From: Andi Kleen <andi@firstfloor.org>
To: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>,
Andi Kleen <andi@firstfloor.org>, Yinghai Lu <yinghai@kernel.org>,
Linus Torvalds <torvalds@linux-foundation.org>,
"ananth@in.ibm.com" <ananth@in.ibm.com>,
Ingo Molnar <mingo@elte.hu>, Thomas Gleixner <tglx@linutronix.de>,
Andrew Morton <akpm@linux-foundation.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH -v2 5/5] x86: use dmi check to treat disabled cpus as hotplug cpus.
Date: Thu, 14 Jan 2010 10:25:15 +0100 [thread overview]
Message-ID: <20100114092515.GG12241@basil.fritz.box> (raw)
In-Reply-To: <1263422958.2865.107.camel@sbs-t61.sc.intel.com>
On Wed, Jan 13, 2010 at 02:49:18PM -0800, Suresh Siddha wrote:
> On Wed, 2010-01-13 at 14:36 -0800, H. Peter Anvin wrote:
> > On 01/13/2010 02:29 PM, Suresh Siddha wrote:
> > >>
> > >> Well, that *is* working around broken code, in this case the broken code
> > >> is the percpu allocation strategy.
> > >
> > > Andi, Recently percpu folks changed the per-cpu static first chunk to
> > > PMD SIZE right. I think that is what causing all this issue.
> > >
> >
> > Please don't tell me we're allocating 2 MB per CPU and throwing away
> > most of it...
>
> Looking at the percpu code, they do seem to free the unused memory in
> that hole.
I took a look at alloc_percpu() at least and it seems to always
allocate for all possible cpus.
Unfortunately we don't have a nice accounting mechanism for it in /proc,
perhaps we should. So it's unclear right now if that is a problem or not.
-Andi
--
ak@linux.intel.com -- Speaking for myself only.
next prev parent reply other threads:[~2010-01-14 9:25 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-01-12 23:17 [PATCH 0/5] clean up logical flat apic mode using Yinghai Lu
2010-01-12 23:17 ` [PATCH -v2 1/5] use nr_cpus= to set nr_cpu_ids early Yinghai Lu
2010-01-12 23:17 ` [PATCH 2/5] x86: using logical flat for amd cpu too Yinghai Lu
2010-01-12 23:17 ` [PATCH -v2 3/5] x86: according to nr_cpu_ids to decide if need to leave logical flat Yinghai Lu
2010-01-12 23:17 ` [PATCH -v2 5/5] x86: use dmi check to treat disabled cpus as hotplug cpus Yinghai Lu
2010-01-12 23:56 ` Suresh Siddha
2010-01-13 0:05 ` Yinghai Lu
2010-01-13 1:48 ` Suresh Siddha
2010-01-13 1:55 ` Yinghai Lu
2010-01-13 2:06 ` Suresh Siddha
2010-01-13 2:13 ` Yinghai Lu
2010-01-13 2:21 ` Suresh Siddha
2010-01-13 2:26 ` Yinghai Lu
2010-01-13 21:46 ` Andi Kleen
2010-01-13 22:00 ` H. Peter Anvin
2010-01-13 22:23 ` Andi Kleen
2010-01-13 22:27 ` H. Peter Anvin
2010-01-13 22:29 ` Suresh Siddha
2010-01-13 22:36 ` H. Peter Anvin
2010-01-13 22:49 ` Suresh Siddha
2010-01-13 23:02 ` Yinghai Lu
2010-01-13 23:13 ` H. Peter Anvin
2010-01-13 23:52 ` Andi Kleen
2010-01-14 9:25 ` Andi Kleen [this message]
2010-01-12 23:17 ` [PATCH 4/5] x86: make 32bit apic flat to physflat switch like 64bit Yinghai Lu
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=20100114092515.GG12241@basil.fritz.box \
--to=andi@firstfloor.org \
--cc=akpm@linux-foundation.org \
--cc=ananth@in.ibm.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=suresh.b.siddha@intel.com \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=yinghai@kernel.org \
/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.