From: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
To: Takuya Yoshikawa <takuya.yoshikawa@gmail.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>,
Avi Kivity <avi@redhat.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 20:23:18 +0800 [thread overview]
Message-ID: <4FA278B6.5090208@linux.vnet.ibm.com> (raw)
In-Reply-To: <20120503091558.866e158916f0dd67daf5a9a2@gmail.com>
On 05/03/2012 08:15 AM, Takuya Yoshikawa wrote:
> On Wed, 02 May 2012 13:39:51 +0800
> Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> wrote:
>
>>> Was the problem really mmu_lock contention?
>
>> Takuya, i am so tired to argue the advantage of lockless write-protect
>> and lockless O(1) dirty-log again and again.
>
> You are missing my point. Please do not take my comments as an objection
> to your whole work: whey do you feel so?
>
Takuya, i am sorry, please forgive my rudeness! Since my English is
so poor that it is easy for me to misunderstand the mail. :(
> I thought that your new fast-page-fault path was fast and optimized
> the guest during dirty logging.
>
> So in this v4, you might get a similar result even before dropping
> mmu_lock, without 07/10?, if the problem Marcelo explained was not there.
>
Actually, the improvement is larger than v2/v3 if ept is enabled, but
it is lower for ept disabled. This is because the fask-fask (rmap.WRITABLE bit)
is dropped for better review.
>
> Of course there is a problem of mmu_lock contention. What I am suggesting
> is to split that problem and do measurement separately so that part of
> your work can be merged soon.
>
> Your guest size and workload was small to make get_dirty hold mmu_lock
> long time. If you want to appeal the real value of lock-less, you need to
> do another measurment.
>
>
> But this is your work and it's up to you. Although I was thinking to help
> your measurement, I cannot do that knowing the fact that you would not
> welcome my help.
>
Of course, any measurement is appreciative!
>
>>> Although I am not certain about what will be really needed in the
>>> final form, if this kind of maybe-needed-overhead is going to be
>>> added little by little, I worry about possible regression.
>
>> Well, will you suggest Linus to reject all patches and stop
>> all discussion for the "possible regression" reason?
>
> My concern was for Marcelo's examples, not your current implementation.
> If you can show explicitely what will be needed in the final form,
> I do not have any concern.
>
>
> Sorry for disturbing.
Sorry again.
next prev parent reply other threads:[~2012-05-03 12:23 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
2012-05-03 0:15 ` Takuya Yoshikawa
2012-05-03 12:23 ` Xiao Guangrong [this message]
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=4FA278B6.5090208@linux.vnet.ibm.com \
--to=xiaoguangrong@linux.vnet.ibm.com \
--cc=avi@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mtosatti@redhat.com \
--cc=takuya.yoshikawa@gmail.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).