Subject: Re: register_timer_hook use in arch/sh/oprofile
From: Peter Zijlstra <peterz@infradead.org>
To: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mundt <lethal@linux-sh.org>,
       Martin Schwidefsky <schwidefsky@de.ibm.com>,
       linux-kernel <linux-kernel@vger.kernel.org>
In-Reply-To: <20090626072350.GI14078@elte.hu>
References: <20090624131104.705c828d@skybase>
	 <20090624112929.GB2079@linux-sh.org> <20090624142828.7c6a2337@skybase>
	 <20090624123416.GB9510@linux-sh.org> <20090624124542.GB32306@elte.hu>
	 <20090624131440.GA9700@linux-sh.org> <20090624132447.GD6224@elte.hu>
	 <1245999685.31755.157.camel@twins>  <20090626072350.GI14078@elte.hu>
Content-Type: text/plain
Content-Transfer-Encoding: 7bit
Date: Fri, 26 Jun 2009 09:36:32 +0200
Message-Id: <1246001792.31755.176.camel@twins>
Mime-Version: 1.0
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1087
Lines: 28

On Fri, 2009-06-26 at 09:23 +0200, Ingo Molnar wrote:
> * Peter Zijlstra <peterz@infradead.org> wrote:
> 
> > On Wed, 2009-06-24 at 15:24 +0200, Ingo Molnar wrote:
> > > 
> > > [ And long-term analysis ('perf stat' type of runs) dont need IRQs 
> > >   anyway - perfcounters reads outs the counts and summarizes them 
> > >   across the measured workload. ]
> > 
> > If the counter width is less than 64 bits we do need to have some 
> > interrupt to read them from before they cycle so we can accumulate 
> > the deltas into a proper u64.
> 
> Yeah - but even that can be driven from some housekeeping hrtimer.

Oh absolutely, but its one of those things one should not forget to do.

> > But for proper 64 bit hardware counters there is indeed no need 
> > for that.
> 
> Indeed - although they are rare.

Paul Mundt mentioned he had some.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/