Forum Discussion

Niklas_Ahl_6703's avatar
Icon for Nimbostratus rankNimbostratus
Jan 23, 2011

High bw app, measure latency/throughput




I'm in the process of migrating a bandwidth intense application into our LTM 1600 (10.2.0, 1755.1).



Is it possible to measure latency of the packets going through the LTM?


What I'm looking for is something in the line of the time it took for the request to come in, and the response going out to the client again.



This application is pretty "bursty" like most web apps.


I would like to keep the config as simple as possible, without having to resort to npath routing.


Is there any optimizations that can be done for the responses going back to the clients?



Is it possible to access any real-time throughput measurements?


Since the app sends a lot in bursts, I need to see the peaks so to speak. The performance graphs seems to be averages over a couple of mines, which averages out the bursts.


The built-in dashboard has a small graph showing throughput, can that data be accessed some other way? Perhaps though the shell?