From owner-freebsd-current@FreeBSD.ORG Fri Jun 13 11:46:30 2003 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 8968A37B401 for ; Fri, 13 Jun 2003 11:46:30 -0700 (PDT) Received: from mail.chesapeake.net (chesapeake.net [208.142.252.6]) by mx1.FreeBSD.org (Postfix) with ESMTP id 69EC043FD7 for ; Fri, 13 Jun 2003 11:46:29 -0700 (PDT) (envelope-from jroberson@chesapeake.net) Received: from localhost (jroberson@localhost) by mail.chesapeake.net (8.11.6/8.11.6) with ESMTP id h5DIk9590551; Fri, 13 Jun 2003 14:46:09 -0400 (EDT) (envelope-from jroberson@chesapeake.net) Date: Fri, 13 Jun 2003 14:46:09 -0400 (EDT) From: Jeff Roberson To: Terry Lambert In-Reply-To: <3EEA04BD.9E06ED0@mindspring.com> Message-ID: <20030613144256.D36168-100000@mail.chesapeake.net> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII cc: John Hay cc: current@freebsd.org Subject: Re: panic: kmem_map too small: the downside of FreeBSD 5 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: Fri, 13 Jun 2003 18:46:30 -0000 On Fri, 13 Jun 2003, Terry Lambert wrote: > John Hay wrote: > > On a 5.1-RELEASE machine I have been able to cause a panic like this: > > panic: kmem_malloc(4096): kmem_map too small: 28610560 total allocated > > Manually tune your system. This panic results from the fact > that zone allocations with fixed limits don't really do the > right thing any more, now that it's possible to implement the > map entry allocations at interrupt. This is FUD. > the deprecation of the zalloci() interface that accompanied it, > an audit should have been done of the system to go through all > previous places zalloci() was used, and make them robust in case > of a NULL return value (allocation failure), since those places > were effectively promised by zalloci() that allocations would > never fail for this reason. > They would fail before. This is FUD. More FUD was deleted. 5.0 simply consumes more memory than 4.x. Unfortunately even with kernel memory taking up 1/3rd of your resources we are not able to satisfy all requests. Some tuning of various memory consumers would be required to get this back down. I think this is a worthwhile effort as we should be able to run on a 32mb system still. Please note that I'm about to get on a plane and I will probably not reply to this message. Thanks, Jeff