1 |
On 28-03-2015 08:50 PM, Mick wrote: |
2 |
> On Saturday 28 Mar 2015 22:48:48 Sebas Pedersen wrote: |
3 |
>> On 28-03-2015 07:37 PM, Volker Armin Hemmann wrote: |
4 |
>> > Am 28.03.2015 um 23:00 schrieb Sebas Pedersen: |
5 |
>> >> On 28-03-2015 06:45 PM, Volker Armin Hemmann wrote: |
6 |
>> >>> Am 28.03.2015 um 14:58 schrieb Sebas Pedersen: |
7 |
>> >>>> Hi guys, |
8 |
>> >>>> |
9 |
>> >>>> From a few days ago I am experimenting an MCE error. |
10 |
>> >>>> Sometimes I turn on the computer and at some point while booting the |
11 |
>> >>>> kernel (after the grub menu) just freezes and puts this: |
12 |
>> >>>> |
13 |
>> >>>> CPU 0: Machine Check Exception: 4 Bank 4: b200000000070f0f |
14 |
>> >>>> TSC f5acc9180 |
15 |
>> >>>> PROCESSOR 2:20fc2 TIME 1427486735 SOCKET 0 APIC 0 microcode 0 |
16 |
>> >>>> |
17 |
>> >>>> the number for TSC may vary, but the b200000000070f0f it's always |
18 |
>> >>>> the |
19 |
>> >>>> same (at least for now). The error message suggest to parse the |
20 |
>> >>>> above |
21 |
>> >>>> error with mcelog. I did that and the result was: |
22 |
>> >>>> |
23 |
>> >>>> Hardware event. This is not a software error. |
24 |
>> >>>> CPU 0 4 northbridge TSC f5acc9180 |
25 |
>> >>>> TIME 1427486735 Fri Mar 27 17:05:35 2015 |
26 |
>> >>>> |
27 |
>> >>>> Northbridge Watchdog error |
28 |
>> >>>> |
29 |
>> >>>> bit57 = processor context corrupt |
30 |
>> >>>> bit61 = error uncorrected |
31 |
>> >>>> |
32 |
>> >>>> bus error 'generic participation, request timed out |
33 |
>> >>>> |
34 |
>> >>>> generic error mem transaction |
35 |
>> >>>> generic access, level generic' |
36 |
>> >>>> |
37 |
>> >>>> STATUS b200000000070f0f MCGSTATUS 4 |
38 |
>> >>>> CPUID Vendor AMD Family 15 Model 44 |
39 |
>> >>>> SOCKET 0 APIC 0 microcode 0 |
40 |
>> >>>> |
41 |
>> >>>> The error suggest it's a hardware problem. I replace de RAM with no |
42 |
>> >>>> luck. Same error keeps happening. |
43 |
>> >>>> |
44 |
>> >>>> Any suggestion for identifying the problem or how to procede? |
45 |
>> >>>> |
46 |
>> >>>> Many thanks in advance! |
47 |
>> >>>> |
48 |
>> >>>> Sebas |
49 |
>> >>> |
50 |
>> >>> bios update/microcode update. A google search suggests that you have |
51 |
>> >>> run |
52 |
>> >>> into an errata. |
53 |
>> >> |
54 |
>> >> Oh OK, thank you. Must have miss that in the search. So you are saying |
55 |
>> >> that the error comes from a bios errata (and don't know what microdode |
56 |
>> >> is), and the fix is to update bios? |
57 |
>> > |
58 |
>> > no, possibly from a CPU errata and a bios update might bring in the |
59 |
>> > microcode update that works around that. |
60 |
>> |
61 |
>> I see, thanks for clarifying that. So looks like not too many options, |
62 |
>> either try to update the bios and/or replace the CPU. |
63 |
>> |
64 |
>> I really appreciated you replys and time. |
65 |
>> |
66 |
>> Thanks!, |
67 |
>> Sebas |
68 |
> |
69 |
> There's 'CONFIG_MICROCODE=y' and friends in the kernel which along with |
70 |
> sys- |
71 |
> apps/microcode-ctl will load what ever is the latest Intel/AMD CPU code |
72 |
> (firmware) to patch any bugs with instructions that the CPU |
73 |
> manufacturers have |
74 |
> discovered. |
75 |
|
76 |
That's nice. I'm gonna compile the kernel and see what happends. |
77 |
|
78 |
Many thanks! |