From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from sc8-sf-mx2-b.sourceforge.net ([10.3.1.12] helo=sc8-sf-mx2.sourceforge.net) by sc8-sf-list1.sourceforge.net with esmtp (Exim 4.30) id 1DEHVY-0006ge-DE for user-mode-linux-devel@lists.sourceforge.net; Wed, 23 Mar 2005 17:51:36 -0800 Received: from smtp005.mail.ukl.yahoo.com ([217.12.11.36]) by sc8-sf-mx2.sourceforge.net with smtp (Exim 4.41) id 1DEHVT-00067d-Ft for user-mode-linux-devel@lists.sourceforge.net; Wed, 23 Mar 2005 17:51:36 -0800 From: Blaisorblade Subject: Re: [uml-devel] [patch 02/12] uml: cpu_relax fix References: <20050322162121.4295D2125C@zion> <4241A2C0.2050206@fujitsu-siemens.com> In-Reply-To: <4241A2C0.2050206@fujitsu-siemens.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200503240250.38153.blaisorblade@yahoo.it> Sender: user-mode-linux-devel-admin@lists.sourceforge.net Errors-To: user-mode-linux-devel-admin@lists.sourceforge.net List-Unsubscribe: , List-Id: The user-mode Linux development list List-Post: List-Help: List-Subscribe: , List-Archive: Date: Thu, 24 Mar 2005 02:50:37 +0100 To: user-mode-linux-devel@lists.sourceforge.net Cc: Bodo Stroesser , akpm@osdl.org, jdike@addtoit.com, linux-kernel@vger.kernel.org On Wednesday 23 March 2005 18:09, Bodo Stroesser wrote: > blaisorblade@yahoo.it wrote: > > Use rep_nop instead of barrier for cpu_relax, following $(SUBARCH)'s > > doing that (i.e. i386 and x86_64). > > IIRC, Jeff had the idea, to use sched_yield() for this (from a discussion > on #uml). Hmm, makes sense, but this is to benchmark well... I remember from early discussions on 2.6 scheduler that using sched_yield might decrease performance (IIRC starve the calling application). Also, that call should be put inside the idle loop, not for cpu_relax, which is very different, since it is used (for instance) in kernel/spinlock.c for spinlocks, and in such things. The "Pause" opcode is explicitly recommended (by Intel manuals, I don't recall why) for things like spinlock loops, and using yield there would be bad. > S390 does something similar using a special DIAG-opcode that > gives permission to zVM, that another Guest might run. > On a host running many UMLs, this might improve performance. > > So, I would like to have the small patch below (it's not tested, just an > idea). -- Paolo Giarrusso, aka Blaisorblade Linux registered user n. 292729 http://www.user-mode-linux.org/~blaisorblade ------------------------------------------------------- This SF.net email is sponsored by Microsoft Mobile & Embedded DevCon 2005 Attend MEDC 2005 May 9-12 in Vegas. Learn more about the latest Windows Embedded(r) & Windows Mobile(tm) platforms, applications & content. Register by 3/29 & save $300 http://ads.osdn.com/?ad_id=6883&alloc_id=15149&op=click _______________________________________________ User-mode-linux-devel mailing list User-mode-linux-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/user-mode-linux-devel