Cumulus Networks today updated its network operations toolset — which monitors the health of the entire data center stack — with features to reduce business disruptions and achieve web-scale.
The toolset, called NetQ, is built specifically for data center networks, which increasingly includes containers and virtual machines (VMs) in addition to everything between switch and port. The adoption of microservices, containers, and VMs has added a layer of complexity to the data center and monitoring tools are struggling to keep up.
“As web-scale networking becomes the enterprise norm, so does complexity. As complexity increases, so does the need for enhanced visibility,” said Partho Mishra, vice president of engineering, product management, and global support at Cumulus.
But, Cumulus provides visibility into this full fabric by combining three key functions in its scalable data ingestion engine: data collection, data analytics, and data visualization.
“Tools available today are either too old and heavily reliant on ancient management protocols, or they simply don’t scan the infrastructure as much as they should, only scanning every 15 minutes or so,” Mishra said. “With NetQ, teams can update their network operations from this manual and reactive approach to one that is automated, agile, and informed.”
NetQ primarily runs on Cumulus Linux switches, which is the company’s Linux-based open network operating system. Though it can also run on other Linux devices including Ubuntu, Red Hat, and CentOS hosts. The toolset captures real-time telemetry and network state information to enable operations teams to process and visualize the data that gives them a holistic view of operations.
Mishra said Cumulus is able to achieve web-scale by adding support for up to 1,000 nodes, and, “by completely gutting the underlying infrastructure and switching from SQL to NoSQL database with Cassandra and Kafka, we’re now able to process massive amounts of data in parallel with better performance. Each one of those ‘lanes’ can be executed on a different thread.”
This new database architecture means that Cumulus is able to host NetQ in the cloud, giving it elastic scalability to handle any size workload. “NetQ correlates configuration and operational status, and instantly identifies and tracks state changes while simplifying management for the entire Linux-based data center,” Mishra said.
The update also includes a new graphic user interface (GUI) and command-line interface (CLI) that provides new network validation and troubleshooting; real-time telemetry; Layer 1 to Layer 3 analytics and insight; rest APIs for a number of third-party tools; validation, trace and proactive alerting; and Kubernetes deployment monitoring.
The update also included data aggregation for any Linux system. Cumulus claims that this delivers more real-time and historic data than other operations toolsets that monitor from the container, VM, or host to the switch and port.