From owner-freebsd-smp Sun Apr 21 20:12:56 2002 Delivered-To: freebsd-smp@freebsd.org Received: from hotmail.com (f24.law3.hotmail.com [209.185.241.24]) by hub.freebsd.org (Postfix) with ESMTP id 31F6037B400 for ; Sun, 21 Apr 2002 20:12:54 -0700 (PDT) Received: from mail pickup service by hotmail.com with Microsoft SMTPSVC; Sun, 21 Apr 2002 20:12:49 -0700 Received: from 203.81.71.2 by lw3fd.law3.hotmail.msn.com with HTTP; Mon, 22 Apr 2002 03:12:48 GMT X-Originating-IP: [203.81.71.2] From: "YeWint htwe" To: freebsd-smp@FreeBSD.org Date: Mon, 22 Apr 2002 09:42:48 +0630 Mime-Version: 1.0 Content-Type: text/plain; format=flowed Message-ID: X-OriginalArrivalTime: 22 Apr 2002 03:12:49.0031 (UTC) FILETIME=[94ECC970:01C1E9AB] 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 subscribe freebsd-smp _________________________________________________________________ MSN Photos is the easiest way to share and print your photos: http://photos.msn.com/support/worldwide.aspx To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Apr 23 2:58: 4 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mail-out-01.piro.net (mail-out-01.piro.net [194.64.31.8]) by hub.freebsd.org (Postfix) with ESMTP id 1F70137B405 for ; Tue, 23 Apr 2002 02:57:56 -0700 (PDT) Received: from pcserver.science-factory.com (Sciencefactory-atm1-181.pironet-ndh.net [195.135.137.205]) by mail-out-01.piro.net (8.9.3/8.9.3/PN-991208) with ESMTP id LAA22699; Tue, 23 Apr 2002 11:57:52 +0200 Received: by pcserver.science-factory.com (Postfix, from userid 511) id 2EF982A2970; Tue, 23 Apr 2002 11:56:43 +0200 (CEST) From: Marc van Woerkom To: marcel@xcllnt.net Cc: freebsd-smp@FreeBSD.ORG Subject: 2 x P4 2.2GHz Supermicro P4DP6 and Linux Emulation References: <20020403034208.GA929@dhcp01.pn.xcllnt.net> Message-Id: <20020423095643.2EF982A2970@pcserver.science-factory.com> Date: Tue, 23 Apr 2002 11:56:43 +0200 (CEST) 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 Hello, we have a nice SMP system here, a 2 x P4 2.2GHz Supermicro P4DP6 that we need to configure with a custom database system. (See dmesg output below). It was originally intended to operate under Mandrake Linux, but the SMP system behaved such unstable, that we can't use it. This gives me the chance to introduce FreeBSD here. :) My hope is that FreeBSD operates smooth on the hardware, and that our Linux emulation is very good. Yesterday evening I installed a 4.5-RELEASE and rolled a SMP Kernel. So far everything works very smoothly. Great, guys! I managed to cvsup the FreeBSD cvs repository and will upgrade to the latest -STABLE during the day. Now comes the tricky bit: The OODB we use (Versant) is released for a Red Hat 7.1 system. This means I need to build a compatible run time environment at least. It would be even better if I could manage to create a build environment as well (which needs a certain gcc release to be able to compile against the OODB libs) to rebuilt our backend software on the box. This means I need some information about the two Linux emulation ports (6.1 and 7.1) in the ports collection. I need RH 7.1 compatibility - does this mean I can just add that 7.1 linux port, or would it interfere with the already installe 6.1 linux port? Has any other crazy person already tried to make use of the Linux emulation on a SMP box? Finally I need to a recent Linux JDK 1.4 port to the box, to allow a Java RMI server process to run on it. It would be nice if the SMP people here, who have run similiar software, could share experience. Regards, Marc ------------------------------------------------------------------------------- Copyright (c) 1992-2002 The FreeBSD Project. Copyright (c) 1979, 1980, 1983, 1986, 1988, 1989, 1991, 1992, 1993, 1994 The Regents of the University of California. All rights reserved. FreeBSD 4.5-RELEASE #0: Mon Apr 22 23:13:28 CEST 2002 root@uebertool.science-factory.com:/usr/src/sys/compile/UT Timecounter "i8254" frequency 1193182 Hz CPU: Pentium 4 (2196.27-MHz 686-class CPU) Origin = "GenuineIntel" Id = 0xf24 Stepping = 4 Features=0x3febfbff,ACC> real memory = 2146959360 (2096640K bytes) avail memory = 2086367232 (2037468K bytes) Programming 24 pins in IOAPIC #0 IOAPIC #0 intpin 2 -> irq 0 Programming 24 pins in IOAPIC #1 Programming 24 pins in IOAPIC #2 Programming 24 pins in IOAPIC #3 Programming 24 pins in IOAPIC #4 FreeBSD/SMP: Multiprocessor motherboard cpu0 (BSP): apic id: 0, version: 0x00050014, at 0xfee00000 cpu1 (AP): apic id: 6, version: 0x00050014, at 0xfee00000 cpu2 (AP): apic id: 1, version: 0x00050014, at 0xfee00000 cpu3 (AP): apic id: 7, version: 0x00050014, at 0xfee00000 io0 (APIC): apic id: 2, version: 0x00178020, at 0xfec00000 io1 (APIC): apic id: 3, version: 0x00178020, at 0xfec80000 io2 (APIC): apic id: 4, version: 0x00178020, at 0xfec80400 io3 (APIC): apic id: 5, version: 0x00178020, at 0xfec81000 io4 (APIC): apic id: 8, version: 0x00178020, at 0xfec81400 Preloaded elf kernel "kernel" at 0xc04a4000. md0: Malloc disk ------------------------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Apr 23 3:17:31 2002 Delivered-To: freebsd-smp@freebsd.org Received: from scribble.fsn.hu (scribble.fsn.hu [193.224.40.95]) by hub.freebsd.org (Postfix) with SMTP id 3F1F437B400 for ; Tue, 23 Apr 2002 03:17:25 -0700 (PDT) Received: (qmail 24984 invoked by uid 1000); 23 Apr 2002 10:19:50 -0000 Received: from localhost (sendmail-bs@127.0.0.1) by localhost with SMTP; 23 Apr 2002 10:19:50 -0000 Date: Tue, 23 Apr 2002 12:19:50 +0200 (CEST) From: Attila Nagy To: Marc van Woerkom Cc: freebsd-smp@FreeBSD.ORG Subject: Re: 2 x P4 2.2GHz Supermicro P4DP6 and Linux Emulation In-Reply-To: <20020423095643.2EF982A2970@pcserver.science-factory.com> 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 Hello, Just a dumb question... > we have a nice SMP system here, a 2 x P4 2.2GHz Supermicro P4DP6 that we ^^^^^^^^^^^^^ > FreeBSD/SMP: Multiprocessor motherboard > cpu0 (BSP): apic id: 0, version: 0x00050014, at 0xfee00000 > cpu1 (AP): apic id: 6, version: 0x00050014, at 0xfee00000 > cpu2 (AP): apic id: 1, version: 0x00050014, at 0xfee00000 > cpu3 (AP): apic id: 7, version: 0x00050014, at 0xfee00000 cpu[0-3], that's 4 processors. Does this mean that FreeBSD can actually handle the hyperthreading in the latest Xeons and recognizes one P4 processor as 2 in an SMP environment? --------[ Free Software ISOs - ftp://ftp.fsn.hu/pub/CDROM-Images/ ]------- Attila Nagy e-mail: Attila.Nagy@fsn.hu Free Software Network (FSN.HU) phone @work: +361 210 1415 (194) cell.: +3630 306 6758 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Apr 23 3:40:52 2002 Delivered-To: freebsd-smp@freebsd.org Received: from hotmail.com (oe50.law10.hotmail.com [64.4.14.22]) by hub.freebsd.org (Postfix) with ESMTP id 38BE937B41E for ; Tue, 23 Apr 2002 03:40:49 -0700 (PDT) Received: from mail pickup service by hotmail.com with Microsoft SMTPSVC; Tue, 23 Apr 2002 03:40:49 -0700 X-Originating-IP: [172.174.234.14] From: "FiberOps" To: References: Subject: Re: 2 x P4 2.2GHz Supermicro P4DP6 and Linux Emulation Date: Tue, 23 Apr 2002 05:40:44 -0500 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 6.00.2600.0000 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2600.0000 Message-ID: X-OriginalArrivalTime: 23 Apr 2002 10:40:49.0090 (UTC) FILETIME=[551A0A20:01C1EAB3] 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 It only means His motherboard has the capability of holding quad cpus ----- Original Message ----- From: "Attila Nagy" To: "Marc van Woerkom" Cc: Sent: Tuesday, April 23, 2002 5:19 AM Subject: Re: 2 x P4 2.2GHz Supermicro P4DP6 and Linux Emulation > Hello, > > Just a dumb question... > > > we have a nice SMP system here, a 2 x P4 2.2GHz Supermicro P4DP6 that we > ^^^^^^^^^^^^^ > > FreeBSD/SMP: Multiprocessor motherboard > > cpu0 (BSP): apic id: 0, version: 0x00050014, at 0xfee00000 > > cpu1 (AP): apic id: 6, version: 0x00050014, at 0xfee00000 > > cpu2 (AP): apic id: 1, version: 0x00050014, at 0xfee00000 > > cpu3 (AP): apic id: 7, version: 0x00050014, at 0xfee00000 > cpu[0-3], that's 4 processors. Does this mean that FreeBSD can actually > handle the hyperthreading in the latest Xeons and recognizes one P4 > processor as 2 in an SMP environment? > > --------[ Free Software ISOs - ftp://ftp.fsn.hu/pub/CDROM-Images/ ]------- > Attila Nagy e-mail: Attila.Nagy@fsn.hu > Free Software Network (FSN.HU) phone @work: +361 210 1415 (194) > cell.: +3630 306 6758 > > > 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 Apr 23 3:51:44 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mail-out-01.piro.net (mail-out-01.piro.net [194.64.31.8]) by hub.freebsd.org (Postfix) with ESMTP id EC70537B419 for ; Tue, 23 Apr 2002 03:51:37 -0700 (PDT) Received: from pcserver.science-factory.com (Sciencefactory-atm1-181.pironet-ndh.net [195.135.137.205]) by mail-out-01.piro.net (8.9.3/8.9.3/PN-991208) with ESMTP id MAA05572; Tue, 23 Apr 2002 12:51:33 +0200 Received: by pcserver.science-factory.com (Postfix, from userid 511) id 2E56827207E; Tue, 23 Apr 2002 12:50:14 +0200 (CEST) From: Marc van Woerkom To: bra@fsn.hu Cc: marc.vanwoerkom@science-factory.com, freebsd-smp@FreeBSD.ORG In-reply-to: (message from Attila Nagy on Tue, 23 Apr 2002 12:19:50 +0200 (CEST)) Subject: Re: 2 x P4 2.2GHz Supermicro P4DP6 and Linux Emulation References: Message-Id: <20020423105014.2E56827207E@pcserver.science-factory.com> Date: Tue, 23 Apr 2002 12:50:14 +0200 (CEST) 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 > Just a dumb question... I'm new to this SMP stuff as well. :) > > we have a nice SMP system here, a 2 x P4 2.2GHz Supermicro P4DP6 that we > ^^^^^^^^^^^^^ > > FreeBSD/SMP: Multiprocessor motherboard > > cpu0 (BSP): apic id: 0, version: 0x00050014, at 0xfee00000 > > cpu1 (AP): apic id: 6, version: 0x00050014, at 0xfee00000 > > cpu2 (AP): apic id: 1, version: 0x00050014, at 0xfee00000 > > cpu3 (AP): apic id: 7, version: 0x00050014, at 0xfee00000 > cpu[0-3], that's 4 processors. Does this mean that FreeBSD can actually > handle the hyperthreading in the latest Xeons and recognizes one P4 > processor as 2 in an SMP environment? It seems that each CPU has two chips on it. I see indeed four cpus showing up in the top listing. By the way: Is there more than 'top' or 'mptable' to monitor the SMP features? Some kind of benchmark I could use to check operations? Regards, Marc To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Apr 23 3:52:52 2002 Delivered-To: freebsd-smp@freebsd.org Received: from hotmail.com (oe19.law10.hotmail.com [64.4.14.123]) by hub.freebsd.org (Postfix) with ESMTP id 2D07837B41D for ; Tue, 23 Apr 2002 03:52:47 -0700 (PDT) Received: from mail pickup service by hotmail.com with Microsoft SMTPSVC; Tue, 23 Apr 2002 03:52:47 -0700 X-Originating-IP: [172.174.234.14] From: "FiberOps" To: References: Subject: Re: 2 x P4 2.2GHz Supermicro P4DP6 and Linux Emulation Date: Tue, 23 Apr 2002 05:52:42 -0500 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 6.00.2600.0000 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2600.0000 Message-ID: X-OriginalArrivalTime: 23 Apr 2002 10:52:47.0101 (UTC) FILETIME=[0111D2D0:01C1EAB5] 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 Nevermind my answer, I thought the P4DP6 was the P4QH6 which is quad . Your thoughts about the hyperthreading seem to be correct unless He was mistaken about the motherboard. ----- Original Message ----- From: "FiberOps" To: Sent: Tuesday, April 23, 2002 5:40 AM Subject: Re: 2 x P4 2.2GHz Supermicro P4DP6 and Linux Emulation > It only means His motherboard has the capability of holding quad cpus > > > ----- Original Message ----- > From: "Attila Nagy" > To: "Marc van Woerkom" > Cc: > Sent: Tuesday, April 23, 2002 5:19 AM > Subject: Re: 2 x P4 2.2GHz Supermicro P4DP6 and Linux Emulation > > > > Hello, > > > > Just a dumb question... > > > > > we have a nice SMP system here, a 2 x P4 2.2GHz Supermicro P4DP6 that we > > ^^^^^^^^^^^^^ > > > FreeBSD/SMP: Multiprocessor motherboard > > > cpu0 (BSP): apic id: 0, version: 0x00050014, at 0xfee00000 > > > cpu1 (AP): apic id: 6, version: 0x00050014, at 0xfee00000 > > > cpu2 (AP): apic id: 1, version: 0x00050014, at 0xfee00000 > > > cpu3 (AP): apic id: 7, version: 0x00050014, at 0xfee00000 > > cpu[0-3], that's 4 processors. Does this mean that FreeBSD can actually > > handle the hyperthreading in the latest Xeons and recognizes one P4 > > processor as 2 in an SMP environment? > > > > --------[ Free Software ISOs - ftp://ftp.fsn.hu/pub/CDROM-Images/ ]------- > > Attila Nagy e-mail: Attila.Nagy@fsn.hu > > Free Software Network (FSN.HU) phone @work: +361 210 1415 (194) > > cell.: +3630 306 6758 > > > > > > 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 > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Apr 23 4:53:16 2002 Delivered-To: freebsd-smp@freebsd.org Received: from scribble.fsn.hu (scribble.fsn.hu [193.224.40.95]) by hub.freebsd.org (Postfix) with SMTP id 889DC37B417 for ; Tue, 23 Apr 2002 04:53:12 -0700 (PDT) Received: (qmail 25413 invoked by uid 1000); 23 Apr 2002 11:55:34 -0000 Received: from localhost (sendmail-bs@127.0.0.1) by localhost with SMTP; 23 Apr 2002 11:55:34 -0000 Date: Tue, 23 Apr 2002 13:55:34 +0200 (CEST) From: Attila Nagy To: Marc van Woerkom Cc: freebsd-smp@FreeBSD.ORG Subject: Re: 2 x P4 2.2GHz Supermicro P4DP6 and Linux Emulation In-Reply-To: <20020423105014.2E56827207E@pcserver.science-factory.com> 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 Hello, > Some kind of benchmark I could use to check operations? For me it would be interesting to see if you have 4 equal performance CPUs, or 2 with some performance boost. I think running a dnetc client would be OK to test this. First run one instance, check the processors performance (with RC5-64, Mkeys/s) then repeat this with 4 instances. If you get ~4x Mkeys/s, then it's quite good. BTW, that motherboard seems to be very cool. Gigabit ethernet on board, etc... --------[ Free Software ISOs - ftp://ftp.fsn.hu/pub/CDROM-Images/ ]------- Attila Nagy e-mail: Attila.Nagy@fsn.hu Free Software Network (FSN.HU) phone @work: +361 210 1415 (194) cell.: +3630 306 6758 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Apr 23 11:56:56 2002 Delivered-To: freebsd-smp@freebsd.org Received: from palrel10.hp.com (palrel10.hp.com [156.153.255.245]) by hub.freebsd.org (Postfix) with ESMTP id 9559637B41B for ; Tue, 23 Apr 2002 11:56:43 -0700 (PDT) Received: from adlmail.cup.hp.com (adlmail.cup.hp.com [15.0.100.30]) by palrel10.hp.com (Postfix) with ESMTP id E14A3C00335; Tue, 23 Apr 2002 11:56:42 -0700 (PDT) Received: from gauss.cup.hp.com (gauss.cup.hp.com [15.28.97.152]) by adlmail.cup.hp.com (8.9.3 (PHNE_18546)/8.9.3 SMKit7.02) with ESMTP id LAA07135; Tue, 23 Apr 2002 11:56:42 -0700 (PDT) Received: (from marcel@localhost) by gauss.cup.hp.com (8.11.6/8.11.6) id g3NIuft51358; Tue, 23 Apr 2002 11:56:41 -0700 (PDT) (envelope-from marcel) Date: Tue, 23 Apr 2002 11:56:41 -0700 From: Marcel Moolenaar To: Marc van Woerkom Cc: freebsd-smp@FreeBSD.ORG Subject: Re: 2 x P4 2.2GHz Supermicro P4DP6 and Linux Emulation Message-ID: <20020423185641.GB51207@gauss.cup.hp.com> References: <20020403034208.GA929@dhcp01.pn.xcllnt.net> <20020423095643.2EF982A2970@pcserver.science-factory.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20020423095643.2EF982A2970@pcserver.science-factory.com> User-Agent: Mutt/1.3.27i 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 Tue, Apr 23, 2002 at 11:56:43AM +0200, Marc van Woerkom wrote: > The OODB we use (Versant) is released for a Red Hat 7.1 system. > This means I need to build a compatible run time environment > at least. > It would be even better if I could manage to create a build > environment as well (which needs a certain gcc release to > be able to compile against the OODB libs) to rebuilt our > backend software on the box. I have an unfinished linux_devtools-7.1 here: http://www.xcllnt.net/~marcel/linux_devtools-7.tar.gz It installs, but the package list is bogus. It will not deinstall cleanly. > This means I need some information about the two > Linux emulation ports (6.1 and 7.1) in the ports collection. > I need RH 7.1 compatibility - does this mean I can just > add that 7.1 linux port, or would it interfere with the > already installe 6.1 linux port? It interferes. Rename /compat/linux to /compat/linux-6.1 before you install 7.1 > Has any other crazy person already tried to make use > of the Linux emulation on a SMP box? Yes, but this was during the 3.x/4.x days. I don't have an SMP box for which linux emulation is ported anymore (ie alpha and i386). I don't see why it shouldn't just work (modulo bugs of course). HTH, -- Marcel Moolenaar USPA: A-39004 marcel@xcllnt.net To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Apr 23 12:25:32 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mail-out-01.piro.net (mail-out-01.piro.net [194.64.31.8]) by hub.freebsd.org (Postfix) with ESMTP id A973437B439 for ; Tue, 23 Apr 2002 12:24:28 -0700 (PDT) Received: from pcserver.science-factory.com (Sciencefactory-atm1-181.pironet-ndh.net [195.135.137.205]) by mail-out-01.piro.net (8.9.3/8.9.3/PN-991208) with ESMTP id VAA21707; Tue, 23 Apr 2002 21:10:26 +0200 Received: by pcserver.science-factory.com (Postfix, from userid 511) id ADAF02A2A39; Tue, 23 Apr 2002 21:09:05 +0200 (CEST) From: Marc van Woerkom To: marcel@cup.hp.com Cc: marc.vanwoerkom@science-factory.com, freebsd-smp@FreeBSD.ORG In-reply-to: <20020423185641.GB51207@gauss.cup.hp.com> (message from Marcel Moolenaar on Tue, 23 Apr 2002 11:56:41 -0700) Subject: Re: 2 x P4 2.2GHz Supermicro P4DP6 and Linux Emulation References: <20020403034208.GA929@dhcp01.pn.xcllnt.net> <20020423095643.2EF982A2970@pcserver.science-factory.com> <20020423185641.GB51207@gauss.cup.hp.com> Message-Id: <20020423190905.ADAF02A2A39@pcserver.science-factory.com> Date: Tue, 23 Apr 2002 21:09:05 +0200 (CEST) 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 Bedankt Marcel, I will try it. Do you have an idea what might be the problem here? This is the Linux j2se 1.4.0. bash-2.05a# javavm -jar Java2Demo.jar current locale is not supported in X11, locale is set to CX locale modifiers are not supported, using defaultWarning: Cannot convert string "Home,_Key_Begin" to type VirtualBinding Warning: Cannot convert string "F1,_Key_Help" to type VirtualBinding Warning: Cannot convert string "ShiftF10,_Key_Menu" to type VirtualBinding Warning: Cannot convert string "F10,Shift_Key_Menu" to type VirtualBinding Warning: Cannot convert string "KP_Enter,_Key_Execute" to type VirtualBinding Warning: Cannot convert string "AltReturn,Alt_Key_KP_Enter" to type VirtualBinding Exception in thread "main" java.lang.InternalError: Current locale is not supported at sun.awt.motif.MWindowPeer.pSetTitle(Native Method) at sun.awt.motif.MWindowPeer.init(MWindowPeer.java:98) at sun.awt.motif.MFramePeer.(MFramePeer.java:58) at sun.awt.motif.MToolkit.createFrame(MToolkit.java:192) at java.awt.Frame.addNotify(Frame.java:469) at java.awt.Window.show(Window.java:433) at java.awt.Component.show(Component.java:1128) at java.awt.Component.setVisible(Component.java:1083) at java2d.Java2Demo.main(Java2Demo.java:444) bash-2.05a# And for some crazy reason, if I start javavm as user (not as root) I get: bash-2.05a$ javavm # # HotSpot Virtual Machine Error, Internal Error # Please report this error at # http://java.sun.com/cgi-bin/bugreport.cgi # # Java VM: Java HotSpot(TM) Client VM (1.4.0-b92 mixed mode) # # Error ID: 4F533F4C494E55580E43505002AB # Abort trap (core dumped) bash-2.05a$ Regards, Marc To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Apr 23 15:32:50 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mail.speakeasy.net (mail12.speakeasy.net [216.254.0.212]) by hub.freebsd.org (Postfix) with ESMTP id 3B00037B4CE for ; Tue, 23 Apr 2002 15:32:30 -0700 (PDT) Received: (qmail 22971 invoked from network); 23 Apr 2002 22:32:29 -0000 Received: from unknown (HELO server.baldwin.cx) ([216.27.160.63]) (envelope-sender ) by mail12.speakeasy.net (qmail-ldap-1.03) with DES-CBC3-SHA encrypted SMTP for ; 23 Apr 2002 22:32:29 -0000 Received: from laptop.baldwin.cx (gw1.twc.weather.com [216.133.140.1]) by server.baldwin.cx (8.11.6/8.11.6) with ESMTP id g3NMWSv04098; Tue, 23 Apr 2002 18:32:28 -0400 (EDT) (envelope-from jhb@FreeBSD.org) Message-ID: X-Mailer: XFMail 1.5.2 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, 23 Apr 2002 18:31:36 -0400 (EDT) From: John Baldwin To: FiberOps Subject: Re: 2 x P4 2.2GHz Supermicro P4DP6 and Linux Emulation 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 23-Apr-2002 FiberOps wrote: > Nevermind my answer, I thought the P4DP6 was the P4QH6 > which is quad . Your thoughts about the hyperthreading seem > to be correct unless He was mistaken about the motherboard. That is actual probed CPU's, not slots, so it looks like we at least see them properly. I'm curious if we IPI them properly since we currently abuse physical ID's for addressing APIC's rather than using logical ID's like we should. Do all 4 CPU's launch ok at the bottom of the boot messages? -- John Baldwin <>< http://www.FreeBSD.org/~jhb/ "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 Apr 24 4:14:36 2002 Delivered-To: freebsd-smp@freebsd.org Received: from rina.r.dl.itc.u-tokyo.ac.jp (rina.r.dl.itc.u-tokyo.ac.jp [133.11.199.247]) by hub.freebsd.org (Postfix) with ESMTP id AC8BE37B41F; Wed, 24 Apr 2002 04:14:16 -0700 (PDT) Received: from sohgo.carrots.uucp.r.dl.itc.u-tokyo.ac.jp (sohgo.carrots.uucp.r.dl.itc.u-tokyo.ac.jp [IPv6:3ffe:b80:5b0:3:200:e8ff:fe14:9f8a]) by rina.r.dl.itc.u-tokyo.ac.jp (8.12.2/3.7W-rina.r-Nankai-Koya) with ESMTP id g3OBCi0o088852 ; Wed, 24 Apr 2002 20:12:45 +0900 (JST) Received: from sohgo.carrots.uucp.r.dl.itc.u-tokyo.ac.jp (localhost [IPv6:::1]) by sohgo.carrots.uucp.r.dl.itc.u-tokyo.ac.jp (8.12.2/3.7W-carrots-Tokyu-Meguro) with ESMTP id g3OBChph026311 ; Wed, 24 Apr 2002 20:12:43 +0900 (JST) Received: (from root@localhost) by sohgo.carrots.uucp.r.dl.itc.u-tokyo.ac.jp (8.12.2/3.7W-submit-carrots-Tokyu-Meguro) with UUCP id g3OBCKeh026310 ; Wed, 24 Apr 2002 20:12:21 +0900 (JST) Received: from bunko.nkth.carrots.uucp.r.dl.itc.u-tokyo.ac.jp (localhost [127.0.0.1]) by bunko (8.12.2/3.7W-nkth.carrots-Saitama-Misono) with ESMTP id g3OB8u8t006194 ; Wed, 24 Apr 2002 20:10:16 +0900 (JST) Message-Id: <200204241110.g3OB8u8t006194@bunko> Date: Wed, 24 Apr 2002 20:08:56 +0900 From: Seigo Tanimura To: current@FreeBSD.org, smp@FreeBSD.org Subject: Locking down a socket, milestone 1 Cc: Seigo Tanimura User-Agent: Wanderlust/2.8.1 (Something) SEMI/1.14.3 (Ushinoya) FLIM/1.14.3 (=?ISO-8859-1?Q?Unebigory=F2mae?=) APEL/10.3 MULE XEmacs/21.1 (patch 14) (Cuyahoga Valley) (i386--freebsd) Organization: Digital Library Research Division, Information Techinology Centre, The University of Tokyo MIME-Version: 1.0 (generated by SEMI 1.14.3 - "Ushinoya") 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 I am now working on locking down a socket. (I have heard that Jeffrey Hsu is also doing that, but I have never seen his patch. Has anyone seen that?) My first milestone patch is now available at: http://people.FreeBSD.org/~tanimura/patches/socket_milestone1.diff.gz The works I have done so far are: - Determine the lock required to protect each of the members in struct socket. - Add mutexes to each of the sockbufs in a socket as BSD/OS does. - Lock down so_count, so_options, so_linger and so_state. - Add a global mutex socq_lock to protect the connection queues of a listening socket. Lock socq_lock to lock two sockets at once, followed by enqueuing or dequeuing a socket, or moving a socket across queues. socq_lock is not an sx lock because we usually have to lock two sockets to modify them. - Add a global sx sigio_lock to protect the pointer to the sigio object of a socket. This is to avoid lock order reversal caused by locking a process in pgsigio(). This lock should be applicable to a pipe as well. Although there are still lots of works to do, the patch has grown up quite a lot. so_options is the most notorious member in struct socket so far because it is used in almost all of the protocol stacks. I would therefore like to test, fix and merge the patch before it blows up. Comments are welcome. Thanks. -- Seigo Tanimura To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Apr 24 7:27:25 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mail.speakeasy.net (mail13.speakeasy.net [216.254.0.213]) by hub.freebsd.org (Postfix) with ESMTP id BF40137B41B for ; Wed, 24 Apr 2002 07:27:19 -0700 (PDT) Received: (qmail 23118 invoked from network); 24 Apr 2002 14:18:53 -0000 Received: from unknown (HELO server.baldwin.cx) ([216.27.160.63]) (envelope-sender ) by mail13.speakeasy.net (qmail-ldap-1.03) with DES-CBC3-SHA encrypted SMTP for ; 24 Apr 2002 14:18:53 -0000 Received: from laptop.baldwin.cx (gw1.twc.weather.com [216.133.140.1]) by server.baldwin.cx (8.11.6/8.11.6) with ESMTP id g3OEIqv06707; Wed, 24 Apr 2002 10:18:52 -0400 (EDT) (envelope-from jhb@FreeBSD.org) Message-ID: X-Mailer: XFMail 1.5.2 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <200204241110.g3OB8u8t006194@bunko> Date: Wed, 24 Apr 2002 10:18:01 -0400 (EDT) From: John Baldwin To: Seigo Tanimura Subject: RE: Locking down a socket, milestone 1 Cc: Seigo Tanimura Cc: Seigo Tanimura , smp@FreeBSD.org, current@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-Apr-2002 Seigo Tanimura wrote: > I am now working on locking down a socket. (I have heard that Jeffrey > Hsu is also doing that, but I have never seen his patch. Has anyone > seen that?) My first milestone patch is now available at: > > > http://people.FreeBSD.org/~tanimura/patches/socket_milestone1.diff.gz > > > The works I have done so far are: > > > - Determine the lock required to protect each of the members in struct > socket. > > - Add mutexes to each of the sockbufs in a socket as BSD/OS does. > > - Lock down so_count, so_options, so_linger and so_state. > > - Add a global mutex socq_lock to protect the connection queues of a > listening socket. Lock socq_lock to lock two sockets at once, > followed by enqueuing or dequeuing a socket, or moving a socket across > queues. socq_lock is not an sx lock because we usually have to lock > two sockets to modify them. Do you actually lock two sockets at once or do you lock one at a time while holding socq_lock. If you do lock two at once, what is the defined locking order? -- John Baldwin <>< http://www.FreeBSD.org/~jhb/ "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 Apr 25 1:10:13 2002 Delivered-To: freebsd-smp@freebsd.org Received: from rina.r.dl.itc.u-tokyo.ac.jp (rina.r.dl.itc.u-tokyo.ac.jp [133.11.199.247]) by hub.freebsd.org (Postfix) with ESMTP id 6F2C337B41B; Thu, 25 Apr 2002 01:10:07 -0700 (PDT) Received: from rina.r.dl.itc.u-tokyo.ac.jp (localhost [127.0.0.1]) by rina.r.dl.itc.u-tokyo.ac.jp (8.12.2/3.7W-rina.r-Nankai-Koya) with ESMTP id g3P8A50o010159 ; Thu, 25 Apr 2002 17:10:05 +0900 (JST) Message-Id: <200204250810.g3P8A50o010159@rina.r.dl.itc.u-tokyo.ac.jp> Date: Thu, 25 Apr 2002 17:10:04 +0900 From: Seigo Tanimura To: Bosko Milekic Cc: Seigo Tanimura , current@FreeBSD.ORG, smp@FreeBSD.ORG Subject: Re: Locking down a socket, milestone 1 In-Reply-To: <20020424085741.A62067@unixdaemons.com> References: <200204241110.g3OB8u8t006194@bunko> User-Agent: Wanderlust/2.8.1 (Something) SEMI/1.14.3 (Ushinoya) FLIM/1.14.3 (=?ISO-8859-1?Q?Unebigory=F2mae?=) APEL/10.3 MULE XEmacs/21.1 (patch 14) (Cuyahoga Valley) (i386--freebsd) Organization: Digital Library Research Division, Information Techinology Centre, The University of Tokyo MIME-Version: 1.0 (generated by SEMI 1.14.3 - "Ushinoya") 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 On Wed, 24 Apr 2002 08:57:41 -0400, Bosko Milekic said: bmilekic> I've literally just had time to glance at this so far, but can you, if bmilekic> you don't mind, please just briefly explain what BSD/OS does with bmilekic> sockbuf locking (do they use the same lock, or...?) In BSD/OS, each of the sockbufs in a socket has a mutex. It protects the data in the sockbuf. In addition, the mutex of the receive sockbuf also protects the whole data of the socket as well. BSD/OS seems to have no global locks to protect the relation between sockets. One thing I am not sure is the lock requirement upon waking up a process tsleeping for socket operation. In BSD/OS, some parts wake up processes with a socket locked, while the other parts not. I am going to make all of the functions calling sowakeup() to lock a socket first. -- Seigo Tanimura To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Apr 25 1:19:12 2002 Delivered-To: freebsd-smp@freebsd.org Received: from rina.r.dl.itc.u-tokyo.ac.jp (rina.r.dl.itc.u-tokyo.ac.jp [133.11.199.247]) by hub.freebsd.org (Postfix) with ESMTP id 511BF37B41D; Thu, 25 Apr 2002 01:19:01 -0700 (PDT) Received: from rina.r.dl.itc.u-tokyo.ac.jp (localhost [127.0.0.1]) by rina.r.dl.itc.u-tokyo.ac.jp (8.12.2/3.7W-rina.r-Nankai-Koya) with ESMTP id g3P8J00o013784 ; Thu, 25 Apr 2002 17:19:00 +0900 (JST) Message-Id: <200204250819.g3P8J00o013784@rina.r.dl.itc.u-tokyo.ac.jp> Date: Thu, 25 Apr 2002 17:19:00 +0900 From: Seigo Tanimura To: John Baldwin Cc: Seigo Tanimura , smp@FreeBSD.org, current@FreeBSD.org Subject: Re: Locking down a socket, milestone 1 In-Reply-To: References: <200204241110.g3OB8u8t006194@bunko> User-Agent: Wanderlust/2.8.1 (Something) SEMI/1.14.3 (Ushinoya) FLIM/1.14.3 (=?ISO-8859-1?Q?Unebigory=F2mae?=) APEL/10.3 MULE XEmacs/21.1 (patch 14) (Cuyahoga Valley) (i386--freebsd) Organization: Digital Library Research Division, Information Techinology Centre, The University of Tokyo MIME-Version: 1.0 (generated by SEMI 1.14.3 - "Ushinoya") 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 On Wed, 24 Apr 2002 10:18:01 -0400 (EDT), John Baldwin said: jhb> On 24-Apr-2002 Seigo Tanimura wrote: >> I am now working on locking down a socket. (I have heard that Jeffrey >> Hsu is also doing that, but I have never seen his patch. Has anyone >> seen that?) My first milestone patch is now available at: >> >> >> http://people.FreeBSD.org/~tanimura/patches/socket_milestone1.diff.gz >> >> >> The works I have done so far are: >> >> >> - Determine the lock required to protect each of the members in struct >> socket. >> >> - Add mutexes to each of the sockbufs in a socket as BSD/OS does. >> >> - Lock down so_count, so_options, so_linger and so_state. >> >> - Add a global mutex socq_lock to protect the connection queues of a >> listening socket. Lock socq_lock to lock two sockets at once, >> followed by enqueuing or dequeuing a socket, or moving a socket across >> queues. socq_lock is not an sx lock because we usually have to lock >> two sockets to modify them. jhb> Do you actually lock two sockets at once or do you lock one at a time while jhb> holding socq_lock. If you do lock two at once, what is the defined locking jhb> order? At the moment, I lock two sockets at once. This is required, eg in soisconnected() to move an accepting socket across the connection queues of a listening socket. The lock order is: 1. socq_lock 2. an accepting socket 3. a listening socket (in so_head of the accepting socket) -- Seigo Tanimura To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Apr 25 1:36:59 2002 Delivered-To: freebsd-smp@freebsd.org Received: from elvis.mu.org (elvis.mu.org [192.203.228.196]) by hub.freebsd.org (Postfix) with ESMTP id 6417337B405; Thu, 25 Apr 2002 01:36:44 -0700 (PDT) Received: by elvis.mu.org (Postfix, from userid 1192) id 1322AAE2E3; Thu, 25 Apr 2002 01:36:44 -0700 (PDT) Date: Thu, 25 Apr 2002 01:36:44 -0700 From: Alfred Perlstein To: Seigo Tanimura Cc: John Baldwin , smp@FreeBSD.org, current@FreeBSD.org Subject: Re: Locking down a socket, milestone 1 Message-ID: <20020425083644.GM38320@elvis.mu.org> References: <200204241110.g3OB8u8t006194@bunko> <200204250819.g3P8J00o013784@rina.r.dl.itc.u-tokyo.ac.jp> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <200204250819.g3P8J00o013784@rina.r.dl.itc.u-tokyo.ac.jp> User-Agent: Mutt/1.3.27i 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 * Seigo Tanimura [020425 01:19] wrote: > >> > >> http://people.FreeBSD.org/~tanimura/patches/socket_milestone1.diff.gz > >> This looks really good so far! Needs some more comments explaining socq_lock. Watch long line wraps. Why is there a "sigio" lock in this delta? -- -Alfred Perlstein [alfred@freebsd.org] 'Instead of asking why a piece of software is using "1970s technology," start asking why software is ignoring 30 years of accumulated wisdom.' Tax deductible donations for FreeBSD: http://www.freebsdfoundation.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Apr 25 2: 1:58 2002 Delivered-To: freebsd-smp@freebsd.org Received: from rina.r.dl.itc.u-tokyo.ac.jp (rina.r.dl.itc.u-tokyo.ac.jp [133.11.199.247]) by hub.freebsd.org (Postfix) with ESMTP id 250C737B400; Thu, 25 Apr 2002 02:01:53 -0700 (PDT) Received: from rina.r.dl.itc.u-tokyo.ac.jp (localhost [127.0.0.1]) by rina.r.dl.itc.u-tokyo.ac.jp (8.12.2/3.7W-rina.r-Nankai-Koya) with ESMTP id g3P91p0o027325 ; Thu, 25 Apr 2002 18:01:51 +0900 (JST) Message-Id: <200204250901.g3P91p0o027325@rina.r.dl.itc.u-tokyo.ac.jp> Date: Thu, 25 Apr 2002 18:01:51 +0900 From: Seigo Tanimura To: Alfred Perlstein Cc: Seigo Tanimura , John Baldwin , smp@FreeBSD.org, current@FreeBSD.org Subject: Re: Locking down a socket, milestone 1 In-Reply-To: <20020425083644.GM38320@elvis.mu.org> References: <200204241110.g3OB8u8t006194@bunko> <200204250819.g3P8J00o013784@rina.r.dl.itc.u-tokyo.ac.jp> <20020425083644.GM38320@elvis.mu.org> User-Agent: Wanderlust/2.8.1 (Something) SEMI/1.14.3 (Ushinoya) FLIM/1.14.3 (=?ISO-8859-1?Q?Unebigory=F2mae?=) APEL/10.3 MULE XEmacs/21.1 (patch 14) (Cuyahoga Valley) (i386--freebsd) Organization: Digital Library Research Division, Information Techinology Centre, The University of Tokyo MIME-Version: 1.0 (generated by SEMI 1.14.3 - "Ushinoya") 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 On Thu, 25 Apr 2002 01:36:44 -0700, Alfred Perlstein said: bright> * Seigo Tanimura [020425 01:19] wrote: >> >> >> >> http://people.FreeBSD.org/~tanimura/patches/socket_milestone1.diff.gz >> >> bright> Why is there a "sigio" lock in this delta? I should have stripped that out, but my patch would result in lock order reversal between a socket lock and a process lock. As we protect p_fd by a process lock, we have to lock it prior to locking a file descriptor or a socket. I suppose I have to commit the stripped patch of a sigio lock first. Speaking of the sigio lock, is that likely to apply to a pipe as well? -- Seigo Tanimura To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Apr 25 7:45: 8 2002 Delivered-To: freebsd-smp@freebsd.org Received: from rina.r.dl.itc.u-tokyo.ac.jp (cvsup2.r.dl.itc.u-tokyo.ac.jp [133.11.199.247]) by hub.freebsd.org (Postfix) with ESMTP id 6F02737B422; Thu, 25 Apr 2002 07:45:01 -0700 (PDT) Received: from silver.carrots.uucp.r.dl.itc.u-tokyo.ac.jp (silver.carrots.uucp.r.dl.itc.u-tokyo.ac.jp [IPv6:3ffe:b80:5b0:3:280:c8ff:fe6b:6d73]) by rina.r.dl.itc.u-tokyo.ac.jp (8.12.2/3.7W-rina.r-Nankai-Koya) with ESMTP id g3PEio0o064224 ; Thu, 25 Apr 2002 23:44:51 +0900 (JST) Received: from silver.carrots.uucp.r.dl.itc.u-tokyo.ac.jp (localhost [127.0.0.1]) by silver.carrots.uucp.r.dl.itc.u-tokyo.ac.jp (8.12.2/3.7W-carrots-Keikyu-Kurihama) with ESMTP id g3PEhTX5017744 ; Thu, 25 Apr 2002 23:44:50 +0900 (JST) Message-Id: <200204251444.g3PEhTX5017744@silver.carrots.uucp.r.dl.itc.u-tokyo.ac.jp> Date: Thu, 25 Apr 2002 23:43:29 +0900 From: Seigo Tanimura To: Alfred Perlstein Cc: Seigo Tanimura , John Baldwin , smp@FreeBSD.org, current@FreeBSD.org Subject: A sigio lock (was: Re: Locking down a socket, milestone 1) In-Reply-To: <200204250901.g3P91p0o027325@rina.r.dl.itc.u-tokyo.ac.jp> References: <200204241110.g3OB8u8t006194@bunko> <200204250819.g3P8J00o013784@rina.r.dl.itc.u-tokyo.ac.jp> <20020425083644.GM38320@elvis.mu.org> <200204250901.g3P91p0o027325@rina.r.dl.itc.u-tokyo.ac.jp> User-Agent: Wanderlust/2.8.1 (Something) SEMI/1.14.3 (Ushinoya) FLIM/1.14.3 (=?ISO-8859-1?Q?Unebigory=F2mae?=) APEL/10.3 MULE XEmacs/21.1 (patch 14) (Cuyahoga Valley) (i386--freebsd) Organization: Digital Library Research Division, Information Techinology Centre, The University of Tokyo MIME-Version: 1.0 (generated by SEMI 1.14.3 - "Ushinoya") 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 On Thu, 25 Apr 2002 18:01:51 +0900, Seigo Tanimura said: Seigo> On Thu, 25 Apr 2002 01:36:44 -0700, Seigo> Alfred Perlstein said: bright> * Seigo Tanimura [020425 01:19] wrote: >>> >> >>> >> http://people.FreeBSD.org/~tanimura/patches/socket_milestone1.diff.gz >>> >> bright> Why is there a "sigio" lock in this delta? Seigo> I should have stripped that out, but my patch would result in lock Seigo> order reversal between a socket lock and a process lock. As we Seigo> protect p_fd by a process lock, we have to lock it prior to locking a Seigo> file descriptor or a socket. Seigo> I suppose I have to commit the stripped patch of a sigio lock first. The patch of a sigio lock is not stripped out at: http://people.FreeBSD.org/~tanimura/patches/sigio.diff.gz -- Seigo Tanimura To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Apr 25 11:36:40 2002 Delivered-To: freebsd-smp@freebsd.org Received: from aurora.sol.net (aurora.sol.net [206.55.65.76]) by hub.freebsd.org (Postfix) with ESMTP id 81B7737B41C; Thu, 25 Apr 2002 11:36:23 -0700 (PDT) Received: (from jgreco@localhost) by aurora.sol.net (8.9.3/8.9.2/SNNS-1.02) id NAA41191; Thu, 25 Apr 2002 13:36:16 -0500 (CDT) From: Joe Greco Message-Id: <200204251836.NAA41191@aurora.sol.net> Subject: Re: kernel trap 9 with interrupts disabled To: dillon@apollo.backplane.com (Matthew Dillon) Date: Thu, 25 Apr 2002 13:36:15 -0500 (CDT) Cc: freebsd-smp@FreeBSD.ORG, freebsd-stable@FreeBSD.ORG In-Reply-To: <200204071822.g37IMbt34515@apollo.backplane.com> from "Matthew Dillon" at Apr 07, 2002 11:22:37 AM X-Mailer: ELM [version 2.5 PL3] 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 > Hmm. Maybe adjust the code to panic the machine when this > situation occurs, then see if you can get a kernel dump out > of it. Looks like I'll be doing that next. Any help available from anyone in looking at that? I'm not big into reading kernel dumps :-) > As to the load issue... that sounds like a classic priority > inversion problem. Check the 'nice' of all the processes in > the system and see if some nice'd-down processes are hogging > the cpu. 'ps axlww' in a big window. Hmmm. I did just notice something. I run setiathome everywhere using a little daemon that punts it down to idprio etc. I just tried to kill them and they didn't, and I looked again and it's because they're running at 0.0%, so then I idprio -t -'d them, and when I did that to the first one, my login session froze for the better part of a minute. It remained pingable but apparently unresponsive. Then it recovered. The second one went as expected. > Also look at the user cpu verses system cpu percentage to see > where the cpu is going. Here's top, any hints? (note: the names have been changed to protect the innocent) last pid: 3145; load averages: 13.60, 13.97, 14.05 up 18+14:27:19 13:26:35 63 processes: 15 running, 47 sleeping, 1 stopped CPU states: 4.5% user, 0.0% nice, 94.8% system, 0.6% interrupt, 0.0% idle Mem: 142M Active, 656M Inact, 145M Wired, 47M Cache, 112M Buf, 14M Free Swap: 2048M Total, 56K Used, 2048M Free PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU CPU COMMAND 78128 useruser 63 0 34696K 33896K RUN 0 83:26 31.30% 31.30% nit 78596 useruser 64 0 18716K 17896K RUN 0 79:59 31.10% 31.10% nit 78959 useruser 64 0 15872K 14728K RUN 0 79:30 29.93% 29.93% nit 57493 use 63 0 6412K 5804K RUN 1 601:36 13.43% 13.43% perl 99887 useruser 63 0 14200K 10420K CPU1 1 3:26 13.09% 13.09% perl 99918 use 64 0 1060K 656K RUN 1 2:26 11.33% 11.33% funny 2059 useruser 63 0 2220K 1424K RUN 1 0:59 11.18% 11.18% grep 507 use 63 0 1060K 656K RUN 1 1:47 9.52% 9.52% funny 1363 use 61 0 1060K 632K RUN 0 0:57 8.98% 8.98% funny 2555 use 63 0 1060K 632K RUN 1 0:34 8.30% 8.30% funny 3127 use 62 0 1060K 596K RUN 0 0:02 9.38% 6.10% funny 1028 root 2 0 964K 572K select 1 42:59 2.73% 2.73% syslogd 3104 use 2 0 1060K 576K sbwait 0 0:01 1.55% 1.22% funny 2945 root 35 0 1996K 1148K CPU0 1 0:02 0.93% 0.93% top 3106 use 2 0 1060K 656K sbwait 1 0:01 1.12% 0.88% funny 3145 use 2 0 1060K 596K sbwait 0 0:00 9.00% 0.44% funny 99230 nobody 37 52 16556K 16424K RUN 1 182.4H 0.00% 0.00% setiathome 21867 nobody 37 52 16556K 16428K RUN 0 171.6H 0.00% 0.00% setiathome 966 root 2 0 1648K 744K select 0 4:27 0.00% 0.00% ntpd 945 bind 2 0 3300K 2608K select 0 2:53 0.00% 0.00% named-dns 1047 root 10 0 1228K 848K nanslp 0 1:22 0.00% 0.00% mon 893 root 10 0 1004K 652K nanslp 0 1:19 0.00% 0.00% cron 57483 use 2 0 896K 400K sbwait 0 1:09 0.00% 0.00% wont 895 root 2 0 2224K 1172K select 0 0:50 0.00% 0.00% sshd 57488 use 2 0 4600K 4096K sbwait 1 0:48 0.00% 0.00% perl 57496 use 2 0 896K 504K accept 1 0:42 0.00% 0.00% mrdata 5828 root 2 0 2308K 1688K select 1 0:24 0.00% 0.00% sshd 950 nobody 2 0 928K 380K select 0 0:10 0.00% 0.00% identd 887 daemon 2 0 904K 540K sbwait 0 0:07 0.00% 0.00% rwhod 72401 userus 3 0 2628K 2244K ttyin 1 0:05 0.00% 0.00% zsh 25432 root 2 0 2348K 1728K select 0 0:04 0.00% 0.00% sshd 72398 root 2 0 2308K 1412K select 0 0:03 0.00% 0.00% sshd 2014 userxx 3 0 2792K 2304K ttyin 0 0:03 0.00% 0.00% lynx 1676 root 2 0 2316K 1636K select 0 0:03 0.00% 0.00% sshd 25551 useruser 3 0 1484K 1068K ttyin 0 0:02 0.00% 0.00% tcsh 2778 root 36 0 1996K 1144K STOP 0 0:02 0.00% 0.00% top 1206 root 28 0 2308K 1632K RUN 0 0:02 0.00% 0.00% sshd 98311 useruser 10 0 640K 280K wait 0 0:01 0.00% 0.00% sh 2777 root 2 -20 1992K 1152K select 1 0:01 0.00% 0.00% top 1248 root 18 0 1384K 992K pause 1 0:00 0.00% 0.00% tcsh 1679 userxx 18 0 2400K 2064K pause 1 0:00 0.00% 0.00% zsh 1207 jgreco 18 0 1380K 992K pause 1 0:00 0.00% 0.00% tcsh 5904 useruser 3 0 1452K 1040K ttyin 1 0:00 0.00% 0.00% tcsh 1008 root 2 0 3320K 2156K select 1 0:00 0.00% 0.00% snmpd 99852 useruser 10 0 1028K 600K wait 0 0:00 0.00% 0.00% bash 98623 mailnull -6 0 2524K 1780K piperd 0 0:00 0.00% 0.00% sendmail 998 nobody 10 52 896K 492K wait 1 0:00 0.00% 0.00% setidaemon 2768 root 10 0 628K 268K wait 1 0:00 0.00% 0.00% sh 98280 useruser 10 0 628K 268K wait 1 0:00 0.00% 0.00% sh 2762 root 10 0 636K 276K wait 1 0:00 0.00% 0.00% sh 98293 useruser 10 0 640K 280K wait 0 0:00 0.00% 0.00% sh 99850 useruser 10 0 628K 268K wait 1 0:00 0.00% 0.00% sh 1036 root 3 0 948K 456K ttyin 1 0:00 0.00% 0.00% getty 1038 root 3 0 948K 456K ttyin 1 0:00 0.00% 0.00% getty 1039 root 10 0 636K 232K wait 0 0:00 0.00% 0.00% sh -- Joe Greco - sol.net Network Services - Milwaukee, WI - http://www.sol.net "We call it the 'one bite at the apple' rule. Give me one chance [and] then I won't contact you again." - Direct Markenitg Ass'n position on e-mail spam(CNN) With 24 million small businesses in the US alone, that's way too many apples. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Apr 25 14:15:27 2002 Delivered-To: freebsd-smp@freebsd.org Received: from apollo.backplane.com (apollo.backplane.com [216.240.41.2]) by hub.freebsd.org (Postfix) with ESMTP id 7248E37B417; Thu, 25 Apr 2002 14:15:13 -0700 (PDT) Received: (from dillon@localhost) by apollo.backplane.com (8.11.6/8.9.1) id g3PLF6c07119; Thu, 25 Apr 2002 14:15:06 -0700 (PDT) (envelope-from dillon) Date: Thu, 25 Apr 2002 14:15:06 -0700 (PDT) From: Matthew Dillon Message-Id: <200204252115.g3PLF6c07119@apollo.backplane.com> To: Joe Greco Cc: freebsd-smp@FreeBSD.ORG, freebsd-stable@FreeBSD.ORG Subject: Re: kernel trap 9 with interrupts disabled References: <200204251836.NAA41191@aurora.sol.net> 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 :> Hmm. Maybe adjust the code to panic the machine when this :> situation occurs, then see if you can get a kernel dump out :> of it. : :Looks like I'll be doing that next. Any help available from anyone in :looking at that? I'm not big into reading kernel dumps :-) : :> As to the load issue... that sounds like a classic priority :> inversion problem. Check the 'nice' of all the processes in :> the system and see if some nice'd-down processes are hogging :> the cpu. 'ps axlww' in a big window. : :Hmmm. I did just notice something. I run setiathome everywhere using a :little daemon that punts it down to idprio etc. I just tried to kill them :and they didn't, and I looked again and it's because they're running at :0.0%, so then I idprio -t -'d them, and when I did that to the first :one, my login session froze for the better part of a minute. It remained :pingable but apparently unresponsive. Then it recovered. The second one :went as expected. : :> Also look at the user cpu verses system cpu percentage to see :> where the cpu is going. : :Here's top, any hints? (note: the names have been changed to protect the :innocent) The classic priority inversion problem occurs when you have a low priority process blocked on I/O and a higher priority process monopolizing the cpu. Even though the lower priority process is woken up by the kernel, it doesn't get cpu until there are no runnable higher priority processes and so it is unable to release any locks it might have been holding for the I/O. The FreeBSD-stable scheduler will dynamically alter the priority of a running process, which prevents the priority inversion from locking up the machine when all the processes in question are on the normal scheduler queue. But it can't cross priority queues so if you have a process on the idle priority queue it can get 'stuck' in a system call while holding a lock (like on a directory vnode or something) and then never get the cpu *at* *all* while other normal processes are monopolizing the cpu. As other normal processes try to obtain the lock they block, locking the whole system up (except for the higher priority processes monopolizing the cpu, but for all intents and purposes the system is locked up). I believe FreeBSD-current solves this problem by aggregating the three priority queues we had in -stable into a single queue for -current, and then allowing a higher priority process to 'lend' its priority to a lower priority process that is holding a lock that the higher priority process wants. I don't know if it's been 100% implemented yet. You could ask John (JHB). In your case I'm sure the normal priority 'nit' and other cpu intensive processes combined with the idprio setiathome processes are creating this problem. I recommend either not running setiathome, or running it with a normal NICE (like nice +19). Alternatively you might consider running -current but I would not recommend it for a production environment yet. -Matt Matthew Dillon :last pid: 3145; load averages: 13.60, 13.97, 14.05 up 18+14:27:19 13:26:35 :63 processes: 15 running, 47 sleeping, 1 stopped :CPU states: 4.5% user, 0.0% nice, 94.8% system, 0.6% interrupt, 0.0% idle :Mem: 142M Active, 656M Inact, 145M Wired, 47M Cache, 112M Buf, 14M Free :Swap: 2048M Total, 56K Used, 2048M Free : : PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU CPU COMMAND :78128 useruser 63 0 34696K 33896K RUN 0 83:26 31.30% 31.30% nit :78596 useruser 64 0 18716K 17896K RUN 0 79:59 31.10% 31.10% nit :78959 useruser 64 0 15872K 14728K RUN 0 79:30 29.93% 29.93% nit :57493 use 63 0 6412K 5804K RUN 1 601:36 13.43% 13.43% perl :99887 useruser 63 0 14200K 10420K CPU1 1 3:26 13.09% 13.09% perl :99918 use 64 0 1060K 656K RUN 1 2:26 11.33% 11.33% funny : 2059 useruser 63 0 2220K 1424K RUN 1 0:59 11.18% 11.18% grep : 507 use 63 0 1060K 656K RUN 1 1:47 9.52% 9.52% funny : 1363 use 61 0 1060K 632K RUN 0 0:57 8.98% 8.98% funny :... : 3145 use 2 0 1060K 596K sbwait 0 0:00 9.00% 0.44% funny :99230 nobody 37 52 16556K 16424K RUN 1 182.4H 0.00% 0.00% setiathome :21867 nobody 37 52 16556K 16428K RUN 0 171.6H 0.00% 0.00% setiathome :-- :Joe Greco - sol.net Network Services - Milwaukee, WI - http://www.sol.net To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message