Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <1621339235-11131-1-git-send-email-wanpengli@tencent.com>
 <1621339235-11131-2-git-send-email-wanpengli@tencent.com> <YKQTx381CGPp7uZY@google.com>
In-Reply-To: <YKQTx381CGPp7uZY@google.com>
From:   Wanpeng Li <kernellwp@gmail.com>
Date:   Wed, 19 May 2021 10:57:55 +0800
Message-ID: <CANRm+Cy_D3cBBEYQ9ApKMNC6p0dpTBQYQXs+dv5vrFedVkOy2w@mail.gmail.com>
Subject: Re: [PATCH v4 2/5] KVM: X86: Bail out of direct yield in case of
 under-committed scenarios
To:     Sean Christopherson <seanjc@google.com>
Cc:     LKML <linux-kernel@vger.kernel.org>, kvm <kvm@vger.kernel.org>,
        Paolo Bonzini <pbonzini@redhat.com>,
        Vitaly Kuznetsov <vkuznets@redhat.com>,
        Wanpeng Li <wanpengli@tencent.com>,
        Jim Mattson <jmattson@google.com>,
        Joerg Roedel <joro@8bytes.org>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Wed, 19 May 2021 at 03:21, Sean Christopherson <seanjc@google.com> wrote:
>
> On Tue, May 18, 2021, Wanpeng Li wrote:
> > From: Wanpeng Li <wanpengli@tencent.com>
> >
> > In case of under-committed scenarios, vCPU can get scheduling easily,
> > kvm_vcpu_yield_to add extra overhead, we can observe a lot of race
> > between vcpu->ready is true and yield fails due to p->state is
> > TASK_RUNNING. Let's bail out in such scenarios by checking the length
> > of current cpu runqueue, it can be treated as a hint of under-committed
> > instead of guarantee of accuracy. The directed_yield_successful/attempted
> > ratio can be improved from 50+% to 80+% in the under-committed scenario.
>
> The "50+% to 80+%" comment will be a bit confusing for future readers now that
> the single_task_running() case counts as an attempt.  I think the new comment
> would be something like "30%+ of directed-yield attempts can avoid the expensive
> lookups in kvm_sched_yield() in an under-committed scenario."  That would also
> provide the real justification, as bumping the success ratio isn't the true goal
> of this path.

Looks good. Hope Paolo can update the patch description when applying. :)

"In case of under-committed scenarios, vCPU can get scheduling easily,
kvm_vcpu_yield_to add extra overhead, we can observe a lot of races
between vcpu->ready is true and yield fails due to p->state is
TASK_RUNNING. Let's bail out in such scenarios by checking the length
of current cpu runqueue, it can be treated as a hint of under-committed
instead of guaranteeing accuracy. 30%+ of directed-yield attempts can
avoid the expensive lookups in kvm_sched_yield() in an under-committed
scenario. "