From owner-freebsd-smp@FreeBSD.ORG Sat Jan 1 12:07:48 2005 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D324916A4CE; Sat, 1 Jan 2005 12:07:48 +0000 (GMT) Received: from emaile.wplus.net (nospam.wplus.net [195.131.104.155]) by mx1.FreeBSD.org (Postfix) with ESMTP id E461743D53; Sat, 1 Jan 2005 12:07:47 +0000 (GMT) (envelope-from pvtrifonov@mail.ru) Envelope-to: freebsd-smp@FreeBSD.org, jhb@FreeBSD.org Received: by emaile.wplus.net with drweb-scanned (WebPlus antispam mailer ) id 1Cki2r-0007aT-00; Sat, 01 Jan 2005 15:07:45 +0300 Received: from [195.131.108.59] (helo=bug) by emaile.wplus.net with esmtp (WebPlus antispam mailer ) id 1Cki2q-0007aN-00; Sat, 01 Jan 2005 15:07:45 +0300 From: "Peter Trifonov" To: "'John Baldwin'" , Date: Sat, 1 Jan 2005 15:07:47 +0300 MIME-Version: 1.0 Content-Type: text/plain; charset="koi8-r" Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Office Outlook, Build 11.0.5510 In-Reply-To: <200412311337.19041.jhb@FreeBSD.org> X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2180 Thread-Index: AcTvcGTQF+38rMoOThC9ffzv3LB8mAAiTJdg Message-Id: X-IP: 195.131.108.59 X-From: pvtrifonov@mail.ru cc: kris@obsecurity.org Subject: RE: Lost interrupts on SMP systems X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 01 Jan 2005 12:07:49 -0000 Hello John, Thank you very much for investigating this problem. > > > > I am running FreeBSD 5.3 RELEASE > > > Can you get a verbose dmesg please? > > ioapic0: Assuming intbase of 0 > > MPTable: Ignoring global interrupt entry for pin 1 > > MPTable: Ignoring global interrupt entry for pin 15 > Ok, well, this is a bit of a problem here. Basically, this > means you don't have any working interrupts as far as I can What does this message mean? In fact, top command reports 0.2-1.0% CPU time used for interrupts. > tell. Can you get the output of > mptable(8) for me? Here it is: mptable -verbose -grope ============================================================================ === MPTable, version 2.0.15 looking for EBDA pointer @ 0x040e, found, searching EBDA @ 0x0009f800 searching CMOS 'top of mem' @ 0x0009f400 (637K) searching default 'top of mem' @ 0x0009fc00 (639K) searching BIOS @ 0x000f0000 MP FPS found in BIOS @ physical addr: 0x000f99a0 ---------------------------------------------------------------------------- --- MP Floating Pointer Structure: location: BIOS physical address: 0x000f99a0 signature: '_MP_' length: 16 bytes version: 1.1 checksum: 0x4b mode: Virtual Wire ---------------------------------------------------------------------------- --- MP Config Table Header: physical address: 0x000f99b0 signature: 'PCMP' base table length: 236 version: 1.1 checksum: 0xe0 OEM ID: 'HP ' Product ID: 'XX ' OEM table pointer: 0x00000000 OEM table size: 0 entry count: 21 local APIC address: 0xfee00000 extended table length: 0 extended table checksum: 0 ---------------------------------------------------------------------------- --- MP Config Base Table Entries: -- Processors: APIC ID Version State Family Model Step Flags 1 0x11 BSP, usable 6 1 0 0xfbff 0 0x11 AP, usable 6 1 0 0xfbff -- Bus: Bus ID Type 1 ISA 0 PCI -- I/O APICs: APIC ID Version State Address 16 0x11 usable 0xfec00000 -- I/O Ints: Type Polarity Trigger Bus ID IRQ APIC ID PIN# INT conforms conforms 1 1 255 1 INT conforms conforms 1 0 255 2 INT conforms conforms 1 3 255 3 INT conforms conforms 1 4 255 4 INT conforms conforms 1 5 255 5 INT conforms conforms 1 6 255 6 INT conforms conforms 1 7 255 7 INT conforms conforms 1 8 255 8 INT conforms conforms 1 9 255 9 INT conforms conforms 1 10 255 10 INT conforms conforms 1 11 255 11 INT conforms conforms 1 12 255 12 INT conforms conforms 1 13 255 13 INT conforms conforms 1 14 255 14 INT conforms conforms 1 15 255 15 -- Local Ints: Type Polarity Trigger Bus ID IRQ APIC ID PIN# NMI conforms conforms 1 2 255 1 ============================================================================ === With best regards, P. Trifonov