Details on how to maximize a performance load test

Use and application of the eValid server loading (LoadTest) capability. And in the cloud computing context for monitoring and loading.

Details on how to maximize a performance load test

Postby BCollins » Thu May 20, 2021 7:00 am

Morning.

Can you give me some suggestions on how to maximizing performance for load test applications?

Thanks
BCollins
 
Posts: 1
Joined: Thu May 20, 2021 6:55 am

Re: Details on how to maximize a performance load test

Postby eValid » Fri May 21, 2021 9:35 am

BCollins wrote:Morning.

Can you give me some suggestions on how to maximizing performance for load test applications?

Thanks


Thanks for posting your question BCollins.

LoadTest runs stress the driver computer a lot. Here are some practical hints on how to get the MOST out of eValid when you are running Load Tests:

(1) Use eVlite. eVlite, available in Ver. 3 of eValid, can easily generate quantities of "background activity", albeit not the full context-preserving transactions which eValid can handle.

The idea here is to keep the servers busy so you can experiment with response times from multiple full-fidelity eValid playbacks being served by a [very] busy server.

Each eVlite takes about 8 MB of RAM, and can play back up to 1000 threads, with each thread representing a separate user session.

(2) Carefully Budget RAM Use. Each eValid instance takes about 9 MB of RAM and each eVlite takes about 8 MB of RAM.

If you use the System Summary information on your machine you can read out the "Available Physical Memory" value.

This is the value against which you will want to budget your eValid/eVlite usages.

Adding additional memory is relatively inexpensive; recently the price for 512 MB chips was about $80.

(3) Increase The Available RAM in Video Card. When you have the minimal amount of available RAM in the video card, i.e. 4 MB, strange results may appear in the PC display with high eValid parallelism values.

From what we observe that the technical results eValid produces themselves do turn out to be correct; it is only the display you see that is goofy.

We get most of our data from a 512 MB machine that has a hi-performance video card which has 64 MB of RAM.

(4) Include Delays To Decrease Effective Playback Duty Cycle.

The duty cycle on eValid goes down if you have a higher percentage of wait time and accordingly a larger number of eValid's can run simultaneously if they are not all running "as fast as possible."

We have observed very wide variations between scripts with a 100% duty cycle and those with a 10% duty cycle, for example.

(5) Use Multiple Playback Machines.

To help out our customers we will be pleased to issue EVAL keys for you so that you can replicate your tests to multiple machines until you sort out the performance/capacity issue on your main machine(s).

If you like details about this, please contact us.


-- eValid Support
eValid
 
Posts: 2165
Joined: Tue Jan 01, 2008 12:48 pm
Location: USA


Return to Performance/Load Testing

Design Downloaded from free phpBB templates | free website templates | Free Web Buttons