1 |
Thanks Mark, I'll look into that config option, and try again with top open. |
2 |
|
3 |
In this case I was doing a home backup to a 1TB WD Caviar black formatted |
4 |
as ext3. |
5 |
|
6 |
I also have a raid0 with 2 other non-WD sata drives, and a single WD |
7 |
velociraptor I can test |
8 |
with. |
9 |
|
10 |
It also doesn't sound too far off that FF could be the culprit (mentioned |
11 |
above), as I have it |
12 |
open all the time, and so far it's been the first place I've noticed these |
13 |
hiccups. That could |
14 |
be coincidence though, as I've pretty much always got it open and these |
15 |
hiccups are |
16 |
system wide. |
17 |
|
18 |
On Mon, Aug 23, 2010 at 10:03 AM, Mark Knecht <markknecht@×××××.com> wrote: |
19 |
|
20 |
> On Sun, Aug 22, 2010 at 12:01 PM, Alan Warren <bluemoonshine@×××××.com> |
21 |
> wrote: |
22 |
> > Hello, |
23 |
> > |
24 |
> > I am having some system performance issues with this kernel release. I |
25 |
> have |
26 |
> > a SMP machine (dual xeon nehalem 8 core / 16 threads) with 24gb non-ecc |
27 |
> > memory. |
28 |
> > |
29 |
> > On occasion (seems random so far) my system feels like a Pentium II |
30 |
> trying |
31 |
> > to cope with Vista. For example, I was in the middle of tar'ing a |
32 |
> semi-large |
33 |
> > file and noticed all of my apps came to a crawl. Scrolling in firefox, |
34 |
> > typing in the terminal, or trying to navigate in my file manager resulted |
35 |
> in |
36 |
> > breif "pauses" that came in waves. On one occasion my system froze |
37 |
> > completely and I had to manually reset the machine. (that was with |
38 |
> > 2.6.35-r1) |
39 |
> > |
40 |
> > I didn't activate anything "new" in this kernel release that I don't |
41 |
> > normally activate. ie, no cpuidle driver |
42 |
> > |
43 |
> > Is there a proper venu for debugging such matters, or should I just wait |
44 |
> for |
45 |
> > this kernel to go prime-time? |
46 |
> > |
47 |
> > Thanks for your time, |
48 |
> > Alan |
49 |
> > |
50 |
> |
51 |
> Hi Alan, |
52 |
> Sorry for the problems. I've seen them also in the recent past. In |
53 |
> my case it was on new hardware so I couldn't say it was due to a |
54 |
> specific kernel release. |
55 |
> |
56 |
> 1) What happens when you watch top while doing the tar? Do you by any |
57 |
> chance see large wait times in top? (Hit '1' to watch all CPUs) If so |
58 |
> the problem could well be how the kernel is dealing with writing data |
59 |
> back to the hard drive. I had this problem with the WD Green drives. |
60 |
> When I changed to WD RAID Edition drives (1/2 the storage for 30% more |
61 |
> money) the problems disappeared. |
62 |
> |
63 |
> 2) If it's not the drive issue then there is a kernel option called (I |
64 |
> think) RCU_CPU_STALL_DETECTION (or something like that. If you turn it |
65 |
> on I may generate a trace of what's keeping a core busy to long. |
66 |
> Mileage will vary. |
67 |
> |
68 |
> Good luck, |
69 |
> Mark |
70 |
> |
71 |
> |