1 |
On Saturday 23 June 2007 10:52:33 Duncan wrote: |
2 |
> Peter Humphrey <prh@××××××××××.uk> posted |
3 |
> > top - 09:04:59 up 23 min, 5 users, load average: 3.60, 4.79, 3.91 |
4 |
> > Tasks: 124 total, 2 running, 122 sleeping, 0 stopped, 0 zombie |
5 |
> > |
6 |
> > Cpu0: 0.3%us, 0.3%sy, 0.0%ni, 99.3%id, [zeroes] |
7 |
> > Cpu1: 0.0%us, 0.3%sy, 99.7%ni, 0.0%id, [zeroes] |
8 |
> > |
9 |
> > PID USER PR NI S %CPU %MEM TIME+ P COMMAND |
10 |
> > 5279 prh 34 19 S 50 1.0 6:53.97 1 setiathome-5.12 |
11 |
> > 5280 prh 34 19 S 50 1.0 6:54.08 0 setiathome-5.12 |
12 |
> > |
13 |
> > I don't think this is a scheduling problem; it goes deeper, so that the |
14 |
> > kernel doesn't have a consistent picture of which processor is which. |
15 |
> |
16 |
> Critical question here, is that in SMP Irix or SMP Solaris mode? (See |
17 |
> the top manpage if you don't know what I mean.) Asked another way, is |
18 |
> that displaying percent of total CPU time (both CPUs) or percent of |
19 |
> total divided by number of CPUs (so percent of one CPU)? |
20 |
|
21 |
That's another oddity. I press <I> (capital letter i) and /top/ says "Irix |
22 |
mode off" and shows half the previous percentage CPU in the process lines: |
23 |
25 in the example above. I then press <I> again and it says "Irix mode on" |
24 |
and shows the 50s again. Is this backwards, or is my utter confusion |
25 |
showing? :-( |
26 |
|
27 |
I want it to show: |
28 |
- for each CPU, the percent to which it is loaded; and, |
29 |
- for each process, how much of a CPU's time it is consuming. |
30 |
The presence of two CPUs requires two CPU lines and allows for two lots of |
31 |
processes. That seems logical to me. Is it Irix mode or Solaris? |
32 |
|
33 |
This morning /top/ is showing this: |
34 |
--- |
35 |
top - 10:51:55 up 2:22, 5 users, load average: 2.43, 2.34, 2.60 |
36 |
Tasks: 121 total, 4 running, 117 sleeping, 0 stopped, 0 zombie |
37 |
Cpu0 : 0.3%us, 0.3%sy, 0.0%ni, 99.3%id, [zeroes] |
38 |
Cpu1 : 0.0%us, 0.3%sy, 99.7%ni, 0.0%id, [zeroes] |
39 |
|
40 |
PID USER PR NI S %CPU %MEM TIME+ P COMMAND |
41 |
5270 prh 34 19 S 50 0.9 67:55.08 1 setiathome-5.12 |
42 |
5271 prh 34 19 S 50 1.1 67:57.80 1 einstein_S5R2_4 |
43 |
--- |
44 |
|
45 |
So CPU1 is fully loaded and CPU0 is idling. Gkrellm shows the same. The box |
46 |
has been running for 2 hours from cold and I haven't tampered with |
47 |
anything; BOINC starts from /etc/init.d/local. When /top/ is behaving this |
48 |
way my problem seems to be one of scheduling, but I'm pretty sure it isn't. |
49 |
|
50 |
> I'm not sure where your bug is, but [...] the problem appears to be way |
51 |
> deeper than scheduling. I'd guess it's ultimately a kernel bug, possibly |
52 |
> due to a hardware bug |
53 |
|
54 |
That's my thought too. |
55 |
|
56 |
> [...] you might wish to file it on top initially, just to see if they've |
57 |
> seen [anything] similar and can tell you what's going on. Unless you want |
58 |
> to double-check patching status yourself, you might as well file the bug |
59 |
> with Gentoo first, in case it's a Gentoo bug. They'll probably end up |
60 |
> closing it "upstream", but at least then when you file it upstream, you |
61 |
> can say you've cleared it with Gentoo first. |
62 |
|
63 |
I'll do that, but I'll wait a day or two to see what else comes up here. |
64 |
|
65 |
> You definitely have a strange one here, and I'd /love/ to see what the |
66 |
> real experts have to say about it! |
67 |
|
68 |
Mm, me too. |
69 |
|
70 |
-- |
71 |
Rgds |
72 |
Peter Humphrey |
73 |
Linux Counter 5290, Aug 93 |
74 |
-- |
75 |
gentoo-amd64@g.o mailing list |