I think I have a problem with spinlocks on my DP264 with dual 667MHz
EV67's.
The machine is running 2.2.14-6.0smp, which is a default RedHat 6.2
kernel.
The ethernet card is a 3Com 3c590.
When I run a program using a lot of CPU time I get this on the console:
eth0: Host error, FIFO diagnostic register 0000.
eth0: Host error, FIFO diagnostic register 0000.
eth0: Host error, FIFO diagnostic register 0000.
eth0: Host error, FIFO diagnostic register 0000.
eth0: Host error, FIFO diagnostic register 0000.
eth0: Host error, FIFO diagnostic register 0000.
eth0: Host error, FIFO diagnostic register 0000.
eth0: Host error, FIFO diagnostic register 8000.
eth0: Host error, FIFO diagnostic register 8000.
eth0: Host error, FIFO diagnostic register 8000.
eth0: Host error, FIFO diagnostic register 8000.
eth0: Host error, FIFO diagnostic register 8000.
eth0: Host error, FIFO diagnostic register 0000.
eth0: Host error, FIFO diagnostic register 0000.
eth0: Host error, FIFO diagnostic register 0000.
eth0: Host error, FIFO diagnostic register 0000.
fault.c:43 spinlock stuck in range at fffffc0000329ec0(1) owner range at
fffffc000032cd64(0) sched.c:30
eth0: Host error, FIFO diagnostic register
0000.
eth0: Host error, FIFO diagnostic register 8000.
eth0: Host error, FIFO diagnostic register 8000.
eth0: Host error, FIFO diagnostic register 8000.
eth0: Host error, FIFO diagnostic register 8000.
eth0: Too much work in interrupt, status 8003. Temporarily disabling
functions (7ffc).
fault.c:43 spinlock stuck in range at fffffc0000329ec0(1) owner range at
fffffc000032cd64(0) sched.c:30
fault.c:43 spinlock stuck in range at fffffc0000329ec0(1) owner range at
fffffc000032cd64(0) sched.c:30
fault.c:43 spinlock stuck in range at fffffc0000329ec0(1) owner range at
fffffc000032cd64(0) sched.c:30
fault.c:43 spinlock stuck in range at fffffc0000329ec0(1) owner range at
fffffc000032cd64(0) sched.c:30
fault.c:43 spinlock stuck in range at fffffc0000329ec0(1) owner range at
fffffc000032cd64(0) sched.c:30
fault.c:43 spinlock stuck in range at fffffc0000329ec0(1) owner range at
fffffc000032cd64(0) sched.c:30
The last message is repeating itself and the machine is stuck.
I also get a similar spinlock message when I boot the machine (marked
with ^^^^):
[start of dmesg]
Linux version 2.2.14-6.0smp ([EMAIL PROTECTED]) (gcc version
egcs-2.91.66 19990314/Linux (egcs-1.1.2 release)) #1 SMP Tue Mar 28
16:45:54 EST 2000
Booting GENERIC on Tsunami variation DP264 using machine vector DP264
from SRM
Command line: root=/dev/sda1 console=ttyS0 bootdevice=sda1
bootfile=boot/vmlinuz-2.2.14-6.0smp
Initial ramdisk at: 0xefefefefefefefef (17289301308300324847 bytes)
SMP: 2 CPUs probed -- cpu_present_mask = 3
Console: colour VGA+ 80x25
Calibrating delay loop... 1325.40 BogoMIPS
initrd overwritten (0xefefefefefefefef < 0xfffffc0000ae3f08) - disabling
it.
Memory: 513400k available
Dentry hash table entries: 65536 (order 7, 1024k)
Buffer cache hash table entries: 524288 (order 9, 4096k)
Page cache hash table entries: 65536 (order 6, 512k)
VFS: Diskquotas version dquot_6.4.0 initialized
POSIX conformance testing by UNIFIX
SMP starting up secondaries.
recv_secondary_console_msg: on 0 message is 'P01>>>START P01>>>'
Calibrating delay loop... 1325.40 BogoMIPS
SMP: Total of 2 processors activated (2650.80 BogoMIPS).
Alpha PCI BIOS32 revision 0.04
PCI: Probing PCI hardware
SMC37c669 Super I/O Controller found @ 0x3f0
Linux NET4.0 for Linux 2.2
Based upon Swansea University Computer Society NET3.039
NET4: Unix domain sockets 1.0 for Linux NET4.0.
NET4: Linux TCP/IP 1.0 for NET4.0
IP Protocols: ICMP, UDP, TCP, IGMP
TCP: Hash tables configured (ehash 524288 bhash 65536)
Starting kswapd v 1.5
buffer.c:43 spinlock stuck in kflushd at fffffc0000355184(1) owner
swapper at fffffc00003102dc(0) init/main.c:43
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
initialize_kbd: Keyboard reset failed, no ACK
Detected PS/2 Mouse Port.
Serial driver version 4.27 with no serial options enabled
keyboard: Too many NACKs -- noisy kbd cable?
keyboard: Too many NACKs -- noisy kbd cable?
ttyS00 at 0x03f8 (irq = 4) is a 16550A
ttyS01 at 0x02f8 (irq = 3) is a 16550A
pty: 256 Unix98 ptys configured
RAM disk driver initialized: 16 RAM disks of 8192K size
PCI_IDE: unknown IDE controller on PCI bus 00 device 29, VID=1080,
DID=c693
PCI_IDE: not 100% native mode: will probe irqs later
ide0: BM-DMA at 0x1100-0x1107, BIOS settings: hda:pio, hdb:pio
ide1: BM-DMA at 0x1108-0x110f, BIOS settings: hdc:pio, hdd:pio
PCI_IDE: unknown IDE controller on PCI bus 00 device 2a, VID=1080,
DID=c693
PCI_IDE: not 100% native mode: will probe irqs later
PCI_IDE: port 0x01f0 already claimed by ide0
PCI_IDE: port 0x0170 already claimed by ide1
PCI_IDE: neither IDE port enabled (BIOS)
hda: CD-ROM CDU4011, ATAPI CDROM drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
io_request_lock is fffffc000055ab40
buffer.c:43 spinlock grabbed in kflushd at fffffc0000355184(1) 4956
ticks
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
hda: ATAPI 40X CD-ROM drive, 120kB Cache
Uniform CDROM driver Revision: 2.56
Floppy drive(s): fd0 is 2.88M
FDC 0 is a post-1991 82077
md driver 0.90.0 MAX_MD_DEVS=256, MAX_REAL=12
linear personality registered
raid0 personality registered
raid1 personality registered
raid5 personality registered
raid5: measuring checksumming speed
8regs : 1800.000 MB/sec
32regs : 1064.000 MB/sec
using fastest function: 8regs (1800.000 MB/sec)
[end of dmesg]
Does this mean that spinlocks and SMP mode is not complete on Linux
Alpha yet ???
Thanks in advance,
--
Steffen Persvold Systems Engineer
Email : mailto:[EMAIL PROTECTED] Scali AS (http://www.scali.com)
Tlf : (+47) 22 62 89 50 Olaf Helsets vei 6
Fax : (+47) 22 62 89 51 N-0621 Oslo, Norway
