2017 Press Releases

March 08, 2017

Cisco HyperFlex Delivers Three Times the Performance of First-Generation Industry Solutions

Cisco unveiled new capabilities for its HyperFlex Systems portfolio and revealed validated test results that showcase unmatched application performance for its hyperconverged infrastructure (HCI). Cisco's approach incorportates the Cisco HX Data Platform, a distributed file system built particularly for HCI clusters, with low-latency UCS fabric and deep network policy engineering to deliver IO consistency and breakthrough performance. HyperFlex is a completely engineered solution with integrated network, compute and storage that offers operational simplicity, a better user experience, and more efficient scaling options.

The simplicity of hyperconverged infrastructure has made it one of the quickest developing technology areas. Yet first-generation HCI solutions use software operating on conventional servers and lack cluster networking integration, which restrains application performance and makes solutions complicated to deploy, troubleshoot and maintain. These disjointed overlay approaches are further compounded by the use of latency-inducing software wrappers around legacy, open-source files systems. As a result, while these legacy HCI offerings have been suited for light isolated workloads, they have limited customers' ability to efficiently expand hyperconvergence to latency-sensitive and business critical applications.

Purpose-Built, Ground-up Innovation for Hyperconverged Infrastructure

The newest release of HyperFlex delivers unprecedented performance component options, intuitive management enhancements, and new enterprise data protection and security features, including:

· High-capacity all-flash nodes and support for 40 Gbps UCS fabric networking to expand customer options for extreme application performance.
· New intuitive platform management with HyperFlex Connect, featuring dynamic system analytics and a standalone HTML5 interface for the management and orchestration of HyperFlex clusters from any device.
· Enterprise-grade data management, protection and security for the most sensitive workloads, with the introduction of a native replication feature to secure applications and new data-at-rest security options using self-encrypting drives.
· Hybrid cloud mobility with the incorporating of Cisco ONE Enterprise Cloud Suite's (ECS) CloudCenter for private and public cloud elasticity.
· Self-service catalogs with metering and workload automation through the newly release of ECS UCS Director integrations that offer customers with IaaS orchestration for private and hybrid services.

According to Liz Centoni, Senior Vice President and General Manager of Cisco’s Computing Systems Product Group, "In less than a year, more than 1,100 customers have embraced HyperFlex to simplify and transform their data centre operations. We purpose-built HX Data Platform, our distributed file system for HCI, to deliver the high performance and consistently low latency needed to allow customers to expand from initial use-cases like VDI to a much broader range of business-critical apps."

Industry-best HCI Performance

HyperFlex has elevated the industry bar by delivering the performance needed to extend HCI far beyond VDI and server virtualisation to more arduous, data intensive workloads. Lab testing conducted by Enterprise Strategy Group (ESG) compared Cisco HyperFlex with three other solutions using an industry standard benchmark for application performance on HCI. Highlights include:

· HyperFlex supports up to three times higher VM density
· Lowest VM read/write latencies
· Seven times reduction in IOPS variability compared to other solutions

Tony Palmer, Senior ESG Lab Analyst and Co-Author of the ESG Lab HCI Report said, "ESG Lab validated that Cisco HyperFlex hybrid and all-flash systems delivered higher, more consistent performance than other similarly configured HCI solutions using simulated OLTP and SQL workloads. For hybrid clusters, HyperFlex not only consistently outpaced competitors in terms of IOPS and latency, it supported more than twice the number of VMs than both software-based and engineered proprietary systems while maintaining high performance."