From owner-freebsd-bugs Wed Jul 10 18:33:22 1996 Return-Path: owner-bugs Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id SAA04160 for bugs-outgoing; Wed, 10 Jul 1996 18:33:22 -0700 (PDT) Received: from root.com (implode.root.com [198.145.90.17]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id SAA04152 for ; Wed, 10 Jul 1996 18:33:17 -0700 (PDT) Received: from localhost (localhost [127.0.0.1]) by root.com (8.7.5/8.6.5) with SMTP id SAA05738; Wed, 10 Jul 1996 18:33:07 -0700 (PDT) Message-Id: <199607110133.SAA05738@root.com> X-Authentication-Warning: implode.root.com: Host localhost [127.0.0.1] didn't use HELO protocol To: Sujal Patel cc: freebsd-bugs@freebsd.org Subject: Re: out of mbuf clusters In-reply-to: Your message of "Wed, 10 Jul 1996 13:34:59 EDT." From: David Greenman Reply-To: davidg@root.com Date: Wed, 10 Jul 1996 18:33:06 -0700 Sender: owner-bugs@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >After you run out of mbuf clusters, the entires system beings swapping >very hard (until rebooted). I know this would normally panic the system >(and it's nice that it doesn't), but is there a memory leak in the >handler for this situation? Mbuf clusters are never freed back to the global free memory pool. If your machine doesn't have much memory and the number of clusters that get allocated is large, then there won't be much left for user processes and the machine will thrash or worse. You have to have the memory resources if you want to handle high networking loads. -DG David Greenman Core-team/Principal Architect, The FreeBSD Project