performance monitoring info

[Scott_14]

hello:

I am have sar running in cron, which gives me data for the day pretty much and I have been using glance for one system as well.. But I am wandering, when I look at some of the numbers such as avwait and avserv, I see numbers from 6.23-8.59 and 11.90-15

Can someone give me, or point me to some information, where I can find out what a happy medium is for a lot of the values, so I have an ideal what is "normal" and what would be considered high etc.

I guess I was hoping there may be somewhat of a chart or something, that gives you an ideal if some of the feed back, from sar or glance is in a normal range, or higher, so I have something to compare it to.

thank you in advance for your help and input.

scott

[James R. Ferguson · Accepted solution]

Hi Scott:

'avwait' is the average time in milliseconds transfer requests waited for the device.

'avserv' is the average time in milliseconds needed to service the transfer request. This includes seek, rotational latency, and data transfer times.

'avwait' greater than 'avserv' indicates a disk bottleneck.

...JRF...

[Christopher Hildrum]

Scott -

If you haven't found better info yet -
Try Document ID: KBRC00000947 from itrc.
It gives good info on sar.

Chris