* Re: [PATCH] disable per cpu intr in /proc/stat [not found] <20060122202204.GA26295@suse.de> @ 2006-01-22 20:31 ` Andrew Morton 2006-01-22 20:59 ` Tony Luck 0 siblings, 1 reply; 2+ messages in thread From: Andrew Morton @ 2006-01-22 20:31 UTC (permalink / raw) To: Olaf Hering; +Cc: linux-kernel, linux-ia64, Luck, Tony Olaf Hering <olh@suse.de> wrote: > > (No bugzilla or benchmark) > > From: schwab@suse.de > Subject: Reading /proc/stat is slooow > > Don't compute and display the per-irq sums on ia64 either, too much > overhead for mostly useless figures. > > --- linux-2.6.14/fs/proc/proc_misc.c.~1~ 2005-12-06 18:12:28.840059961 +0100 > +++ linux-2.6.14/fs/proc/proc_misc.c 2005-12-06 18:13:51.211896515 +0100 > @@ -498,7 +498,7 @@ static int show_stat(struct seq_file *p, > } > seq_printf(p, "intr %llu", (unsigned long long)sum); > > -#if !defined(CONFIG_PPC64) && !defined(CONFIG_ALPHA) > +#if !defined(CONFIG_PPC64) && !defined(CONFIG_ALPHA) && !defined(CONFIG_IA64) > for (i = 0; i < NR_IRQS; i++) > seq_printf(p, " %u", kstat_irqs(i)); > #endif We'd need a big ack from the ia64 team for this, please. ^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: [PATCH] disable per cpu intr in /proc/stat 2006-01-22 20:31 ` [PATCH] disable per cpu intr in /proc/stat Andrew Morton @ 2006-01-22 20:59 ` Tony Luck 0 siblings, 0 replies; 2+ messages in thread From: Tony Luck @ 2006-01-22 20:59 UTC (permalink / raw) To: Andrew Morton; +Cc: Olaf Hering, linux-kernel, linux-ia64 On 1/22/06, Andrew Morton <akpm@osdl.org> wrote: > Olaf Hering <olh@suse.de> wrote: > > Don't compute and display the per-irq sums on ia64 either, too much > > overhead for mostly useless figures. > > We'd need a big ack from the ia64 team for this, please. This was found early in December. I proposed: http://marc.theaimsgroup.com/?l=linux-kernel&m\x113398553428807&w=2 dropping it for all architectures, but got no response. The problem is the horribly cache unfriendly scan of all percpu structures ... not too much of a problem for low cpu count, but really bad when the count gets high (just configured high is enough to cause the problem in a CONFIG_HOTPLUG_CPU kernel ... even if the cpu isn't present we still scan). An alternative if someone really is using these values would be to compute the sums earlier in the function ... but that would require a memory allocation to save the per-irq sums. Unless someone comes up soon with the name of an existing application that depends on these per-irq sums, consider this Acked-by: Tony Luck <tony.luck@intel.com> -Tony ^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2006-01-22 20:59 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
[not found] <20060122202204.GA26295@suse.de>
2006-01-22 20:31 ` [PATCH] disable per cpu intr in /proc/stat Andrew Morton
2006-01-22 20:59 ` Tony Luck
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox