Cisco and Violin Memory Set Best Combined IO/s and Latency

Violin Memory, Inc. served as the storage platform required by Cisco Systems, Inc. to set the 2-socket server world record in cloud computing performance as measured by the VMware VMmark 2.1 benchmark.

A record of this magnitude validates the sustained performance achieved by Violin Memory Arrays and their ability to provide the infrastructure necessary to support virtualized and cloud environments.

VMmark 2.1: Virtualization Platform Benchmark
VMmark 2.1 is a multi-server datacenter virtualization benchmark which assesses the performance of a group of virtualized real world applications. It includes a variety of common platform-level workloads such as live migration of virtual machines, cloning and deploying of virtual machines, and automatic virtual machine load balancing across the datacenter. To achieve the best results, end-to-end performance from server to storage is needed.

"Cloud computing is a key driver for the acceleration of solid-state adoption in data centers," said Joseph Unsworth, research VP at Gartner. "Companies that can deliver high-performance and reliable solutions at aggressive price-points are best positioned to exploit this opportunity."

The VMmark 2.1 results emphasize that the Violin 6000 Series flash Memory Arrays have the best combined IOPS and latency to virtualize and consolidate demanding business critical applications and desktops.

"Cisco UCS has established the best VMmark scores for 2-socket servers, and storage performance was a key requirement," said Don Basile, CEO of Violin Memory. "With  random IO performance, economics and sustained low latency, the Violin 6000 was the obvious storage infrastructure choice for this effort. Offering the best IOPS per terabyte, Violin enables storage consolidation just like Cisco UCS drives server consolidation."

The Violin 6000 Series flash Memory Arrays bring storage performance in balance with high speed compute and networking, offering an opportunity for infrastructure consolidation. A single system fits in a 3U of rack space and can deliver one million IOPS with 4GB/s of bandwidth – enough performance to replace multiple racks of traditional disk arrays for savings of both CAPEX and OPEX. The arrays attach to the network for shared primary storage. Multiple arrays can be clustered together to achieve petabytes of capacity and high aggregate bandwidth.