Date: Tue, 11 Nov 2003 11:58:04 -0800
From: Andrew Morton <akpm@osdl.org>
To: Ravikiran G Thirumalai <kiran@in.ibm.com>
Cc: steiner@sgi.com, linux-kernel@vger.kernel.org
Subject: Re: hot cache line due to note_interrupt()
Message-Id: <20031111115804.4aaafd28.akpm@osdl.org>
In-Reply-To: <20031111082915.GC1130@llm08.in.ibm.com>
References: <20031110215844.GC21632@sgi.com>
	<20031111082915.GC1130@llm08.in.ibm.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: 1186
Lines: 28

Ravikiran G Thirumalai <kiran@in.ibm.com> wrote:
>
> On Mon, Nov 10, 2003 at 03:58:44PM -0600, Jack Steiner wrote:
> > 
> > I dont know the background on note_interrupt() in arch/ia64/kernel/irq.c, 
> > but I had to disable the function on our large systems (IA64).
> > 
> > The function updates a counter in the irq_desc_t table. An entry in this table
> > is shared by all cpus that take a specific interrupt #. For most interrupt #'s,
> > this is a problem but it is prohibitive for the timer tick on big systems.
> > 
> > Updating the counter causes a cache line to be bounced between
> > cpus at a rate of at least HZ*active_cpus. (The number of bus transactions
> 
> The answer to this is probably alloc_percpu for the counters.

Or just make noirqdebug the default.

The note_interrupt() stuff is only useful for diagnosing mysterious lockups
(and hasn't proven useful for that, actually).  It should be disabled for
production use.


-
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/