We recently invested in a new database server (MySQL), a Dual P4 Xeon (2 x
2GHz Prestonia, 1GB RDRAM) system, it's mainboard is a Supermicro P4DCE+
based on the i860 chipset.
After installing 2.4.17 and experiencing random lockups with an interval
of about two days (lockup = totally dead, only cold boot could solve it
and no info in the logs), we installed the latest BIOS for the mainboard
and upgraded kernel to 2.4.18rc4. The problems continued and we gave up on
2.4 and tried installing a clean 2.2.20.
However, while booting 2.2.20, the following messages appear:
Keyboard: Timeout - AT keyboard not present?
hda: WDC WD1000JB-32CWE0, ATA DISK drive
hdc: WDC WD1000JB-32CWE0, ATA DISK drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
ide1 at 0x170-0x177,0x376 on irq 15
hda: lost interrupt
hda: lost interrupt
hda: lost interrupt
hda: WDC WD1000JB-32CWE0, 95396MB w/8192kB Cache, CHS=12161/255/63
hdc: lost interrupt
hdc: lost interrupt
hdc: lost interrupt
hdc: WDC WD1000JB-32CWE0, 95396MB w/8192kB Cache, CHS=193821/16/63
Floppy drived(s): fd0 is 1.44M
floppy0: no floppy controllers found
...then after initiating the NIC etc....:
Partition check:
hda:hda: lost interrupt
hda: lost interrupt
hda1 hda2 hda3 hda4
hdc:hdc: lost interrupt
hdc: lost interrupt
[PTBL] [12161/255/63] hdc1 hdc2 hdc3 hdc4
hda: lost interrupt
hda: lost interrupt
hda: lost interrupt
hda: lost interrupt
....
...and the last message repeated over and over. After having read the
archives of this list and the problems with the IDE controller PIIX4, I
tried installing a new IDE patch on 2.2.20, tried disabling DMA in kernel
and then in BIOS, tried changing from 80pin IDE cables to 40pin but
nothing changed, the above error messages continued coming. I suspect this
failure to boot issue in 2.2 can be related to the random lockups in 2.4,
could that be the case?
When booting 2.4, I get the following messages:
Feb 27 18:33:22 db2 kernel: Linux version 2.4.18-rc4 (root@db2) (gcc
version 2.95.3 20010315 (release)) #1 SMP Sat Feb 23 01:27:10 CET 2002
Feb 27 18:33:22 db2 kernel: BIOS-provided physical RAM map:
Feb 27 18:33:22 db2 kernel: BIOS-e820: 0000000000000000 -
00000000000a0000 (usable)
Feb 27 18:33:22 db2 kernel: BIOS-e820: 00000000000f0000 -
0000000000100000 (reserved)
Feb 27 18:33:22 db2 kernel: BIOS-e820: 0000000000100000 -
000000003fff0000 (usable)
Feb 27 18:33:22 db2 kernel: BIOS-e820: 000000003fff0000 -
000000003fff3000 (ACPI NVS)
Feb 27 18:33:22 db2 kernel: BIOS-e820: 000000003fff3000 -
0000000040000000 (ACPI data)
Feb 27 18:33:22 db2 kernel: BIOS-e820: 00000000fec00000 -
0000000100000000 (reserved)
Feb 27 18:33:22 db2 kernel: 127MB HIGHMEM available.
Feb 27 18:33:22 db2 kernel: found SMP MP-table at 000f5010
Feb 27 18:33:22 db2 kernel: hm, page 000f5000 reserved twice.
Feb 27 18:33:22 db2 kernel: hm, page 000f6000 reserved twice.
Feb 27 18:33:22 db2 kernel: hm, page 000f1000 reserved twice.
Feb 27 18:33:22 db2 kernel: hm, page 000f2000 reserved twice.
Feb 27 18:33:22 db2 kernel: On node 0 totalpages: 262128
Feb 27 18:33:22 db2 kernel: zone(0): 4096 pages.
Feb 27 18:33:22 db2 kernel: zone(1): 225280 pages.
Feb 27 18:33:22 db2 kernel: zone(2): 32752 pages.
Feb 27 18:33:22 db2 kernel: Intel MultiProcessor Specification v1.1
Feb 27 18:33:22 db2 kernel: Virtual Wire compatibility mode.
Feb 27 18:33:22 db2 kernel: OEM ID: OEM00000 Product ID: PROD00000000 APIC
at: 0xFEE00000
Feb 27 18:33:22 db2 kernel: Processor #0 Unknown CPU [15:2] APIC version
17
Feb 27 18:33:22 db2 kernel: Processor #1 Unknown CPU [15:2] APIC version
17
Feb 27 18:33:22 db2 kernel: I/O APIC #2 Version 17 at 0xFEC00000.
Feb 27 18:33:22 db2 kernel: Processors: 2
Feb 27 18:33:22 db2 kernel: Kernel command line: BOOT_IMAGE=linux ro
root=301
Feb 27 18:33:22 db2 kernel: Initializing CPU#0
Feb 27 18:33:22 db2 kernel: Detected 1982.582 MHz processor.
Feb 27 18:33:22 db2 kernel: Console: colour VGA+ 80x25
Feb 27 18:33:22 db2 kernel: Calibrating delay loop... 3958.37 BogoMIPS
Feb 27 18:33:22 db2 kernel: Memory: 1029988k/1048512k available (823k
kernel code, 18140k reserved, 224k data, 212k init, 131008k highmem)
Feb 27 18:33:22 db2 kernel: Dentry-cache hash table entries: 131072
(order: 8, 1048576 bytes)
Feb 27 18:33:22 db2 kernel: Inode-cache hash table entries: 65536 (order:
7, 524288 bytes)
Feb 27 18:33:22 db2 kernel: Mount-cache hash table entries: 16384 (order:
5, 131072 bytes)
Feb 27 18:33:22 db2 kernel: Buffer-cache hash table entries: 65536 (order:
6, 262144 bytes)
Feb 27 18:33:22 db2 kernel: Page-cache hash table entries: 262144 (order:
8, 1048576 bytes)
Feb 27 18:33:22 db2 kernel: CPU: Before vendor init, caps: 3febfbff
00000000 00000000, vendor = 0
Feb 27 18:33:22 db2 kernel: CPU: L1 I cache: 12K, L1 D cache: 8K
Feb 27 18:33:22 db2 kernel: CPU: L2 cache: 512K
Feb 27 18:33:22 db2 kernel: CPU: Physical Processor ID: 0
Feb 27 18:33:22 db2 kernel: CPU: After vendor init, caps: 3febfbff
00000000 00000000 00000000
Feb 27 18:33:22 db2 kernel: Intel machine check architecture supported.
Feb 27 18:33:22 db2 kernel: Intel machine check reporting enabled on
CPU#0.
Feb 27 18:33:22 db2 kernel: CPU: After generic, caps: 3febfbff
00000000 00000000 00000000
Feb 27 18:33:22 db2 kernel: CPU: Common caps: 3febfbff
00000000 00000000 00000000
Feb 27 18:33:22 db2 kernel: Enabling fast FPU save and restore... done.
Feb 27 18:33:22 db2 kernel: Enabling unmasked SIMD FPU exception
support... done.
Feb 27 18:33:22 db2 kernel: Checking 'hlt' instruction... OK.
Feb 27 18:33:22 db2 kernel: POSIX conformance testing by UNIFIX
Feb 27 18:33:22 db2 kernel: mtrr: v1.40 (20010327) Richard Gooch
([email protected])
Feb 27 18:33:22 db2 kernel: mtrr: detected mtrr type: Intel
Feb 27 18:33:22 db2 kernel: CPU: Before vendor init, caps: 3febfbff
00000000 00000000, vendor = 0
Feb 27 18:33:22 db2 kernel: CPU: L1 I cache: 12K, L1 D cache: 8K
Feb 27 18:33:22 db2 kernel: CPU: L2 cache: 512K
Feb 27 18:33:22 db2 kernel: CPU: Physical Processor ID: 0
Feb 27 18:33:22 db2 kernel: CPU: After vendor init, caps: 3febfbff
00000000 00000000 00000000
Feb 27 18:33:22 db2 kernel: Intel machine check reporting enabled on
CPU#0.
Feb 27 18:33:22 db2 kernel: CPU: After generic, caps: 3febfbff
00000000 00000000 00000000
Feb 27 18:33:22 db2 kernel: CPU: Common caps: 3febfbff
00000000 00000000 00000000
Feb 27 18:33:22 db2 kernel: CPU0: Intel(R) XEON(TM) CPU 2.00GHz stepping
04
Feb 27 18:33:22 db2 kernel: per-CPU timeslice cutoff: 1463.19 usecs.
Feb 27 18:33:22 db2 kernel: enabled ExtINT on CPU#0
Feb 27 18:33:22 db2 kernel: ESR value before enabling vector: 00000000
Feb 27 18:33:22 db2 kernel: ESR value after enabling vector: 00000000
Feb 27 18:33:22 db2 kernel: Booting processor 1/1 eip 2000
Feb 27 18:33:22 db2 kernel: Initializing CPU#1
Feb 27 18:33:22 db2 kernel: masked ExtINT on CPU#1
Feb 27 18:33:22 db2 kernel: ESR value before enabling vector: 00000000
Feb 27 18:33:22 db2 kernel: ESR value after enabling vector: 00000000
Feb 27 18:33:22 db2 kernel: Calibrating delay loop... 3958.37 BogoMIPS
Feb 27 18:33:22 db2 kernel: CPU: Before vendor init, caps: 3febfbff
00000000 00000000, vendor = 0
Feb 27 18:33:22 db2 kernel: CPU: L1 I cache: 12K, L1 D cache: 8K
Feb 27 18:33:22 db2 kernel: CPU: L2 cache: 512K
Feb 27 18:33:22 db2 kernel: CPU: Physical Processor ID: 3
Feb 27 18:33:22 db2 kernel: CPU: After vendor init, caps: 3febfbff
00000000 00000000 00000000
Feb 27 18:33:22 db2 kernel: Intel machine check reporting enabled on
CPU#1.
Feb 27 18:33:22 db2 kernel: CPU: After generic, caps: 3febfbff
00000000 00000000 00000000
Feb 27 18:33:22 db2 kernel: CPU: Common caps: 3febfbff
00000000 00000000 00000000
Feb 27 18:33:22 db2 kernel: CPU1: Intel(R) XEON(TM) CPU 2.00GHz stepping
04
Feb 27 18:33:22 db2 kernel: Total of 2 processors activated (7916.74
BogoMIPS).
Feb 27 18:33:22 db2 kernel: WARNING: No sibling found for CPU 0.
Feb 27 18:33:22 db2 kernel: WARNING: No sibling found for CPU 1.
Feb 27 18:33:22 db2 kernel: ENABLING IO-APIC IRQs
Feb 27 18:33:22 db2 kernel: Setting 2 in the phys_id_present_map
Feb 27 18:33:22 db2 kernel: ...changing IO-APIC physical APIC ID to 2 ...
ok.
Feb 27 18:33:22 db2 kernel: init IO_APIC IRQs
Feb 27 18:33:22 db2 kernel: IO-APIC (apicid-pin) 2-0, 2-5, 2-10, 2-11,
2-12, 2-18, 2-20, 2-21, 2-22 not connected.
Feb 27 18:33:22 db2 kernel: ..TIMER: vector=0x31 pin1=2 pin2=0
Feb 27 18:33:22 db2 kernel: number of MP IRQ sources: 16.
Feb 27 18:33:22 db2 kernel: number of IO-APIC #2 registers: 24.
Feb 27 18:33:22 db2 kernel: testing the IO APIC.......................
Feb 27 18:33:22 db2 kernel:
Feb 27 18:33:22 db2 kernel: IO APIC #2......
Feb 27 18:33:22 db2 kernel: .... register #00: 02000000
Feb 27 18:33:22 db2 kernel: ....... : physical APIC id: 02
Feb 27 18:33:22 db2 kernel: .... register #01: 00178020
Feb 27 18:33:22 db2 kernel: ....... : max redirection entries: 0017
Feb 27 18:33:22 db2 kernel: ....... : PRQ implemented: 1
Feb 27 18:33:22 db2 kernel: ....... : IO APIC version: 0020
Feb 27 18:33:22 db2 kernel: .... register #02: 00000000
Feb 27 18:33:22 db2 kernel: ....... : arbitration: 00
Feb 27 18:33:22 db2 kernel: .... IRQ redirection table:
Feb 27 18:33:22 db2 kernel: NR Log Phy Mask Trig IRR Pol Stat Dest Deli
Vect:
Feb 27 18:33:22 db2 kernel: 00 000 00 1 0 0 0 0 0 0
00
Feb 27 18:33:22 db2 kernel: 01 003 03 0 0 0 0 0 1 1
39
Feb 27 18:33:23 db2 kernel: 02 003 03 0 0 0 0 0 1 1
31
Feb 27 18:33:23 db2 kernel: 03 003 03 0 0 0 0 0 1 1
41
Feb 27 18:33:23 db2 kernel: 04 003 03 0 0 0 0 0 1 1
49
Feb 27 18:33:23 db2 kernel: 05 000 00 1 0 0 0 0 0 0
00
Feb 27 18:33:23 db2 kernel: 06 003 03 0 0 0 0 0 1 1
51
Feb 27 18:33:23 db2 kernel: 07 003 03 0 0 0 0 0 1 1
59
Feb 27 18:33:23 db2 kernel: 08 003 03 0 0 0 0 0 1 1
61
Feb 27 18:33:23 db2 kernel: 09 003 03 0 0 0 0 0 1 1
69
Feb 27 18:33:23 db2 kernel: 0a 000 00 1 0 0 0 0 0 0
00
Feb 27 18:33:23 db2 kernel: 0b 000 00 1 0 0 0 0 0 0
00
Feb 27 18:33:23 db2 kernel: 0c 000 00 1 0 0 0 0 0 0
00
Feb 27 18:33:23 db2 kernel: 0d 003 03 0 0 0 0 0 1 1
71
Feb 27 18:33:23 db2 kernel: 0e 003 03 0 0 0 0 0 1 1
79
Feb 27 18:33:23 db2 kernel: 0f 003 03 0 0 0 0 0 1 1
81
Feb 27 18:33:23 db2 kernel: 10 003 03 1 1 0 1 0 1 1
89
Feb 27 18:33:23 db2 kernel: 11 003 03 1 1 0 1 0 1 1
91
Feb 27 18:33:23 db2 kernel: 12 000 00 1 0 0 0 0 0 0
00
Feb 27 18:33:23 db2 kernel: 13 003 03 1 1 0 1 0 1 1
99
Feb 27 18:33:23 db2 kernel: 14 000 00 1 0 0 0 0 0 0
00
Feb 27 18:33:23 db2 kernel: 15 000 00 1 0 0 0 0 0 0
00
Feb 27 18:33:23 db2 kernel: 16 000 00 1 0 0 0 0 0 0
00
Feb 27 18:33:23 db2 kernel: 17 003 03 1 1 0 1 0 1 1
A1
Feb 27 18:33:23 db2 kernel: IRQ to pin mappings:
Feb 27 18:33:23 db2 kernel: IRQ0 -> 0:2
Feb 27 18:33:23 db2 kernel: IRQ1 -> 0:1
Feb 27 18:33:23 db2 kernel: IRQ3 -> 0:3
Feb 27 18:33:23 db2 kernel: IRQ4 -> 0:4
Feb 27 18:33:23 db2 kernel: IRQ5 -> 0:23
Feb 27 18:33:23 db2 kernel: IRQ6 -> 0:6
Feb 27 18:33:23 db2 kernel: IRQ7 -> 0:7
Feb 27 18:33:23 db2 kernel: IRQ8 -> 0:8
Feb 27 18:33:23 db2 kernel: IRQ9 -> 0:9
Feb 27 18:33:23 db2 kernel: IRQ10 -> 0:19
Feb 27 18:33:23 db2 kernel: IRQ11 -> 0:16
Feb 27 18:33:23 db2 kernel: IRQ12 -> 0:17
Feb 27 18:33:23 db2 kernel: IRQ13 -> 0:13
Feb 27 18:33:23 db2 kernel: IRQ14 -> 0:14
Feb 27 18:33:23 db2 kernel: IRQ15 -> 0:15
Feb 27 18:33:23 db2 kernel: .................................... done.
Feb 27 18:33:23 db2 kernel: Using local APIC timer interrupts.
Feb 27 18:33:23 db2 kernel: calibrating APIC timer ...
Feb 27 18:33:23 db2 kernel: ..... CPU clock speed is 1982.5358 MHz.
Feb 27 18:33:23 db2 kernel: ..... host bus clock speed is 99.1267 MHz.
Feb 27 18:33:23 db2 kernel: cpu: 0, clocks: 991267, slice: 330422
Feb 27 18:33:23 db2 kernel:
CPU0<T0:991264,T1:660832,D:10,S:330422,C:991267>
Feb 27 18:33:23 db2 kernel: cpu: 1, clocks: 991267, slice: 330422
Feb 27 18:33:23 db2 kernel:
CPU1<T0:991264,T1:330416,D:4,S:330422,C:991267>
Feb 27 18:33:23 db2 kernel: checking TSC synchronization across CPUs:
passed.
Feb 27 18:33:23 db2 kernel: Waiting on wait_init_idle (map = 0x2)
Feb 27 18:33:23 db2 kernel: All processors have done init_idle
Feb 27 18:33:23 db2 kernel: mtrr: your CPUs had inconsistent fixed MTRR
settings
Feb 27 18:33:23 db2 kernel: mtrr: probably your BIOS does not setup all
CPUs
Feb 27 18:33:23 db2 kernel: PCI: PCI BIOS revision 2.10 entry at 0xfb3e0,
last bus=4
Feb 27 18:33:23 db2 kernel: PCI: Using configuration type 1
Feb 27 18:33:23 db2 kernel: PCI: Probing PCI hardware
Feb 27 18:33:23 db2 kernel: Unknown bridge resource 0: assuming
transparent
Feb 27 18:33:23 db2 kernel: Unknown bridge resource 1: assuming
transparent
Feb 27 18:33:23 db2 kernel: Unknown bridge resource 2: assuming
transparent
Feb 27 18:33:23 db2 kernel: Unknown bridge resource 0: assuming
transparent
Feb 27 18:33:23 db2 kernel: Unknown bridge resource 2: assuming
transparent
Feb 27 18:33:23 db2 kernel: Unknown bridge resource 0: assuming
transparent
Feb 27 18:33:23 db2 kernel: Unknown bridge resource 2: assuming
transparent
Feb 27 18:33:23 db2 kernel: Unknown bridge resource 2: assuming
transparent
Feb 27 18:33:23 db2 kernel: PCI: Using IRQ router PIIX [8086/2440] at
00:1f.0
Feb 27 18:33:23 db2 kernel: Linux NET4.0 for Linux 2.4
Feb 27 18:33:23 db2 kernel: Based upon Swansea University Computer Society
NET3.039
Feb 27 18:33:23 db2 kernel: Initializing RT netlink socket
Feb 27 18:33:23 db2 kernel: Starting kswapd
Feb 27 18:33:23 db2 kernel: allocated 32 pages and 32 bhs reserved for the
highmem bounces
Feb 27 18:33:23 db2 kernel: Real Time Clock Driver v1.10e
Feb 27 18:33:23 db2 kernel: block: 128 slots per queue, batch=32
Feb 27 18:33:23 db2 kernel: Uniform Multi-Platform E-IDE driver Revision:
6.31
Feb 27 18:33:23 db2 kernel: ide: Assuming 33MHz system bus speed for PIO
modes; override with idebus=xx
Feb 27 18:33:23 db2 kernel: PIIX4: IDE controller on PCI bus 00 dev f9
Feb 27 18:33:23 db2 kernel: PIIX4: chipset revision 4
Feb 27 18:33:23 db2 kernel: PIIX4: not 100%% native mode: will probe irqs
later
Feb 27 18:33:23 db2 kernel: ide0: BM-DMA at 0xf000-0xf007, BIOS
settings: hda:DMA, hdb:pio
Feb 27 18:33:23 db2 kernel: ide1: BM-DMA at 0xf008-0xf00f, BIOS
settings: hdc:DMA, hdd:pio
Feb 27 18:33:23 db2 kernel: hda: WDC WD1000JB-32CWE0, ATA DISK drive
Feb 27 18:33:23 db2 kernel: hdc: WDC WD1000JB-32CWE0, ATA DISK drive
Feb 27 18:33:23 db2 kernel: ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
Feb 27 18:33:23 db2 kernel: ide1 at 0x170-0x177,0x376 on irq 15
Feb 27 18:33:23 db2 kernel: hda: 195371568 sectors (100030 MB) w/8192KiB
Cache, CHS=12161/255/63, UDMA(33)
Feb 27 18:33:23 db2 kernel: hdc: 195371568 sectors (100030 MB) w/8192KiB
Cache, CHS=193821/16/63, UDMA(33)
Feb 27 18:33:23 db2 kernel: Partition check:
Feb 27 18:33:23 db2 kernel: hda: hda1 hda2 hda3 hda4
Feb 27 18:33:23 db2 kernel: hdc: [PTBL] [12161/255/63] hdc1 hdc2 hdc3
hdc4
Feb 27 18:33:23 db2 kernel: Floppy drive(s): fd0 is 1.44M
Feb 27 18:33:23 db2 kernel: FDC 0 is a post-1991 82077
Feb 27 18:33:23 db2 kernel: eepro100.c:v1.09j-t 9/29/99 Donald Becker
http://www.scyld.com/network/eepro100.html
Feb 27 18:33:23 db2 kernel: eepro100.c: $Revision: 1.36 $ 2000/11/17
Modified by Andrey V. Savochkin <[email protected]> and others
Feb 27 18:33:23 db2 kernel: eth0: OEM i82557/i82558 10/100 Ethernet,
00:30:48:21:B5:1A, IRQ 11.
Feb 27 18:33:23 db2 kernel: Board assembly 000000-000, Physical
connectors present: RJ45
Feb 27 18:33:23 db2 kernel: Primary interface chip i82555 PHY #1.
Feb 27 18:33:23 db2 kernel: General self-test: passed.
Feb 27 18:33:23 db2 kernel: Serial sub-system self-test: passed.
Feb 27 18:33:23 db2 kernel: Internal registers self-test: passed.
Feb 27 18:33:23 db2 kernel: ROM checksum self-test: passed (0x04f4518b).
Feb 27 18:33:23 db2 kernel: NET4: Linux TCP/IP 1.0 for NET4.0
Feb 27 18:33:23 db2 kernel: IP Protocols: ICMP, UDP, TCP
Feb 27 18:33:23 db2 kernel: IP: routing cache hash table of 8192 buckets,
64Kbytes
Feb 27 18:33:23 db2 kernel: TCP: Hash tables configured (established
262144 bind 65536)
Feb 27 18:33:23 db2 kernel: NET4: Unix domain sockets 1.0/SMP for Linux
NET4.0.
Feb 27 18:33:23 db2 kernel: VFS: Mounted root (ext2 filesystem) readonly.
Feb 27 18:33:23 db2 kernel: Freeing unused kernel memory: 212k freed
Feb 27 18:33:23 db2 kernel: Adding Swap: 104416k swap-space (priority -1)
What looks weird here to my untrained eyes are the "Unknown bridge
resource" messages and that my harddisks run on UDMA33 (the MPS v1.1
instead of 1.4 is due to running the BIOS in "failsafe" mode - nothing
that fixed the lockups though).
>lspci
00:00.0 Host bridge: Intel Corporation: Unknown device 2531 (rev 04)
00:01.0 PCI bridge: Intel Corporation: Unknown device 2532 (rev 04)
00:02.0 PCI bridge: Intel Corporation: Unknown device 2533 (rev 04)
00:1e.0 PCI bridge: Intel Corporation: Unknown device 244e (rev 04)
00:1f.0 ISA bridge: Intel Corporation: Unknown device 2440 (rev 04)
00:1f.1 IDE interface: Intel Corporation: Unknown device 244b (rev 04)
00:1f.2 USB Controller: Intel Corporation: Unknown device 2442 (rev 04)
00:1f.3 SMBus: Intel Corporation: Unknown device 2443 (rev 04)
00:1f.4 USB Controller: Intel Corporation: Unknown device 2444 (rev 04)
00:1f.5 Multimedia audio controller: Intel Corporation: Unknown device
2445 (rev 04)
02:1f.0 PCI bridge: Intel Corporation 82806AA PCI64 Hub PCI Bridge (rev
03)
03:00.0 PIC: Intel Corporation 82806AA PCI64 Hub Advanced Programmable
Interrupt Controller (rev 01)
04:03.0 VGA compatible controller: S3 Inc. Trio 64V2/DX or /GX (rev 06)
04:04.0 Ethernet controller: Intel Corporation 82557 [Ethernet Pro 100]
(rev 08)
>more /proc/interrupts
CPU0 CPU1
0: 49970 0 IO-APIC-edge timer
1: 34 0 IO-APIC-edge keyboard
2: 0 0 XT-PIC cascade
8: 1 0 IO-APIC-edge rtc
11: 39725 0 IO-APIC-level eth0
14: 9581 1 IO-APIC-edge ide0
15: 7 1 IO-APIC-edge ide1
NMI: 0 0
LOC: 49887 49886
ERR: 0
MIS: 0
If there is any additional information you need, please do not hesitate to
ask. I dearly hope there's some fix for either the 2.2 or the 2.4 problems
as this is a production machine and the problems are very stressful :-(
Thank you,
Johan
> However, while booting 2.2.20, the following messages appear:
Make sure you have all the pnp os settings disabled in the bios - the
below looks awfully like the IRQ routing wasnt set up by the bios
> failure to boot issue in 2.2 can be related to the random lockups in 2.4,
> could that be the case?
Who knows. "Random lockup" you can start at the power supply and work right
through the software - without any more info its very hard to debug
> Feb 27 18:33:22 db2 kernel: hm, page 000f5000 reserved twice.
> Feb 27 18:33:22 db2 kernel: hm, page 000f6000 reserved twice.
> Feb 27 18:33:22 db2 kernel: hm, page 000f1000 reserved twice.
> Feb 27 18:33:22 db2 kernel: hm, page 000f2000 reserved twice.
These are OK
> Feb 27 18:33:22 db2 kernel: OEM ID: OEM00000 Product ID: PROD00000000 APIC
> at: 0xFEE00000
Your BIOS vendor didn't even fill in the MP1.1 table with their info -
confidence level in BIOS _zero_
> Feb 27 18:33:22 db2 kernel: Processor #0 Unknown CPU [15:2] APIC version
> 17
Curious but should be harmless
> Feb 27 18:33:22 db2 kernel: WARNING: No sibling found for CPU 0.
> Feb 27 18:33:22 db2 kernel: WARNING: No sibling found for CPU 1.
HT but not hyperthreading activated in the kernel (acpismp=force). Again
harmless just might be costing performance if your box is HT capable
> What looks weird here to my untrained eyes are the "Unknown bridge
> resource" messages and that my harddisks run on UDMA33 (the MPS v1.1
> instead of 1.4 is due to running the BIOS in "failsafe" mode - nothing
> that fixed the lockups though).
The unknown resource should be fine. The UDMA33 may well be because the
ide code in the base tree isnt up on i860 hardware yet.
Starting points I'd suggest:
= Try a non highmem kernel
= See if a single CPU kernel is reliable
If it is consider swapping the cpus over and retesting
(might point to software or hardware)
= Ensure your ventilation is fine and your PSU is approved
and to spec for the system
You might want to run a memory test but thats normally seen as random
corruption/oopses not a hang and if you have ECC ram life should be fine
> Make sure you have all the pnp os settings disabled in the bios
Yes, they are disabled.
> HT but not hyperthreading activated in the kernel (acpismp=force).
Hyperthreading were disabled in the BIOS. It's the default setting in
"fail safe" but curiously also in "optimized settings".
It is now enabled together with the acpismp=force in lilo. Note however
that the "WARNING: No sibling found" messages are still there. Strange?
The newly compiled kernel is without highmem as suggested and the BIOS
values for UDMA have been updated (the reason they showed UDMA33 were
because of "fail safe" BIOS settings, sorry for missing that).
> See if a single CPU kernel is reliable
I will if this highmem off setting doesn't fix it. I really need both
working or the load will skyrocket :-(
>Ensure your ventilation is fine and your PSU is approved
Both are excellent, should not be an issue.
The new boot messages, with acpismp=force and HT enabled in BIOS, note new
ACPI messages, like "Searched entire block, no RSDP was found". Problem?
Feb 27 22:07:16 db2 kernel: Linux version 2.4.18-rc4 (root@db2) (gcc
version 2.95.3 20010315 (release)) #1 SMP Wed Feb 27 22:03:01 CET 2002
Feb 27 22:07:16 db2 kernel: BIOS-provided physical RAM map:
Feb 27 22:07:16 db2 kernel: BIOS-e820: 0000000000000000 -
00000000000a0000 (usable)
Feb 27 22:07:16 db2 kernel: BIOS-e820: 00000000000f0000 -
0000000000100000 (reserved)
Feb 27 22:07:16 db2 kernel: BIOS-e820: 0000000000100000 -
0000000040000000 (usable)
Feb 27 22:07:16 db2 kernel: BIOS-e820: 00000000fec00000 -
0000000100000000 (reserved)
Feb 27 22:07:16 db2 kernel: Warning only 896MB will be used.
Feb 27 22:07:16 db2 kernel: Use a HIGHMEM enabled kernel.
Feb 27 22:07:16 db2 kernel: found SMP MP-table at 000f5010
Feb 27 22:07:16 db2 kernel: hm, page 000f5000 reserved twice.
Feb 27 22:07:16 db2 kernel: hm, page 000f6000 reserved twice.
Feb 27 22:07:16 db2 kernel: hm, page 000f1000 reserved twice.
Feb 27 22:07:16 db2 kernel: hm, page 000f2000 reserved twice.
Feb 27 22:07:16 db2 kernel: On node 0 totalpages: 229376
Feb 27 22:07:16 db2 kernel: zone(0): 4096 pages.
Feb 27 22:07:16 db2 kernel: zone(1): 225280 pages.
Feb 27 22:07:16 db2 kernel: zone(2): 0 pages.
Feb 27 22:07:16 db2 kernel: ACPI: Searched entire block, no RSDP was
found.
Feb 27 22:07:16 db2 kernel: ACPI: Searched entire block, no RSDP was
found.
Feb 27 22:07:16 db2 kernel: ACPI: System description tables not found
Feb 27 22:07:16 db2 kernel: Intel MultiProcessor Specification v1.4
Feb 27 22:07:16 db2 kernel: Virtual Wire compatibility mode.
Feb 27 22:07:16 db2 kernel: OEM ID: OEM00000 Product ID: PROD00000000 APIC
at: 0xFEE00000
Feb 27 22:07:16 db2 kernel: Processor #0 Unknown CPU [15:2] APIC version
17
Feb 27 22:07:16 db2 kernel: Processor #1 Unknown CPU [15:2] APIC version
17
Feb 27 22:07:16 db2 kernel: I/O APIC #2 Version 17 at 0xFEC00000.
Feb 27 22:07:16 db2 kernel: Processors: 2
Feb 27 22:07:16 db2 kernel: Kernel command line: auto BOOT_IMAGE=linux ro
root=301 acpismp=force
Feb 27 22:07:16 db2 kernel: Initializing CPU#0
Feb 27 22:07:16 db2 kernel: Detected 1982.543 MHz processor.
Feb 27 22:07:16 db2 kernel: Console: colour VGA+ 80x25
Feb 27 22:07:16 db2 kernel: Calibrating delay loop... 3958.37 BogoMIPS
Feb 27 22:07:16 db2 kernel: Memory: 901096k/917504k available (808k kernel
code, 16024k reserved, 183k data, 212k init, 0k highmem)
Feb 27 22:07:16 db2 kernel: Dentry-cache hash table entries: 131072
(order: 8, 1048576 bytes)
Feb 27 22:07:16 db2 kernel: Inode-cache hash table entries: 65536 (order:
7, 524288 bytes)
Feb 27 22:07:16 db2 kernel: Mount-cache hash table entries: 16384 (order:
5, 131072 bytes)
Feb 27 22:07:16 db2 kernel: Buffer-cache hash table entries: 65536 (order:
6, 262144 bytes)
Feb 27 22:07:16 db2 kernel: Page-cache hash table entries: 262144 (order:
8, 1048576 bytes)
Feb 27 22:07:16 db2 kernel: CPU: Before vendor init, caps: 3febfbff
00000000 00000000, vendor = 0
Feb 27 22:07:16 db2 kernel: CPU: L1 I cache: 12K, L1 D cache: 8K
Feb 27 22:07:16 db2 kernel: CPU: L2 cache: 512K
Feb 27 22:07:16 db2 kernel: CPU: Physical Processor ID: 0
Feb 27 22:07:16 db2 kernel: CPU: After vendor init, caps: 3febfbff
00000000 00000000 00000000
Feb 27 22:07:16 db2 kernel: Intel machine check architecture supported.
Feb 27 22:07:16 db2 kernel: Intel machine check reporting enabled on
CPU#0.
Feb 27 22:07:16 db2 kernel: CPU: After generic, caps: 3febfbff
00000000 00000000 00000000
Feb 27 22:07:16 db2 kernel: CPU: Common caps: 3febfbff
00000000 00000000 00000000
Feb 27 22:07:16 db2 kernel: Enabling fast FPU save and restore... done.
Feb 27 22:07:16 db2 kernel: Enabling unmasked SIMD FPU exception
support... done.
Feb 27 22:07:16 db2 kernel: Checking 'hlt' instruction... OK.
Feb 27 22:07:16 db2 kernel: POSIX conformance testing by UNIFIX
Feb 27 22:07:16 db2 kernel: mtrr: v1.40 (20010327) Richard Gooch
([email protected])
Feb 27 22:07:16 db2 kernel: mtrr: detected mtrr type: Intel
Feb 27 22:07:16 db2 kernel: CPU: Before vendor init, caps: 3febfbff
00000000 00000000, vendor = 0
Feb 27 22:07:16 db2 kernel: CPU: L1 I cache: 12K, L1 D cache: 8K
Feb 27 22:07:16 db2 kernel: CPU: L2 cache: 512K
Feb 27 22:07:16 db2 kernel: CPU: Physical Processor ID: 0
Feb 27 22:07:16 db2 kernel: CPU: After vendor init, caps: 3febfbff
00000000 00000000 00000000
Feb 27 22:07:16 db2 kernel: Intel machine check reporting enabled on
CPU#0.
Feb 27 22:07:16 db2 kernel: CPU: After generic, caps: 3febfbff
00000000 00000000 00000000
Feb 27 22:07:16 db2 kernel: CPU: Common caps: 3febfbff
00000000 00000000 00000000
Feb 27 22:07:16 db2 kernel: CPU0: Intel(R) XEON(TM) CPU 2.00GHz stepping
04
Feb 27 22:07:16 db2 kernel: per-CPU timeslice cutoff: 1463.19 usecs.
Feb 27 22:07:16 db2 kernel: enabled ExtINT on CPU#0
Feb 27 22:07:16 db2 kernel: ESR value before enabling vector: 00000000
Feb 27 22:07:16 db2 kernel: ESR value after enabling vector: 00000000
Feb 27 22:07:16 db2 kernel: Booting processor 1/1 eip 2000
Feb 27 22:07:16 db2 kernel: Initializing CPU#1
Feb 27 22:07:16 db2 kernel: masked ExtINT on CPU#1
Feb 27 22:07:16 db2 kernel: ESR value before enabling vector: 00000000
Feb 27 22:07:16 db2 kernel: ESR value after enabling vector: 00000000
Feb 27 22:07:16 db2 kernel: Calibrating delay loop... 3958.37 BogoMIPS
Feb 27 22:07:16 db2 kernel: CPU: Before vendor init, caps: 3febfbff
00000000 00000000, vendor = 0
Feb 27 22:07:16 db2 kernel: CPU: L1 I cache: 12K, L1 D cache: 8K
Feb 27 22:07:16 db2 kernel: CPU: L2 cache: 512K
Feb 27 22:07:16 db2 kernel: CPU: Physical Processor ID: 3
Feb 27 22:07:16 db2 kernel: CPU: After vendor init, caps: 3febfbff
00000000 00000000 00000000
Feb 27 22:07:16 db2 kernel: Intel machine check reporting enabled on
CPU#1.
Feb 27 22:07:16 db2 kernel: CPU: After generic, caps: 3febfbff
00000000 00000000 00000000
Feb 27 22:07:16 db2 kernel: CPU: Common caps: 3febfbff
00000000 00000000 00000000
Feb 27 22:07:16 db2 kernel: CPU1: Intel(R) XEON(TM) CPU 2.00GHz stepping
04
Feb 27 22:07:16 db2 kernel: Total of 2 processors activated (7916.74
BogoMIPS).
Feb 27 22:07:16 db2 kernel: WARNING: No sibling found for CPU 0.
Feb 27 22:07:16 db2 kernel: WARNING: No sibling found for CPU 1.
Feb 27 22:07:16 db2 kernel: ENABLING IO-APIC IRQs
Feb 27 22:07:16 db2 kernel: Setting 2 in the phys_id_present_map
Feb 27 22:07:16 db2 kernel: ...changing IO-APIC physical APIC ID to 2 ...
ok.
Feb 27 22:07:16 db2 kernel: init IO_APIC IRQs
Feb 27 22:07:16 db2 kernel: IO-APIC (apicid-pin) 2-0, 2-10, 2-11, 2-12,
2-17, 2-18, 2-20, 2-21, 2-22 not connected.
Feb 27 22:07:16 db2 kernel: ..TIMER: vector=0x31 pin1=2 pin2=0
Feb 27 22:07:16 db2 kernel: number of MP IRQ sources: 18.
Feb 27 22:07:17 db2 kernel: number of IO-APIC #2 registers: 24.
Feb 27 22:07:17 db2 kernel: testing the IO APIC.......................
Feb 27 22:07:17 db2 kernel:
Feb 27 22:07:17 db2 kernel: IO APIC #2......
Feb 27 22:07:17 db2 kernel: .... register #00: 02000000
Feb 27 22:07:17 db2 kernel: ....... : physical APIC id: 02
Feb 27 22:07:17 db2 kernel: .... register #01: 00178020
Feb 27 22:07:17 db2 kernel: ....... : max redirection entries: 0017
Feb 27 22:07:17 db2 kernel: ....... : PRQ implemented: 1
Feb 27 22:07:17 db2 kernel: ....... : IO APIC version: 0020
Feb 27 22:07:17 db2 kernel: .... register #02: 00000000
Feb 27 22:07:17 db2 kernel: ....... : arbitration: 00
Feb 27 22:07:17 db2 kernel: .... IRQ redirection table:
Feb 27 22:07:17 db2 kernel: NR Log Phy Mask Trig IRR Pol Stat Dest Deli
Vect:
Feb 27 22:07:17 db2 kernel: 00 000 00 1 0 0 0 0 0 0
00
Feb 27 22:07:17 db2 kernel: 01 003 03 0 0 0 0 0 1 1
39
Feb 27 22:07:17 db2 kernel: 02 003 03 0 0 0 0 0 1 1
31
Feb 27 22:07:17 db2 kernel: 03 003 03 0 0 0 0 0 1 1
41
Feb 27 22:07:17 db2 kernel: 04 003 03 0 0 0 0 0 1 1
49
Feb 27 22:07:17 db2 kernel: 05 003 03 0 0 0 0 0 1 1
51
Feb 27 22:07:17 db2 kernel: 06 003 03 0 0 0 0 0 1 1
59
Feb 27 22:07:17 db2 kernel: 07 003 03 0 0 0 0 0 1 1
61
Feb 27 22:07:17 db2 kernel: 08 003 03 0 0 0 0 0 1 1
69
Feb 27 22:07:17 db2 kernel: 09 003 03 0 0 0 0 0 1 1
71
Feb 27 22:07:17 db2 kernel: 0a 000 00 1 0 0 0 0 0 0
00
Feb 27 22:07:17 db2 kernel: 0b 000 00 1 0 0 0 0 0 0
00
Feb 27 22:07:17 db2 kernel: 0c 000 00 1 0 0 0 0 0 0
00
Feb 27 22:07:17 db2 kernel: 0d 003 03 0 0 0 0 0 1 1
79
Feb 27 22:07:17 db2 kernel: 0e 003 03 0 0 0 0 0 1 1
81
Feb 27 22:07:17 db2 kernel: 0f 003 03 0 0 0 0 0 1 1
89
Feb 27 22:07:17 db2 kernel: 10 003 03 1 1 0 1 0 1 1
91
Feb 27 22:07:17 db2 kernel: 11 000 00 1 0 0 0 0 0 0
00
Feb 27 22:07:17 db2 kernel: 12 000 00 1 0 0 0 0 0 0
00
Feb 27 22:07:17 db2 kernel: 13 003 03 1 1 0 1 0 1 1
99
Feb 27 22:07:17 db2 kernel: 14 000 00 1 0 0 0 0 0 0
00
Feb 27 22:07:17 db2 kernel: 15 000 00 1 0 0 0 0 0 0
00
Feb 27 22:07:17 db2 kernel: 16 000 00 1 0 0 0 0 0 0
00
Feb 27 22:07:17 db2 kernel: 17 003 03 1 1 0 1 0 1 1
A1
Feb 27 22:07:17 db2 kernel: IRQ to pin mappings:
Feb 27 22:07:17 db2 kernel: IRQ0 -> 0:2
Feb 27 22:07:17 db2 kernel: IRQ1 -> 0:1
Feb 27 22:07:17 db2 kernel: IRQ3 -> 0:3
Feb 27 22:07:17 db2 kernel: IRQ4 -> 0:4
Feb 27 22:07:17 db2 kernel: IRQ5 -> 0:5
Feb 27 22:07:17 db2 kernel: IRQ6 -> 0:6
Feb 27 22:07:17 db2 kernel: IRQ7 -> 0:7
Feb 27 22:07:17 db2 kernel: IRQ8 -> 0:8
Feb 27 22:07:17 db2 kernel: IRQ9 -> 0:9
Feb 27 22:07:17 db2 kernel: IRQ13 -> 0:13
Feb 27 22:07:17 db2 kernel: IRQ14 -> 0:14
Feb 27 22:07:17 db2 kernel: IRQ15 -> 0:15
Feb 27 22:07:17 db2 kernel: IRQ16 -> 0:16
Feb 27 22:07:17 db2 kernel: IRQ19 -> 0:19
Feb 27 22:07:17 db2 kernel: IRQ23 -> 0:23
Feb 27 22:07:17 db2 kernel: .................................... done.
Feb 27 22:07:17 db2 kernel: Using local APIC timer interrupts.
Feb 27 22:07:17 db2 kernel: calibrating APIC timer ...
Feb 27 22:07:17 db2 kernel: ..... CPU clock speed is 1982.5340 MHz.
Feb 27 22:07:17 db2 kernel: ..... host bus clock speed is 99.1265 MHz.
Feb 27 22:07:17 db2 kernel: cpu: 0, clocks: 991265, slice: 330421
Feb 27 22:07:17 db2 kernel:
CPU0<T0:991264,T1:660832,D:11,S:330421,C:991265>
Feb 27 22:07:17 db2 kernel: cpu: 1, clocks: 991265, slice: 330421
Feb 27 22:07:17 db2 kernel:
CPU1<T0:991264,T1:330416,D:6,S:330421,C:991265>
Feb 27 22:07:17 db2 kernel: checking TSC synchronization across CPUs:
passed.
Feb 27 22:07:17 db2 kernel: Waiting on wait_init_idle (map = 0x2)
Feb 27 22:07:17 db2 kernel: All processors have done init_idle
Feb 27 22:07:17 db2 kernel: mtrr: your CPUs had inconsistent fixed MTRR
settings
Feb 27 22:07:17 db2 kernel: mtrr: probably your BIOS does not setup all
CPUs
Feb 27 22:07:17 db2 kernel: PCI: PCI BIOS revision 2.10 entry at 0xfb3e0,
last bus=4
Feb 27 22:07:17 db2 kernel: PCI: Using configuration type 1
Feb 27 22:07:17 db2 kernel: PCI: Probing PCI hardware
Feb 27 22:07:17 db2 kernel: Unknown bridge resource 0: assuming
transparent
Feb 27 22:07:17 db2 kernel: Unknown bridge resource 1: assuming
transparent
Feb 27 22:07:17 db2 kernel: Unknown bridge resource 2: assuming
transparent
Feb 27 22:07:17 db2 kernel: Unknown bridge resource 0: assuming
transparent
Feb 27 22:07:17 db2 kernel: Unknown bridge resource 2: assuming
transparent
Feb 27 22:07:17 db2 kernel: Unknown bridge resource 0: assuming
transparent
Feb 27 22:07:17 db2 kernel: Unknown bridge resource 2: assuming
transparent
Feb 27 22:07:17 db2 kernel: Unknown bridge resource 2: assuming
transparent
Feb 27 22:07:17 db2 kernel: PCI: Using IRQ router PIIX [8086/2440] at
00:1f.0
Feb 27 22:07:17 db2 kernel: PCI->APIC IRQ transform: (B0,I31,P1) -> 19
Feb 27 22:07:17 db2 kernel: PCI->APIC IRQ transform: (B4,I3,P0) -> 19
Feb 27 22:07:17 db2 kernel: PCI->APIC IRQ transform: (B4,I4,P0) -> 16
Feb 27 22:07:17 db2 kernel: Linux NET4.0 for Linux 2.4
Feb 27 22:07:17 db2 kernel: Based upon Swansea University Computer Society
NET3.039
Feb 27 22:07:17 db2 kernel: Initializing RT netlink socket
Feb 27 22:07:17 db2 kernel: Starting kswapd
Feb 27 22:07:17 db2 kernel: Real Time Clock Driver v1.10e
Feb 27 22:07:17 db2 kernel: block: 128 slots per queue, batch=32
Feb 27 22:07:17 db2 kernel: Uniform Multi-Platform E-IDE driver Revision:
6.31
Feb 27 22:07:17 db2 kernel: ide: Assuming 33MHz system bus speed for PIO
modes; override with idebus=xx
Feb 27 22:07:17 db2 kernel: PIIX4: IDE controller on PCI bus 00 dev f9
Feb 27 22:07:17 db2 kernel: PIIX4: chipset revision 4
Feb 27 22:07:17 db2 kernel: PIIX4: not 100%% native mode: will probe irqs
later
Feb 27 22:07:17 db2 kernel: ide0: BM-DMA at 0xf000-0xf007, BIOS
settings: hda:DMA, hdb:pio
Feb 27 22:07:17 db2 kernel: ide1: BM-DMA at 0xf008-0xf00f, BIOS
settings: hdc:DMA, hdd:pio
Feb 27 22:07:17 db2 kernel: hda: WDC WD1000JB-32CWE0, ATA DISK drive
Feb 27 22:07:17 db2 kernel: hdc: WDC WD1000JB-32CWE0, ATA DISK drive
Feb 27 22:07:17 db2 kernel: ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
Feb 27 22:07:17 db2 kernel: ide1 at 0x170-0x177,0x376 on irq 15
Feb 27 22:07:17 db2 kernel: hda: 195371568 sectors (100030 MB) w/8192KiB
Cache, CHS=12161/255/63, UDMA(100)
Feb 27 22:07:17 db2 kernel: hdc: 195371568 sectors (100030 MB) w/8192KiB
Cache, CHS=193821/16/63, UDMA(100)
Feb 27 22:07:17 db2 kernel: Partition check:
Feb 27 22:07:17 db2 kernel: hda: hda1 hda2 hda3 hda4
Feb 27 22:07:17 db2 kernel: hdc: [PTBL] [12161/255/63] hdc1 hdc2 hdc3
hdc4
Feb 27 22:07:17 db2 kernel: Floppy drive(s): fd0 is 1.44M
Feb 27 22:07:17 db2 kernel: FDC 0 is a post-1991 82077
Feb 27 22:07:17 db2 kernel: eepro100.c:v1.09j-t 9/29/99 Donald Becker
http://www.scyld.com/network/eepro100.html
Feb 27 22:07:17 db2 kernel: eepro100.c: $Revision: 1.36 $ 2000/11/17
Modified by Andrey V. Savochkin <[email protected]> and others
Feb 27 22:07:17 db2 kernel: eth0: OEM i82557/i82558 10/100 Ethernet,
00:30:48:21:B5:1A, IRQ 16.
Feb 27 22:07:17 db2 kernel: Board assembly 000000-000, Physical
connectors present: RJ45
Feb 27 22:07:17 db2 kernel: Primary interface chip i82555 PHY #1.
Feb 27 22:07:17 db2 kernel: General self-test: passed.
Feb 27 22:07:17 db2 kernel: Serial sub-system self-test: passed.
Feb 27 22:07:17 db2 kernel: Internal registers self-test: passed.
Feb 27 22:07:17 db2 kernel: ROM checksum self-test: passed (0x04f4518b).
Feb 27 22:07:17 db2 kernel: NET4: Linux TCP/IP 1.0 for NET4.0
Feb 27 22:07:17 db2 kernel: IP Protocols: ICMP, UDP, TCP
Feb 27 22:07:17 db2 kernel: IP: routing cache hash table of 8192 buckets,
64Kbytes
Feb 27 22:07:17 db2 kernel: TCP: Hash tables configured (established
262144 bind 65536)
Feb 27 22:07:17 db2 kernel: NET4: Unix domain sockets 1.0/SMP for Linux
NET4.0.
Feb 27 22:07:17 db2 kernel: VFS: Mounted root (ext2 filesystem) readonly.
Feb 27 22:07:17 db2 kernel: Freeing unused kernel memory: 212k freed
Feb 27 22:07:17 db2 kernel: Adding Swap: 104416k swap-space (priority -1)
> It is now enabled together with the acpismp=force in lilo. Note however
> that the "WARNING: No sibling found" messages are still there. Strange?
Means it isnt find the HT tables
> The new boot messages, with acpismp=force and HT enabled in BIOS, note new
> ACPI messages, like "Searched entire block, no RSDP was found". Problem?
It couldnt find an ACPI table - The hyperthreading data is described in
the ACPI tables in the BIOS. Without them we can't do much with it
HT tends to be worth 20% performance so its worth finding out why 8)
I'm sorry having to admit this but I had ACPI turned off in BIOS. Turned
it back on and now hyperthreading seems to work and "top" gives me four
processors! Damn that's sweet :-)
I can't say anything about added performance though as that has to be
tested during peak hours. With 15833.49 bogomips, it has to be good ;-)
Only time can tell what happened to the random lockups though, hopefully
they will go away as highmem were turned off and "resources controlled by"
in BIOS were set to "manual" instead of "auto(ESCD)".
Below is the boot messages when HT is working. Some strange messages like
"no RSDP was found" and then "RSDP located at physical address c00f6bf0"
are present as well as "init.c:148: bad pte 3fff3163" but none seem
serious.
Thanks,
Johan
Feb 28 02:17:50 db2 kernel: Linux version 2.4.18-rc4 (root@db2) (gcc
version 2.95.3 20010315 (release)) #1 SMP Wed Feb 27 22:03:01 CET 2002
Feb 28 02:17:50 db2 kernel: BIOS-provided physical RAM map:
Feb 28 02:17:50 db2 kernel: BIOS-e820: 0000000000000000 -
00000000000a0000 (usable)
Feb 28 02:17:50 db2 kernel: BIOS-e820: 00000000000f0000 -
0000000000100000 (reserved)
Feb 28 02:17:50 db2 kernel: BIOS-e820: 0000000000100000 -
000000003fff0000 (usable)
Feb 28 02:17:50 db2 kernel: BIOS-e820: 000000003fff0000 -
000000003fff3000 (ACPI NVS)
Feb 28 02:17:50 db2 kernel: BIOS-e820: 000000003fff3000 -
0000000040000000 (ACPI data)
Feb 28 02:17:50 db2 kernel: BIOS-e820: 00000000fec00000 -
0000000100000000 (reserved)
Feb 28 02:17:50 db2 kernel: Warning only 896MB will be used.
Feb 28 02:17:50 db2 kernel: Use a HIGHMEM enabled kernel.
Feb 28 02:17:50 db2 kernel: found SMP MP-table at 000f5010
Feb 28 02:17:50 db2 kernel: hm, page 000f5000 reserved twice.
Feb 28 02:17:50 db2 kernel: hm, page 000f6000 reserved twice.
Feb 28 02:17:50 db2 kernel: hm, page 000f1000 reserved twice.
Feb 28 02:17:50 db2 kernel: hm, page 000f2000 reserved twice.
Feb 28 02:17:50 db2 kernel: On node 0 totalpages: 229376
Feb 28 02:17:50 db2 kernel: zone(0): 4096 pages.
Feb 28 02:17:50 db2 kernel: zone(1): 225280 pages.
Feb 28 02:17:50 db2 kernel: zone(2): 0 pages.
Feb 28 02:17:50 db2 kernel: ACPI: Searched entire block, no RSDP was
found.
Feb 28 02:17:50 db2 kernel: ACPI: RSDP located at physical address
c00f6bf0
Feb 28 02:17:50 db2 kernel: RSD PTR v0 [IntelR]
Feb 28 02:17:50 db2 kernel: ACPI table found: RSDT v1 [IntelR AWRDACPI
16944.11825]
Feb 28 02:17:50 db2 kernel: init.c:148: bad pte 3fff3163.
Feb 28 02:17:50 db2 kernel: ACPI table found: FACP v1 [IntelR AWRDACPI
16944.11825]
Feb 28 02:17:50 db2 kernel: init.c:148: bad pte 3fff3163.
Feb 28 02:17:50 db2 kernel: ACPI table found: APIC v1 [IntelR AWRDACPI
16944.11825]
Feb 28 02:17:50 db2 kernel: init.c:148: bad pte 3fff6163.
Feb 28 02:17:50 db2 kernel: LAPIC (acpi_id[0x0000] id[0x0] enabled[1])
Feb 28 02:17:50 db2 kernel: CPU 0 (0x0000) enabledProcessor #0 Unknown CPU
[15:2] APIC version 16
Feb 28 02:17:50 db2 kernel:
Feb 28 02:17:50 db2 kernel: LAPIC (acpi_id[0x0001] id[0x1] enabled[1])
Feb 28 02:17:50 db2 kernel: CPU 1 (0x0100) enabledProcessor #1 Unknown CPU
[15:2] APIC version 16
Feb 28 02:17:50 db2 kernel:
Feb 28 02:17:50 db2 kernel: LAPIC (acpi_id[0x0002] id[0x2] enabled[1])
Feb 28 02:17:50 db2 kernel: CPU 2 (0x0200) enabledProcessor #2 Unknown CPU
[15:2] APIC version 16
Feb 28 02:17:50 db2 kernel:
Feb 28 02:17:50 db2 kernel: LAPIC (acpi_id[0x0003] id[0x3] enabled[1])
Feb 28 02:17:50 db2 kernel: CPU 3 (0x0300) enabledProcessor #3 Unknown CPU
[15:2] APIC version 16
Feb 28 02:17:50 db2 kernel:
Feb 28 02:17:50 db2 kernel: IOAPIC (id[0x2] address[0xfec00000]
global_irq_base[0x0])
Feb 28 02:17:50 db2 kernel: INT_SRC_OVR (bus[0] irq[0x0] global_irq[0x2]
polarity[0x1] trigger[0x3])
Feb 28 02:17:50 db2 kernel: INT_SRC_OVR (bus[0] irq[0x9] global_irq[0x9]
polarity[0x1] trigger[0x3])
Feb 28 02:17:50 db2 kernel: 4 CPUs total
Feb 28 02:17:50 db2 kernel: Local APIC address fee00000
Feb 28 02:17:50 db2 kernel: Enabling the CPU's according to the ACPI table
Feb 28 02:17:50 db2 kernel: Intel MultiProcessor Specification v1.4
Feb 28 02:17:50 db2 kernel: Virtual Wire compatibility mode.
Feb 28 02:17:50 db2 kernel: OEM ID: OEM00000 Product ID: PROD00000000 APIC
at: 0xFEE00000
Feb 28 02:17:50 db2 kernel: I/O APIC #2 Version 17 at 0xFEC00000.
Feb 28 02:17:50 db2 kernel: Processors: 4
Feb 28 02:17:50 db2 kernel: init.c:148: bad pte 3fff6163.
Feb 28 02:17:50 db2 kernel: Kernel command line: auto BOOT_IMAGE=linux ro
root=301 acpismp=force
Feb 28 02:17:50 db2 kernel: Initializing CPU#0
Feb 28 02:17:50 db2 kernel: Detected 1982.583 MHz processor.
Feb 28 02:17:50 db2 kernel: Console: colour VGA+ 80x25
Feb 28 02:17:50 db2 kernel: Calibrating delay loop... 3958.37 BogoMIPS
Feb 28 02:17:50 db2 kernel: Memory: 901096k/917504k available (808k kernel
code, 16024k reserved, 183k data, 212k init, 0k highmem)
Feb 28 02:17:50 db2 kernel: Dentry-cache hash table entries: 131072
(order: 8, 1048576 bytes)
Feb 28 02:17:50 db2 kernel: Inode-cache hash table entries: 65536 (order:
7, 524288 bytes)
Feb 28 02:17:50 db2 kernel: Mount-cache hash table entries: 16384 (order:
5, 131072 bytes)
Feb 28 02:17:50 db2 kernel: Buffer-cache hash table entries: 65536 (order:
6, 262144 bytes)
Feb 28 02:17:50 db2 kernel: Page-cache hash table entries: 262144 (order:
8, 1048576 bytes)
Feb 28 02:17:50 db2 kernel: CPU: Before vendor init, caps: 3febfbff
00000000 00000000, vendor = 0
Feb 28 02:17:50 db2 kernel: CPU: L1 I cache: 12K, L1 D cache: 8K
Feb 28 02:17:50 db2 kernel: CPU: L2 cache: 512K
Feb 28 02:17:50 db2 kernel: CPU: Physical Processor ID: 0
Feb 28 02:17:50 db2 kernel: CPU: After vendor init, caps: 3febfbff
00000000 00000000 00000000
Feb 28 02:17:50 db2 kernel: Intel machine check architecture supported.
Feb 28 02:17:50 db2 kernel: Intel machine check reporting enabled on
CPU#0.
Feb 28 02:17:50 db2 kernel: CPU: After generic, caps: 3febfbff
00000000 00000000 00000000
Feb 28 02:17:50 db2 kernel: CPU: Common caps: 3febfbff
00000000 00000000 00000000
Feb 28 02:17:50 db2 kernel: Enabling fast FPU save and restore... done.
Feb 28 02:17:50 db2 kernel: Enabling unmasked SIMD FPU exception
support... done.
Feb 28 02:17:50 db2 kernel: Checking 'hlt' instruction... OK.
Feb 28 02:17:50 db2 kernel: POSIX conformance testing by UNIFIX
Feb 28 02:17:50 db2 kernel: mtrr: v1.40 (20010327) Richard Gooch
([email protected])
Feb 28 02:17:50 db2 kernel: mtrr: detected mtrr type: Intel
Feb 28 02:17:50 db2 kernel: CPU: Before vendor init, caps: 3febfbff
00000000 00000000, vendor = 0
Feb 28 02:17:50 db2 kernel: CPU: L1 I cache: 12K, L1 D cache: 8K
Feb 28 02:17:50 db2 kernel: CPU: L2 cache: 512K
Feb 28 02:17:50 db2 kernel: CPU: Physical Processor ID: 0
Feb 28 02:17:50 db2 kernel: CPU: After vendor init, caps: 3febfbff
00000000 00000000 00000000
Feb 28 02:17:50 db2 kernel: Intel machine check reporting enabled on
CPU#0.
Feb 28 02:17:50 db2 kernel: CPU: After generic, caps: 3febfbff
00000000 00000000 00000000
Feb 28 02:17:50 db2 kernel: CPU: Common caps: 3febfbff
00000000 00000000 00000000
Feb 28 02:17:50 db2 kernel: CPU0: Intel(R) XEON(TM) CPU 2.00GHz stepping
04
Feb 28 02:17:50 db2 kernel: per-CPU timeslice cutoff: 1463.19 usecs.
Feb 28 02:17:50 db2 kernel: enabled ExtINT on CPU#0
Feb 28 02:17:50 db2 kernel: ESR value before enabling vector: 00000000
Feb 28 02:17:50 db2 kernel: ESR value after enabling vector: 00000000
Feb 28 02:17:51 db2 kernel: Booting processor 1/1 eip 2000
Feb 28 02:17:51 db2 kernel: Initializing CPU#1
Feb 28 02:17:51 db2 kernel: masked ExtINT on CPU#1
Feb 28 02:17:51 db2 kernel: ESR value before enabling vector: 00000000
Feb 28 02:17:51 db2 kernel: ESR value after enabling vector: 00000000
Feb 28 02:17:51 db2 kernel: Calibrating delay loop... 3958.37 BogoMIPS
Feb 28 02:17:51 db2 kernel: CPU: Before vendor init, caps: 3febfbff
00000000 00000000, vendor = 0
Feb 28 02:17:51 db2 kernel: CPU: L1 I cache: 12K, L1 D cache: 8K
Feb 28 02:17:51 db2 kernel: CPU: L2 cache: 512K
Feb 28 02:17:51 db2 kernel: CPU: Physical Processor ID: 3
Feb 28 02:17:51 db2 kernel: CPU: After vendor init, caps: 3febfbff
00000000 00000000 00000000
Feb 28 02:17:51 db2 kernel: Intel machine check reporting enabled on
CPU#1.
Feb 28 02:17:51 db2 kernel: CPU: After generic, caps: 3febfbff
00000000 00000000 00000000
Feb 28 02:17:51 db2 kernel: CPU: Common caps: 3febfbff
00000000 00000000 00000000
Feb 28 02:17:51 db2 kernel: CPU1: Intel(R) XEON(TM) CPU 2.00GHz stepping
04
Feb 28 02:17:51 db2 kernel: Booting processor 2/2 eip 2000
Feb 28 02:17:51 db2 kernel: Initializing CPU#2
Feb 28 02:17:51 db2 kernel: masked ExtINT on CPU#2
Feb 28 02:17:51 db2 kernel: ESR value before enabling vector: 00000000
Feb 28 02:17:51 db2 kernel: ESR value after enabling vector: 00000000
Feb 28 02:17:51 db2 kernel: Calibrating delay loop... 3958.37 BogoMIPS
Feb 28 02:17:51 db2 kernel: CPU: Before vendor init, caps: 3febfbff
00000000 00000000, vendor = 0
Feb 28 02:17:51 db2 kernel: CPU: L1 I cache: 12K, L1 D cache: 8K
Feb 28 02:17:51 db2 kernel: CPU: L2 cache: 512K
Feb 28 02:17:51 db2 kernel: CPU: Physical Processor ID: 0
Feb 28 02:17:51 db2 kernel: CPU: After vendor init, caps: 3febfbff
00000000 00000000 00000000
Feb 28 02:17:51 db2 kernel: Intel machine check reporting enabled on
CPU#2.
Feb 28 02:17:51 db2 kernel: CPU: After generic, caps: 3febfbff
00000000 00000000 00000000
Feb 28 02:17:51 db2 kernel: CPU: Common caps: 3febfbff
00000000 00000000 00000000
Feb 28 02:17:51 db2 kernel: CPU2: Intel(R) XEON(TM) CPU 2.00GHz stepping
04
Feb 28 02:17:51 db2 kernel: Booting processor 3/3 eip 2000
Feb 28 02:17:51 db2 kernel: Initializing CPU#3
Feb 28 02:17:51 db2 kernel: masked ExtINT on CPU#3
Feb 28 02:17:51 db2 kernel: ESR value before enabling vector: 00000000
Feb 28 02:17:51 db2 kernel: ESR value after enabling vector: 00000000
Feb 28 02:17:51 db2 kernel: Calibrating delay loop... 3958.37 BogoMIPS
Feb 28 02:17:51 db2 kernel: CPU: Before vendor init, caps: 3febfbff
00000000 00000000, vendor = 0
Feb 28 02:17:51 db2 kernel: CPU: L1 I cache: 12K, L1 D cache: 8K
Feb 28 02:17:51 db2 kernel: CPU: L2 cache: 512K
Feb 28 02:17:51 db2 kernel: CPU: Physical Processor ID: 3
Feb 28 02:17:51 db2 kernel: CPU: After vendor init, caps: 3febfbff
00000000 00000000 00000000
Feb 28 02:17:51 db2 kernel: Intel machine check reporting enabled on
CPU#3.
Feb 28 02:17:51 db2 kernel: CPU: After generic, caps: 3febfbff
00000000 00000000 00000000
Feb 28 02:17:51 db2 kernel: CPU: Common caps: 3febfbff
00000000 00000000 00000000
Feb 28 02:17:51 db2 kernel: CPU3: Intel(R) XEON(TM) CPU 2.00GHz stepping
04
Feb 28 02:17:51 db2 kernel: Total of 4 processors activated (15833.49
BogoMIPS).
Feb 28 02:17:51 db2 kernel: cpu_sibling_map[0] = 2
Feb 28 02:17:51 db2 kernel: cpu_sibling_map[1] = 3
Feb 28 02:17:51 db2 kernel: cpu_sibling_map[2] = 0
Feb 28 02:17:51 db2 kernel: cpu_sibling_map[3] = 1
Feb 28 02:17:51 db2 kernel: ENABLING IO-APIC IRQs
Feb 28 02:17:51 db2 kernel: BIOS bug, IO-APIC#0 ID 2 is already used!...
Feb 28 02:17:51 db2 kernel: ... fixing up to 4. (tell your hw vendor)
Feb 28 02:17:51 db2 kernel: ...changing IO-APIC physical APIC ID to 4 ...
ok.
Feb 28 02:17:51 db2 kernel: init IO_APIC IRQs
Feb 28 02:17:51 db2 kernel: IO-APIC (apicid-pin) 4-0, 4-10, 4-11, 4-15,
4-17, 4-18, 4-20, 4-21, 4-22 not connected.
Feb 28 02:17:51 db2 kernel: ..TIMER: vector=0x31 pin1=2 pin2=0
Feb 28 02:17:51 db2 kernel: number of MP IRQ sources: 18.
Feb 28 02:17:51 db2 kernel: number of IO-APIC #4 registers: 24.
Feb 28 02:17:51 db2 kernel: testing the IO APIC.......................
Feb 28 02:17:51 db2 kernel:
Feb 28 02:17:51 db2 kernel: IO APIC #4......
Feb 28 02:17:51 db2 kernel: .... register #00: 04000000
Feb 28 02:17:51 db2 kernel: ....... : physical APIC id: 04
Feb 28 02:17:51 db2 kernel: .... register #01: 00178020
Feb 28 02:17:51 db2 kernel: ....... : max redirection entries: 0017
Feb 28 02:17:51 db2 kernel: ....... : PRQ implemented: 1
Feb 28 02:17:51 db2 kernel: ....... : IO APIC version: 0020
Feb 28 02:17:51 db2 kernel: .... register #02: 00000000
Feb 28 02:17:51 db2 kernel: ....... : arbitration: 00
Feb 28 02:17:51 db2 kernel: .... IRQ redirection table:
Feb 28 02:17:51 db2 kernel: NR Log Phy Mask Trig IRR Pol Stat Dest Deli
Vect:
Feb 28 02:17:51 db2 kernel: 00 000 00 1 0 0 0 0 0 0
00
Feb 28 02:17:51 db2 kernel: 01 00F 0F 0 0 0 0 0 1 1
39
Feb 28 02:17:51 db2 kernel: 02 00F 0F 0 0 0 0 0 1 1
31
Feb 28 02:17:51 db2 kernel: 03 00F 0F 0 0 0 0 0 1 1
41
Feb 28 02:17:51 db2 kernel: 04 00F 0F 0 0 0 0 0 1 1
49
Feb 28 02:17:51 db2 kernel: 05 00F 0F 0 0 0 0 0 1 1
51
Feb 28 02:17:51 db2 kernel: 06 00F 0F 0 0 0 0 0 1 1
59
Feb 28 02:17:51 db2 kernel: 07 00F 0F 0 0 0 0 0 1 1
61
Feb 28 02:17:51 db2 kernel: 08 00F 0F 0 0 0 0 0 1 1
69
Feb 28 02:17:51 db2 kernel: 09 00F 0F 0 0 0 0 0 1 1
71
Feb 28 02:17:51 db2 kernel: 0a 000 00 1 0 0 0 0 0 0
00
Feb 28 02:17:51 db2 kernel: 0b 000 00 1 0 0 0 0 0 0
00
Feb 28 02:17:51 db2 kernel: 0c 00F 0F 0 0 0 0 0 1 1
79
Feb 28 02:17:51 db2 kernel: 0d 00F 0F 0 0 0 0 0 1 1
81
Feb 28 02:17:51 db2 kernel: 0e 00F 0F 0 0 0 0 0 1 1
89
Feb 28 02:17:51 db2 kernel: 0f 000 00 1 0 0 0 0 0 0
00
Feb 28 02:17:51 db2 kernel: 10 00F 0F 1 1 0 1 0 1 1
91
Feb 28 02:17:51 db2 kernel: 11 000 00 1 0 0 0 0 0 0
00
Feb 28 02:17:51 db2 kernel: 12 000 00 1 0 0 0 0 0 0
00
Feb 28 02:17:51 db2 kernel: 13 00F 0F 1 1 0 1 0 1 1
99
Feb 28 02:17:51 db2 kernel: 14 000 00 1 0 0 0 0 0 0
00
Feb 28 02:17:51 db2 kernel: 15 000 00 1 0 0 0 0 0 0
00
Feb 28 02:17:51 db2 kernel: 16 000 00 1 0 0 0 0 0 0
00
Feb 28 02:17:51 db2 kernel: 17 00F 0F 1 1 0 1 0 1 1
A1
Feb 28 02:17:51 db2 kernel: IRQ to pin mappings:
Feb 28 02:17:51 db2 kernel: IRQ0 -> 0:2
Feb 28 02:17:51 db2 kernel: IRQ1 -> 0:1
Feb 28 02:17:51 db2 kernel: IRQ3 -> 0:3
Feb 28 02:17:51 db2 kernel: IRQ4 -> 0:4
Feb 28 02:17:51 db2 kernel: IRQ5 -> 0:5
Feb 28 02:17:51 db2 kernel: IRQ6 -> 0:6
Feb 28 02:17:51 db2 kernel: IRQ7 -> 0:7
Feb 28 02:17:51 db2 kernel: IRQ8 -> 0:8
Feb 28 02:17:51 db2 kernel: IRQ9 -> 0:9
Feb 28 02:17:51 db2 kernel: IRQ12 -> 0:12
Feb 28 02:17:51 db2 kernel: IRQ13 -> 0:13
Feb 28 02:17:51 db2 kernel: IRQ14 -> 0:14
Feb 28 02:17:51 db2 kernel: IRQ16 -> 0:16
Feb 28 02:17:51 db2 kernel: IRQ19 -> 0:19
Feb 28 02:17:51 db2 kernel: IRQ23 -> 0:23
Feb 28 02:17:51 db2 kernel: .................................... done.
Feb 28 02:17:51 db2 kernel: Using local APIC timer interrupts.
Feb 28 02:17:51 db2 kernel: calibrating APIC timer ...
Feb 28 02:17:51 db2 kernel: ..... CPU clock speed is 1982.5248 MHz.
Feb 28 02:17:51 db2 kernel: ..... host bus clock speed is 99.1260 MHz.
Feb 28 02:17:51 db2 kernel: cpu: 0, clocks: 991260, slice: 198252
Feb 28 02:17:51 db2 kernel:
CPU0<T0:991248,T1:792976,D:20,S:198252,C:991260>
Feb 28 02:17:51 db2 kernel: cpu: 2, clocks: 991260, slice: 198252
Feb 28 02:17:51 db2 kernel: cpu: 1, clocks: 991260, slice: 198252
Feb 28 02:17:51 db2 kernel: cpu: 3, clocks: 991260, slice: 198252
Feb 28 02:17:51 db2 kernel:
CPU1<T0:991248,T1:594736,D:8,S:198252,C:991260>
Feb 28 02:17:51 db2 kernel:
CPU2<T0:991248,T1:396480,D:12,S:198252,C:991260>
Feb 28 02:17:51 db2 kernel:
CPU3<T0:991248,T1:198240,D:0,S:198252,C:991260>
Feb 28 02:17:51 db2 kernel: checking TSC synchronization across CPUs:
passed.
Feb 28 02:17:51 db2 kernel: Waiting on wait_init_idle (map = 0xe)
Feb 28 02:17:51 db2 kernel: All processors have done init_idle
Feb 28 02:17:51 db2 kernel: mtrr: your CPUs had inconsistent fixed MTRR
settings
Feb 28 02:17:51 db2 kernel: mtrr: probably your BIOS does not setup all
CPUs
Feb 28 02:17:51 db2 kernel: PCI: PCI BIOS revision 2.10 entry at 0xfb3e0,
last bus=4
Feb 28 02:17:51 db2 kernel: PCI: Using configuration type 1
Feb 28 02:17:51 db2 kernel: PCI: Probing PCI hardware
Feb 28 02:17:51 db2 kernel: Unknown bridge resource 0: assuming
transparent
Feb 28 02:17:51 db2 kernel: Unknown bridge resource 1: assuming
transparent
Feb 28 02:17:51 db2 kernel: Unknown bridge resource 2: assuming
transparent
Feb 28 02:17:51 db2 kernel: Unknown bridge resource 0: assuming
transparent
Feb 28 02:17:51 db2 kernel: Unknown bridge resource 2: assuming
transparent
Feb 28 02:17:51 db2 kernel: Unknown bridge resource 0: assuming
transparent
Feb 28 02:17:52 db2 kernel: Unknown bridge resource 2: assuming
transparent
Feb 28 02:17:52 db2 kernel: Unknown bridge resource 2: assuming
transparent
Feb 28 02:17:52 db2 kernel: PCI: Using IRQ router PIIX [8086/2440] at
00:1f.0
Feb 28 02:17:52 db2 kernel: PCI->APIC IRQ transform: (B0,I31,P1) -> 19
Feb 28 02:17:52 db2 kernel: PCI->APIC IRQ transform: (B4,I3,P0) -> 19
Feb 28 02:17:52 db2 kernel: PCI->APIC IRQ transform: (B4,I4,P0) -> 16
Feb 28 02:17:52 db2 kernel: Linux NET4.0 for Linux 2.4
Feb 28 02:17:52 db2 kernel: Based upon Swansea University Computer Society
NET3.039
Feb 28 02:17:52 db2 kernel: Initializing RT netlink socket
Feb 28 02:17:52 db2 kernel: Starting kswapd
Feb 28 02:17:52 db2 kernel: Real Time Clock Driver v1.10e
Feb 28 02:17:52 db2 kernel: block: 128 slots per queue, batch=32
Feb 28 02:17:52 db2 kernel: Uniform Multi-Platform E-IDE driver Revision:
6.31
Feb 28 02:17:52 db2 kernel: ide: Assuming 33MHz system bus speed for PIO
modes; override with idebus=xx
Feb 28 02:17:52 db2 kernel: PIIX4: IDE controller on PCI bus 00 dev f9
Feb 28 02:17:52 db2 kernel: PIIX4: chipset revision 4
Feb 28 02:17:52 db2 kernel: PIIX4: not 100%% native mode: will probe irqs
later
Feb 28 02:17:52 db2 kernel: ide0: BM-DMA at 0xf000-0xf007, BIOS
settings: hda:DMA, hdb:pio
Feb 28 02:17:52 db2 kernel: hda: WDC WD1000JB-32CWE0, ATA DISK drive
Feb 28 02:17:52 db2 kernel: ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
Feb 28 02:17:52 db2 kernel: hda: 195371568 sectors (100030 MB) w/8192KiB
Cache, CHS=12161/255/63, UDMA(100)
Feb 28 02:17:52 db2 kernel: Partition check:
Feb 28 02:17:52 db2 kernel: hda: hda1 hda2 hda3 hda4
Feb 28 02:17:52 db2 kernel: Floppy drive(s): fd0 is 1.44M
Feb 28 02:17:52 db2 kernel: FDC 0 is a post-1991 82077
Feb 28 02:17:52 db2 kernel: eepro100.c:v1.09j-t 9/29/99 Donald Becker
http://www.scyld.com/network/eepro100.html
Feb 28 02:17:52 db2 kernel: eepro100.c: $Revision: 1.36 $ 2000/11/17
Modified by Andrey V. Savochkin <[email protected]> and others
Feb 28 02:17:52 db2 kernel: eth0: OEM i82557/i82558 10/100 Ethernet,
00:30:48:21:B5:1A, IRQ 16.
Feb 28 02:17:52 db2 kernel: Board assembly 000000-000, Physical
connectors present: RJ45
Feb 28 02:17:52 db2 kernel: Primary interface chip i82555 PHY #1.
Feb 28 02:17:52 db2 kernel: General self-test: passed.
Feb 28 02:17:52 db2 kernel: Serial sub-system self-test: passed.
Feb 28 02:17:52 db2 kernel: Internal registers self-test: passed.
Feb 28 02:17:52 db2 kernel: ROM checksum self-test: passed (0x04f4518b).
Feb 28 02:17:52 db2 kernel: NET4: Linux TCP/IP 1.0 for NET4.0
Feb 28 02:17:52 db2 kernel: IP Protocols: ICMP, UDP, TCP
Feb 28 02:17:52 db2 kernel: IP: routing cache hash table of 8192 buckets,
64Kbytes
Feb 28 02:17:52 db2 kernel: TCP: Hash tables configured (established
262144 bind 65536)
Feb 28 02:17:52 db2 kernel: NET4: Unix domain sockets 1.0/SMP for Linux
NET4.0.
Feb 28 02:17:52 db2 kernel: VFS: Mounted root (ext2 filesystem) readonly.
Feb 28 02:17:52 db2 kernel: Freeing unused kernel memory: 212k freed
Feb 28 02:17:52 db2 kernel: Adding Swap: 104416k swap-space (priority -1)
Aww, it died again, lockup (hard - caps lock light on keyboard doesn't
react when the button is pressed) and cold boot required to get it up
again. That's what I deserve for getting my hopes up.
Tried 2.2 again thinking it might work now with the fixed BIOS settings
but no, still getting the "Keyboard: Timeout - AT keyboard not present?"
and "hda: lost interrupt" messages. So I can't even boot 2.2 and I have no
clue what to try next. Instead, I'll concentrate on trying to get it
stable on 2.4. I've read that the random hard lockups can be caused by the
network card I'm using (built in Intel EtherExpress Pro 100 (PILA8470B))
and are now trying the e100 driver that Intel released for the card
instead of the driver that comes with the kernel (by Donald Becker). The
Intel driver is reported to have fixed similar problems for other people.
We'll see what it can do for me.
Other suggestions on what I could try to find the cause of the lockups are
much appreciated.
Thanks,
Johan
On Wed, 27 Feb 2002, texas wrote:
> We recently invested in a new database server (MySQL), a Dual P4 Xeon (2 x
> 2GHz Prestonia, 1GB RDRAM) system, it's mainboard is a Supermicro P4DCE+
> based on the i860 chipset.
After boot disable screen blanking with "setterm -blank 0" and see if that
helps. Seems some video cards do something odd at blanking time (or
perhaps you're using the BIOS blanking option). Only seems to happen with
SMP, and I got this from IBM support, so I doubt it's totally a folk tale.
--
bill davidsen <[email protected]>
CTO, TMR Associates, Inc
Doing interesting things with little computers since 1979.
> Tried 2.2 again thinking it might work now with the fixed BIOS settings
> but no, still getting the "Keyboard: Timeout - AT keyboard not present?"
> and "hda: lost interrupt" messages. So I can't even boot 2.2 and I have no
I guess that box is always assuming PnP or ACPI setup in which case 2.2
will never work on it.
Cold boot in the sense that reset buttons don't work or cold in the sense
ctrl-alt-del doesn't work. If the reset button isn't working thats a real
"hardware died" alarm bell
> are present as well as "init.c:148: bad pte 3fff3163" but none seem
The bad pte one needs looking into. That may actually be cured in the
bt_ioremap diffs pending though.
Alan
Ok, my "change NIC driver" idea was a bad one (surprise) as the server
locked up yet again.
> Cold boot in the sense that reset buttons don't work or cold in the
> sense ctrl-alt-del doesn't work.
ctrl-alt-del doesn't work but holding in the "off" button for 4 seconds
does work (turns off the machine) and I therefore assume that the reset
button would work as well (no reset button installed on this machine
unfortunately).
> The bad pte one needs looking into.
Is this something that could be the cause of the lockup problems?
> I guess that box is always assuming PnP or ACPI setup in which case 2.2
> will never work on it.
Lo and behold, after following Mark Hahn's advice of adding "noapic" to
lilo append, 2.2 is booting without any complaints! He actually suggested
it for 2.4 and after having successfully testing it on 2.2, I'm now
running 2.4 with noapic, hoping it will magically make my lockup
problems go away just as it fixed 2.2.
When 2.4 dies on me next time (after thinking "this will surely fix it!"
after every potential fix and getting disappointed, I've stopped using
"if"), I will try 2.2. The sad thing about that is that there's no
Hyperthreading but if it's stable, it's most definitely worth the
performance penalty.
> After boot disable screen blanking with "setterm -blank 0"
I'm using echo -e "\33[9;0]" > /dev/console to disable screen-blanking on
all my servers. There's something about a monitor suddenly going blank
that gets my heart pumping...
Thanks,
Johan
On Fri, 1 Mar 2002, Alan Cox wrote:
> > Tried 2.2 again thinking it might work now with the fixed BIOS settings
> > but no, still getting the "Keyboard: Timeout - AT keyboard not present?"
> > and "hda: lost interrupt" messages. So I can't even boot 2.2 and I have no
>
> I guess that box is always assuming PnP or ACPI setup in which case 2.2
> will never work on it.
hmm. I guess this begs the question, is ACPI 100% working and stable now?
I've got a similar problem with add-in IDE controllers which add more than
8 IDE devices -- the 9th and higher devices are inaccessable with the same
"hd?: lost interrupt" messages (beginning with hdi). The machine in
question is a dual AthlonXP/MP 1900+ on that new Tyan S2466 mainboard. I
figured it was a BIOS issue, but if the BIOS demands that ACPI configure
stuff, then perhaps enabling ACPI is the key. I just wihs that BIOS
manufacturers would get a fucking clue and realize that not all of us are
going to be running that other ACPI-dependent OS on the board, and make a
BIOS that configures devices the old-fashioned way: doing the work itself.
Tyan also needs to realize that assigning the same address to two sensors
on the I2C bus just isn't a good idea...
Hopefully this fixes my problem. Thanks for the pointer! ;)
Kelsey Hudson [email protected]
Associate Software Engineer
Compendium Technologies, Inc (619) 725-0771
---------------------------------------------------------------------------
==== 0100101101001001010000110100101100100000010010010101010000100001 =====
> > I guess that box is always assuming PnP or ACPI setup in which case 2.2
> > will never work on it.
>
> hmm. I guess this begs the question, is ACPI 100% working and stable now?
Not yet
> 8 IDE devices -- the 9th and higher devices are inaccessable with the same
> "hd?: lost interrupt" messages (beginning with hdi). The machine in
> question is a dual AthlonXP/MP 1900+ on that new Tyan S2466 mainboard. I
For the MP boards we use the MP1.1/MP1.4 tables. The MP1.4 tables on some
MP boards seem rather suspect
Nope, "noapic" didn't do it for 2.4, it locked up on me again :-(
I am currently running a vanilla 2.2.20 with "noapic". As mentioned, it
fixes the boot problem but we'll see about lockups in 2.2.
Thanks,
Johan
Ok, it's been a few days now since installing Kernel 2.2 with "noapic"
added to lilo append and the server does seem stable. That probably means
there's something wrong in 2.4 that are causing the lockups. I'm no kernel
guru and have no idea what it could be but will be running 2.2 until I
hear about others being able to run 2.4 stable on dual P4 Xeon systems
with the i860 chipset. It's rather new hardware and I assume the lockups
could be caused by lack of support for it in the kernel...? Or maybe not,
since 2.2 works well and it's even older.
It's sad not being able to run 2.4 as I seem to loose a lot of
performance. The load average on this database server is now 4 or higher
while it was 3 or lower when I ran 2.4. Hyperthreading might be part of
the reason for the performance improvement and that's a feature I'd really
like to be able to use. Note that I tried running 2.4 with HT turned off
in both kernel and BIOS and the server still locked on me so HT should not
be the cause of the stability problems.
If this might be a kernel issue in 2.4 and you need more info to debug it,
just ask me for any stats you might need, I'd be glad to supply it. If you
think it's a BIOS problem, should I contact Supermicro and let them know
about this?
Thanks,
Johan