On Monday 11 February 2008, James wrote:
> Hello,
>
> One of the workstations (amd64 2gig ram) has a load that never drops
> below 1.0, as seen by top. Looking at a ps nothing stands out. I did
> notice that 'X' is at the top of the list, even when the machine is
> quiescent (nobody doing anything). Suspiciaous. Clearly I have a run
> away or hidden process using resources. Although all my system run
> kde 3.5.8 only one shows this problem.
>
> None of my other Gentoo system suffer this fate. Any ideas on finding
> the culprit(proccess)?

First thing to understand is exactly what the system load is. Maybe you
already know this, but I'll post it anyway for the benefit of everyone
else reading.

Load is defined as the number of processes waiting for cpu time averaged
over a certain time period. top and uptime measure this in three
periods - 1 minute, 5 minutes and 15 minutes. A process can be waiting
for cpu time because it is "blocked" - waiting for some I/O to
complete. Therefore it's easy to get a high load and low cpu
utilization. I find this in fact to be the most common reason (!)

vmstat is your friend here. It's all in the man page, so use it and
narrow down the process that's blocking. Maybe you have a threading
race condition or similar.

Also look into a hardware difference between this machine and the
others, and differences in the kernel config and loaded modules.

If all this reveals nothing, then maybe you do have a suspicious
problem. In which case, post back real quick :-)


--
Alan McKinnon
alan dot mckinnon at gmail dot com

--
gentoo-user@lists.gentoo.org mailing list

atop 3

filter by "p"



El lun, 11-02-2008 a las 19:49 +0000, James escribió:
> Hello,
>
> One of the workstations (amd64 2gig ram) has a load that never drops below
> 1.0, as seen by top. Looking at a ps nothing stands out. I did notice that
> 'X' is at the top of the list, even when the machine is quiescent (nobody
> doing anything). Suspiciaous. Clearly I have a run away or hidden process using
> resources. Although all my system run kde 3.5.8 only one shows this problem.
>
> None of my other Gentoo system suffer this fate. Any ideas on finding the
> culprit(proccess)?
>
>
>
> James
>
>


--
gentoo-user@lists.gentoo.org mailing list

On 23:27 Mon 11 Feb , Miguel Peña Gomez wrote:
>
>
> atop 3
>
> filter by "p"
>
>
>
> El lun, 11-02-2008 a las 19:49 +0000, James escribió:
> > Hello,
> >
> > One of the workstations (amd64 2gig ram) has a load that never drops below
> > 1.0, as seen by top. Looking at a ps nothing stands out. I did notice that
> > 'X' is at the top of the list, even when the machine is quiescent (nobody
> > doing anything). Suspiciaous. Clearly I have a run away or hidden process using
> > resources. Although all my system run kde 3.5.8 only one shows this problem.
> >
> > None of my other Gentoo system suffer this fate. Any ideas on finding the
> > culprit(proccess)?

WOW!!, this atop program is great, one of the best diagnostic tools I've
seen. Why haven't I heard more about it?

Bill Roberts

443-653-1569 wrote:

On 23:27 Mon 11 Feb , Miguel Peña Gomez wrote:


atop 3

filter by "p"





WOW!!, this atop program is great, one of the best diagnostic tools I've
seen. Why haven't I heard more about it?

Bill Roberts



What package provides that command?

Dale

:-) :-)
--

gentoo-user@lists.gentoo.org mailing list

Dale <dalek1967@bellsouth.net> wrote:

> 443-653-1569 wrote:
>> On 23:27 Mon 11 Feb , Miguel Peña Gomez wrote:
>>
>>> atop 3
>>>
>>> filter by "p"
>>>
>>>
>>>
>>
>> WOW!!, this atop program is great, one of the best diagnostic tools I've
>> seen. Why haven't I heard more about it?
>>
>> Bill Roberts
>>
>
> What package provides that command?

atop

Michael

--
gentoo-user@lists.gentoo.org mailing list

Dale wrote:

443-653-1569 wrote:

On 23:27 Mon 11 Feb , Miguel Peña Gomez wrote:


atop 3

filter by "p"





WOW!!, this atop program is great, one of the best diagnostic tools I've
seen. Why haven't I heard more about it?

Bill Roberts



What package provides that command?

Dale

:-) :-)


Never mind. I just needed my glasses. I thought it was _S_top not
_A_top. :/


Dale

:-) :-)
--

gentoo-user@lists.gentoo.org mailing list

Alan McKinnon <alan.mckinnon <at> gmail.com> writes:


> > One of the workstations (amd64 2gig ram) has a load that never drops
> > below 1.0, as seen by top. Looking at a ps nothing stands out. I did
> > notice that 'X' is at the top of the list, even when the machine is
> > quiescent (nobody doing anything). Suspiciaous. Clearly I have a run
> > away or hidden process using resources. Although all my system run
> > kde 3.5.8 only one shows this problem.


> vmstat is your friend here. It's all in the man page, so use it and
> narrow down the process that's blocking. Maybe you have a threading
> race condition or similar.

# vmstat
procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu----
r b swpd free buff cache si so bi bo in cs us sy id wa
0 0 0 847368 224736 403404 0 0 26 12 172 251 1 0 98 1

vmstat -s

2057808 total memory
1212156 used memory
611628 active memory
341672 inactive memory
845652 free memory
224784 buffer memory
404524 swap cache
6273340 total swap
0 used swap
6273340 free swap
20189 non-nice user cpu ticks
110 nice user cpu ticks
3748 system cpu ticks
2444468 idle cpu ticks
28905 IO-wait cpu ticks
588 IRQ cpu ticks
80 softirq cpu ticks
0 stolen cpu ticks
659529 pages paged in
289340 pages paged out
0 pages swapped in
0 pages swapped out
4307893 interrupts
6269353 CPU context switches
1202832933 boot time
7300 forks



> Also look into a hardware difference between this machine and the
> others, and differences in the kernel config and loaded modules.

Nothing here, all is similar to other system. And historically,
this system has not had this problem. I'm not certain when it started:

$ w
14:39:25 up 3:23, 1 user, load average: 1.00, 1.00, 1.00


It looks more like corruption in the application binary to me.
When have you ever seen a system at all three timing interval
locked at 1.00 when a system is quiescent?

What package is top part of?


> If all this reveals nothing, then maybe you do have a suspicious
> problem. In which case, post back real quick


I do not suspect a 'hack' is involved, because if I pull the ethernet
cable, it does not effect the load (still at 1.00).



Jame




--
gentoo-user@lists.gentoo.org mailing list

Miguel Peña Gomez <mpena <at> linuxhelp.cl> writes:


> atop 3
> filter by "p"



ATOP - galiot 2008/02/12 14:49:18 3 seconds elapsed
PRC | sys 0.01s | user 0.09s | #proc 130 | #zombie 0 | #exit ? |
CPU | sys 1% | user 3% | irq 0% | idle 197% | wait 0% |
cpu | sys 0% | user 3% | irq 0% | idle 97% | cpu001 w 0% |
cpu | sys 0% | user 0% | irq 0% | idle 99% | cpu000 w 0% |
CPL | avg1 1.00 | avg5 1.01 | avg15 1.00 | csw 1639 | intr 1100 |
MEM | tot 2.0G | free 824.6M | cache 395.2M | buff 219.5M | slab 182.9M |
SWP | tot 6.0G | free 6.0G | | vmcom 477.2M | vmlim 7.0G |

NPROCS SYSCPU USRCPU VSIZE RSIZE RDDSK WRDSK RNET SNET CPU CMD 1/1
1 0.00s 0.03s 489.2M 122.6M 0 0 0 0 1% X
1 0.00s 0.02s 614.7M 179.8M 0 0 0 0 1% seamonkey-bin
1 0.00s 0.02s 124.4M 18172K 0 0 0 0 1% konsole
1 0.01s 0.01s 20808K 3448K 0 0 0 0 1% atop
1 0.00s 0.01s 114.1M 10928K 0 0 0 0 0% klipper
1 0.00s 0.00s 0K 0K 0 0 0 0 0% khubd



OK, I see X hosed at the top, like I stated earlier. I rebuilt xorg-server,
just for grins but it makes no difference.

Any ideas?

James

--
gentoo-user@lists.gentoo.org mailing list

Any ideas?
No.But do you also see this without X running, without most daemons running, in single user mode...?

Henry Gebhardt <hsggebhardt <at> googlemail.com> writes:


> Any ideas?

> No.But do you also see this without X running,

Yep, same load with X killed off

without most daemons running,

Yep....


in single user mode...?
I did not try this. what's the option to boot into single user mode?


What would it prove?



James






--
gentoo-user@lists.gentoo.org mailing list