From: Avi Kivity <avi@redhat.com>
To: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
Cc: mtosatti@redhat.com, kvm@vger.kernel.org
Subject: Re: [PATCH 1/3] KVM: MMU: Make pte_list_desc fit cache lines well
Date: Thu, 15 Mar 2012 11:22:21 +0200 [thread overview]
Message-ID: <4F61B4CD.5020205@redhat.com> (raw)
In-Reply-To: <20120315181943.66eb7284.yoshikawa.takuya@oss.ntt.co.jp>
On 03/15/2012 11:19 AM, Takuya Yoshikawa wrote:
> We have PTE_LIST_EXT + 1 pointers in this structure and these 40/20
> bytes do not fit cache lines well. Furthermore some allocators may
> use 64/32-byte objects for the pte_list_desc cache.
>
> This patch solves this problem by raising PTE_LIST_EXT to 7.
>
> Note: with EPT/NPT we almost always have a single spte in each reverse
> mapping and nothing will be changed by this.
It might be better to drop it to 3. Without EPT/NPT, anonymous guest
pages will have two mappings (a kernel mapping and a user mapping).
Only file pages will have many mappings.
--
error compiling committee.c: too many arguments to function
next prev parent reply other threads:[~2012-03-15 9:22 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-03-15 9:18 [PATCH 0/3] KVM: MMU: Improve rmap handling Takuya Yoshikawa
2012-03-15 9:19 ` [PATCH 1/3] KVM: MMU: Make pte_list_desc fit cache lines well Takuya Yoshikawa
2012-03-15 9:22 ` Avi Kivity [this message]
2012-03-15 9:20 ` [PATCH 2/3] KVM: MMU: Improve iteration over sptes linked by rmap Takuya Yoshikawa
2012-03-15 9:44 ` Avi Kivity
2012-03-15 10:25 ` Takuya Yoshikawa
2012-03-15 9:21 ` [PATCH 3/3] KVM: MMU: Separate trivial NULL check out from rmap_get_next() Takuya Yoshikawa
2012-03-15 9:49 ` Avi Kivity
2012-03-15 10:15 ` Takuya Yoshikawa
2012-03-15 12:01 ` Avi Kivity
2012-03-15 13:41 ` Takuya Yoshikawa
2012-03-15 13:45 ` Avi Kivity
2012-03-15 13:46 ` Avi Kivity
2012-03-20 6:37 ` Takuya Yoshikawa
2012-03-20 11:56 ` Avi Kivity
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=4F61B4CD.5020205@redhat.com \
--to=avi@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=mtosatti@redhat.com \
--cc=yoshikawa.takuya@oss.ntt.co.jp \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.