Date: Mon, 13 Sep 2004 22:05:21 -0700
From: Andrew Morton <akpm@osdl.org>
To: William Lee Irwin III <wli@holomorphy.com>
Cc: raybry@sgi.com, jbarnes@engr.sgi.com, linux-kernel@vger.kernel.org
Subject: Re: [profile] amortize atomic hit count increments
Message-Id: <20040913220521.03d0e539.akpm@osdl.org>
In-Reply-To: <20040914044748.GZ9106@holomorphy.com>
References: <20040913015003.5406abae.akpm@osdl.org>
	<20040914044748.GZ9106@holomorphy.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1149
Lines: 26

William Lee Irwin III <wli@holomorphy.com> wrote:
>
> read_proc_profile()
>  does not flush the per-cpu hashtables because flushing may cause
>  timeslice overrun on the systems where prof_buffer cacheline bounces
>  are so problematic as to livelock the timer interrupt.

That's a bit of a problem, isn't it?  As we can accumulate an arbitrarily
large number of hits within the hash table is it not possible that the
/proc/profile results could be grossly inaccurate?

If you had two front-ends per cpu to the profiling buffer then the CPU
which is running the /proc/profile read could tell all the other CPUs to
flip to their alternate buffer and can then perform accumulation at its
leisure.

How does oprofile get around this?  I guess in most modes the CPUs are not
synchronised.

One wonders how long we should keep flogging the /prof/profile profiling
code.  What systems are seeing this livelock?
-
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/