NetBeez installed 42 agents to help monitor InteropNet during the Interop conference. Here's a few things we saw.
Interop is one of the largest trade shows for IT professionals. Each year, the organizers assemble a team of volunteers and vendor partners to build InteropNet, a state-of-the-art network that provides connectivity for the show's 12,000 attendees and 300 exhibitors.
Interop Las Vegas is showtime for the InteropNet NOC crew, which has to quickly fix anything that breaks so that organizers, attendees, and exhibitors don't have to think twice about network connectivity and performance.
This is where end-user network monitoring comes into play. Proactive network monitoring is of utmost importance: the sooner a network issue is detected, the faster the troubleshooting process starts.
The faster that affected users and locations are identified, the easier it is for the NOC team to triage the problem and resolve it.
NetBeez installed 42 agents at the two collocation data centers, the trade show, and in the cloud:
· 11 around the expo, registration, media center, and keynote floor
The following table summarizes InteropNet’s end-user monitoring requirements and the types of tests NetBeez configured to fulfill those requirements.
End-User Monitoring Requirements
Access each other
Full mesh Ping among all agents
Access the San Francisco and Denver DCs
Ping, Traceroute from all agents against the DCs
Access the Internet
Ping, DNS, HTTP, Traceroute against google.com
Access the DNS servers
Ping, Traceroute against the DNS servers
Perform name lookups
DNS lookups against google.com
Access the Interop website
DNS, HTTP, Traceroute against interop.com
The excellent planning and testing that took place during Hot Stage resulted in a smooth setup of InteropNet in Las Vegas.
As expected, when thousands of attendees stormed the trade show during expo hours, the agents experienced increased time to fetch Internet pages, such as google.com, as shown in the screenshot.
On the morning of Wednesday April 28, we came across an interesting performance alert that showed an increase in the latency time from the agents in Las Vegas to google.com.
The spike occurred at 3:30 am, happened pretty abruptly, and stayed constant after that. It was easily identified on the ping historical graph, as shown in the screenshot.
At the same time, there was an alert triggered on the traceroute tests targetting google.com. The historical showed that the number of hops went from nine to twelve, clearly indicating a routing change that caused the ping latency spike.
The good news was that this change was planned by the NOC and thus wasn’t a cause for concern. Nonetheless, it demonstrated the role of proactive monitoring to identify network performance and connectivity issues.
InteropNet is built from scratch year after year to demonstrate the latest networking and monitoring technologies to the attendees of the show.
It's also a way for the NOC team to stay abreast of the latest developments and educate interns that volunteer for at least two weeks between Hot Stage and Interop itself. NetBeez is looking forward to next year's event!
Panos is a cofounder of NetBeez, a distributed end-user network and application monitoring tool. He developed parallel computing algorithms at Carnegie Mellon University before cofounding NetBeez. He is in charge of operations and of developing the perfect "Beez." View Full Bio
We welcome your comments on this topic on our social media channels, or [contact us directly] with questions about the site.
2018 State of the CloudCloud adoption is growing, but how are organizations taking advantage of it? Interop ITX and InformationWeek surveyed technology decision-makers to find out, read this report to discover what they had to say!
Infographic: The State of DevOps in 2017Is DevOps helping organizations reduce costs and time-to-market for software releases? What's getting in the way of DevOps adoption? Find out in this InformationWeek and Interop ITX infographic on the state of DevOps in 2017.