Monitoring Server Reliability 24X7 so your site stays up!

Many different factors must be controlled in order to ensure server and network system reliability. Temperature, fire, power brownouts or failures, equipment failure, and connection failure can all cause reliability problems. In addition, since it is not possible to control these elements 100% of the time, high availability systems require redundancy to make certain that they are up and running all the time.

Temperature Control

Both environmental temperature and equipment operating temperature must be controlled to ensure reliable operation. The Benchmark Server Center has two ten ton industrial air conditioners which are sufficient to keep the environmental temperature at an optimal 65 degrees fahrenheit. The Server Center features raised flooring. This enables a  constant flow of conditioned air and helps to maintain uniform room temperature  at all times. In addition, raised flooring reduces static and ensures a professional, computer grade environment.To control internal operating temperature, each web server is equipped with a positive pressure filtered-air cooling system. Four large fans pull filtered air into each server's protective case and the components within are cooled by fans which circulate this purified air. Constant introduction of clean air into the case creates a positive pressure environment ensuring dust and particles remain outside of the server and can not insulate components and raise temperatures. Motherboard, CPU and power supply sensors sound an alarm if operating temperature should rise into the danger zone.

Fire Control

Power Control

To guard against local power failures and brownouts, the server center has two industrial-grade, three phase Liebert UPS systems. These act as back-up batteries, maintaining uninterrupted power in case of surges or power outages. With these backup systems in place, our network can stay up and running indefinitely without relying on external power.

Server Redundancy

Network  Redundancy

Benchmark uses intelligent end-user routing software called Border Gateway Protocol (BGP), between Qwest, GC and GTE, who use the same protocol. BGP identifies which path is the most efficient for each data packet and then routes the packet to its destination on the fastest path. This increases the speed at which web pages sent from our Server Center arrive at their destination.

Studies have shown that the most common reason for downtime is circuit failure on Tier 1 provider backbones, the major data highways. To guard against this potential problem, we have three Tier-1 providers. If one experiences problems, we can route traffic down the others. Furthermore, because our Server Center is OnNet with GlobalCenter, Qwest and GTE, we share their digital distribution architecture, which includes private peering network connections to major Internet carriers such as MCI,  Sprint, UUNET, EUNET, AT&T, AOL, Best, Erols, @Home, IBM Advantis and others. These private peering arrangements allow Benchmark to exchange packets of data with every major backbone carrier in a one-to-one  environment quickly and efficiently.

In addition, GC has  high-speed links to eight public exchanges including both MAE East and West and several NAPS. Through these public exchanges, customers have the ability to reach their site, no matter from where they are coming on the Internet.

Network  Reliability

Industry analysis reveals that 70% of downtime over ten hours with any ISP is caused by telephone circuit failure. Since our Server Center is in the same building as Global Center, Qwest and GTE, circuit failure is virtually eliminated because there is no phone circuit  between us and our providers. Instead, there is a direct connection between our Cisco 7500 routers and theirs.

[Home] [Web Hosting Plans] [E-Commerce] [Contact]