From: Avi Kivity <avi@redhat.com>
To: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>,
Takuya Yoshikawa <takuya.yoshikawa@gmail.com>,
LKML <linux-kernel@vger.kernel.org>, KVM <kvm@vger.kernel.org>
Subject: Re: [PATCH v4 06/10] KVM: MMU: fast path of handling guest page fault
Date: Thu, 03 May 2012 15:13:47 +0300 [thread overview]
Message-ID: <4FA2767B.5010707@redhat.com> (raw)
In-Reply-To: <4FA27578.1010509@linux.vnet.ibm.com>
On 05/03/2012 03:09 PM, Xiao Guangrong wrote:
> Actually, the improvement of lockless is that it can let vcpu to be parallel
> as possible.
>
> From the test result, lockless gains little improvement for unix-migration,
> in this case, the vcpus are almost idle (at least not busy).
>
> The large improvement is from dbench-migration, in this case, all vcpus are
> busy accessing memory which is write-protected by dirty-log. If you enable
> page-fault/fast-page-fault tracepoints, you can see huge number of page fault
> from different vcpu during the migration.
>
We can kill the page faults completely by using A/D bits in shadow page
tables. The latest version of the Intel SDM defines A/D bits for EPT,
and NPT has had them from day one.
Of course this comes at a cost, instead of traversing a bitmap we have
to read all sptes, which are 64x as large. But it's probably worthwhile
for large guests and perhaps also for smaller ones.
--
error compiling committee.c: too many arguments to function
next prev parent reply other threads:[~2012-05-03 12:13 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-04-25 4:00 [PATCH v4 00/10] KVM: MMU: fast page fault Xiao Guangrong
2012-04-25 4:01 ` [PATCH v4 01/10] KVM: MMU: return bool in __rmap_write_protect Xiao Guangrong
2012-04-25 4:01 ` [PATCH v4 02/10] KVM: MMU: abstract spte write-protect Xiao Guangrong
2012-04-25 4:02 ` [PATCH v4 03/10] KVM: VMX: export PFEC.P bit on ept Xiao Guangrong
2012-04-25 4:02 ` [PATCH v4 04/10] KVM: MMU: introduce SPTE_MMU_WRITEABLE bit Xiao Guangrong
2012-04-25 4:03 ` [PATCH v4 05/10] KVM: MMU: introduce SPTE_WRITE_PROTECT bit Xiao Guangrong
2012-04-25 4:03 ` [PATCH v4 06/10] KVM: MMU: fast path of handling guest page fault Xiao Guangrong
2012-04-26 23:45 ` Marcelo Tosatti
2012-04-27 5:53 ` Xiao Guangrong
2012-04-27 14:52 ` Marcelo Tosatti
2012-04-28 6:10 ` Xiao Guangrong
2012-05-01 1:34 ` Marcelo Tosatti
2012-05-02 5:28 ` Xiao Guangrong
2012-05-02 21:07 ` Marcelo Tosatti
2012-05-03 11:26 ` Xiao Guangrong
2012-05-05 14:08 ` Marcelo Tosatti
2012-05-06 9:36 ` Avi Kivity
2012-05-07 6:52 ` Xiao Guangrong
2012-04-29 8:50 ` Takuya Yoshikawa
2012-05-01 2:31 ` Marcelo Tosatti
2012-05-02 5:39 ` Xiao Guangrong
2012-05-02 21:10 ` Marcelo Tosatti
2012-05-03 12:09 ` Xiao Guangrong
2012-05-03 12:13 ` Avi Kivity [this message]
2012-05-03 0:15 ` Takuya Yoshikawa
2012-05-03 12:23 ` Xiao Guangrong
2012-05-03 12:40 ` Takuya Yoshikawa
2012-04-25 4:04 ` [PATCH v4 07/10] KVM: MMU: lockless update spte on fast page fault path Xiao Guangrong
2012-04-25 4:04 ` [PATCH v4 08/10] KVM: MMU: trace fast page fault Xiao Guangrong
2012-04-25 4:05 ` [PATCH v4 09/10] KVM: MMU: fix kvm_mmu_pagetable_walk tracepoint Xiao Guangrong
2012-04-25 4:06 ` [PATCH v4 10/10] KVM: MMU: document mmu-lock and fast page fault Xiao Guangrong
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=4FA2767B.5010707@redhat.com \
--to=avi@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mtosatti@redhat.com \
--cc=takuya.yoshikawa@gmail.com \
--cc=xiaoguangrong@linux.vnet.ibm.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).