Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: Re: [PATCH] KVM: LAPIC: Periodically revaluate appropriate
 lapic_timer_advance_ns
To:     Wanpeng Li <kernellwp@gmail.com>
Cc:     LKML <linux-kernel@vger.kernel.org>, kvm <kvm@vger.kernel.org>,
        =?UTF-8?B?UmFkaW0gS3LEjW3DocWZ?= <rkrcmar@redhat.com>
References: <1565329531-12327-1-git-send-email-wanpengli@tencent.com>
 <fad8ceed-8b98-8fc4-5b6a-63bbca4059a8@redhat.com>
 <CANRm+CwMMUEyZXmiUu5Y8GA=BEUYGLw31CRyZTc2uA+ct4Bamg@mail.gmail.com>
From:   Paolo Bonzini <pbonzini@redhat.com>
Openpgp: preference=signencrypt
Message-ID: <ba07fb02-9b55-15e4-d240-24da59e09369@redhat.com>
Date:   Wed, 14 Aug 2019 14:50:01 +0200
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101
 Thunderbird/60.8.0
MIME-Version: 1.0
In-Reply-To: <CANRm+CwMMUEyZXmiUu5Y8GA=BEUYGLw31CRyZTc2uA+ct4Bamg@mail.gmail.com>
Content-Type: text/plain; charset=utf-8
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On 12/08/19 11:06, Wanpeng Li wrote:
> On Fri, 9 Aug 2019 at 18:24, Paolo Bonzini <pbonzini@redhat.com> wrote:
>>
>> On 09/08/19 07:45, Wanpeng Li wrote:
>>> From: Wanpeng Li <wanpengli@tencent.com>
>>>
>>> Even if for realtime CPUs, cache line bounces, frequency scaling, presence
>>> of higher-priority RT tasks, etc can cause different response. These
>>> interferences should be considered and periodically revaluate whether
>>> or not the lapic_timer_advance_ns value is the best, do nothing if it is,
>>> otherwise recaluate again.
>>
>> How much fluctuation do you observe between different runs?
> 
> Sometimes can ~1000 cycles after converting to guest tsc freq.

Hmm, I wonder if we need some kind of continuous smoothing.  Something like

        if (abs(advance_expire_delta) < LAPIC_TIMER_ADVANCE_ADJUST_DONE) {
                /* no update for random fluctuations */
		return;
	}

        if (unlikely(timer_advance_ns > 5000))
                timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT;
        apic->lapic_timer.timer_advance_ns = timer_advance_ns;

and removing all the timer_advance_adjust_done stuff.  What do you think?

Paolo