From owner-freebsd-current@FreeBSD.ORG Tue Mar 8 21:16:46 2005 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: by hub.freebsd.org (Postfix, from userid 758) id 7065916A4CF; Tue, 8 Mar 2005 21:16:46 +0000 (GMT) Date: Tue, 8 Mar 2005 21:16:46 +0000 From: Kris Kennaway To: Alan Cox Message-ID: <20050308211646.GG30165@hub.freebsd.org> References: <20050308194832.GD30165@hub.freebsd.org> <20050308202451.GC23301@cs.rice.edu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20050308202451.GC23301@cs.rice.edu> User-Agent: Mutt/1.4.2.1i cc: alc@FreeBSD.org cc: Kris Kennaway cc: dg@FreeBSD.org cc: current@FreeBSD.org Subject: Re: SIGABRT under load (tracked to vm_map_find() returning KERN_NO_SPACE) 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: Tue, 08 Mar 2005 21:16:46 -0000 On Tue, Mar 08, 2005 at 02:24:51PM -0600, Alan Cox wrote: > Elsewhere, specifically kern_exec.c, we use kmem_alloc_wait() and > kmem_free_wakeup() to allocate and deallocate exec_map space. These > functions allow for sleeping until virtual address space is > available. Try mechanically converting the vm_map_find() and > vm_map_remove() calls in imgact_elf.c to kmem_alloc_wait() and > kmem_free_wakeup(). I took a quick look but it looks like it'll take more time than I have right now. If someone else can whip up a patch I'll test it, otherwise I'll get back to this later. Kris -- In God we Trust -- all others must submit an X.509 certificate. -- Charles Forsythe