From: Andi Kleen <andi@firstfloor.org>
To: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>,
Andi Kleen <andi@firstfloor.org>,
paulmck@linux.vnet.ibm.com, linux-kernel@vger.kernel.org,
mingo@elte.hu, rjw@sisk.pl, dipankar@in.ibm.com,
tglx@linuxtronix.de
Subject: Re: [PATCH] rudimentary tracing for Classic RCU
Date: Thu, 9 Oct 2008 10:06:01 +0200 [thread overview]
Message-ID: <20081009080601.GD24560@one.firstfloor.org> (raw)
In-Reply-To: <20081009161232.DEDC.KOSAKI.MOTOHIRO@jp.fujitsu.com>
On Thu, Oct 09, 2008 at 04:14:26PM +0900, KOSAKI Motohiro wrote:
> Hi Lai-san,
>
> > >> In this case, why not define it as:
> > >> static char buf[20*NR_CPUS + 100];
> > >
> > > Actually you should near never use NR_CPUS now but always num_possible_cpus()
> > > (or even num_online_cpus()) Using NR_CPUS can lead to extreme waste
> > > of memory on kernels which are compiled for 4096 CPUs for example.
> > >
> > > And with num_possible_cpus() kmalloc is needed.
> >
> > I thought the default value of NR_CPUS is 32.
>
> it's pointless.
> Almost distribution use _very_ large NR_CPUS (likes 4096).
Right now it's more like 8-128, but at least there is some effort
to make a 4096 CPU distribution possible and Mike Travis has been
tirelessly working on eradicating all the rogue NR_CPUs all over
the tree. So it's better to not add more.
> So, We should concern large NR_CPUS.
Agreed.
-Andi
--
ak@linux.intel.com
next prev parent reply other threads:[~2008-10-09 7:59 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-10-06 14:12 scheduler hang on cpu re-hotplug with 2.6.27rc8 Andi Kleen
2008-10-06 23:28 ` RCU " Andi Kleen
2008-10-07 3:08 ` Paul E. McKenney
2008-10-07 7:15 ` Andi Kleen
2008-10-07 15:26 ` Paul E. McKenney
2008-10-07 15:49 ` Andi Kleen
2008-10-07 16:34 ` Paul E. McKenney
2008-10-07 21:09 ` Andi Kleen
2008-10-07 21:22 ` Paul E. McKenney
2008-10-09 1:08 ` [PATCH] rudimentary tracing for Classic RCU Paul E. McKenney
2008-10-09 6:20 ` Lai Jiangshan
2008-10-09 6:55 ` Andi Kleen
2008-10-09 7:05 ` Lai Jiangshan
2008-10-09 7:14 ` KOSAKI Motohiro
2008-10-09 7:26 ` Lai Jiangshan
2008-10-09 8:06 ` Andi Kleen [this message]
2008-10-10 11:48 ` Paul E. McKenney
2008-10-09 11:50 ` Paul E. McKenney
2008-10-09 11:50 ` Paul E. McKenney
2008-10-09 10:23 ` Frédéric Weisbecker
2008-10-09 10:53 ` Andi Kleen
2008-10-09 11:44 ` Frédéric Weisbecker
2008-10-09 11:54 ` Paul E. McKenney
2008-10-09 13:01 ` Frédéric Weisbecker
2008-10-10 3:44 ` [PATCH] v2 " Paul E. McKenney
2008-10-13 23:09 ` [PATCH] v3 " Paul E. McKenney
2008-10-14 3:53 ` Lai Jiangshan
2008-10-14 14:35 ` Paul E. McKenney
2008-10-23 11:12 ` Lai Jiangshan
2008-10-26 21:59 ` Paul E. McKenney
2008-10-27 21:50 ` Paul E. McKenney
2008-10-27 23:57 ` Paul E. McKenney
2008-10-29 1:16 ` Paul E. McKenney
2008-10-29 1:31 ` Lai Jiangshan
2008-10-30 15:52 ` Paul E. McKenney
2008-10-09 1:33 ` RCU hang on cpu re-hotplug with 2.6.27rc8 Paul E. McKenney
2008-10-09 4:56 ` Andi Kleen
2008-10-09 7:24 ` Thomas Gleixner
2008-10-09 8:22 ` Andi Kleen
2008-10-09 11:44 ` Paul E. McKenney
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=20081009080601.GD24560@one.firstfloor.org \
--to=andi@firstfloor.org \
--cc=dipankar@in.ibm.com \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=laijs@cn.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=paulmck@linux.vnet.ibm.com \
--cc=rjw@sisk.pl \
--cc=tglx@linuxtronix.de \
/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
Powered by JetHome