[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAFTL4hxe8Rwj7sqo0G_xPisvXB_tMhVSdD+z32aQnJM9A=31WQ@mail.gmail.com>
Date: Sat, 27 Apr 2013 01:01:30 +0200
From: Frederic Weisbecker <fweisbec@...il.com>
To: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
Ingo Molnar <mingo@...nel.org>
Cc: LKML <linux-kernel@...r.kernel.org>,
Christoph Lameter <cl@...ux.com>,
Hakan Akkan <hakanakkan@...il.com>,
Kevin Hilman <khilman@...aro.org>,
Li Zhong <zhong@...ux.vnet.ibm.com>,
Paul Gortmaker <paul.gortmaker@...driver.com>,
Peter Zijlstra <peterz@...radead.org>,
Steven Rostedt <rostedt@...dmis.org>,
Thomas Gleixner <tglx@...utronix.de>
Subject: Re: [PATCH 1/2] nohz: Select VIRT_CPU_ACCOUNTING_GEN from full
dynticks config
2013/4/26 Frederic Weisbecker <fweisbec@...il.com>:
> On Fri, Apr 26, 2013 at 08:39:56AM -0700, Paul E. McKenney wrote:
>> > config VIRT_CPU_ACCOUNTING_GEN
>> > bool "Full dynticks CPU time accounting"
>> > - depends on HAVE_CONTEXT_TRACKING && 64BIT
>> > + depends on HAVE_CONTEXT_TRACKING && 64BIT && NO_HZ_FULL
>>
>> Do you really want this change? This prohibits VIRT_CPU_ACCOUNTING_GEN
>> unless NO_HZ_FULL, which means that it can no longer be used in situations
>> where it used to be usable. My guess is that you want to leave this
>> particular line as it was.
>
> Hmm, this can make sense. This can be used to perform comparisons between
> tick-based and tickless cputime accounting easily.
>
> I'll respin.
So Ingo please pull "timers/nohz-v2" instead. It does the same but
keeps VIRT_CPU_ACCOUNTING_GEN available even without full dynticks
(could be useful when users need something more precise than tick
based cputime accounting.)
HEAD is 8c23b80ec7f1f5405f07bb56c2f8378800ecf401
If you've already pulled the previous branch I'll make a delta instead.
Thanks.
--
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