Network Visibility Tools
Datavision Consulting Services: Arista Network Visibility Tools
Datavision’s network engineering and support services help our clients plan for cloud-centric OpenStack initiatives. Our consultants will work with you to assess the current environment, design a roadmap and architecture to integrate the technology, and realize the network infrastructure best suited to the business needs. Our services include the following general stages of engagement:
- Design Planning
- Implementation: Integration & Migration
- Operational Support/Training
- Network Optimization
Our experts can provide assistance with operating your network with you on a short- or long-term basis. We can also develop training for your personnel to thoroughly understand the technology being implemented in the network, and to help ensure a smooth transition from the prior network architecture to the new.
Datavision Services Supporting Arista’s Software-Driven Cloud Networking
Arista’s Software-Driven Cloud Networking (SDCN) combines the principles that have made cloud computing operationally and functionally effective. The use of automation, self-service provisioning and linear scaling of both performance and network economics coupled with SDN delivers network virtualization, custom programmability, simplified architectures and improved economics to the carried and enterprise environments.
These evolutions in software and networking hardware functionality create a best-in-class foundation for maximizing the value of the network to both the enterprise and service provider data center: a new architecture for the most mission-critical location within the IT infrastructure that simplifies management and provisioning, speeds up service delivery, lowers costs and creates opportunities for competitive differentiation, while restoring a higher degree of control and visibility to network operations.
Virtualization has largely transformed the data center with flexible and automated server provisioning. But networking and storage infrastructure have not kept pace. In fact, they often serve as the bottleneck. Software-defined data center (SDDC) strategies could be key to moving this infrastructure to a more reliable state. The concept behind SDDC is to bring every aspect of an IT environment to match the same ease of provisioning as virtual computing, resulting with all infrastructure delivered as a service and automated by software.
The question is, how can operators monitor and manage the “new” infrastructure in a more comprehensive and effective manner?
Through the use of the Arista DANZ Framework, Datavision can help you control, measure and monitor your data center.
The three major components of the Arista DANZ Framework are:
- Advanced Monitoring
- Precision Instrumentation
- Event-Driven Programmability
Simple Tap Aggregation And Measure Network Latency With Arista’s Advanced Toolsets
The suite of services offered by Datavision encompasses assessment, design, implementation and testing/turn up of Arista’s Network Visibility and Performance framework; Arista DataANalyZer (DANZ), Arista Latency ANalyZer (LANZ) and Advanced Event Management (AEM).
The DANZ toolset helps to solve one of the more challenging aspects of monitoring the network through taps. As an integrated feature set of Arista EOS, DANZ is currently available on their 7150 series switches.
DANZ provides a solution to monitoring and visibility challenges at 10/40Gbps and higher with unmatched price-performance and precision. The Arista DANZ software features give IT operations and planning departments the following capabilities:
- Aggregate, replicate and capture traffic for processing without affecting production
- Apply advanced filtering and precision time stamping at wire rate in hardware
- Monitor, capture and correlate congestion and microburst events in real time
- Deliver application layer feedback directly to applications and tools
- Integrate with any standard 3rd party API and Application/Network management tools
- Achieve all of these features in Arista’s full-featured switches without additional equipment
With Arista DANZ, organizations that have to perform critical analytical and monitoring functions with increasingly higher data volumes and higher network bandwidths can maintain security, compliance and reporting for all traffic without the addition of proprietary out-of-band monitoring infrastructure of backhaul networks. Troubleshooting applications and performance problems, performing traffic interceptions when necessary and managing overall customer satisfaction and response times can be accomplished cost-effectively with limited new investment and using existing tools.
Arista Latency Analyzer or LANZ is a breakthrough technology from Arista that tracks sources of congestion and latency with real-time reporting in microseconds. Historically, if “the network was slow,” administrators would attach a probe/collector and hope the problem happened again. No longer. With LANZ you will know when congestion happened, track the sources of congestion and be able to export real-time events to external applications like Solace Systems middleware. This enables the application layer to make intelligent traffic routing decisions with unprecedented visibility into the network layer.
A key application of integrated LANZ is for the financial services market, where trading plant performance is key. With LANZ, the network operations teams and administrators will have more visibility than ever before into the network and know if “microbursts” are really happening or not. With sub-millisecond reporting intervals, congestion can be detected and application-layer messages sent faster than some products can forward a packet.
LANZ is a proactive, event-driven solution that operates through providing real-time notification of congestion hot spots and their effect on application performance and latency at nanosecond resolution. This is a completely different approach than traditional SNMP and RMON polling approaches that allows LANZ to be a much more accurate measurement tool of network latency. LANZ functionality operates based on monitoring and exporting in real-time the queue length data, based on a user configurable high/low threshold. When the thresholds are crossed, indicating congestion, the system generates a time-stamped congestion event. This technique allows events as short as 100nS to be reported. Monitoring at the queue versus the port allows monitoring of specific traffic classes within the network.
The third aspect of Arista’s Analyzing Framework is Advanced Event Management, or AEM. AEM is a powerful and flexible set of tools to automate tasks and customize the behavior of the system and associated operation of the switching infrastructure. AEM also allows operators to fully utilize the intelligence within EOS to respond to real-time events, automate routine tasks and take local automated action based on changing network conditions. AEM is very customizable, making it easy for one of our Datavision experts to design an AEM to work with each customer’s unique operating environment and train other users to make customizations to the system as needed. This means clients have an event-driven service model.