1 |
>>> The gcc update just failed to compile on one of my systems with a |
2 |
>>> segfault, but then succeeded after trying again even though I didn't |
3 |
>>> change anything. Does that indicate a hardware problem for sure? |
4 |
>>> Should I run memtester? Any other tests to run? Nothing in dmesg. |
5 |
>> |
6 |
>> Not definitively anything; it could have been a race condition. |
7 |
>> |
8 |
>> Memtest if you like. prime95 is designed for CPU and memory burning, |
9 |
>> too, and wouldn't require you to shutdown your system. |
10 |
> |
11 |
> Thanks everyone. I ran memtester for a little bit and it came up with |
12 |
> this before I killed it: |
13 |
> |
14 |
> # memtester 14000 |
15 |
> memtester version 4.0.8 (64-bit) |
16 |
> Copyright (C) 2007 Charles Cazabon. |
17 |
> Licensed under the GNU General Public License version 2 (only). |
18 |
> |
19 |
> pagesize is 4096 |
20 |
> pagesizemask is 0xfffffffffffff000 |
21 |
> want 14000MB (14680064000 bytes) |
22 |
> got 14000MB (14680064000 bytes), trying mlock ...locked. |
23 |
> Loop 1: |
24 |
> Stuck Address : ok |
25 |
> Random Value : ok |
26 |
> FAILURE: 0x524e8edb0512f3a7 != 0x524ecedb0512f3a7 at offset 0x04bd5130. |
27 |
> FAILURE: 0x224c0b76048d37c0 != 0x224c4b76048d37c0 at offset 0x0de17970. |
28 |
> FAILURE: 0x207dad0b8c3aced0 != 0x207ded0b8c3aced0 at offset 0x0de36970. |
29 |
> FAILURE: 0x847e610e840fb84e != 0x847e210e840fb84e at offset 0x1dc7922f. |
30 |
> FAILURE: 0x3f69916b940c7907 != 0x3f69d16b940c7907 at offset 0x1ed37770. |
31 |
> Compare XOR : FAILURE: 0x13664bb2c7a58ca3 != |
32 |
> 0x13668bb2c7a58ca3 at offset 0x04bd5130. |
33 |
> FAILURE: 0x61bcd9d27eba2967 != 0x61bd19d27eba2967 at offset 0x0686b930. |
34 |
> FAILURE: 0xe363c84dc71fd0bc != 0xe364084dc71fd0bc at offset 0x0de17970. |
35 |
> FAILURE: 0xe19569e34ecd67cc != 0xe195a9e34ecd67cc at offset 0x0de36970. |
36 |
> FAILURE: 0x7b844f40969fc496 != 0x7b848f40969fc496 at offset 0x0de94930. |
37 |
> FAILURE: 0x45961de646a2514a != 0x4595dde646a2514a at offset 0x1dc7922f. |
38 |
> FAILURE: 0x67e4594142a19ffa != 0x67e4994142a19ffa at offset 0x1ea14730. |
39 |
> FAILURE: 0x8341dc6542a103ab != 0x83421c6542a103ab at offset 0x1ecd4730. |
40 |
> FAILURE: 0x814e43569f1203 != 0x818e43569f1203 at offset 0x1ed37770. |
41 |
> Compare SUB : FAILURE: 0x1082d4779192eec4 != |
42 |
> 0xefbfd4779192eec4 at offset 0x02d10930. |
43 |
> FAILURE: 0xad2dd70ca745ff5c != 0x8c6ad70ca745ff5c at offset 0x04bd5130. |
44 |
> FAILURE: 0x189f6452fe165a2c != 0xf7dc6452fe165a2c at offset 0x0686b930. |
45 |
> FAILURE: 0xc9ac41a7eab20330 != 0xa8e941a7eab20330 at offset 0x0de17970. |
46 |
> FAILURE: 0x1b9b05b99a41be70 != 0xfad805b99a41be70 at offset 0x0de36970. |
47 |
> FAILURE: 0x300cb2e02ea06f8 != 0xe23dcb2e02ea06f8 at offset 0x0de94930. |
48 |
> FAILURE: 0xb29086ae7fdf2d4 != 0xea66086ae7fdf2d4 at offset 0x0e1c5970. |
49 |
> FAILURE: 0x89126e3b0ccb5288 != 0xa9d56e3b0ccb5288 at offset 0x1dc7922f. |
50 |
> FAILURE: 0x4d7afcf6378f9248 != 0x2cb7fcf6378f9248 at offset 0x1ea14730. |
51 |
> FAILURE: 0x5a9034aa259352fc != 0x39cd34aa259352fc at offset 0x1ecd4730. |
52 |
> FAILURE: 0x7b1c0d3184539edc != 0x5a590d3184539edc at offset 0x1ed37770. |
53 |
> Compare MUL : FAILURE: 0x00000000 != 0x00000001 at offset 0x0686b930. |
54 |
> FAILURE: 0x00000000 != 0x00000001 at offset 0x0de36970. |
55 |
> Compare DIV : Compare OR : ok |
56 |
> Compare AND : ok |
57 |
> Sequential Increment: ok |
58 |
> Solid Bits : testing 29 |
59 |
> |
60 |
> Now I've emerged gimps and I'm running the mprime "Blend" stress test |
61 |
> so we'll see what that turns up. |
62 |
> |
63 |
> - Grant |
64 |
|
65 |
mprime ran for about 1.5 hours until it found this: |
66 |
|
67 |
[Work thread Feb 23 13:04] FATAL ERROR: Rounding was 0.5, expected less than 0.4 |
68 |
[Work thread Feb 23 13:04] Hardware failure detected, consult stress.txt file. |
69 |
[Work thread Feb 23 13:04] Torture Test completed 85 tests in 1 hour, |
70 |
33 minutes - 1 errors, 0 warnings. |
71 |
[Work thread Feb 23 13:04] Worker stopped. |
72 |
[Main thread Feb 23 13:04] Execution halted. |
73 |
|
74 |
I have a 1200 watt Corsair power supply and my temps are very low even |
75 |
during the stress test so I'm thinking bad (Corsair) RAM. I should |
76 |
remove modules one at a time and re-test to narrow it down? |
77 |
|
78 |
- Grant |