From owner-freebsd-smp Mon Aug 14 14:30:56 2000 Delivered-To: freebsd-smp@freebsd.org Received: from backdraft.gmx.com (backdraft.gmxinc.net [199.165.179.2]) by hub.freebsd.org (Postfix) with ESMTP id A6D4C37B601 for ; Mon, 14 Aug 2000 14:30:50 -0700 (PDT) (envelope-from kevind@ikadega.com) Received: (from fwtk@localhost) by backdraft.gmx.com (8.7.4/8.7.3) id QAA06750 for ; Mon, 14 Aug 2000 16:06:09 -0500 (CDT) X-Authentication-Warning: backdraft.gmx.com: fwtk set sender to using -f Received: from ilpostino.gmx.com(88.0.0.230) by backdraft.gmx.com via smap (V1.3) id sma006730; Mon Aug 14 16:05:19 2000 Received: from ikadega.com ([88.0.0.115]) by ilpostino.gmx.com (8.8.5/8.8.5) with ESMTP id QAA07903 for ; Mon, 14 Aug 2000 16:12:07 -0500 (CDT) Message-ID: <39986529.30890E36@ikadega.com> Date: Mon, 14 Aug 2000 16:31:21 -0500 From: Kevin Day X-Mailer: Mozilla 4.74 [en] (X11; U; Linux 2.2.12 i386) X-Accept-Language: en MIME-Version: 1.0 To: freebsd-smp@freebsd.org Subject: SMP on Compaq Proliant ML530 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org I've got a dual proc Compaq Proliant ML530 (933 PIII Xeon) server that seems to be having trouble with SMP. Everything actually works as far as I can tell, but some things look a little scary. From mptable: =============================================================================== MPTable, version 2.0.15 ------------------------------------------------------------------------------- MP Floating Pointer Structure: location: BIOS physical address: 0x000f4ff0 signature: '_MP_' length: 16 bytes version: 1.4 checksum: 0xc1 mode: Virtual Wire ------------------------------------------------------------------------------- MP Config Table Header: physical address: 0x000f28a8 signature: 'PCMP' base table length: 268 version: 1.4 checksum: 0x99 OEM ID: 'COMPAQ ' Product ID: 'PROLIANT ' OEM table pointer: 0x00000000 OEM table size: 0 entry count: 25 local APIC address: 0xfee00000 extended table length: 252 extended table checksum: 246 ------------------------------------------------------------------------------- MP Config Base Table Entries: -- Processors: APIC ID Version State Family Model Step Flags 1 0x10 BSP, usable 6 8 3 0x383fbff 0 0x10 AP, usable 6 8 3 0x383fbff -- Bus: Bus ID Type 0 PCI 2 PCI 5 PCI 15 ISA -- I/O APICs: APIC ID Version State Address 8 0x11 usable 0xfec00000 -- I/O Ints: Type Polarity Trigger Bus ID IRQ APIC ID PIN# INT active-hi edge 15 1 8 1 INT active-hi edge 15 0 8 2 INT active-hi edge 15 3 8 3 INT active-hi edge 15 4 8 4 INT active-lo level 15 5 8 5 INT active-hi edge 15 6 8 6 INT active-hi edge 15 7 8 7 INT active-hi edge 15 8 8 8 INT active-lo level 15 9 8 9 INT active-lo level 15 10 8 10 INT active-lo level 15 11 8 11 INT active-hi edge 15 12 8 12 INT active-lo level 15 13 8 13 INT active-hi edge 15 14 8 14 INT active-hi edge 15 15 8 15 -- Local Ints: Type Polarity Trigger Bus ID IRQ APIC ID PIN# ExtINT conforms conforms 15 0 255 0 NMI conforms conforms 15 0 255 1 ------------------------------------------------------------------------------- MP Config Extended Table Entries: Extended Table HOSED! If I compile a SMP kernel I get: CPU: Pentium III/Pentium III Xeon/Celeron (863.94-MHz 686-class CPU) Origin = "GenuineIntel" Id = 0x683 Stepping = 3 Features=0x383fbff real memory = 1207943168 (1179632K bytes) avail memory = 1169346560 (1141940K bytes) Programming 35 pins in IOAPIC #0 IOAPIC #0 intpin 2 -> irq 0 FreeBSD/SMP: Multiprocessor motherboard cpu0 (BSP): apic id: 1, version: 0x00040011, at 0xfee00000 cpu1 (AP): apic id: 0, version: 0x00040011, at 0xfee00000 io0 (APIC): apic id: 8, version: 0x00220011, at 0xfec00000 APIC_IO: Testing 8254 interrupt delivery APIC_IO: Broken MP table detected: 8254 is not connected to IOAPIC #0 intpin 2 APIC_IO: routing 8254 via 8259 and IOAPIC #0 intpin 0 SMP: AP CPU #1 Launched! Everything *seems* ok, but those messages kinda scare me. Has anyone seen anything like this? -- Kevin To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Mon Aug 14 14:37:58 2000 Delivered-To: freebsd-smp@freebsd.org Received: from mass.osd.bsdi.com (adsl-63-202-177-115.dsl.snfc21.pacbell.net [63.202.177.115]) by hub.freebsd.org (Postfix) with ESMTP id E51C337B601 for ; Mon, 14 Aug 2000 14:37:54 -0700 (PDT) (envelope-from msmith@mass.osd.bsdi.com) Received: from mass.osd.bsdi.com (localhost [127.0.0.1]) by mass.osd.bsdi.com (8.9.3/8.9.3) with ESMTP id OAA04930; Mon, 14 Aug 2000 14:50:03 -0700 (PDT) (envelope-from msmith@mass.osd.bsdi.com) Message-Id: <200008142150.OAA04930@mass.osd.bsdi.com> X-Mailer: exmh version 2.1.1 10/15/1999 To: Kevin Day Cc: freebsd-smp@freebsd.org Subject: Re: SMP on Compaq Proliant ML530 In-reply-to: Your message of "Mon, 14 Aug 2000 16:31:21 CDT." <39986529.30890E36@ikadega.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 14 Aug 2000 14:50:03 -0700 From: Mike Smith Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > MP Config Extended Table Entries: > > Extended Table HOSED! This is a bit ugly, but you may be able to improve things by switching OS modes in 'advanced' mode in the ECU. Hit Alt-A at the first setup screen once you've booted SmartStart and see whether tweaking anything there helps. The system will work OK like this though. > Programming 35 pins in IOAPIC #0 > IOAPIC #0 intpin 2 -> irq 0 > FreeBSD/SMP: Multiprocessor motherboard > cpu0 (BSP): apic id: 1, version: 0x00040011, at 0xfee00000 > cpu1 (AP): apic id: 0, version: 0x00040011, at 0xfee00000 > io0 (APIC): apic id: 8, version: 0x00220011, at 0xfec00000 This is OK, although now we'd move the ioapic down to id 2. > APIC_IO: Testing 8254 interrupt delivery > APIC_IO: Broken MP table detected: 8254 is not connected to IOAPIC #0 > intpin 2 > APIC_IO: routing 8254 via 8259 and IOAPIC #0 intpin 0 This is very typical, hence us having a workaround for it. > Everything *seems* ok, but those messages kinda scare me. Has anyone > seen anything like this? Yeah, it's all pretty common. The warning messages are a bit alarming though, granted. -- ... 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] To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Mon Aug 14 14:46:59 2000 Delivered-To: freebsd-smp@freebsd.org Received: from backdraft.gmx.com (backdraft.gmxinc.net [199.165.179.2]) by hub.freebsd.org (Postfix) with ESMTP id 58B5137B612; Mon, 14 Aug 2000 14:46:53 -0700 (PDT) (envelope-from kevind@ikadega.com) Received: (from fwtk@localhost) by backdraft.gmx.com (8.7.4/8.7.3) id QAA06985; Mon, 14 Aug 2000 16:22:13 -0500 (CDT) X-Authentication-Warning: backdraft.gmx.com: fwtk set sender to using -f Received: from ilpostino.gmx.com(88.0.0.230) by backdraft.gmx.com via smap (V1.3) id sma006961; Mon Aug 14 16:22:01 2000 Received: from ikadega.com ([88.0.0.115]) by ilpostino.gmx.com (8.8.5/8.8.5) with ESMTP id QAA08158; Mon, 14 Aug 2000 16:28:50 -0500 (CDT) Message-ID: <39986913.E99D87B1@ikadega.com> Date: Mon, 14 Aug 2000 16:48:03 -0500 From: Kevin Day X-Mailer: Mozilla 4.74 [en] (X11; U; Linux 2.2.12 i386) X-Accept-Language: en MIME-Version: 1.0 To: Mike Smith Cc: freebsd-smp@freebsd.org Subject: Re: SMP on Compaq Proliant ML530 References: <200008142150.OAA04930@mass.osd.bsdi.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Mike Smith wrote: > > MP Config Extended Table Entries: > > > > Extended Table HOSED! > > This is a bit ugly, but you may be able to improve things by switching OS > modes in 'advanced' mode in the ECU. Hit Alt-A at the first setup screen > once you've booted SmartStart and see whether tweaking anything there > helps. The system will work OK like this though. > I played with that a bit before posting. If I tell it I'm using Windows NT, my SCSI devices seem to disappear. If I tell it I'm using NetWare, I can only see the first PCI bus. Telling it I'm running RedHat Linux is the only way I got this far. There are a few more obscure OS choices there (who still uses Banyan Vines, especially on a server this size?) that I'll keep trying. > > > Programming 35 pins in IOAPIC #0 > > IOAPIC #0 intpin 2 -> irq 0 > > FreeBSD/SMP: Multiprocessor motherboard > > cpu0 (BSP): apic id: 1, version: 0x00040011, at 0xfee00000 > > cpu1 (AP): apic id: 0, version: 0x00040011, at 0xfee00000 > > io0 (APIC): apic id: 8, version: 0x00220011, at 0xfec00000 > > This is OK, although now we'd move the ioapic down to id 2. Perhaps this is a carryover from the ML530's bigger brother that has 8 procs. > > > APIC_IO: Testing 8254 interrupt delivery > > APIC_IO: Broken MP table detected: 8254 is not connected to IOAPIC #0 > > intpin 2 > > APIC_IO: routing 8254 via 8259 and IOAPIC #0 intpin 0 > > This is very typical, hence us having a workaround for it. Ok. Perhaps a second test after doing the reroute that says "Workaround successful" so people like me don't worry quite as much about it? :) > > > > Everything *seems* ok, but those messages kinda scare me. Has anyone > > seen anything like this? > > Yeah, it's all pretty common. The warning messages are a bit alarming > though, granted. Now if we can only get Compaq to list FreeBSD under the "other" category of OS's in the startup software. :) Thanks, -- Kevin To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Aug 15 13:47: 4 2000 Delivered-To: freebsd-smp@freebsd.org Received: from smtp1-ext.oskarmobil.cz (smtp1-ext.oskarmobil.cz [195.47.29.137]) by hub.freebsd.org (Postfix) with ESMTP id D120C37BC82 for ; Tue, 15 Aug 2000 13:46:53 -0700 (PDT) (envelope-from milon.papezik@oskarmobil.cz) Received: from wh01ex02.ceskymobil.cz (exchange1.ceskymobil.cz [172.20.128.42]) by smtp1-ext.oskarmobil.cz (8.9.3/8.9.3) with ESMTP id WAA68709; Tue, 15 Aug 2000 22:43:41 +0200 (CEST) Received: from oskarmobil.cz (papezik.ceskymobil.cz [172.20.128.9]) by wh01ex02.ceskymobil.cz with SMTP (Microsoft Exchange Internet Mail Service Version 5.5.2650.21) id Q9SGMVNK; Tue, 15 Aug 2000 22:46:29 +0200 Message-ID: <3999AB39.11230CE9@oskarmobil.cz> Date: Tue, 15 Aug 2000 22:42:33 +0200 From: Milon Papezik X-Mailer: Mozilla 4.7 [en] (X11; I; FreeBSD 3.4-RELEASE i386) X-Accept-Language: cs, en MIME-Version: 1.0 To: Kevin Day Cc: freebsd-smp@FreeBSD.ORG Subject: Re: SMP on Compaq Proliant ML530 References: <200008142150.OAA04930@mass.osd.bsdi.com> <39986913.E99D87B1@ikadega.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Kevin Day wrote: > > Mike Smith wrote: > > > > MP Config Extended Table Entries: > > > > > > Extended Table HOSED! > > > > This is a bit ugly, but you may be able to improve things by switching OS > > modes in 'advanced' mode in the ECU. Hit Alt-A at the first setup screen > > once you've booted SmartStart and see whether tweaking anything there > > helps. The system will work OK like this though. > > > > I played with that a bit before posting. If I tell it I'm using Windows NT, > my SCSI devices seem to disappear. If I tell it I'm using NetWare, I can > only see the first PCI bus. Telling it I'm running RedHat Linux is the only > way I got this far. There are a few more obscure OS choices there (who still > uses Banyan Vines, especially on a server this size?) that I'll keep trying. UnixWare 7 is usualy a good choice to get correct MP table on Compaqs. Could you please try it and let us know? Thanks in advance, Milon -- milon.papezik@oskarmobil.cz > > > > > > Programming 35 pins in IOAPIC #0 > > > IOAPIC #0 intpin 2 -> irq 0 > > > FreeBSD/SMP: Multiprocessor motherboard > > > cpu0 (BSP): apic id: 1, version: 0x00040011, at 0xfee00000 > > > cpu1 (AP): apic id: 0, version: 0x00040011, at 0xfee00000 > > > io0 (APIC): apic id: 8, version: 0x00220011, at 0xfec00000 > > > > This is OK, although now we'd move the ioapic down to id 2. > > Perhaps this is a carryover from the ML530's bigger brother that has 8 > procs. > > > > > > APIC_IO: Testing 8254 interrupt delivery > > > APIC_IO: Broken MP table detected: 8254 is not connected to IOAPIC #0 > > > intpin 2 > > > APIC_IO: routing 8254 via 8259 and IOAPIC #0 intpin 0 > > > > This is very typical, hence us having a workaround for it. > > Ok. Perhaps a second test after doing the reroute that says "Workaround > successful" so people like me don't worry quite as much about it? :) > > > > > > > > Everything *seems* ok, but those messages kinda scare me. Has anyone > > > seen anything like this? > > > > Yeah, it's all pretty common. The warning messages are a bit alarming > > though, granted. > > Now if we can only get Compaq to list FreeBSD under the "other" category of > OS's in the startup software. :) > > Thanks, > > -- Kevin > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-smp" in the body of the message To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Aug 15 23:22:40 2000 Delivered-To: freebsd-smp@freebsd.org Received: from mass.osd.bsdi.com (adsl-63-202-177-115.dsl.snfc21.pacbell.net [63.202.177.115]) by hub.freebsd.org (Postfix) with ESMTP id 3A1A037BB1A for ; Tue, 15 Aug 2000 23:22:33 -0700 (PDT) (envelope-from msmith@mass.osd.bsdi.com) Received: from mass.osd.bsdi.com (localhost [127.0.0.1]) by mass.osd.bsdi.com (8.9.3/8.9.3) with ESMTP id XAA18007; Tue, 15 Aug 2000 23:34:39 -0700 (PDT) (envelope-from msmith@mass.osd.bsdi.com) Message-Id: <200008160634.XAA18007@mass.osd.bsdi.com> X-Mailer: exmh version 2.1.1 10/15/1999 To: Kevin Day Cc: freebsd-smp@freebsd.org Subject: Re: SMP on Compaq Proliant ML530 In-reply-to: Your message of "Mon, 14 Aug 2000 16:48:03 CDT." <39986913.E99D87B1@ikadega.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 15 Aug 2000 23:34:39 -0700 From: Mike Smith Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > Mike Smith wrote: > > > > MP Config Extended Table Entries: > > > > > > Extended Table HOSED! > > > > This is a bit ugly, but you may be able to improve things by switching OS > > modes in 'advanced' mode in the ECU. Hit Alt-A at the first setup screen > > once you've booted SmartStart and see whether tweaking anything there > > helps. The system will work OK like this though. > > > > I played with that a bit before posting. If I tell it I'm using Windows NT, > my SCSI devices seem to disappear. If I tell it I'm using NetWare, I can > only see the first PCI bus. Telling it I'm running RedHat Linux is the only > way I got this far. There are a few more obscure OS choices there (who still > uses Banyan Vines, especially on a server this size?) that I'll keep trying. Make sure you're in the secret "advanced" mode, and you get a lot more choices. Linux has basically the same expectations about the APIC layout, so it should be a good choice. As was medntioned, Unixware 7 is also a good one. > > > Programming 35 pins in IOAPIC #0 > > > IOAPIC #0 intpin 2 -> irq 0 > > > FreeBSD/SMP: Multiprocessor motherboard > > > cpu0 (BSP): apic id: 1, version: 0x00040011, at 0xfee00000 > > > cpu1 (AP): apic id: 0, version: 0x00040011, at 0xfee00000 > > > io0 (APIC): apic id: 8, version: 0x00220011, at 0xfec00000 > > > > This is OK, although now we'd move the ioapic down to id 2. > > Perhaps this is a carryover from the ML530's bigger brother that has 8 > procs. That would make sense. As Tor pointed out, we wouldn't actually move it - it will Just Work. > > > APIC_IO: Testing 8254 interrupt delivery > > > APIC_IO: Broken MP table detected: 8254 is not connected to IOAPIC #0 > > > intpin 2 > > > APIC_IO: routing 8254 via 8259 and IOAPIC #0 intpin 0 > > > > This is very typical, hence us having a workaround for it. > > Ok. Perhaps a second test after doing the reroute that says "Workaround > successful" so people like me don't worry quite as much about it? :) The 'routing' message is meant to be the "ok, this is how we deal with it" message - if it doesn't work, things typically hang at that point. (Yes, lame. I'm poking the individual that's currently working on this code. John, are you listening? 8) > > > Everything *seems* ok, but those messages kinda scare me. Has anyone > > > seen anything like this? > > > > Yeah, it's all pretty common. The warning messages are a bit alarming > > though, granted. > > Now if we can only get Compaq to list FreeBSD under the "other" category of > OS's in the startup software. :) *grin* -- ... 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] To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Aug 16 7:54:44 2000 Delivered-To: freebsd-smp@freebsd.org Received: from jason04.u.washington.edu (jason04.u.washington.edu [140.142.78.5]) by hub.freebsd.org (Postfix) with ESMTP id 6FB8F37BE81 for ; Wed, 16 Aug 2000 07:54:41 -0700 (PDT) (envelope-from egpeters@u.washington.edu) Received: from dante57.u.washington.edu (root@dante57.u.washington.edu [140.142.15.107]) by jason04.u.washington.edu (8.9.3+UW00.05/8.9.3+UW00.01) with ESMTP id HAA38220 for ; Wed, 16 Aug 2000 07:54:38 -0700 Received: from localhost (egpeters@localhost) by dante57.u.washington.edu (8.9.3+UW00.05/8.9.3+UW99.09) with ESMTP id HAA84700 for ; Wed, 16 Aug 2000 07:54:37 -0700 Date: Wed, 16 Aug 2000 07:54:36 -0700 (PDT) From: Eric Peters To: freebsd-smp@FreeBSD.org Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org subscribe freebsd-smp To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Aug 16 11:55:40 2000 Delivered-To: freebsd-smp@freebsd.org Received: from thelab.hub.org (nat204.85.mpoweredpc.net [142.177.204.85]) by hub.freebsd.org (Postfix) with ESMTP id 09C0737B6EC; Wed, 16 Aug 2000 11:55:27 -0700 (PDT) (envelope-from scrappy@hub.org) Received: from localhost (scrappy@localhost) by thelab.hub.org (8.9.3/8.9.3) with ESMTP id PAA51384; Wed, 16 Aug 2000 15:53:11 -0300 (ADT) (envelope-from scrappy@hub.org) X-Authentication-Warning: thelab.hub.org: scrappy owned process doing -bs Date: Wed, 16 Aug 2000 15:53:11 -0300 (ADT) From: The Hermit Hacker To: freebsd-smp@freebsd.org Cc: freebsd-stable@freebsd.org Subject: problem with smp in 4.1-STABLE ... or just 4.1-stable itself ... ? Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org wow, just hung my machine up solid twice in about a half hour period ... I just upgraded my machine to a Dual-PIII 700 on an ASUS P2B-D motherboard ... everything has been running great the past 2 days, things just fly along, hardly ever see the load average rise about 1 ... today, I'm working on improving stats generation for my virtual hosts and wrote a simple script that goes through and runs webalizer against any domain that has had activity since the last run ... basically it checks a domain, runs webalizer in the background and goes off to the next one ... as soon as I start the script, the load avg climbs relatively quickly (last one I saw was 26 and rising), the machine gets more and more lag'd until it just locks up solid ... I'm running remotely, and have the serial console configured, but altho I can see the machine boot, get to single user mode and all that, as soon as I goes multi-user my keyboard no longer works, so I can't get to DDB ... I'm running 4.1-STABLE code as of Monday night ... I hate to do it, but I'm going to try and kill it once more with top running and see if anything odd comes up in there ... yup, third time is the charm ... all when I do my stats run. top shows: last pid: 13913; load averages: 71.25, 37.03, 15.564 up 0+00:09:43 14:52:23 262 processes: 2 running, 258 sleeping, 2 zombie CPU states: 37.1% user, 0.0% nice, 45.3% system, 1.3% interrupt, 16.3% idle Mem: 368M Active, 42M Inact, 53M Wired, 2244K Cache, 61M Buf, 37M Free Swap: 2047M Total, 602M Used, 1446M Free, 29% Inuse, 12M In PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU CPU COMMAND 13513 corey 2 0 2220K 1324K select 1 0:03 32.17% 11.67% top 13512 jeff 2 0 2220K 1316K select 0 0:03 31.77% 11.52% top 918 scrappy 64 0 2208K 704K CPU1 1 0:11 26.25% 9.52% top 8568 root -22 0 1026M 218M swread 0 0:16 4.40% 4.39% webalizer 610 root 2 0 2916K 1128K select 1 0:12 2.15% 0.78% named 13535 nobody -6 0 3724K 3128K pipdwt 0 0:00 3.01% 0.78% perl 13534 nobody -6 0 3724K 3128K pipdwt 1 0:00 2.82% 0.73% perl 1485 nobody 2 0 8956K 904K sbwait 0 0:01 1.75% 0.63% libhttpsd. 14003 root 64 0 864K 508K CPU0 0 0:00 0.00% 0.00% sh I have 768Meg of RAM on this machine, and >2gig of swap space ... I actually saw a loadavg of 90 while watching, but couldn't capture it ... does 4.1-STABLE have any known problems with not being able to handle "bursts" of processes? *raised eyebrow* I'm suspecting the other lock(s) were just high load too, now that I watch top ... Comments? Marc G. Fournier ICQ#7615664 IRC Nick: Scrappy Systems Administrator @ hub.org primary: scrappy@hub.org secondary: scrappy@{freebsd|postgresql}.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Aug 16 20: 4:27 2000 Delivered-To: freebsd-smp@freebsd.org Received: from thelab.hub.org (nat204.85.mpoweredpc.net [142.177.204.85]) by hub.freebsd.org (Postfix) with ESMTP id DC8F537BB2D; Wed, 16 Aug 2000 20:04:19 -0700 (PDT) (envelope-from scrappy@hub.org) Received: from localhost (scrappy@localhost) by thelab.hub.org (8.9.3/8.9.3) with ESMTP id AAA93137; Thu, 17 Aug 2000 00:02:05 -0300 (ADT) (envelope-from scrappy@hub.org) X-Authentication-Warning: thelab.hub.org: scrappy owned process doing -bs Date: Thu, 17 Aug 2000 00:02:05 -0300 (ADT) From: The Hermit Hacker To: freebsd-smp@FreeBSD.ORG Cc: freebsd-stable@FreeBSD.ORG Subject: Re: problem with smp in 4.1-STABLE ... or just 4.1-stable itself ... ? In-Reply-To: Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org later this aft, I found the problem ... it seems that running webalizer against the logs of one of my domains genrated a 'dnscache' file that is >1gig in size. When webalizer runs, it loads the whole damn thing up into memory ... before things locked up one of these times, I got to the point where I could see that swap was something like 800+Meg used and rising *roll eyes* On Wed, 16 Aug 2000, The Hermit Hacker wrote: > > wow, just hung my machine up solid twice in about a half hour period ... > > I just upgraded my machine to a Dual-PIII 700 on an ASUS P2B-D motherboard > ... everything has been running great the past 2 days, things just fly > along, hardly ever see the load average rise about 1 ... > > today, I'm working on improving stats generation for my virtual hosts and > wrote a simple script that goes through and runs webalizer against any > domain that has had activity since the last run ... > > basically it checks a domain, runs webalizer in the background and goes > off to the next one ... > > as soon as I start the script, the load avg climbs relatively quickly > (last one I saw was 26 and rising), the machine gets more and more lag'd > until it just locks up solid ... > > I'm running remotely, and have the serial console configured, but altho I > can see the machine boot, get to single user mode and all that, as soon as > I goes multi-user my keyboard no longer works, so I can't get to DDB ... > > I'm running 4.1-STABLE code as of Monday night ... > > I hate to do it, but I'm going to try and kill it once more with top > running and see if anything odd comes up in there ... yup, third time is > the charm ... all when I do my stats run. top shows: > > last pid: 13913; load averages: 71.25, 37.03, 15.564 up 0+00:09:43 14:52:23 > 262 processes: 2 running, 258 sleeping, 2 zombie > CPU states: 37.1% user, 0.0% nice, 45.3% system, 1.3% interrupt, 16.3% idle > Mem: 368M Active, 42M Inact, 53M Wired, 2244K Cache, 61M Buf, 37M Free > Swap: 2047M Total, 602M Used, 1446M Free, 29% Inuse, 12M In > > PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU CPU COMMAND > 13513 corey 2 0 2220K 1324K select 1 0:03 32.17% 11.67% top > 13512 jeff 2 0 2220K 1316K select 0 0:03 31.77% 11.52% top > 918 scrappy 64 0 2208K 704K CPU1 1 0:11 26.25% 9.52% top > 8568 root -22 0 1026M 218M swread 0 0:16 4.40% 4.39% webalizer > 610 root 2 0 2916K 1128K select 1 0:12 2.15% 0.78% named > 13535 nobody -6 0 3724K 3128K pipdwt 0 0:00 3.01% 0.78% perl > 13534 nobody -6 0 3724K 3128K pipdwt 1 0:00 2.82% 0.73% perl > 1485 nobody 2 0 8956K 904K sbwait 0 0:01 1.75% 0.63% libhttpsd. > 14003 root 64 0 864K 508K CPU0 0 0:00 0.00% 0.00% sh > > I have 768Meg of RAM on this machine, and >2gig of swap space ... I > actually saw a loadavg of 90 while watching, but couldn't capture it ... > > does 4.1-STABLE have any known problems with not being able to handle > "bursts" of processes? *raised eyebrow* I'm suspecting the other > lock(s) were just high load too, now that I watch top ... > > Comments? > > Marc G. Fournier ICQ#7615664 IRC Nick: Scrappy > Systems Administrator @ hub.org > primary: scrappy@hub.org secondary: scrappy@{freebsd|postgresql}.org > > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-stable" in the body of the message > Marc G. Fournier ICQ#7615664 IRC Nick: Scrappy Systems Administrator @ hub.org primary: scrappy@hub.org secondary: scrappy@{freebsd|postgresql}.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Fri Aug 18 1:53:11 2000 Delivered-To: freebsd-smp@freebsd.org Received: from smtp.OpenBit.NET (smtp.OpenBit.NET [211.14.152.40]) by hub.freebsd.org (Postfix) with ESMTP id 36C1237B423; Fri, 18 Aug 2000 01:53:08 -0700 (PDT) Received: from hermite.FreeBit.NET (dhcp0086.office.FreeBit.NET [211.14.146.86]) by smtp.OpenBit.NET (8.10.2/8.10.2) with SMTP id e7I8qc338929; Fri, 18 Aug 2000 17:52:39 +0900 (JST) Message-Id: <200008180852.AA01142@hermite.FreeBit.NET> From: IWAIZAKO Takahiro Date: Fri, 18 Aug 2000 17:52:51 +0900 To: Mike Smith Cc: freebsd-smp@FreeBSD.ORG Subject: Re: SMP on Compaq Proliant ML530 In-Reply-To: <200008160634.XAA18007@mass.osd.bsdi.com> References: <200008160634.XAA18007@mass.osd.bsdi.com> MIME-Version: 1.0 X-Mailer: AL-Mail32 Version 1.11 Content-Type: text/plain; charset=us-ascii Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Mike Smith wrote: >> > > MP Config Extended Table Entries: >> > > >> > > Extended Table HOSED! >> > >> > This is a bit ugly, but you may be able to improve things by switching OS >> > modes in 'advanced' mode in the ECU. Hit Alt-A at the first setup screen >> > once you've booted SmartStart and see whether tweaking anything there >> > helps. The system will work OK like this though. >> > >> >> I played with that a bit before posting. If I tell it I'm using Windows NT, >> my SCSI devices seem to disappear. If I tell it I'm using NetWare, I can >> only see the first PCI bus. Telling it I'm running RedHat Linux is the only >> way I got this far. There are a few more obscure OS choices there (who still >> uses Banyan Vines, especially on a server this size?) that I'll keep trying. > >Make sure you're in the secret "advanced" mode, and you get a lot more >choices. Linux has basically the same expectations about the APIC >layout, so it should be a good choice. As was medntioned, Unixware 7 is >also a good one. Hi Mike, I'm trying Compaq DL360. I have same problem. About APIC configuration in the SCU, both fulltable and fulltable map does not work. (Linux is fulltable map. Unixware 7 is fulltable.) This is already reported in PR 19338. http://www.freebsd.org/cgi/query-pr.cgi?pr=19338 --- rabit@FreeBit.NET To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sat Aug 19 10:36:38 2000 Delivered-To: freebsd-smp@freebsd.org Received: from adsl-63-192-211-186.dsl.snfc21.pacbell.net (adsl-63-192-211-186.dsl.snfc21.pacbell.net [63.192.211.186]) by hub.freebsd.org (Postfix) with ESMTP id 9710D37B43C for ; Sat, 19 Aug 2000 10:36:36 -0700 (PDT) Received: from localhost.minions.com (bifrost@localhost.minions.com [127.0.0.1]) by adsl-63-192-211-186.dsl.snfc21.pacbell.net (8.9.3/8.9.3) with ESMTP id KAA19991 for ; Sat, 19 Aug 2000 10:36:34 -0700 (PDT) Date: Sat, 19 Aug 2000 10:36:34 -0700 (PDT) From: Tom To: freebsd-smp@FreeBSD.ORG Subject: Kernel Config for Supermicro P6DBE Board Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org I've poked around but I haven't found a kernel config for my Supermicro board that works right. Every time I run mptable I still get the extended table hosed message. I've thought about updating the BIOS, but Supermicro doesn't really have much on their site for it. Anyone? I know people are running them out there... --- Tom bifrost@minions.com "Where am I and why am I in this handbasket?" To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sat Aug 19 11:11:30 2000 Delivered-To: freebsd-smp@freebsd.org Received: from femail1.sdc1.sfba.home.com (femail1.sdc1.sfba.home.com [24.0.95.81]) by hub.freebsd.org (Postfix) with ESMTP id 930E937B424 for ; Sat, 19 Aug 2000 11:11:28 -0700 (PDT) Received: from cx443070a ([24.4.93.90]) by femail1.sdc1.sfba.home.com (InterMail vM.4.01.03.00 201-229-121) with SMTP id <20000819181123.GNLZ29012.femail1.sdc1.sfba.home.com@cx443070a>; Sat, 19 Aug 2000 11:11:23 -0700 Message-ID: <000a01c00a09$0ad6da10$5a5d0418@cx443070a> From: "Jeremiah Gowdy" To: "Tom" , References: Subject: Re: Kernel Config for Supermicro P6DBE Board Date: Sat, 19 Aug 2000 11:12:31 -0700 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 5.50.4133.2400 X-MimeOLE: Produced By Microsoft MimeOLE V5.50.4133.2400 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > I've poked around but I haven't found a kernel config for my Supermicro > board that works right. Every time I run mptable I still get the > extended table hosed message. I've thought about updating the BIOS, but > Supermicro doesn't really have much on their site for it. > > Anyone? I know people are running them out there... I was running a Supermicro P6DBE board with Dual Pentium II 333s, and then Dual Pentium III 450s. I had no problems with the board. The basic SMP kernel config worked fine for me. However, I did update the bios. Revision 2 of the motherboard http://www.supermicro.com/TECHSUPPORT/BIOS/BIOS_ZIP/sbs4061.zip Revision 0/1 of the motherboard http://www.supermicro.com/TECHSUPPORT/BIOS/BIOS_ZIP/dgs4061.zip To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sat Aug 19 12:13:49 2000 Delivered-To: freebsd-smp@freebsd.org Received: from mass.osd.bsdi.com (c228380-a.sfmissn1.sfba.home.com [24.20.90.44]) by hub.freebsd.org (Postfix) with ESMTP id ED57937B423 for ; Sat, 19 Aug 2000 12:13:46 -0700 (PDT) Received: from mass.osd.bsdi.com (localhost [127.0.0.1]) by mass.osd.bsdi.com (8.9.3/8.9.3) with ESMTP id MAA00678; Sat, 19 Aug 2000 12:26:31 -0700 (PDT) (envelope-from msmith@mass.osd.bsdi.com) Message-Id: <200008191926.MAA00678@mass.osd.bsdi.com> X-Mailer: exmh version 2.1.1 10/15/1999 To: Tom Cc: freebsd-smp@FreeBSD.ORG Subject: Re: Kernel Config for Supermicro P6DBE Board In-reply-to: Your message of "Sat, 19 Aug 2000 10:36:34 PDT." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sat, 19 Aug 2000 12:26:31 -0700 From: Mike Smith Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > I've poked around but I haven't found a kernel config for my Supermicro > board that works right. Every time I run mptable I still get the > extended table hosed message. I've thought about updating the BIOS, but > Supermicro doesn't really have much on their site for it. > > Anyone? I know people are running them out there... What's the issue? The system should run fine regardless of the state of the extended table; changing the kernel config won't magically "fix" the table - that's a BIOS bug. -- ... 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] To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message