for guest like ARM. Both
> programming timer in guest and the emulated timer fires incur vmexits.
> This patchset tries to avoid vmexit which is incurred by the emulated
> timer fires in dedicated instance scenario.
>
> When nohz_full is enabled in dedicated instances scenario, the unpinned
> timer will be moved to the nearest busy housekeepers after commit
> 9642d18eee2cd (nohz: Affine unpinned timers to housekeepers) and commit
> 444969223c8 ("sched/nohz: Fix affine unpinned timers mess"). However,
> KVM always makes lapic timer pinned to the pCPU which vCPU residents, the
> reason is explained by commit 61abdbe0 (kvm: x86: make lapic hrtimer
> pinned). Actually, these emulated timers can be offload to the housekeeping
> cpus since APICv is really common in recent years. The guest timer interrupt
> is injected by posted-interrupt which is delivered by housekeeping cpu
> once the emulated timer fires.
>
> The host admin should fine tuned, e.g. dedicated instances scenario w/
> nohz_full cover the pCPUs which vCPUs resident, several pCPUs surplus
> for busy housekeeping, disable mwait/hlt/pause vmexits to keep in non-root
> mode, ~3% redis performance benefit can be observed on Skylake server.
>
> w/o patchset:
>
>             VM-EXIT  Samples  Samples%  Time%   Min Time  Max Time   Avg time
>
> EXTERNAL_INTERRUPT    42916    49.43%   39.30%   0.47us   106.09us   0.71us ( +-   1.09% )
>
> w/ patchset:
>
>             VM-EXIT  Samples  Samples%  Time%   Min Time  Max Time         Avg time
>
> EXTERNAL_INTERRUPT    6871     9.29%     2.96%   0.44us    57.88us   0.72us ( +-   4.02% )
>
> Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
> Cc: Radim KrÄmÃÅ <rkrcmar@xxxxxxxxxx>
> Cc: Marcelo Tosatti <mtosatti@xxxxxxxxxx>
>
> v6 -> v7:
>  * remove bool argument
>
> v5 -> v6:
>  * don't overwrites whatever the user specified
>  * introduce kvm_can_post_timer_interrupt and kvm_use_posted_timer_interrupt
>  * remove kvm_hlt_in_guest() condition
>  * squash all of 2/3/4 together
>
> v4 -> v5:
>  * update patch description in patch 1/4
>  * feed latest apic->lapic_timer.expired_tscdeadline to kvm_wait_lapic_expire()
>  * squash advance timer handling to patch 2/4
>
> v3 -> v4:
>  * drop the HRTIMER_MODE_ABS_PINNED, add kick after set pending timer
>  * don't posted inject already-expired timer
>
> v2 -> v3:
>  * disarming the vmx preemption timer when posted_interrupt_inject_timer_enabled()
>  * check kvm_hlt_in_guest instead
>
> v1 -> v2:
>  * check vcpu_halt_in_guest
>  * move module parameter from kvm-intel to kvm
>  * add housekeeping_enabled
>  * rename apic_timer_expired_pi to kvm_apic_inject_pending_timer_irqs
>
>
> Wanpeng Li (2):
>   KVM: LAPIC: Make lapic timer unpinned
>   KVM: LAPIC: Inject timer interrupt via posted interrupt

There is a further optimization for this feature in houseeking/hrtimer
subsystem.

[1] https://lkml.org/lkml/2019/7/25/963
[2] https://lkml.org/lkml/2019/6/28/231

The [2] patch tries to optimize the worst case, however, it will not
be merged by maintainers and get offline confirm, Thomas will refactor
this to avoid to predict the future on every timer enqueue. Anyway, it
still should be considered to be backported to product environment as
long as get_nohz_timer_target() is using.

Regards,
Wanpeng Li