[Bugme-new] [Bug 4238] New: sata_promise induced crash on x86_64
bugme-daemon at osdl.org
bugme-daemon at osdl.org
Tue Feb 22 07:30:07 PST 2005
http://bugme.osdl.org/show_bug.cgi?id=4238
Summary: sata_promise induced crash on x86_64
Kernel Version: 2.6.11-rc4
Status: NEW
Severity: high
Owner: andmike at us.ibm.com
Submitter: lionel at mamane.lu
Distribution: Debian GNU/Linux sid (unstable)
Hardware Environment: Opteron (model 5, stepping 8) single-CPU machine, Asus
SK8N motherboard (NFORCE3 150 Pro chipset, Promise SATA378 TX2Plus), two Maxtor
6Y120M0 SATA hard drives
Software Environment: 64bit kernel, 32bit userspace. Latest motherboard release
BIOS (revision 1007).
Problem Description:
With Linux 2.6.7 to 2.6.11-rc4, machine locks up under disk activity (e.g. "find
/ > /dev/null"). I tested 2.6.11-rc4 Linus' tree, the others are Debian kernels.
2.6.5 works rock-solid. It enables "noapic" automatically. Passing noapic and/or
acpi=off to later kernels does not solve the crash.
After running for about 30s, the disk activity stops. After a few seconds, the
console says
ata1: command timeout
and after a few seconds, hard lock-up (Magic SysRq key not working anymore), and
MCE error on console:
Machine Check Exception CPU0 4 Bank 0: d453c00000000833
TSC 6e1a571d1c ADDR 13e8211c0
Machine Check Exception CPU0 4 Bank 2: d000400000000863
TSC 6e1a572203
Machine Check Exception CPU0 4 Bank 4: b200000000070F0F
TSC 6e1a5723f2
The hex numbers seem to change every time. Another time:
Machine Check Exception CPU0 4 Bank 0: 9410400000000833
TSC 2f5cdfadc4 ADDR 13ea7fa80
Machine Check Exception CPU0 4 Bank 2: d000400000000863
TSC 2f5cdfb24a
Machine Check Exception CPU0 4 Bank 4: b200000000070f0f
TSC 2f5cdbb439
And another time:
Machine Check Exception CPU0 4 Bank 4: b200000000070f0f
TSC 7bf5e47120
Any other info that would be useful?
------- You are receiving this mail because: -------
You are on the CC list for the bug, or are watching someone who is.
More information about the Bugme-new
mailing list