[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20100118095527.GV12666@kryten>
Date: Mon, 18 Jan 2010 20:55:27 +1100
From: Anton Blanchard <anton@...ba.org>
To: Martin Schwidefsky <schwidefsky@...ibm.com>
Cc: Bharata B Rao <bharata@...ux.vnet.ibm.com>,
KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>,
Ingo Molnar <mingo@...e.hu>,
Balbir Singh <balbir@...ux.vnet.ibm.com>, mingo@...hat.com,
hpa@...or.com, linux-kernel@...r.kernel.org,
a.p.zijlstra@...llo.nl, balajirrao@...il.com,
dhaval@...ux.vnet.ibm.com, tglx@...utronix.de,
kamezawa.hiroyu@...fujitsu.com, akpm@...ux-foundation.org,
Tony Luck <tony.luck@...el.com>,
Fenghua Yu <fenghua.yu@...el.com>,
Heiko Carstens <heiko.carstens@...ibm.com>, linux390@...ibm.com
Subject: Re: [PATCH] sched: cpuacct: Use bigger percpu counter batch values
for stats counters
Hi Martin,
> For s390 the jiffies_to_cputime is a compile time constant. No need to
> initialize it at runtime, no?
Indeed it is, I didn't look closely enough. Same with ia64 so no work to
do on either arch :)
> The patch itself trades some accuracy (larger cpu accounting value that
> are stored per-cpu) against runtime overhead (spinlock to transfer the
> value to the global variable in __percpu_counter_add). Did you
> calculate how big the loss in accuracy is?
The idea is we are already batching percpu_counter_batch jiffies, so
with CONFIG_VIRT_CPU_ACCOUNTING we batch the equivalent amount in
cputime.
Anton
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists