From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stephen Hemminger Subject: Re: [PATCH] Bound TSO defer time (resend) Date: Wed, 18 Oct 2006 09:40:23 -0700 Message-ID: <20061018094023.1be31440@freekitty> References: <20061016202035.6d55b96e@localhost.localdomain> <45345999.4000300@psc.edu> <200610181737.36135.ak@suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: John Heffner , netdev@vger.kernel.org Return-path: Received: from smtp.osdl.org ([65.172.181.4]:25540 "EHLO smtp.osdl.org") by vger.kernel.org with ESMTP id S1422675AbWJRQkm (ORCPT ); Wed, 18 Oct 2006 12:40:42 -0400 To: Andi Kleen In-Reply-To: <200610181737.36135.ak@suse.de> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Wed, 18 Oct 2006 17:37:36 +0200 Andi Kleen wrote: > On Tuesday 17 October 2006 06:18, John Heffner wrote: > > Stephen Hemminger wrote: > > > On Mon, 16 Oct 2006 20:53:20 -0400 (EDT) > > > John Heffner wrote: > > > > >> This patch limits the amount of time you will defer sending a TSO segment > > >> to less than two clock ticks, or the time between two acks, whichever is > > >> longer. > > > > > > > > Okay, but doing any timing on clock ticks makes the behavior dependent > > > on the value of HZ which doesn't seem desirable. Should this be based > > > on RTT or a real-time values? > > > > It would be nice to use a high res clock so you don't depend on HZ, but > > this is still expensive on most SMP arch's as I understand it. > > You can always use xtime. It doesn't have better solution than jiffies > though, but it gives you real time. > > Drawback is that there is some work towards tickless kernels and with > that xtime will be more expensive again. But hopefully not by that much. > > -Andi Actually the thing to use now is ktime. It would then be compatiable with hrtimers. But it seems a bit of overkill in this case. -- Stephen Hemminger