Re: random slow query

Alan Hodgson wrote:
> On Tuesday 30 June 2009, Mike Ivanov <mikei@activestate.com> wrote:
>> Hi Scott,
>>
>>> Well, we can't be sure OP's only got one core.
>> In fact, we can, Sean posted what top -b -n 1 says. There was only one
>> CPU line.
>>
>
> Recent versions of top on Linux (on RedHat 5 anyway) may show only one
> combined CPU line unless you break them out with an option.

I have not noticed that to be the case. I ran RHEL3 from early 2004 until a
little after RHEL5 came out. I now run that (updated whenever updates come
out), and I do not recall ever setting any flag to get it to split the CPU
into 4 pieces.

I know the flag is there, but I do not recall ever setting it.
>
>>> the number of cores, it's the IO subsystem is too slow for the load.
>>> More cores wouldn't fix that.
>> While I agree on the IO, more cores would definitely help to improve
>> ~6.5 load average.
>
> No, I agree with the previous poster. His load is entirely due to IO wait.
> Only one of those processes was trying to do anything. IO wait shows up as
> high load averages.
>
If you run xosview, you can see all that stuff broken out, in my case at
one-second intervals. It shows user, nice, system, idle, wait, hardware
interrupt, software interrupt.

It also shows disk read, write, and idle time.

Lots of other stuff too.

--
   .~.  Jean-David Beyer          Registered Linux User 85642.
   /V\  PGP-Key: 9A2FC99A         Registered Machine   241939.
  /( )\ Shrewsbury, New Jersey    http://counter.li.org
  ^^-^^ 14:55:01 up 12 days, 1:44, 3 users, load average: 4.34, 4.36, 4.41