From owner-cvs-all Fri Jul 12 17: 9: 9 2002 Delivered-To: cvs-all@freebsd.org Received: from mx1.FreeBSD.org (mx1.FreeBSD.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 59AC637B400; Fri, 12 Jul 2002 17:09:01 -0700 (PDT) Received: from elvis.mu.org (elvis.mu.org [192.203.228.196]) by mx1.FreeBSD.org (Postfix) with ESMTP id 15B4443E3B; Fri, 12 Jul 2002 17:09:01 -0700 (PDT) (envelope-from bright@elvis.mu.org) Received: by elvis.mu.org (Postfix, from userid 1192) id BBEAAAE1EE; Fri, 12 Jul 2002 16:37:25 -0700 (PDT) Date: Fri, 12 Jul 2002 16:37:25 -0700 From: Alfred Perlstein To: Matthew Dillon Cc: Alan Cox , cvs-committers@FreeBSD.ORG, cvs-all@FreeBSD.ORG Subject: Re: cvs commit: src/sys/kern kern_synch.c src/sys/sys proc.h src/sys/vm vm_zeroidle.c src/sys/i386/i386 genassym.c pmap.c Message-ID: <20020712233725.GQ97638@elvis.mu.org> References: <200207122017.g6CKH7fx096339@freefall.freebsd.org> <20020712205516.GD5265@cs.rice.edu> <200207122221.g6CMLZwi063791@apollo.backplane.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <200207122221.g6CMLZwi063791@apollo.backplane.com> User-Agent: Mutt/1.3.27i Sender: owner-cvs-all@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG * Matthew Dillon [020712 15:48] wrote: > > :I think we should try to take this a step further. Specifically, we > :should recognize when processors are running in user mode in order > :to avoid IPIs on kernel pmap changes. On reentry to the kernel, > :the processor would then do whatever is necessary to resync. If > :too many kernel pmap changes accumulate, then you force a single > :IPI that performs the changes in bulk. > : > :As a start, it would be interesting to know how many IPIs could be > :avoided by such a scheme. > : > :Alan > > We need to run statistics to see where the IPIs are coming from. > A deferral mechanism is only going to be more efficient if its > simple and it might be better to instead just knock down the > subsystems responsible for the majority of IPIs within the > subsystem itself. I'm quite sure Alan's method is described in Vahalia's(sp?) book as an optimization the SVR4.2 (the SVR with mp) took that helped quite a bit. -- -Alfred Perlstein [alfred@freebsd.org] 'Instead of asking why a piece of software is using "1970s technology," start asking why software is ignoring 30 years of accumulated wisdom.' Tax deductible donations for FreeBSD: http://www.freebsdfoundation.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe cvs-all" in the body of the message