Date: Tue, 9 Jun 2015 10:05:56 +0200 (CEST)
From: Thomas Gleixner <tglx@linutronix.de>
To: George Spelvin <linux@horizon.com>
cc: linux-kernel@vger.kernel.org, peterz@infradead.org,
        viresh.kumar@linaro.org
Subject: Re: [patch 2/7] timer: Remove FIFO guarantee
In-Reply-To: <20150609053930.25020.qmail@ns.horizon.com>
Message-ID: <alpine.DEB.2.11.1506091001020.4133@nanos>
References: <20150609053930.25020.qmail@ns.horizon.com>
User-Agent: Alpine 2.11 (DEB 23 2013-08-11)
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1118
Lines: 36

On Tue, 9 Jun 2015, George Spelvin wrote:
> Thomas Gleixner wrote:
> 
> > After thinking more about it, I'm even more sure that any code which
> > relies on the FIFO "guarantee" is broken today.
> 
> Indeed, I am completely convinced.  All I might request is a reassignment
> of blame in the commit message.

Will do. Thanks for spotting it!
 
> Thank you for your comments on my other blue-sky ideas, too.
> 
> I need to look into why we're using wheels, and what the point is.
> How much of an advantage do they have over an efficient priority queue
> like a pairing heap?

The only reason is performance. The wheel has O(1) insertion and
deletion time while heaps and trees usually have O(log(n)).

Timer wheel timers are usually timeouts and 99% of them are canceled
before expiry. Networking is probably the heaviest use case followed
by disk I/O.

Thanks,

	tglx


--
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/