Hi have just built a new sunfire 280r with solaris 9 and i Have 2 questions

1) where can i view some information that will tell me for definate that the 2*900 mhz processors are both being used, i tried using "top" but it doesnt tell me for sure that both processors are churning away together

2) Our company uses SAS which is like a statistics number crunching app, when the SAS guys run a job, It is supposed to utilise the wonderful new dual 900mhz processors, but when i open "top" the SAS processes are using under 5% (if im lucky !). The interesting thing is that along the top of the "top" screen it says

CPU States -5% idle- 1% user - 3% Kernel- 95% iowait - 0% swap

can anybody tell me why iowait is at 95% and what the hell does it mean anyway !!!? . This box is running nothing but SAS and O/S associated processes, and the data it is sourcing is on the same box, so there are no NFS data access issues So why are my processes using hardly any CPU ?

any help on this would be greatly appreciated

Thought this might be of any help.

Ignore High iowait

The iowait statistic can be misleading on large machines..........

This is kinda confusing.

Your cpus are being utilized because if your system's idle state is at 5% that means the sytem is under heavy use.

if your sytem was at something higher like in the 90s then you can decide if the cpus are being utilized.

bottom line is idle percent number of 5% indicates your systems is heavily being used

Hi,

Sorry to hook in this late, I hope we are still in time.
This is something you never want to see !!

Especialy with internal disks. Please make sure you have the latest top-patch installed ! If so take a closer look as top is not realy a good advisor on systemload, but of cours should still be a bit more accurate.
WIO is Waiting for IO and means that your disks are so bussy that another request for IO had to be put into wait. Your system will take it of waiting after a while again and will retry in a moment.
WIO is slowing down your server a lot. This can be caused by swap as well (running out of memory).

Anyway, for a good check you should do the following :

sar -u 2 20 # This will tell you the actual cpu usage
sar -d 2 20 # If wio keeps high, check the disk and see which one it is

You'dd better check the disk if this is just a single disk. ES should replace the disk/fibre channel or whatever if it's realy staying at such a load.
Most of all a "format" --> specify the bussy disk --> analyze --> read , should come up with timout errors. keep a "tail -f /var/adm/messages" open !

I think this is more than enough food for you now
Let me know if I was in time, or if you need some extra help.


Regs David