Subscribe to Blog Notification Emails

Latest Blog Post

Looking Glass of Cloud Networking

Jayshree Ullal
by Jayshree Ullal on Dec 8, 2020 6:00:17 AM

Since the 2000 era, the network has changed dramatically, becoming more and more mission-critical. There are so many drivers powering today’s digital network transformation. Think about the Internet of Things or the cloud native applications or OT, operational technology. All of these are connected via cognitive cloud networking with its agile software stack, programmability and a leaf-spine network for all traffic types. This cloud network, pioneered by Arista is hungry for more innovation when it comes to secure visibility. It is a hard problem after all—network data is orders of magnitude more voluminous then typical data sources of ingestion.

I am reminded of the Alice in Wonderland fairy tale and the alternate universe described where contrary to the real world, things were not as they should be. Arista began this “looking glass” journey in 2015 in our quest for real-time mirroring and visibility across the entire enterprise. The recent acquisition of Big Switch has upped the ante to steer mirrored packets across the client to cloud. Arista analytics platforms started with DANZ (Data ANalyZer) in 2015, CloudVision® telemetry in 2018 and our latest DANZ Monitoring Fabric software on Arista’s switch platforms for the 2020 era.

Next Generation Contextual Visibility

As the lifeline for digital communications, network traffic analysis is paramount for delivering real-time client-to-application to cloud experiences. Legacy network packet broker (NPB) approaches rely on complicated scale-up designs, are complex to operate and cost prohibitive to deploy, especially for enterprise-wide visibility. To address these challenges, Arista is introducing a new generation of network observability enhancing depth to cloud networking principles via data mirroring and contextual insights. By integrating its Data Analyzer (DANZ) with acquired Big Switch’s monitoring fabric software, Arista is embarking on a new category of software for enterprise-wide network observability that migrates beyond packets to deliver insights on mission-critical network traffic, packet and flow monitoring and improved efficiencies through the adoption of modern cloud networking principles. Network observability is the next frontier for contextual-driven monitoring bringing deep network visibility across data center, campus and edge networking use cases as shown below.


Introducing the Arista DMF

Arista’s DANZ Monitoring Fabric (DMF) is optimized for grounded truth and observability with a scale-out leaf-spine and clustering architecture and an API based programmability model. The DMF console supports zero-touch workflows and brings unique multi-tenant capability for multiple operational models to consume DMF “as an IT service” which reduces silo monitoring costs. The Arista DANZ Monitoring Fabric augments the deep insights and observability with packet recorder analysis and service nodes. These nodes maintain a historic archival of packets on the network that is useful for investigations as well as to perform retrospective detection of threats based on new intelligence even if those might have gone unnoticed in the past. It can also optimize on the amount of storage or bring efficiency to monitoring tools by avoiding traffic duplication. Full packet capture, query and replay with built-in application identification is yet another attribute Arista DMF can share with network and security analytics to enhance the fidelity of information and provide more context to network and security operators. Information could be exchanged between DMF nodes and EOS based switching platforms for insightful tracking.

Seamless DMF Solution

Arista DMF is an industry leading solution for delivering a fully integrated network time machine, contextual monitoring and secure switching experience. This system-level approach delivers metadata and associated contexts as well as packet capture of traffic. The one-click workflows across nodes allows operators to zoom-in on anomalies that have occurred in the past by instantaneously retrieving historical network traffic. DMF’s machine learning capability dynamically identifies anomalous network behaviors through auto-baselining. Mission-critical monitoring also demands lossless packet delivery which necessitates the use of Arista’s flagship 7280R3 (deep buffer) platforms and popular 7050X3 (25G and 100G) platforms. DMF nodes support 40G to 320GB performance with scale-out clustering support, enabling multi-terabit processing capacity. Its flexible fabric ensures security tools receive all relevant network traffic to detect and hunt threats. DMF integrates with Awake Security’s, Arista’s recent acquisition, AI-driven Network Detection and Response (NDR), bringing ingest points to deliver zero-trust networking. It is truly bringing legacy and costly monitoring silos to the next generation of observability by unifying network time machine, security and switching experiences.

The Wonderland of Network Observability

For digital transformation to be successful, one must be able to implicitly design the underlying network to be observable and visible. This is why I am excited about the introduction of Arista’s DMF as a compelling proof point for contextual insights, one-click traffic replay and holistic switch platform support. We work with partners such as Dell and Radware to bring DMF to the enterprise in an open, standards-based manner.

Welcome to the new wonderland of cognitive and contextual cloud networking. For more details check out the references below or send queries to Here is wishing our employees, customers, readers and well-wishers a happy and safe holiday season.


Opinions expressed here are the personal opinions of the original authors, not of Arista Networks. The content is provided for informational purposes only and is not meant to be an endorsement or representation by Arista Networks or any other party.

Jayshree Ullal
Written by Jayshree Ullal
As CEO and Chairperson of Arista, Jayshree Ullal is responsible for Arista's business and thought leadership in AI and cloud networking. She led the company to a historic and successful IPO in June 2014 from zero to a multibillion-dollar business. Formerly Jayshree was Senior Vice President at Cisco, responsible for a $10B business in datacenter, switching and services. With more than 40 years of networking experience, she is the recipient of numerous awards including E&Y's "Entrepreneur of the Year" in 2015, Barron's "World's Best CEOs" in 2018 and one of Fortune's "Top 20 Business persons" in 2019. Jayshree holds a B.S. in Engineering (Electrical) and an M.S. degree in engineering management. She is a recipient of the SFSU and SCU Distinguished Alumni Awards in 2013 and 2016.

Related posts

The Era of Microperimeters

Paradigm Shift to Zero Trust Networking

The new age of edge, multi-cloud, multi-device collaboration for hybrid work has given...

Jayshree Ullal
By Jayshree Ullal - April 30, 2024
The New AI Era: Networking for AI and AI for Networking*

As we all recover from NVIDIA’s exhilarating GTC 2024 in San Jose last week, AI state-of-the-art news seems fast and furious....

Jayshree Ullal
By Jayshree Ullal - March 25, 2024
The Arrival of Open AI Networking

Recently I attended the 50th golden anniversary of Ethernet at the Computer History Museum. It was a reminder of how familiar...

Jayshree Ullal
By Jayshree Ullal - July 19, 2023