From owner-freebsd-smp Mon Jul 23 15:20:18 2001 Delivered-To: freebsd-smp@freebsd.org Received: from cc-solutions.com (cc-solutions.com [207.159.130.219]) by hub.freebsd.org (Postfix) with ESMTP id 422BB37B408; Mon, 23 Jul 2001 15:20:13 -0700 (PDT) (envelope-from ccs@cc-solutions.com) Received: from ap550 (ComputerSolutions2.dsl.concentric.net [216.112.41.170]) by cc-solutions.com (8.9.3/8.9.3) with ESMTP id SAA09536 From: "C.C.S." Organization: Complete Computer Solutions, Inc. To: "Virus Info" Date: Mon, 23 Jul 2001 18:14:35 -0500 X-Distribution: Moderate MIME-Version: 1.0 Content-type: text/plain; charset=US-ASCII Content-transfer-encoding: 7BIT Subject: IMPORTANT VIRUS INFORMATION! (NOT A HOAX, PLEASE READ) Message-ID: <3B5C698B.9948.1A18D4F@localhost> X-mailer: Pegasus Mail for Win32 (v3.12c) Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org We recently received an email from lfleming@powersourceonline.com that contains the SirCam virus. After doing some research, we found your email address as a possbile recipient. If you also received it, delete it immediately! The virus was discovered only 6 days ago and is spreading rapidly. If you haven't updated your virus protection software since then, it will NOT be detected. The subject and the body of the message are semi-random but always starts with "Hi! How are you?" and ends with "See you later. Thanks." For more information, visit Symantec's AntiVirus Research Center at http://www.symantec.com/avcenter and then click on the SirCam link. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Jul 24 16:36:47 2001 Delivered-To: freebsd-smp@freebsd.org Received: from hotmail.com (f172.law7.hotmail.com [216.33.237.172]) by hub.freebsd.org (Postfix) with ESMTP id 2D72D37B405 for ; Tue, 24 Jul 2001 16:36:43 -0700 (PDT) (envelope-from balaviswanathan@hotmail.com) Received: from mail pickup service by hotmail.com with Microsoft SMTPSVC; Tue, 24 Jul 2001 16:36:42 -0700 Received: from 147.145.40.41 by lw7fd.law7.hotmail.msn.com with HTTP; Tue, 24 Jul 2001 23:36:42 GMT X-Originating-IP: [147.145.40.41] From: "Bala Viswanathan" To: freebsd-smp@freebsd.org Subject: SMP performance Date: Tue, 24 Jul 2001 23:36:42 Mime-Version: 1.0 Content-Type: text/plain; format=flowed Message-ID: X-OriginalArrivalTime: 24 Jul 2001 23:36:42.0996 (UTC) FILETIME=[7E9E9B40:01C11499] Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org I have been trying to get some idea of the status of SMP support in FreeBSD-current especially as far as performance is concerned. I have looked at the FreeBSD SMP Project page, other related links and the archives of the various FreeBSD mailing lists. But have not found any information that appears current. So I ran a synthetic benchmark to measure the performance of a FreeBSD system running a -current kernel (cvsup'ed on July 17th, 2001) as a network file server. The test involves a number of simulated clients connecting over TCP to file server processes running on the FreeBSD systems and reading/writing files. Each client was serviced by a dedicated process and used its own set of files. The client processes were distributed among a bunch of Solaris 2.7 systems that I had available. The system running FreeBSD was a Intel STL2 server system with 2 Pentium 3 cpus. Here is the cpu description output by dmesg: CPU: Pentium III/Pentium III Xeon/Celeron (999.72-MHz 686-class CPU) Based on the results from my tests, the performance of a non-SMP kernel was twice that of a SMP kernel. Is this the expected results given the status of the SMP support in current? If this is expected then does anyone know approximately when one can expect SMP support to improve performance. If not, i.e. results are unexpected, are there any SMP specific tuning parameters that I need to be looking at? Please note that this first mail intentionally lacks in details about my configuration and tests. My intent is to get a feel for the progress of the SMP support in FreeBSD. thanks in advance, Bala _________________________________________________________________ Get your FREE download of MSN Explorer at http://explorer.msn.com/intl.asp To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Jul 24 17: 3: 7 2001 Delivered-To: freebsd-smp@freebsd.org Received: from meow.osd.bsdi.com (meow.osd.bsdi.com [204.216.28.88]) by hub.freebsd.org (Postfix) with ESMTP id 22F9937B406 for ; Tue, 24 Jul 2001 17:03:03 -0700 (PDT) (envelope-from jhb@FreeBSD.org) Received: from laptop.baldwin.cx (john@jhb-laptop.osd.bsdi.com [204.216.28.241]) by meow.osd.bsdi.com (8.11.4/8.11.2) with ESMTP id f6P02rv42894; Tue, 24 Jul 2001 17:02:53 -0700 (PDT) (envelope-from jhb@FreeBSD.org) Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: Date: Tue, 24 Jul 2001 17:02:52 -0700 (PDT) From: John Baldwin To: Bala Viswanathan Subject: RE: SMP performance Cc: freebsd-smp@FreeBSD.org Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 24-Jul-01 Bala Viswanathan wrote: > > I have been trying to get some idea of the status of SMP support > in FreeBSD-current especially as far as performance is concerned. I > have looked at the FreeBSD SMP Project page, other related > links and the archives of the various FreeBSD mailing lists. > But have not found any information that appears current. Right now 95+% (and that's somewhat of a guess, but it should be pretty close) is still under the Giant lock. This effectively means interrupts are blocked out of almost all of the kernel, and is equivalent to running the entire kernel at splhigh() using spl() semantics. This should help explain that the performance is not great right now, nor is it going to be great until subsystems are locked and moved out of Giant. -- John Baldwin -- http://www.FreeBSD.org/~jhb/ PGP Key: http://www.baldwin.cx/~john/pgpkey.asc "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Jul 25 18:49:12 2001 Delivered-To: freebsd-smp@freebsd.org Received: from beppo.feral.com (beppo.feral.com [192.67.166.79]) by hub.freebsd.org (Postfix) with ESMTP id 1EAB437B406 for ; Wed, 25 Jul 2001 18:49:07 -0700 (PDT) (envelope-from mjacob@feral.com) Received: from beppo (mjacob@beppo [192.67.166.79]) by beppo.feral.com (8.11.3/8.11.3) with ESMTP id f6Q1n6I39488 for ; Wed, 25 Jul 2001 18:49:06 -0700 (PDT) (envelope-from mjacob@feral.com) Date: Wed, 25 Jul 2001 18:49:06 -0700 (PDT) From: Matthew Jacob X-Sender: mjacob@beppo Reply-To: mjacob@feral.com To: smp@freebsd.org Subject: kaboom... Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org This is top of tree more or less. I can't get any more info- I had to shut down for a powerdown at NASA/AMes: login: lock order reversal 1st 0xfffffe0008781b88 process lock @ ../../../vm/vm_glue.c:469 2nd 0xfffffe00000d7c00 lockmgr interlock @ ../../../kern/kern_lock.c:239 recursed on non-recursive lock (sleep mutex) process lock @ ../../../kern/kern_lock.c:262 first acquired @ ../../../kern/kern_exit.c:327 panic: recurse cpuid = 8; panic Stopped at Debugger+0x34: zapnot v0,#0xf,a0 db> t Debugger() at Debugger+0x34 panic() at panic+0x178 witness_lock() at witness_lock+0x498 lockmgr() at lockmgr+0x2e8 vm_map_lock_read() at vm_map_lock_read+0x28 vm_map_lookup() at vm_map_lookup+0xa8 vm_fault1() at vm_fault1+0xdc vm_fault() at vm_fault+0xf4 trap() at trap+0x1058 XentMM() at XentMM+0x2c --- memory management fault (from ipl 0) --- exit1() at exit1+0x15e4 sys_exit() at sys_exit+0x24 syscall() at syscall+0x728 XentSys() at XentSys+0x64 --- syscall (1, FreeBSD ELF, sys_exit) --- --- user mode --- db> show locks exclusive (sleep mutex) lockmgr (0xfffffc000077e688) locked @ ../../../kern/kern_lock.c:239 exclusive (sleep mutex) process lock (0xfffffe000877f9c8) locked @ ../../../kern/kern_exit.c:327 exclusive (sx) proctree (0xfffffc00007dcc08) locked @ ../../../kern/kern_exit.c:282 exclusive (sleep mutex) Giant (0xfffffc00007e4af8) locked @ ../../../vm/vm_fault.c:195 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Jul 26 3: 4:17 2001 Delivered-To: freebsd-smp@freebsd.org Received: from mass.dis.org (sat.dis.org [216.240.44.14]) by hub.freebsd.org (Postfix) with ESMTP id 0F2A637B407 for ; Thu, 26 Jul 2001 03:04:04 -0700 (PDT) (envelope-from msmith@mass.dis.org) Received: from mass.dis.org (localhost [127.0.0.1]) by mass.dis.org (8.11.4/8.11.3) with ESMTP id f6ONiT702189; Tue, 24 Jul 2001 16:44:29 -0700 (PDT) (envelope-from msmith@mass.dis.org) Message-Id: <200107242344.f6ONiT702189@mass.dis.org> X-Mailer: exmh version 2.1.1 10/15/1999 To: "Bala Viswanathan" Cc: freebsd-smp@freebsd.org Subject: Re: SMP performance In-reply-to: Your message of "Tue, 24 Jul 2001 23:36:42." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 24 Jul 2001 16:44:29 -0700 From: Mike Smith Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org > Please note that this first mail intentionally lacks in details about > my configuration and tests. My intent is to get a feel for the > progress of the SMP support in FreeBSD. It's rather impolite to publish something like this with "it sucks" teasers without offering enough data for an informed reader to provide you with any sort of useful response. However, to answer the question you profess to be asking, FreeBSD SMP in the 5.x branch is still a work-in-progress, and there are many things which might be responsible for your results. If you're interested in getting involved, then your tests and observations could be very valuable to us. Regards, Mike -- ... every activity meets with opposition, everyone who acts has his rivals and unfortunately opponents also. But not because people want to be opponents, rather because the tasks and relationships force people to take different points of view. [Dr. Fritz Todt] V I C T O R Y N O T V E N G E A N C E To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Jul 26 8: 7:42 2001 Delivered-To: freebsd-smp@freebsd.org Received: from mail5.speakeasy.net (mail5.speakeasy.net [216.254.0.205]) by hub.freebsd.org (Postfix) with SMTP id F2A5C37B403 for ; Thu, 26 Jul 2001 08:07:35 -0700 (PDT) (envelope-from jhb@FreeBSD.org) Received: (qmail 96658 invoked from network); 26 Jul 2001 15:07:34 -0000 Received: from unknown (HELO laptop.baldwin.cx) ([64.81.54.73]) (envelope-sender ) by mail5.speakeasy.net (qmail-ldap-1.03) with SMTP for ; 26 Jul 2001 15:07:34 -0000 Message-ID: X-Mailer: XFMail 1.4.0 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: Date: Thu, 26 Jul 2001 08:07:19 -0700 (PDT) From: John Baldwin To: Matthew Jacob Subject: RE: kaboom... Cc: smp@freebsd.org Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 26-Jul-01 Matthew Jacob wrote: > > This is top of tree more or less. > > I can't get any more info- I had to shut down for a powerdown at NASA/AMes: > > login: lock order reversal > 1st 0xfffffe0008781b88 process lock @ ../../../vm/vm_glue.c:469 > 2nd 0xfffffe00000d7c00 lockmgr interlock @ ../../../kern/kern_lock.c:239 This is quite known. It's where we get a trylock on the vm_map lock. It will go away when we switch to sx locks for those locks. It's kind of due to the way lockmgr() does things. > recursed on non-recursive lock (sleep mutex) process lock @ > ../../../kern/kern_lock.c:262 > first acquired @ ../../../kern/kern_exit.c:327 This is new however. The real problem is something trap'd during exit1(). It would be helpful to see what source line is at exit1+0x15e4. The other issue is that I've no idea why the process lock is being used as the interlock for a vm_map lock. > panic: recurse > cpuid = 8; panic > Stopped at Debugger+0x34: zapnot v0,#0xf,a0 > db> t > Debugger() at Debugger+0x34 > panic() at panic+0x178 > witness_lock() at witness_lock+0x498 > lockmgr() at lockmgr+0x2e8 > vm_map_lock_read() at vm_map_lock_read+0x28 > vm_map_lookup() at vm_map_lookup+0xa8 > vm_fault1() at vm_fault1+0xdc > vm_fault() at vm_fault+0xf4 > trap() at trap+0x1058 > XentMM() at XentMM+0x2c > --- memory management fault (from ipl 0) --- > exit1() at exit1+0x15e4 > sys_exit() at sys_exit+0x24 > syscall() at syscall+0x728 > XentSys() at XentSys+0x64 > --- syscall (1, FreeBSD ELF, sys_exit) --- > --- user mode --- > db> show locks > exclusive (sleep mutex) lockmgr (0xfffffc000077e688) locked @ > ../../../kern/kern_lock.c:239 > exclusive (sleep mutex) process lock (0xfffffe000877f9c8) locked @ > ../../../kern/kern_exit.c:327 > exclusive (sx) proctree (0xfffffc00007dcc08) locked @ > ../../../kern/kern_exit.c:282 > exclusive (sleep mutex) Giant (0xfffffc00007e4af8) locked @ > ../../../vm/vm_fault.c:195 -- John Baldwin -- http://www.FreeBSD.org/~jhb/ PGP Key: http://www.baldwin.cx/~john/pgpkey.asc "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Jul 26 15:39:37 2001 Delivered-To: freebsd-smp@freebsd.org Received: from mail.gmx.net (pop.gmx.net [194.221.183.20]) by hub.freebsd.org (Postfix) with SMTP id F1C7137B406 for ; Thu, 26 Jul 2001 15:39:30 -0700 (PDT) (envelope-from tmoestl@gmx.net) Received: (qmail 3680 invoked by uid 0); 26 Jul 2001 22:39:29 -0000 Received: from p3e9bc056.dip.t-dialin.net (HELO forge.local) (62.155.192.86) by mail.gmx.net (mail08) with SMTP; 26 Jul 2001 22:39:29 -0000 Received: from tmm by forge.local with local (Exim 3.30 #1) id 15Ptmz-000JSG-00; Fri, 27 Jul 2001 00:39:29 +0200 Date: Fri, 27 Jul 2001 00:39:29 +0200 From: Thomas Moestl To: freebsd-stable@FreeBSD.org, freebsd-smp@FreeBSD.org Cc: Ian Dowse Subject: Please test: -stable SMP locking fix Message-ID: <20010727003929.B73365@crow.dom2ip.de> Mail-Followup-To: freebsd-stable@FreeBSD.org, freebsd-smp@FreeBSD.org, Ian Dowse Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="lrZ03NoBR/3+SXJZ" Content-Disposition: inline User-Agent: Mutt/1.2.5i Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org --lrZ03NoBR/3+SXJZ Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Hi, I have attached a patch that should fix some panics (caused by sleeping with a lock held) and lock-order reversals on -stable SMP systems. These usually only seem to occur when using NFS. I'd like to commit this fix before 4.4 is released (if I can make it). Due to locking changes, this will need to be solved differently on -current, so it will need to be directly committed to -stable. Therefore, to anybody who uses stable on an SMP box (and dares ;): please, please test this, and report back any problems! If you do, please drop me a private mail so that I get an idea about the test coverage that it got. The risk should be relatively low (this removes a lock/unlock pair, but all relevant code should also be protected by the mp_lock). On UP machines, this patch does not change anything at all. - thomas --lrZ03NoBR/3+SXJZ Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="vinval.diff" Index: vfs_subr.c =================================================================== RCS file: /home/ncvs/src/sys/kern/vfs_subr.c,v retrieving revision 1.249.2.9 diff -u -r1.249.2.9 vfs_subr.c --- vfs_subr.c 2001/06/26 04:20:08 1.249.2.9 +++ vfs_subr.c 2001/07/25 21:35:01 @@ -730,12 +730,10 @@ /* * Destroy the copy in the VM cache, too. */ - simple_lock(&vp->v_interlock); if (VOP_GETVOBJECT(vp, &object) == 0) { vm_object_page_remove(object, 0, 0, (flags & V_SAVE) ? TRUE : FALSE); } - simple_unlock(&vp->v_interlock); if (!TAILQ_EMPTY(&vp->v_dirtyblkhd) || !TAILQ_EMPTY(&vp->v_cleanblkhd)) panic("vinvalbuf: flush failed"); --lrZ03NoBR/3+SXJZ-- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Fri Jul 27 10:34:41 2001 Delivered-To: freebsd-smp@freebsd.org Received: from bdr-xcon.matchlogic.com (mail.matchlogic.com [205.216.147.127]) by hub.freebsd.org (Postfix) with ESMTP id 9141B37B403 for ; Fri, 27 Jul 2001 10:34:38 -0700 (PDT) (envelope-from crandall@matchlogic.com) Received: by mail.matchlogic.com with Internet Mail Service (5.5.2653.19) id ; Fri, 27 Jul 2001 11:34:28 -0600 Message-ID: <5FE9B713CCCDD311A03400508B8B30130828F1C2@bdr-xcln.corp.matchlogic.com> From: Charles Randall To: "smp@freebsd.org" Subject: RE: Dell 1550 SMP crash Date: Fri, 27 Jul 2001 11:32:33 -0600 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.2653.19) Content-Type: text/plain; charset="iso-8859-1" Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org This may be hard to believe, but there's no panic message that I can see (I've connected the serial console and disabled logins on that tty so that just console messages go there). I just got this stack trace which may be the same or a different problem. I was running a large sort using /usr/bin/sort to generate I/O load. mp_lock = 01000002; cpuid = 1; lapic.id = 00000000 instruction pointer = 0x8:0xc030eeb8 stack pointer = 0x10:0xf7b5fcec frame pointer = 0x10:0xf7b5fcec code segment = base 0x0, limit 0xfffff, type 0x1b = DPL 0, pres 1, def32 1, gran 1 processor eflags = interrupt enabled, IOPL = 0 current process = 52601 (sort) interrupt mask = none <- SMP: XXX kernel: type 29 trap, code=0 Stopped at apic_ipi+0x50: testb $0x10,%ah db> trace apic_ipi(c0000,90,0,f7b5fd08,c030e0de) at apic_ipi+0x50 smp_invltlb(f7b5fd20,c030fc16,e1508000,d1c18d30,d1aa8770) at smp_invltlb+0x2f invlpg(e1508000) at invlpg+0xe pmap_qenter(e1502000,d1aa8828,10) at pmap_qenter+0x4e cluster_wbuild(f7aca380,2000,10,8,f7aca380) at cluster_wbuild+0x46b cluster_write(d1c18d30,20000,0,11) at cluster_write+0x33a ffs_write(f7b5fe68,f7b11d80,f7b11d80,2000,1) at ffs_write+0x472 vn_write(c60e27c0,f7b5fed8,c569d880,0,f7b11d80) at vn_write+0x148 dofilewrite(f7b11d80,c60e27c0,13,80e6000,2000) at dofilewrite+0xb1 write(f7b11d80,f7b5ff80,280e9628,280fba40,80e6000) at write+0x33 syscall2(80e002f,280f002f,bfbf002f,80e6000,280fba40) at syscall2+0x219 Xint0x80_syscall() at Xint0x80_syscall+0x2b Any clues? -Charles To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sat Jul 28 7:57:14 2001 Delivered-To: freebsd-smp@freebsd.org Received: from absinthe.carnagecopia.com (absinthe.carnagecopia.com [216.18.9.200]) by hub.freebsd.org (Postfix) with SMTP id EDE6037B408 for ; Sat, 28 Jul 2001 07:57:09 -0700 (PDT) (envelope-from random@carnagecopia.com) Received: (qmail 78382 invoked from network); 28 Jul 2001 14:57:08 -0000 Received: from firewall-vancouver.carnagecopia.com (HELO axiontwist.carnagecopia.com) (66.38.134.97) by absinthe.carnagecopia.com with SMTP; 28 Jul 2001 14:57:08 -0000 Date: Sat, 28 Jul 2001 07:55:53 -0700 From: Vincent Janelle To: freebsd-smp@freebsd.org Subject: install on a quad xeon, 4GB of ram, 4.3-STABLE Message-Id: <20010728075553.49d57063.random@carnagecopia.com> Organization: Goblin Studios X-Mailer: Sylpheed version 0.5.0 (GTK+ 1.2.10; i686-pc-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org I can't seem to get the kernel to boot up on a machine with 4GB of ram.. On bootup, it panics with: panic: swap_pager_swap_init: swap_zone=NULL I took the drives out and plugged it into another machine, modified NKGPT to be 64. Any clues? To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message