From owner-freebsd-questions@FreeBSD.ORG Sun Aug 1 16:11:14 2004 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B943416A4CE; Sun, 1 Aug 2004 16:11:14 +0000 (GMT) Received: from mail.revolutionsp.com (ganymede.revolutionsp.com [64.246.0.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id 67A8843D2D; Sun, 1 Aug 2004 16:11:14 +0000 (GMT) (envelope-from klr@6s-gaming.com) Received: from mail.revolutionsp.com (localhost [127.0.0.1]) by mail.revolutionsp.com (Postfix) with ESMTP id AE4D215C95; Sun, 1 Aug 2004 13:08:56 +0000 (GMT) Received: from 81.84.175.12 (SquirrelMail authenticated user klr@6s-gaming.com); by mail.revolutionsp.com with HTTP; Sun, 1 Aug 2004 13:08:56 -0000 (GMT) Message-ID: <50335.81.84.175.12.1091365736.squirrel@81.84.175.12> Date: Sun, 1 Aug 2004 13:08:56 -0000 (GMT) From: "Hugo Silva" To: freebsd-smp@freebsd.org, freebsd-questions@FreeBSD.org User-Agent: SquirrelMail/1.4.3a X-Mailer: SquirrelMail/1.4.3a MIME-Version: 1.0 Content-Type: text/plain;charset=iso-8859-1 Content-Transfer-Encoding: 8bit X-Priority: 3 (Normal) Importance: Normal Subject: FreeBSD 5.2.1 kernel w/ SMP under high load = panic X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 01 Aug 2004 16:11:14 -0000 I am running a Dual Xeon 2.8ghz w/ SMP, SCHED_ULE on FreeBSD 5.2.1-RELEASE-p9. Whenever I load the server a bit more (let seti@home run, compile stuff in multiple jails, etc), it will simple go offline. I confirmed with the datacenter and it is indeed a panic, but the datacenter didn't give me the panic message. I know for *sure* it's because of the high loads. I need to sort this out, this is a powerful server being cut because of FreeBSD/SMP, and I know there is a kernel option to prevent the panic, I read about it ages ago on a forum. But I can't locate it. That user said if he disabled SMP, panics would stop. But another user suggested adding a kernel option (which I simply don't remember), and panics stopped, even with SMP. I tried KVA_PAGES=512, but it only caused another panic, this time as soon as the system started up.. syncing disks, buffers remaining... panic: pmap_invalidate_range: interrupts disabled cpuid = 0; boot() called on cpu#0 uptime: 9s That was the most I got from the datacenter since the sysadmin is on vacations and the guy I spoke to isn't very technical. So, KVA_PAGES isn't the solution.. Here are my rc.conf & sysctl.conf & loader.conf: rc.conf: sshd_enable="YES" usbd_enable="YES" sendmail_enable="NONE" syslogd_enable="YES" syslogd_flags="-ss" linux_enable="YES" inetd_enable="NO" clear_tmp_enable="YES" enable_quotas="YES" check_quotas="YES" update_motd="NO" pf_enable="YES" pf_logd="YES" pf_conf="/etc/pf.conf" sysctl.conf: security.bsd.see_other_uids=0 net.inet.tcp.recvspace=32768 net.inet.tcp.sendspace=32768 net.inet.icmp.drop_redirect=1 net.inet.tcp.blackhole=2 net.inet.udp.blackhole=2 net.inet.tcp.log_in_vain=0 net.inet.udp.log_in_vain=0 kern.maxfiles=32768 security.jail.set_hostname_allowed=0 kern.maxfilesperproc=2000 kern.maxprocperuid=400 kern.coredump=0 net.inet.tcp.msl=7500 kern.ipc.somaxconn=16424 loader.conf: hint.acpi.0.disabled=1 kern.ipc.nmbclusters=32768 kern.ipc.maxsockets=16424 kern.maxproc=8000 These are my custom kernel options: options IPSTEALTH options QUOTA options RANDOM_IP_ID options SC_DISABLE_REBOOT Any help is really appreciated, I have this server idling (compile lots of stuff=die) for 2 weeks now :/ Regards