From owner-freebsd-current@FreeBSD.ORG Wed Aug 18 09:07:42 2004 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 313BC16A4CE for ; Wed, 18 Aug 2004 09:07:42 +0000 (GMT) Received: from ptcnat.era.pl (ptcnat.era.pl [213.158.197.100]) by mx1.FreeBSD.org (Postfix) with ESMTP id A2D2543D6E for ; Wed, 18 Aug 2004 09:07:41 +0000 (GMT) (envelope-from zaks@era.pl) Received: by localhost (Postfix, from userid 1001) id 92F43117C9; Wed, 18 Aug 2004 11:07:39 +0200 (CEST) To: Julian Elischer From: =?iso-8859-2?q?S=B3awek_=AFak?= References: <20040813121208.M31181@cvs.imp.ch> <86y8kfqcp8.fsf@thirst.unx.era.pl> <41223C15.7050305@elischer.org> Date: Wed, 18 Aug 2004 11:07:39 +0200 In-Reply-To: <41223C15.7050305@elischer.org> (Julian Elischer's message of "Tue, 17 Aug 2004 10:10:45 -0700") Message-ID: <863c2kolus.fsf@thirst.unx.era.pl> User-Agent: Gnus/5.110003 (No Gnus v0.3) XEmacs/21.4 (Reasonable Discussion, berkeley-unix) MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-2 Content-Transfer-Encoding: 8bit cc: freebsd-current@freebsd.org Subject: Re: Deadlocks with recent SMP current X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 18 Aug 2004 09:07:42 -0000 Julian Elischer writes: > Sławek Żak wrote: [...] >> MySQLd is running with libpthread and can go up to 400% without >> significantly afecting the idle percentage shown by top. I don't see how I >> could fit 400% into 20% on those two suckers, therefore I ask :) > > Cpu percentage use is broken for pthread applications.. > it's almost impossible to work out the right way of doing it > due to the nature of M:N threading where there is no fixed rule as > to which user thread is run by which kernel thread. > > I have ideas but it will probably have to be an aggreagate cpu% for the thread > group, divided by the number of kernel threads in the group. Well. Better this than the current sorry, saying nothing number :) /S -- Sławek Żak : UNIX Systems Administrator : PTC Sp. zoo