Re: calculate saving ratio of *link bandwidth*

    So *roughly* speaking the *IP/TCP/HTTP* overhead is *nearly* double or
    *triple* than *the result via squid log*.
  
this is including ICP but you said 'excluding icp before' :-(

    It is not 10%, but nearly <100 %.

If you use ICP, maybe. I think the 'shroud' around the data is really not
enought cause this, nor the DNS load. We saw at most 20% variance from the
netflow data compared to our measure of application volume.
  
Is there room for error in the methodology? Could you be getting interface
octets which include L2 header and the like from an FDDI or ATM?

I am very suprised its that high. 2:1 overhead feels wrong.

-George

--
George Michaelson         |  DSTC Pty Ltd
Email: ggm@dstc.edu.au    |  University of Qld 4072
Phone: +61 7 3365 4310    |  Australia
  Fax: +61 7 3365 4311    |  http://www.dstc.edu.au