Date: Fri, 15 Sep 2006 11:58:10 -0500
From: Dimitri Sivanich <sivanich@sgi.com>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org, akpm@osdl.org, Andi Kleen <ak@suse.de>
Subject: Re: [PATCH] Migration of standard timers
Message-ID: <20060915165810.GA3832@sgi.com>
References: <20060914132917.GA9898@sgi.com> <1158338360.5724.442.camel@localhost.localdomain>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <1158338360.5724.442.camel@localhost.localdomain>
User-Agent: Mutt/1.5.6i
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 957
Lines: 19

On Fri, Sep 15, 2006 at 06:39:19PM +0200, Thomas Gleixner wrote:
> Are you trying to work around the latencies caused by long running timer
> callbacks ? I'm not convinced that this is not curing the symptoms
> instead of the root cause.

Yes, both latency from long running timer callbacks as well as
potential latency from a temporal grouping of timer callbacks
(those occuring on the same tick).

While I agree that root causes of the former should be addressed,
more latencies of this type can always easily creep in.  Timer
migration works as a long term preventative aid, not just a fix
for the problem of the moment.  And adding this needn't restrict
anyone from looking at the aforementioned root causes.
-
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/