From owner-cvs-all Tue Dec 4 15:58:52 2001 Delivered-To: cvs-all@freebsd.org Received: from elvis.mu.org (elvis.mu.org [216.33.66.196]) by hub.freebsd.org (Postfix) with ESMTP id 5DF5337B405; Tue, 4 Dec 2001 15:58:38 -0800 (PST) Received: by elvis.mu.org (Postfix, from userid 1192) id F04D581D03; Tue, 4 Dec 2001 17:58:37 -0600 (CST) Date: Tue, 4 Dec 2001 17:58:37 -0600 From: Alfred Perlstein To: Bosko Milekic Cc: Luigi Rizzo , cvs-committers@FreeBSD.org, cvs-all@FreeBSD.org Subject: Re: cvs commit: src/sys/kern uipc_mbuf.c Message-ID: <20011204175837.X92148@elvis.mu.org> References: <200112040213.fB42DBl08877@freefall.freebsd.org> <20011203214418.A87350@technokratis.com> <20011203184737.D48755@iguana.aciri.org> <20011203222303.A2690@technokratis.com> <20011203205623.B49974@iguana.aciri.org> <20011204090509.A8591@technokratis.com> <20011204083922.B54383@iguana.aciri.org> <3C0D14AC.412D674C@dsuper.net> <20011204123627.K92148@elvis.mu.org> <20011204180633.A11305@technokratis.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5i In-Reply-To: <20011204180633.A11305@technokratis.com>; from bmilekic@technokratis.com on Tue, Dec 04, 2001 at 06:06:33PM -0500 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 * Bosko Milekic [011204 17:07] wrote: > > On Tue, Dec 04, 2001 at 12:36:27PM -0600, Alfred Perlstein wrote: > > * Bosko Milekic [011204 12:24] wrote: > > > > > > I hope this clears up the issue... > > > > While I agree with your points I don't see any other clean way of doing > > it other than possibly passing the __FILE__/__FUNCTION__ to mget > > so that i can carp there. > > > > Please let this just go through at least for the time being. > > Alfred, I have NO idea what the heck you're talking about. .) We need some way to inform the users that mbuf allocations are failing. .) Blindly calling printf(9) in the drivers causes the machines to DoS themselves. .) Putting a printf(9) in the mbuf system centralizes this and allows us to rate limit the amount of carping that occurs when mbufs are exhausted in a trivial manner for the time being. --however-- .) It doesn't tell us who is hitting upon the limit. So for now it seems quite acceptable. The reason I brought up __FILE__:__func__ was to suggest it as a possible way to pass information to the mbuf macros in order to be more explanitory about where the error was originating from. I think I would make sense to change the printf to output once or maybe every so often "mbuf utilization at 80% suggest increasing NMBCLUSTERS" rather than waiting for the inevitable explosion when we hit 100%. -- -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.' http://www.morons.org/rants/gpl-harmful.php3 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe cvs-all" in the body of the message