From owner-freebsd-current@FreeBSD.ORG Wed Jun 2 07:17:13 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 17E4A16A4D0 for ; Wed, 2 Jun 2004 07:17:13 -0700 (PDT) Received: from freefall.freebsd.org (freefall.freebsd.org [216.136.204.21]) by mx1.FreeBSD.org (Postfix) with ESMTP id 099E943D4C; Wed, 2 Jun 2004 07:17:13 -0700 (PDT) (envelope-from bmilekic@FreeBSD.org) Received: from freefall.freebsd.org (bmilekic@localhost [127.0.0.1]) i52EHCFY037312; Wed, 2 Jun 2004 07:17:12 -0700 (PDT) (envelope-from bmilekic@freefall.freebsd.org) Received: (from bmilekic@localhost) by freefall.freebsd.org (8.12.11/8.12.11/Submit) id i52EHCCN037311; Wed, 2 Jun 2004 07:17:12 -0700 (PDT) (envelope-from bmilekic) Date: Wed, 2 Jun 2004 07:17:12 -0700 From: Bosko Milekic To: Frode Nordahl Message-ID: <20040602141712.GB33162@freefall.freebsd.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.4.1i cc: freebsd-current@freebsd.org Subject: Re: [HEADS-UP] mbuma is in the tree 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, 02 Jun 2004 14:17:13 -0000 >>Additional things worth noting/known issues (READ): > >[snip] > >> - Giant leak in NFS code sometimes occurs, can't >> reproduce but currently analyzing; brueffer is >> able to reproduce but THIS IS NOT an mbuma-specific >> problem and currently occurs even WITHOUT mbuma. > >Just a mee too on this one. > >I'm running two NFS servers on 5.2.1-RELEASE (with the old mbuf code >obviously), and I see the problem with leakage here. Don't know a way >to reproduce it yet, but it happends over time. This happends both on a >UP and a SMP machine. I'm afraid you misunderstood what I meant by "Giant leak." :-) I was referring to a potential leak of the Giant _lock_, not a leak of Mbufs and Clusters. But what you are seeing seems to very much be an Mbuf leak, at least, and should be investigated. Please cvsup to -CURRENT (follow the -current mailing list to figure out when it should be reasonably safe to do so) and verify whether this problem has been fixed, as it is posssible that it already has. If not, collect as most data as possible and get back to me. -Bosko