100% disk activity in glance

[Colin Rice]

Hi

We are using glanceplus (B3692A GlancePlus C.02.30.00), and in the "DiskRpt" screen, the "Disk Util" is shown as a current % at the top.

Question: how does glance determine the i/o ("Disk Util") is 100%? Does it relate that to your HBAs? Does it compare w/physical rd/wt?

Cheers
COLIN

[Michael Tully]

Hi Colin,

First have a look at the below from within glance.
This gives an explanation of what is being
reported and where the figures come from.

F7 (Help) --> Current Screen Metrics -->
Disk IO Rate

HTH
-Michael

[Colin Rice]

Michael

Tried it, but only shows help for the 'local' and 'remote' section at the bottom, not the 'disk util' at the top...

Cheers
COLIN

[Michael Tully]

Hi Colin,

okay I should have been more clear.... Once you
start the 'glance' session it shows the first
screen being

CPU Util
Disk Util
Mem Util
Swap Util

Then it show under that the Process Name PID
etc

From this screen F7 (Help) --> Current Screen Metrics --> Disk IO Rate

This will show a lot more than local and remote.
If you choose the Disk Rpt (F4) you will only
get the local and remote selections.

HTH
-Michael

[Animesh Chakraborty]

Hi,
See the link
http://us-support.external.hp.com/cki/bin/doc.pl/sid=73ba4e8209a29b74a6/screen=ckiDisplayDocument?docId=200000054947419



Best of luck
Animesh

[Colin Rice]

Hi Animesh

This refers to a bug on 10.20 whereby sar -d displays 100% all the time. We are using 11.0, and we don't get the 100% all the time. We actually have variable %, simply we are trying to understand what that 100% relates to.

Good try; worth 7 points ;^)

[Stefan Farrelly]

According to the help file for glance Disk Util is measured using the metric BYDSK_UTIL which is described as;

The percentage of the time during the interval that the disk device had IO in progress from the point of view of the Operating System. In other words, the utilization or percentage of time busy servicing requests for this device.

This is a measure of the ability of the IO path to meet the transfer demands being placed on it. Slower disk devices may show a higher utilization with lower IO rates than faster disk devices such as disk arrays. A value of greater than 50% utilization over time may indicate that this device or its IO path is a bottleneck, and the access pattern of the workload, database, or files may need reorganizing for better balance of disk IO load.

[Tim D Fulford]

whaty does disk util mean?
disk util is the % time the disk is dealing with IO/s. It is the disk util of the most utilised disk.

So say the most utilised disk has an IO rate of 100/s & the disk is 50% utilised, it roughly takes 5ms per IO. I hope this make it clearer.

Personally I just use glance. If I see disk util high I then do u - io by disk. From this I can see which disk(s) is(are) causing a problem. I then do S & select its number. I let the screen refresh a few times before viewing the results. My principal concern is how many IO's are queued. If the utilisation is say 80% & the q is zero I tend not to worry, it's dealing with everything being thrown at it. However, if I start to see a queue builging up that means that some processes are waiting before being allowed to do IO (blocked in IO).

I hope the above helps

Tim