Real-time computing. Real-time news.
November 10, 2008
Rapid, Granular, Global Network Management
1 | 2 | 3 All »
On his quest to find the golden city of Timbuktu, explorer Alexander Gordon Laing would dispatch a trusty messenger to carry updates back to his sponsors in Tripoli. Laing wouldn’t know for months if the messenger made it, if he ever knew at all. That was a typical problem with 19th-century information “technology.”
Today, people who live and die by network and application performance worry about information lag, too -- and for good reason. According to a survey by Infonetics Research, outages and slow-downs cause midsize companies to experience about 140 hours of downtime every year, to the tune of about $800,000 annually. Focusing on the source of application outages could save many organizations “a significant amount of money,” Infonetics analysts conclude.
There is no lack of vendors offering ways to monitor network performance, but SevOne does a few things that might make it stand out. The company launched in 2005 to develop network- and application-performance technology that would be real-time responsive, but inexpensive and easy to use compared to legacy products. The technology is targeted at people who need to see exactly what’s going on and when, way out across their network empire, remote outposts and all.
“We developed a distributed, peer-to-peer architecture for network management that allows our customers to capture the data they need to respond to specific performance issues,” says SevOne CEO Michael Phelan. “Our design criteria were to make something very scalable, that could accommodate change very quickly, and was much faster than other tools. Being able to scale to cover every application, every device, in a cost-effective and meaningful way are a few of the things that we think make us unique.”
Its software and two types of appliances embody the company’s technology. The Performance Appliance Solution (PAS) is the standard device, incorporating SNMP and NetFlow monitoring, alerting, and sub-minute polling. There are five PAS models, capable of watching from 5,000 to 65,000 network elements. The Dedicated Network Flow Collector (DNC) appliance exists specifically for large NetFlow-based deployments. SevOne’s hardware/software package installs in a datacenter “as near to end-users as possible to collect traffic data and allow operators to immediately pinpoint problems anywhere and avoid dev
eloping slowdowns,” Phelan says.
“Each one of our appliances is both a data collector and a reporter,” he explains. “They can work stand-alone, or be joined with others using our P2P architecture. Essentially, they operate as a distributed environment, processing volumes of data that gets pushed out. You request a report or an operation. One appliance could be in Boston, one in New York, one in Chicago, and they all work together. It’s a lot like a grid computer. All the systems share a database that lets them know which peer has the information needed to originate a report. You can log into any of the peered appliances to get a report on any indicator.” SevOne supports all the usual application and network monitoring standards. If, for example, a spike is identified using SNMP, an analyst can drill down further using NetFlow.
SevOne set out to design a system that can scale not just in terms of network size but that also can expand to handle new devices and new applications quickly. “Our company founders have a background in the banking industry, where consolidation has resulted in organizations having two of everything, lots of legacy tools, management tools from all kinds of vendors,” says Phelan. “They’re asked to handle different types of applications, like video and VoIP, and different types of devices. There’s frustration trying to keep pace with these changes.”
As new routers, switches, access points and so on are added to a network, PAS can either discover them automatically or they can be added using an API. “In a health care situation, you might add a new scanner to the network,” Phelan says. “We can have it logged in and be monitoring its performance sometimes in minutes, perhaps a couple days at most.”
In an increasingly on-demand real-time world, though, it’s not only what you can monitor, but how often. “A lot of bad things can happen in under a minute,” Phelan says. “Our technology can monitor the most critical components, including your server CPUs all the way to up-links, at whatever frequency your … service level agreements require. If performance requirements aren’t going to be met, our appliance can issue an alert. Critical links need to be monitored at sub-minute frequencies, and our system will let you do that. Our customers in financial trading need to monitor things down to the second.”
He continues, touting the distributed nature of the solution: “The system has to be able to react. Bad things happen quickly. You can’t wait for reports to generate. With our appliances stationed across the network, we’re using processors across that distributed grid to create large reports that have millions of indicators in seconds. People think we’re using a canned graphic when we produce a graph that charts utilization over 24 hours and it takes a tenth of a second. We have all these cores working together to collect data and generate a report.”
Page: 1 of 31 | 2 | 3 All »
Article Tools
Share Options
(Digg, Technorati, more)
