August 25, 2004, 2:24 PM — IT professionals dream of robust networking environments that are capable of processing weekly payroll, monthly commissions, and end-of-year accounting -- A/R, A/P, General Ledger "close outs" -- while at the same time maintaining their daily ERP, CRM, and e-mail systems. Most servers, even in extreme conditions, rarely reach maximum processing power. In fact, in a typical work day environment, most servers (particularly Windows) rarely surpass a 10% utilization rate.
Fortunately for IT professionals, virtualization is making the dream a reality.
Although most companies are not taking advantage of virtual server expansion and contraction capabilities today, it is possible to "borrow" CPU and memory capacity from other servers that are not being heavily taxed. When it is no longer needed, that borrowed capacity can then be returned to its original owners in its original state. Imagine spoofing servers into thinking they have unlimited CPU and memory capacity and as a result never running into processing/workload thresholds.
Engineers at Evolving Solutions, Inc., a data disaster recovery, storage architecture, and business continuity solutions provider, predict that by the end of 2004 and into early 2005 servers that auto-monitor and auto-adjust for data-on-demand requirements will become common in larger IT shops. Servers that are able to auto-adjust to continuously changing CPU and memory needs will become as widely accepted as the current "cascading servers" methodology. More than simply a foray into virtualization, this is a complete leap into autonomic computing.
Local server virtualization
Processing power needed for multiple employees to open large files located on a single server can push CPUs and memory past pre-defined thresholds that are typically set at 70%-80%. When they exceed their thresholds, the lack of processing power drastically inhibits data and document retrieval speeds across your LANs and WANs. This often results in hard dollar costs (replacing smaller servers with larger ones or clustering existing servers) and soft dollar costs (mainly from lost employee productivity). Grow this scenario into an online transaction processing (OLTP) environment and you can imagine how rapidly costs would mount.
Take the example of Local Books, a small fictional company that sells books written by local authors from their store on Main street. The first day they launched their online shopping site, they received 30,000 hits and hundreds of attempted transactions. Because they had not effectively planned for this activity, they found their OLTP and backend database server being significantly taxed.
Wait cycles increased because the CPUs and memory were functioning constantly beyond an 80% utilization threshold. Spikes in wait times meant Web site visitors and online buyers were negatively impacted. All of this happened while their SQL, file and print, and Exchange servers were running essentially idle at less than 10% utilization.
Unfortunately, this type of scenario is fairly typical. While most organizations plan for system failure, they often forget to plan for success and system scalability. If Local Books had a plan in place to provide additional capacity on-demand when the orders came flooding in, their systems would have been ready for the onslaught, orders would not have been dropped, and their customers would not have been frustrated by long wait times.
A virtualized server environment, using products like VMware or IBM's Orchestrater, would have prevented Local Books' OLTP server from reaching the processing threshold of 70%-80%. The server would have dynamically accessed any of the available resources from the SQL, file and print, and Exchange servers to temporarily borrow processing power to complete transactions during peak ordering periods, eliminating wait times. When the capacity was no longer needed, the OLTP server would have returned the capacity back to the respective servers. Local Books' brand equity would have remained intact and a hefty profit would have been made on the opening day of the online store.
Remote server virtualization
Soon, Local Books grew to become National Books, and they had in place a plan for exponential growth. They implemented a virtualized server environment, which reduced wait times and processed more online orders than they could initially fathom. Now the National Books Web site receives millions of hits and processes tens of thousands of online transactions and book orders each day.
