LoadMaster 1500 vs Enterprise R16

Both Kemp Technologies and Loadbalancer.org pride themselves on offering affordable load balancing appliances that work. It is these companies that have driven down the price of such solutions; making load balancing appliances available to companies who previously would not have been in a position to consider such investments.

It is because of the two companies reputation as 'value-for-money' vendors that I have decided to compare the bottom of the range, financially viable appliance on offer from both. Specification comparisons were taken and analysed and each appliance was performance tested to examine whether performance levels met that of the stated specification.

Firstly, lets look at the stated specifications of each load balancer.

Kemp's budget appliance, the LM1500, offers layer 4 and 7 server load balancing with up to 256 virtual and 1000 real servers. This appliance is capable of layer 7 content switching and SSL acceleration up to 100 TPS. This solution will give you up to 100 Mbps throughput and set you back £1300. For full specification details of the LoadMaster 1500 click here.

The similarly marketed loadbalancer.org appliance, the Enterprise R16, also offers layer 4 and 7 load balancing. With full layer 7 proxy support including cookie insertion/inspection and SSL termination at 150 TPS to enable layer 7 cookie inspection.

Loadbalancer.org claim their Enterprise R16 can be used across 16 servers however this is misleading. In actual fact it can only be utilised for 4 real servers each with 4 virtual servers, hence 16 servers. The Enterprise R16 can handle 3 million+ simultaneous load balanced connections using 512 MB RAM and retails at £1495.

Loadbalancer.org have recently re-branded their Eco model however the website has not been updated and hence the Eco is actually the R16, click here for full specification details.

It's all well and good comparing the specifications but for a truly valid comparison I have personally performance tested each appliance.

In terms of SSL transactions the results proved extremely interesting. Whilst the LM1500 claimed up to 100 TPS, the appliance actually fell far short of this managing a mere 49.04 TPS. Conversely the R16 claimed 150 TPS and actually significantly exceeded this managing 192.15 TPS.

The mean time per request (across all concurrent requests) for the LM1500 was 20.392 (ms) while for the R16 it was significantly faster at 5.204 (ms).

When looking at the transfer rate the Loadbalancer.org appliance continued to out-perform the Kemp receiving 61.49 Kbytes/sec as opposed to a mere 15.69 Kbytes/sec with the LoadMaster.

Furthermore, the LM1500 had a concurrency level of 1 and took 4.78366 seconds to perform the tests, compared to a concurrency level of 10 and a time of 1.40843 seconds with the R16.

In conclusion, if you wish to purchase a financially viable load balancing appliance then both Kemp and Loadbalancer.org would have to be considered.

However, reading into and comparing specifications may not provide you with the whole picture. If you were to base your purchase solely on this information then you may be tempted into the Kemp option as it is in fact slightly cheaper.

This would not be wise. For the extra £195 you will get an appliance that will out-perform its counterpart in almost every way. Furthermore this out-performance is not minor. Loadbalancer.org's Enterprise R16 is approximately 4 times more powerful than its direct competitor, the Kemp LoadMaster1500. Therefore the minimal extra cost is a well-advised choice and will help to maximise your Return on Investment.

For totally impartial, in depth, load balancer comparisons of virtually all vendors and models visit loadbalancer.biz.