1 |
On Thursday 09 November 2006 07:51, Duncan wrote: |
2 |
> Mauro Maroni <mmaroni@××××××.ar> posted |
3 |
> 200611082025.25462.mmaroni@××××××.ar, excerpted below, on Wed, 08 Nov |
4 |
> |
5 |
> 2006 20:25:25 -0300: |
6 |
> > Well, then I got segfaults compiling other packages, and a couple of |
7 |
> > times the machine freezed doing trivial things like browsing the web. |
8 |
> > Could this be a hardware issue? RAM seems to be OK as I ran memtest |
9 |
> > during the night and did not show any error after 9 hours. |
10 |
> |
11 |
> That's a classic hardware issue, yes. The cause can be one of several |
12 |
> things. Note that there are at least two ways RAM can be bad and memtest |
13 |
> checks only one -- memory actually corrupting in storage. From hard |
14 |
> experience, I know the other one all too well -- AND know that memtest |
15 |
> doesn't catch it AT ALL. That one is memory timing issues, and as |
16 |
> memory speeds increase, it's becoming more and more common. Taking my |
17 |
> case as an example, the RAM was rated PC3200, but simply wasn't stable at |
18 |
> that. Unfortunately, my mobo was new enough at the time, and using the |
19 |
> then new AMD64 memory-controller-on-CPU technology, that the BIOS didn't |
20 |
> have the usual memory speed tweaking options. After fighting with it for |
21 |
> some time, a BIOS upgrade was eventually made available that added these |
22 |
> options, and a very simple (with the right BIOS option) tweak to reduce |
23 |
> memory clocking from the rated PC3200 (200 MHz DDRed to 400, times 8 bit |
24 |
> bus width, equals 3200) to ~PC3000 (183 MHz DDred to 366, times 8, rounds |
25 |
> to 3000) eliminated the issue entirely. The system was then rock-stable, |
26 |
> even after tweaking some of the detailed individual wait-state settings |
27 |
> back up to increase the performance a bit from the defaults. |
28 |
> |
29 |
> So, before you eliminate memory as a possibility, check your BIOS and try |
30 |
> declocking it a notch or two. |
31 |
|
32 |
It has been very stable during the last days. But I will give this a try if |
33 |
the problem comes back. Thanks a lot for your answer. |
34 |
|
35 |
Mauro |
36 |
|
37 |
-- |
38 |
gentoo-amd64@g.o mailing list |