1 |
On Sunday 22 August 2010 21:04:56 Robert Bridge wrote: |
2 |
|
3 |
> Well, the fix is in the line for 2.6.36 IIRC, so wouldn't be in an |
4 |
> 2.6.35 kernel. |
5 |
> |
6 |
> That said, the problem supposedly being fixed goes back well before |
7 |
> 2.6.34, so if that kernel works, it suggests that it is a different |
8 |
> issue you are hitting. |
9 |
|
10 |
Alan's problem sounds like the one I've been having through several |
11 |
kernel versions - the way I describe the symptom is that the system |
12 |
"lurches" through its work. It's an i5 box with 4 GB simple RAM (4 |
13 |
cores, 8 threads). |
14 |
|
15 |
I did mention this here a few weeks ago, but when I discovered that |
16 |
killing BOINC, or reducing its allowed CPU load, seemed to cure it I |
17 |
took no further action. |
18 |
|
19 |
> However... If there was a FF update, that could be triggering the bug, |
20 |
> as FF3.5+ are pretty stinky for I/O levels. |
21 |
|
22 |
You may be onto something there. My genlop history of firefox goes back |
23 |
to January, when 3.5.6 was installed together with sys-kernel/gentoo- |
24 |
sources-2.6.32-r1. I don't remember when I first noticed the lurching |
25 |
though. |
26 |
|
27 |
-- |
28 |
Rgds |
29 |
Peter. Linux Counter 5290, 1994-04-23. |