LOAD is used to view/analyze the queue-depth for command-response style protocols.


You use on "response time" fields,   like rpc.time   for NFS.

It will then calculate and plot how the queue-depth changes throughout the capture.
For ease of implementation it uses integer math for these calculations, as such a value of 1000 on the Y-axis represents 1(ONE) I/O in flight.

This is very useful since it is shows the relation in performance between the initiator and the target and is the only real way of measuring initiator(client) performance.


regards
ronnie sahlberg

On Wed, Mar 4, 2009 at 8:45 AM, Bland Chuck-CNGR85 <Chuck.Bland@xxxxxxxxxxxx> wrote:

I am really trying to get a handle on the Load(*) graph. I've only found one message in the archive and little-to-nothing in the manual.

Is there something else on this topic out there? I sure would like some detail.

Chuck Bland

___________________________________________________________________________
Sent via:    Wireshark-users mailing list <wireshark-users@xxxxxxxxxxxxx>
Archives:    http://www.wireshark.org/lists/wireshark-users
Unsubscribe: https://wireshark.org/mailman/options/wireshark-users
            mailto:wireshark-users-request@xxxxxxxxxxxxx?subject=unsubscribe