From: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
To: Marcelo Tosatti <mtosatti@redhat.com>
Cc: gleb@redhat.com, avi.kivity@gmail.com, pbonzini@redhat.com,
linux-kernel@vger.kernel.org, kvm@vger.kernel.org
Subject: Re: [PATCH v7 04/11] KVM: MMU: zap pages in batch
Date: Mon, 27 May 2013 10:20:12 +0800 [thread overview]
Message-ID: <51A2C2DC.6080403@linux.vnet.ibm.com> (raw)
In-Reply-To: <20130524203432.GB4525@amt.cnet>
On 05/25/2013 04:34 AM, Marcelo Tosatti wrote:
> On Thu, May 23, 2013 at 03:55:53AM +0800, Xiao Guangrong wrote:
>> Zap at lease 10 pages before releasing mmu-lock to reduce the overload
>> caused by requiring lock
>>
>> After the patch, kvm_zap_obsolete_pages can forward progress anyway,
>> so update the comments
>>
>> [ It improves kernel building 0.6% ~ 1% ]
>
> Can you please describe the overload in more detail? Under what scenario
> is kernel building improved?
Yes.
The scenario is we do kernel building, meanwhile, repeatedly read PCI rom
every one second.
[
echo 1 > /sys/bus/pci/devices/0000\:00\:03.0/rom
cat /sys/bus/pci/devices/0000\:00\:03.0/rom > /dev/null
]
next prev parent reply other threads:[~2013-05-27 2:20 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-05-22 19:55 [PATCH v7 00/11] KVM: MMU: fast zap all shadow pages Xiao Guangrong
2013-05-22 19:55 ` [PATCH v7 01/11] KVM: x86: drop calling kvm_mmu_zap_all in emulator_fix_hypercall Xiao Guangrong
2013-05-22 19:55 ` [PATCH v7 02/11] KVM: MMU: drop unnecessary kvm_reload_remote_mmus Xiao Guangrong
2013-05-22 19:55 ` [PATCH v7 03/11] KVM: MMU: fast invalidate all pages Xiao Guangrong
2013-05-24 20:23 ` Marcelo Tosatti
2013-05-26 8:26 ` Gleb Natapov
2013-05-26 20:37 ` Marcelo Tosatti
2013-05-27 22:59 ` Xiao Guangrong
2013-05-27 2:02 ` Xiao Guangrong
2013-05-22 19:55 ` [PATCH v7 04/11] KVM: MMU: zap pages in batch Xiao Guangrong
2013-05-24 20:34 ` Marcelo Tosatti
2013-05-27 2:20 ` Xiao Guangrong [this message]
2013-05-28 0:18 ` Marcelo Tosatti
2013-05-28 15:02 ` Xiao Guangrong
2013-05-29 11:11 ` Marcelo Tosatti
2013-05-29 13:09 ` Xiao Guangrong
2013-05-29 13:21 ` Marcelo Tosatti
2013-05-29 14:00 ` Xiao Guangrong
2013-05-29 13:32 ` Marcelo Tosatti
2013-05-29 14:02 ` Xiao Guangrong
2013-05-29 16:03 ` Xiao Guangrong
2013-05-22 19:55 ` [PATCH v7 05/11] KVM: x86: use the fast way to invalidate all pages Xiao Guangrong
2013-05-22 19:55 ` [PATCH v7 06/11] KVM: MMU: show mmu_valid_gen in shadow page related tracepoints Xiao Guangrong
2013-05-22 19:55 ` [PATCH v7 07/11] KVM: MMU: add tracepoint for kvm_mmu_invalidate_all_pages Xiao Guangrong
2013-05-22 19:55 ` [PATCH v7 08/11] KVM: MMU: do not reuse the obsolete page Xiao Guangrong
2013-05-22 19:55 ` [PATCH v7 09/11] KVM: MMU: introduce kvm_mmu_prepare_zap_obsolete_page Xiao Guangrong
2013-05-23 5:57 ` Gleb Natapov
2013-05-23 6:13 ` Xiao Guangrong
2013-05-23 6:18 ` Gleb Natapov
2013-05-23 6:31 ` Xiao Guangrong
2013-05-23 7:37 ` Gleb Natapov
2013-05-23 7:50 ` Xiao Guangrong
2013-05-23 8:09 ` Gleb Natapov
2013-05-23 8:33 ` Xiao Guangrong
2013-05-23 11:13 ` Xiao Guangrong
2013-05-23 12:39 ` Gleb Natapov
2013-05-23 13:03 ` Xiao Guangrong
2013-05-23 15:57 ` Gleb Natapov
2013-05-24 5:39 ` Xiao Guangrong
2013-05-24 5:53 ` Xiao Guangrong
2013-05-28 0:13 ` Marcelo Tosatti
2013-05-28 14:51 ` Xiao Guangrong
2013-05-29 12:25 ` Marcelo Tosatti
2013-05-29 13:43 ` Xiao Guangrong
2013-05-22 19:55 ` [PATCH v7 10/11] KVM: MMU: collapse TLB flushes when zap all pages Xiao Guangrong
2013-05-23 6:12 ` Gleb Natapov
2013-05-23 6:26 ` Xiao Guangrong
2013-05-23 7:24 ` Gleb Natapov
2013-05-23 7:37 ` Xiao Guangrong
2013-05-23 7:38 ` Xiao Guangrong
2013-05-23 7:56 ` Gleb Natapov
2013-05-28 0:36 ` Marcelo Tosatti
2013-05-28 15:19 ` Xiao Guangrong
2013-05-29 3:03 ` Xiao Guangrong
2013-05-29 12:39 ` Marcelo Tosatti
2013-05-29 13:19 ` Xiao Guangrong
2013-05-30 0:53 ` Gleb Natapov
2013-05-30 16:24 ` Takuya Yoshikawa
2013-05-30 17:10 ` Takuya Yoshikawa
2013-05-22 19:56 ` [PATCH v7 11/11] KVM: MMU: reduce KVM_REQ_MMU_RELOAD when root page is zapped 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=51A2C2DC.6080403@linux.vnet.ibm.com \
--to=xiaoguangrong@linux.vnet.ibm.com \
--cc=avi.kivity@gmail.com \
--cc=gleb@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mtosatti@redhat.com \
--cc=pbonzini@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).