NetCelera Does More With Less

Each NetCelera pair maintains persistent, logical connections (tunnels) through which packets are exchanged using ITWorx's ACM5 (Adaptive Connection Compression and Multiplexing at Layer 5) architecture. Tunnels are application-specific and dynamically allocated depending on load. ACM5 captures and inspects packets at Layer 5 before they go across WAN links, identifying and eliminating redundant data, such as repeated phrases, blank lines and zeros, to optimize compression ratios. The compressed data is then multiplexed into tunnels to traverse the WAN. On the receiving end, a NetCelera demultiplexes (demuxes) and decompresses the data, and then delivers it.

ITWorx engineers visited our Syracuse University Real-World Labs® and embedded NetCelera appliances on both sides of a simulated WAN link. The WAN united two LANs representing an enterprise headquarters and a remote branch office. A black box (i686) running a Linux 2.4 kernel with 512 MB RAM separated the LANs using Candela Technologies' LANforge ICE WAN Simulator. ICE emulated T1 (1.544-Mbps) and T3 (50-Mbps) links between the HQ and the branch office. It was set to drop and reorder 10 packets out of every 1 million with a 1,024-byte buffer, 60 milliseconds of latency and a random jitter value of 10. This resulted in an average 125-ms delay over the WAN.

In the HQ LAN, I plugged in a Sun Microsystems Sun Fire 280R (dual UltraSPARC III with 750 MHz and 2 GB RAM) running Sun Solaris 9 and an Apache Web server. From there, I mirrored the intranet Web pages for Network Computing. This provided a platform to generate real traffic from the remote-branch LAN using Mercury Interactive Corp.'s LoadRunner 7.5.1 with up to 200 virtual HTTP and FTP users on Dell Intel Celeron (500-MHz) PCs.

Giving It the Squeeze

After running multiple tests, I averaged the results to find a significant bandwidth savings for HTTP data: The NetCeleras reduced an 11-minute test to a 6-minute test, using only 50 MB to send approximately 107 MB of data from the HQ to the remote branch, which equaled a 53 percent savings in bandwidth.In addition, the NetCeleras improved application response time in HTTP tests by raising the average number of hits per second from 7.68 to 11.79. To accomplish this, each NetCelera maintains persistent TCP sessions for user applications across the WAN up to a maximum of 4,000 concurrent TCP sessions. When an application such as a Web browser initiates a TCP session with a remote machine, the local NetCelera responds to the request with a LAN-only TCP session between the application and the appliance. The local NetCelera instructs the remote appliance to open a TCP session with the appropriate application on the other end. Under normal conditions, TCP window sizes shrink under high network loads. NetCelera appliances, however, act like application proxies that minimize TCP setup and tear down traffic over the WAN while maintaining TCP window sizes.

Turning my attention to FTP traffic, I ran a benchmark of multiple tests sending approximately 172 MB of doc, ppt, txt and xls files from the HQ to the remote branch. The NetCeleras saved 21 percent bandwidth by reducing the traffic to 136 MB of data.

NetCelera isn't going to save you much bandwidth if your WAN pipes regularly transmit highly compressed files such as gif and jpeg or archive files like tar and zip. Recompressing already compressed files for transmission is like wringing an already wrung sponge. Sending 175 MB of compressed Windows setup files resulted in only a 0.57 percent bandwidth savings. Conversely, removing the compressed pdf files resulted in a 72 percent savings in bandwidth. Fortunately, ITWorx gives enterprises a free bandwidth analysis tool, NetCelera Scout, to determine if the state of their WANs can be improved without overprovisioning bandwidth. While testing, I used the Scout on a port mirroring the traffic on the remote-branch LAN. The Scout classified traffic by protocol and accurately predicted the bandwidth savings for all my tests (see screenshot).

NetCelera appliances provide a hard return on your investment. Although you might be able to find a discount on a T1 or T3 line, tariff rates continue to increase. A short-haul T1 line may cost $1,000 to $2,000 per month to operate, and a T3 can range from $3,500 to $35,000 depending on location and distance. In light of these prices, a pair of NetCeleras may provide a more meaningful ROI in a relatively short period of time. Scout it out for yourself.Sean Doherty is a technology editor and lawyer based at our Syracuse University Real-World Labs®. Write to him at [email protected].

Post a comment or question on this story.