From: Keir Fraser <keir@xen.org>
To: Jan Beulich <JBeulich@suse.com>,
Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: TimDeegan <tim@xen.org>, Olaf Hering <olaf@aepfle.de>,
IanCampbell <Ian.Campbell@citrix.com>,
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
George Dunlap <George.Dunlap@eu.citrix.com>,
Ian Jackson <Ian.Jackson@eu.citrix.com>,
George Shuklin <george.shuklin@gmail.com>,
xen-devel@lists.xen.org, DarioFaggioli <raistlin@linux.it>,
Kurt Hackel <kurt.hackel@oracle.com>,
Zhigang Wang <zhigang.x.wang@oracle.com>
Subject: Re: Proposed new "memory capacity claim" hypercall/feature
Date: Fri, 02 Nov 2012 09:30:14 +0000 [thread overview]
Message-ID: <CCB94326.50E8F%keir@xen.org> (raw)
In-Reply-To: <50939A1502000078000A5F61@nat28.tlf.novell.com>
On 02/11/2012 09:01, "Jan Beulich" <JBeulich@suse.com> wrote:
> Plus, if necessary, that loop could be broken up so that only the
> initial part of it gets run with the lock held (see c/s
> 22135:69e8bb164683 for why the unlock was moved past the
> loop). That would make for a shorter lock hold time, but for a
> higher allocation latency on large oder allocations (due to worse
> cache locality).
In fact I believe only the first page needs to have its count_info set to !=
PGC_state_free, while the lock is held. That is sufficient to defeat the
buddy merging in free_heap_pages(). Similarly, we could hoist most of the
first loop in free_heap_pages() outside the lock. There's a lot of scope for
optimisation here.
-- Keir
next prev parent reply other threads:[~2012-11-02 9:30 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-10-29 17:06 Proposed new "memory capacity claim" hypercall/feature Dan Magenheimer
2012-10-29 18:24 ` Keir Fraser
2012-10-29 21:08 ` Dan Magenheimer
2012-10-29 22:22 ` Keir Fraser
2012-10-29 23:03 ` Dan Magenheimer
2012-10-29 23:17 ` Keir Fraser
2012-10-30 15:13 ` Dan Magenheimer
2012-10-30 14:43 ` Keir Fraser
2012-10-30 16:33 ` Dan Magenheimer
2012-10-30 9:11 ` George Dunlap
2012-10-30 16:13 ` Dan Magenheimer
2012-10-29 22:35 ` Tim Deegan
2012-10-29 23:21 ` Dan Magenheimer
2012-10-30 8:13 ` Tim Deegan
2012-10-30 15:26 ` Dan Magenheimer
2012-10-30 8:29 ` Jan Beulich
2012-10-30 15:43 ` Dan Magenheimer
2012-10-30 16:04 ` Jan Beulich
2012-10-30 17:13 ` Dan Magenheimer
2012-10-31 8:14 ` Jan Beulich
2012-10-31 16:04 ` Dan Magenheimer
2012-10-31 16:19 ` Jan Beulich
2012-10-31 16:51 ` Dan Magenheimer
2012-11-02 9:01 ` Jan Beulich
2012-11-02 9:30 ` Keir Fraser [this message]
2012-11-04 19:43 ` Dan Magenheimer
2012-11-04 20:35 ` Tim Deegan
2012-11-05 0:23 ` Dan Magenheimer
2012-11-05 10:29 ` Ian Campbell
2012-11-05 14:54 ` Dan Magenheimer
2012-11-05 22:24 ` Ian Campbell
2012-11-05 22:58 ` Zhigang Wang
2012-11-05 22:58 ` Dan Magenheimer
2012-11-06 13:23 ` Ian Campbell
2012-11-05 22:33 ` Dan Magenheimer
2012-11-06 10:49 ` Jan Beulich
2012-11-05 9:16 ` Jan Beulich
2012-11-07 22:17 ` Dan Magenheimer
2012-11-08 7:36 ` Keir Fraser
2012-11-08 10:11 ` Ian Jackson
2012-11-08 10:57 ` Keir Fraser
2012-11-08 21:45 ` Dan Magenheimer
2012-11-12 11:03 ` Ian Jackson
2012-11-08 8:00 ` Jan Beulich
2012-11-08 8:18 ` Keir Fraser
2012-11-08 8:54 ` Jan Beulich
2012-11-08 9:12 ` Keir Fraser
2012-11-08 9:47 ` Jan Beulich
2012-11-08 10:50 ` Keir Fraser
2012-11-08 13:48 ` Jan Beulich
2012-11-08 19:16 ` Dan Magenheimer
2012-11-08 22:32 ` Keir Fraser
2012-11-09 8:47 ` Jan Beulich
2012-11-08 18:38 ` Dan Magenheimer
2012-11-05 17:14 ` George Dunlap
2012-11-05 18:21 ` Dan Magenheimer
2012-11-01 2:13 ` Dario Faggioli
2012-11-01 15:51 ` Dan Magenheimer
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=CCB94326.50E8F%keir@xen.org \
--to=keir@xen.org \
--cc=George.Dunlap@eu.citrix.com \
--cc=Ian.Campbell@citrix.com \
--cc=Ian.Jackson@eu.citrix.com \
--cc=JBeulich@suse.com \
--cc=dan.magenheimer@oracle.com \
--cc=george.shuklin@gmail.com \
--cc=konrad.wilk@oracle.com \
--cc=kurt.hackel@oracle.com \
--cc=olaf@aepfle.de \
--cc=raistlin@linux.it \
--cc=tim@xen.org \
--cc=xen-devel@lists.xen.org \
--cc=zhigang.x.wang@oracle.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).