Random freezes

DaBlade · 10-05-2008, 07:06 PM

Hello
Recently, I've noticed that my machine randomly freezes. Usually, it's not when I'm around (like when I'm asleep or so). I try to use it, and it simply doesn't respond. Neither keyboard nor mouse input seems to have any effect.

I tried to have a look at the syslog, and this is the last that seems to have happened there prior to the crash:

Code:

Oct  5 23:42:59 Shadowfax kernel: [24667.430155]
Oct  5 23:42:59 Shadowfax kernel: [24667.430155]
Oct  5 23:42:59 Shadowfax kernel: [24667.430155] Code: 48 c7 c7 60 16 52 80 45 31 f6 41 55 45 31 ed 41 54 55 53 48 81 ec d0 00 00 00 e8 64 a3 06 00 48 8b 3d c8 11 2b 00 49 89 e4 eb 53 <83>
bf b0 00 00 00 00 48 8b af c0 00 00 00 0f 18 8d c0 00 00 00
Oct  5 23:42:59 Shadowfax kernel: [24667.430155] RIP  [<ffffffff803be60d>] dst_gc_task+0x2d/0x1a4
Oct  5 23:42:59 Shadowfax kernel: [24667.430155]  RSP <ffff81022f165dc0>
Oct  5 23:42:59 Shadowfax kernel: [24667.430155] CR2: ffff8101c286b3b0
Oct  5 23:42:59 Shadowfax kernel: [24667.430155] ---[ end trace 79949407e91317d1 ]---
Oct  5 23:43:01 Shadowfax kernel: [24669.171316] e1000: eth3: e1000_clean_tx_irq: Detected Tx Unit Hang
Oct  5 23:43:01 Shadowfax kernel: [24669.171316]   Tx Queue             <0>
Oct  5 23:43:01 Shadowfax kernel: [24669.171316]   TDH                  <d8>
Oct  5 23:43:01 Shadowfax kernel: [24669.171316]   TDT                  <ec>
Oct  5 23:43:01 Shadowfax kernel: [24669.171316]   next_to_use          <ec>
Oct  5 23:43:01 Shadowfax kernel: [24669.171316]   next_to_clean        <d6>
Oct  5 23:43:01 Shadowfax kernel: [24669.171316] buffer_info[next_to_clean]
Oct  5 23:43:01 Shadowfax kernel: [24669.171316]   time_stamp           <1004a86af>
Oct  5 23:43:01 Shadowfax kernel: [24669.171316]   next_to_watch        <d8>
Oct  5 23:43:01 Shadowfax kernel: [24669.171316]   jiffies              <1004a8eb9>
Oct  5 23:43:01 Shadowfax kernel: [24669.171316]   next_to_watch.status <0>
Oct  5 23:43:03 Shadowfax kernel: [24671.179402] e1000: eth3: e1000_clean_tx_irq: Detected Tx Unit Hang
Oct  5 23:43:03 Shadowfax kernel: [24671.179404]   Tx Queue             <0>
Oct  5 23:43:03 Shadowfax kernel: [24671.179405]   TDH                  <d8>
Oct  5 23:43:03 Shadowfax kernel: [24671.179406]   TDT                  <ec>
Oct  5 23:43:03 Shadowfax kernel: [24671.179407]   next_to_use          <ec>
Oct  5 23:43:03 Shadowfax kernel: [24671.179408]   next_to_clean        <d6>
Oct  5 23:43:03 Shadowfax kernel: [24671.179409] buffer_info[next_to_clean]
Oct  5 23:43:03 Shadowfax kernel: [24671.179409]   time_stamp           <1004a86af>
Oct  5 23:43:03 Shadowfax kernel: [24671.179411]   next_to_watch        <d8>
Oct  5 23:43:03 Shadowfax kernel: [24671.179411]   jiffies              <1004a90ad>
Oct  5 23:43:03 Shadowfax kernel: [24671.179412]   next_to_watch.status <0>
Oct  6 01:54:11 Shadowfax syslogd 1.5.0#5: restart.

Now, I have no idea whether this is a software or hardware-related problem..

Anyhow, here are my specs:
Debian Sid
Kernel 2.6.26-1-amd64
KDE 3.5
AMD Phenom X4 Quad-Core Processor GP-9830 Black Edition overclocked to 2632.131MHz
8GB DDR2-RAM
250GB hard drive
GeForce 8800GTS 512mb gfx
Gigabyte GA-MA790FX-DQ6 motherboard
Intel Pro/GT 1000 PCI NIC

If I forgot to write anything of significance, tell me.

Anyway, I hope someone out there can help me out =)

amani · 10-06-2008, 11:52 AM

EMI effects between RAM modules ...maybe?

salasi · 10-06-2008, 12:15 PM

Quote:

AMD Phenom X4 Quad-Core Processor GP-9830 Black Edition overclocked to 2632.131MHz

The first thing to check is whether it goes away if you put the clock settings back to standard.

DaBlade · 10-06-2008, 02:05 PM

amani: EMI?
salasi: That's an idea.. I can give it a try, problem is, the freezes occur a few times a week, so it'll take a while to know if it helped.

salasi · 10-07-2008, 04:55 AM

Its always a bit difficult with these infrequent problems, but I wouldn't be getting heavily involved in other measures while overclocking is still in place. Having said that, it is quite possible that a memory test program (memtest) shows up a problem more rapidly than just general usage would.

Quote:

EMI effects between RAM modules ...maybe?

Technically, it wouldn't really be an EMI problem, but an SI problem. In any case, if you have overclocked the bus to memory or tightened the timings from the default values, put them back immediately and try again.

DaBlade · 10-09-2008, 01:13 AM

Ok, it's been a few days since I turned off the overclocking, so far no freezes. Looks like that might have been the problem, alright.. =)
If it happens again, I'll post here, if not, thanks, guys =)

Electro · 10-09-2008, 04:36 AM

It just the module for your Intel NIC crashed. It is nothing to do with your entire computer. I suggest recompile the kernel with different settings for the e1000 module. Before you re-configure and re-compile the kernel, try taking out the Intel NIC.

I suggest do not over clock your processor because Linux does not have a high tolerance for errors. If the hardware is producing errors, Linux will halt the process because of chance of data corruption.

I think you mis-type the model for your processor because there is no 9830 but there is 9850.

DaBlade · 10-09-2008, 07:00 PM

Electro: I'll have a look at the module tomorrow (too tired now :P ).
As for the CPU, I wasn't the one who wrote it...

Code:

cat /proc/cpuinfo
processor       : 0
vendor_id       : AuthenticAMD
cpu family      : 16
model           : 2
model name      : AMD Phenom(tm) X4 Quad-Core Processor GP-9830
stepping        : 3
cpu MHz         : 2511.445
cache size      : 512 KB
physical id     : 0
siblings        : 4
core id         : 0
cpu cores       : 4
apicid          : 0
initial apicid  : 0
fpu             : yes
fpu_exception   : yes
cpuid level     : 5
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm 3dnowext 3dnow constant_tsc rep_good pni monitor cx16 popcnt lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs
bogomips        : 5027.90
TLB size        : 1024 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 48 bits physical, 48 bits virtual
power management: ts ttp tm stc 100mhzsteps hwpstate

processor       : 1
vendor_id       : AuthenticAMD
cpu family      : 16
model           : 2
model name      : AMD Phenom(tm) X4 Quad-Core Processor GP-9830
stepping        : 3
cpu MHz         : 2511.445
cache size      : 512 KB
physical id     : 0
siblings        : 4
core id         : 1
cpu cores       : 4
apicid          : 1
initial apicid  : 1
fpu             : yes
fpu_exception   : yes
cpuid level     : 5
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm 3dnowext 3dnow constant_tsc rep_good pni monitor cx16 popcnt lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs
bogomips        : 5023.08
TLB size        : 1024 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 48 bits physical, 48 bits virtual
power management: ts ttp tm stc 100mhzsteps hwpstate

processor       : 2
vendor_id       : AuthenticAMD
cpu family      : 16
model           : 2
model name      : AMD Phenom(tm) X4 Quad-Core Processor GP-9830
stepping        : 3
cpu MHz         : 2511.445
cache size      : 512 KB
physical id     : 0
siblings        : 4
core id         : 2
cpu cores       : 4
apicid          : 2
initial apicid  : 2
fpu             : yes
fpu_exception   : yes
cpuid level     : 5
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm 3dnowext 3dnow constant_tsc rep_good pni monitor cx16 popcnt lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs
bogomips        : 5022.99
TLB size        : 1024 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 48 bits physical, 48 bits virtual
power management: ts ttp tm stc 100mhzsteps hwpstate

processor       : 3
vendor_id       : AuthenticAMD
cpu family      : 16
model           : 2
model name      : AMD Phenom(tm) X4 Quad-Core Processor GP-9830
stepping        : 3
cpu MHz         : 2511.445
cache size      : 512 KB
physical id     : 0
siblings        : 4
core id         : 3
cpu cores       : 4
apicid          : 3
initial apicid  : 3
fpu             : yes
fpu_exception   : yes
cpuid level     : 5
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm 3dnowext 3dnow constant_tsc rep_good pni monitor cx16 popcnt lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs
bogomips        : 5022.94
TLB size        : 1024 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 48 bits physical, 48 bits virtual
power management: ts ttp tm stc 100mhzsteps hwpstate

:/