Measuring Latency Of Cloud Server

[conrad]

Hi All

Just started watching Hak5 but on too small a screen for my eye's comfort

I am somewhat of a networking noob so forgive me if I come across that way.

I am interested in experimenting on network latency and jitter of cloud providers e.g. Amazon EC2 and rackspace - as it occurs to me that network latency ought to be one of the big problem areas of the cloud.

Firstly, I understand that ping is used to measure round trip latency, but a single ping is not really what I had in mind. So the idea is that you have applications which can send out pings at intervals and puts give you nice feedback e.g in to a graph. I have tried to get smokeping working but as yet without success :( I must be doing something wrong? If I can't get it running, does anyone know of good easy to use alternatives?

So for the experiment, if I set up a cloud server on e.g. EC2, I can ping this cloud server with the ping application and it will give me a picture of network latency. However, pinging an idle server doesn't tell you that much as latency is effected by loading and the types of applications that are running, which all needs to be considered.

I could set up a web server or a game server on the cloud but in a way this doesn't get me far as this will not have traffic or load on it. I don't really know what would be the best way of doing this, any ideas?. Would it be possible to simulate load of various applications on one of the cloud servers with a piece of software?

Any help would be appreciated!

Thanks

C