linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>
To: Paolo Bonzini <pbonzini@redhat.com>, <rkrcmar@redhat.com>,
	<joro@8bytes.org>, <bp@alien8.de>, <gleb@kernel.org>,
	<alex.williamson@redhat.com>
Cc: <kvm@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
	<wei@redhat.com>, <sherry.hurwitz@amd.com>
Subject: Re: [PART1 RFC v2 05/10] KVM: x86: Detect and Initialize AVIC support
Date: Wed, 16 Mar 2016 13:22:03 +0700	[thread overview]
Message-ID: <56E8FB8B.7050700@amd.com> (raw)
In-Reply-To: <56E844E2.6090507@redhat.com>

Hi,

On 03/16/2016 12:22 AM, Paolo Bonzini wrote:
>>> Why is this necessary?  The APIC access page is a peculiarity of Intel
>>> >>processors (and the special memslot for only needs to map 0xfee00000 to
>>> >>0xfee00fff; after that there is the MSI area).
>> >
>> >The current lapic regs page is allocated using get_zeroed_page(), which
>> >can be paged out. If I use these pages for AVIC backing pages, it seems
>> >to cause VM to slow down quite a bit due to a lot of page faults.
> What causes the lapic regs page to be paged out?
>

This is mainly causing a large number of VMEXIT due to NPF.  In my test 
running hackbench in the guest. The following are perf result profiling 
for 10 seconds in the host in two cases:

CASE1: Using x86_set_memory_region() for AVIC backing page

# ./perf-vmexit.sh 10
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 2.813 MB perf.data.guest (30356 samples) ]


Analyze events for all VMs, all VCPUs:

              VM-EXIT    Samples  Samples%     Time%    Min Time    Max 
Time         Avg time

            interrupt      10042    66.30%    81.33%      0.43us 
202.50us      7.43us ( +-   1.20% )
                  msr       5004    33.04%    15.76%      0.73us 
12.21us      2.89us ( +-   0.43% )
                pause         58     0.38%     0.18%      0.56us 
5.88us      2.92us ( +-   6.43% )
                  npf         35     0.23%     2.01%      6.41us 
207.78us     52.70us ( +-  23.67% )
                  nmi          4     0.03%     0.02%      2.31us 
4.67us      3.49us ( +-  14.26% )
                   io          3     0.02%     0.70%     82.75us 
360.90us    214.28us ( +-  37.64% )
      avic_incomp_ipi          1     0.01%     0.00%      2.17us 
2.17us      2.17us ( +-   0.00% )

Total Samples:15147, Total events handled time:91715.78us.


CASE2: Using the lapic regs page for AVIC backing page.

# ./perf-vmexit.sh 10
[ perf record: Woken up 255 times to write data ]
[ perf record: Captured and wrote 509.202 MB perf.data.guest (5718856 
samples) ]


Analyze events for all VMs, all VCPUs:

              VM-EXIT    Samples  Samples%     Time%    Min Time    Max 
Time         Avg time

                  npf    1897710    99.33%    98.08%      1.09us 
243.22us      1.67us ( +-   0.04% )
            interrupt       7818     0.41%     1.44%      0.44us 
216.55us      5.97us ( +-   1.92% )
                  msr       5001     0.26%     0.45%      0.68us 
12.58us      2.89us ( +-   0.50% )
                pause         25     0.00%     0.00%      0.71us 
4.23us      2.03us ( +-  10.76% )
                   io          4     0.00%     0.03%     73.91us 
337.29us    206.74us ( +-  26.38% )
                  nmi          1     0.00%     0.00%      5.92us 
5.92us      5.92us ( +-   0.00% )

Total Samples:1910559, Total events handled time:3229214.64us.

Thanks,
Suravee

  reply	other threads:[~2016-03-16  6:22 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-04 20:45 [PART1 RFC v2 00/10] KVM: x86: Introduce SVM AVIC support Suravee Suthikulpanit
2016-03-04 20:45 ` [PART1 RFC v2 01/10] KVM: x86: Misc LAPIC changes to exposes helper functions Suravee Suthikulpanit
2016-03-04 20:46 ` [PART1 RFC v2 02/10] KVM: x86: Introducing kvm_x86_ops VCPU blocking/unblocking Suravee Suthikulpanit
2016-03-07 15:42   ` Paolo Bonzini
2016-03-14  6:19     ` Suravee Suthikulpanit
2016-03-04 20:46 ` [PART1 RFC v2 03/10] svm: Introduce new AVIC VMCB registers Suravee Suthikulpanit
2016-03-07 15:44   ` Paolo Bonzini
2016-03-14  7:41     ` Suravee Suthikulpanit
2016-03-14 12:25       ` Paolo Bonzini
2016-03-15 12:51         ` Suravee Suthikulpanit
2016-03-04 20:46 ` [PART1 RFC v2 04/10] svm: clean up V_TPR, V_IRQ, V_INTR_PRIO, and V_INTR_MASKING Suravee Suthikulpanit
2016-03-04 20:46 ` [PART1 RFC v2 05/10] KVM: x86: Detect and Initialize AVIC support Suravee Suthikulpanit
2016-03-07 16:41   ` Paolo Bonzini
2016-03-15 17:09     ` Suravee Suthikulpanit
2016-03-15 17:22       ` Paolo Bonzini
2016-03-16  6:22         ` Suravee Suthikulpanit [this message]
2016-03-16  7:20           ` Paolo Bonzini
2016-03-16  8:21             ` Suravee Suthikulpanit
2016-03-16 11:12               ` Paolo Bonzini
2016-03-04 20:46 ` [PART1 RFC v2 06/10] svm: Add interrupt injection via AVIC Suravee Suthikulpanit
2016-03-07 15:36   ` Paolo Bonzini
2016-03-08 21:54     ` Radim Krčmář
2016-03-09 11:10       ` Paolo Bonzini
2016-03-09 16:00         ` Radim Krčmář
2016-03-14  9:41           ` Suravee Suthikulpanit
2016-03-14 12:27             ` Paolo Bonzini
2016-03-14  9:50         ` Suravee Suthikulpanit
2016-03-14  5:25     ` Suravee Suthikulpanit
2016-03-14  8:54       ` Suravee Suthikulpanit
2016-03-04 20:46 ` [PART1 RFC v2 07/10] svm: Add VMEXIT handlers for AVIC Suravee Suthikulpanit
2016-03-07 15:58   ` Paolo Bonzini
2016-03-08 22:05     ` Radim Krčmář
2016-03-09 10:56       ` Paolo Bonzini
2016-03-09 20:55   ` Radim Krčmář
2016-03-10 19:34     ` Radim Krčmář
2016-03-10 19:54       ` Paolo Bonzini
2016-03-10 20:44         ` Radim Krčmář
2016-03-17  3:58     ` Suravee Suthikulpanit
2016-03-17  9:35       ` Paolo Bonzini
2016-03-17 19:44     ` Suravee Suthikulpanit
2016-03-17 20:27       ` [PATCH] KVM: split kvm_vcpu_wake_up from kvm_vcpu_kick Radim Krčmář
2016-03-18  5:13         ` Suravee Suthikulpanit
2016-03-04 20:46 ` [PART1 RFC v2 08/10] svm: Do not expose x2APIC when enable AVIC Suravee Suthikulpanit
2016-03-04 20:46 ` [PART1 RFC v2 09/10] svm: Do not intercept CR8 " Suravee Suthikulpanit
2016-03-07 15:39   ` Paolo Bonzini
2016-03-14  6:09     ` Suravee Suthikulpanit
2016-03-14 12:28       ` Paolo Bonzini
2016-03-04 20:46 ` [PART1 RFC v2 10/10] svm: Manage vcpu load/unload " Suravee Suthikulpanit
2016-03-09 21:46   ` Radim Krčmář
2016-03-10 14:01     ` Radim Krčmář
2016-03-14 11:58       ` Suravee Suthikulpanit
2016-03-14 16:54         ` Radim Krčmář
2016-03-14 11:48     ` Suravee Suthikulpanit
2016-03-14 16:40       ` Radim Krčmář

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=56E8FB8B.7050700@amd.com \
    --to=suravee.suthikulpanit@amd.com \
    --cc=alex.williamson@redhat.com \
    --cc=bp@alien8.de \
    --cc=gleb@kernel.org \
    --cc=joro@8bytes.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=rkrcmar@redhat.com \
    --cc=sherry.hurwitz@amd.com \
    --cc=wei@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).