The next generation of Wi-Fi, 802.11ac couples the freedom of wireless with the speed of gigabit Ethernet. This also translates in additional load on the backbone of the network, which has to deliver at least 3 times the capacity of the current gold standard, the 802.11n based network.
Cisco launched the Unified Access architecture to scale linearly with the increased load on the network with 60 Gbps Wi-Fi throughput on the Cisco 5760 Wireless LAN Controller and 40 Gbps Wi-Fi throughput on the Catalyst 3850 Series Switch with a built-in wireless controller. Both these platforms are based on the Cisco Unified Access Data Plane (UADP) programmable ASIC, which provides high performance and scale, common open APIs, and enables consistent QoS policies for both wired and wireless networks.
Aruba recently launched the 7240 series controllers with a throughput of up to 40Gbps claimed, with the same goal of delivering 802.11ac capable performance across the network. This controller is based on a generic network processor and not a purpose built ASIC like the Cisco controller.
Miercom performed a third-party evaluation to benchmark these products using IMIX (Internet Mix) packet traffic and test QoS traffic for high priority application. IMIX is traffic pattern consisting of a preset mixture of small, medium and large frame sizes used to emulate real-world traffic scenarios in a testing environment. We wanted to give you a sneak peek at some of the results.
Cisco 5760 is six times faster and Catalyst 3850 is 4 times faster as compared to Aruba 7240
The Cisco 5760, 3850 and the Aruba 7240 were tested for throughput using RFC 2544 and IMIX Traffic. The Cisco 5760 and 3850 performed extremely well by achieving 50 Gbps and 37 Gbps, whereas Aruba 7240 fell short by just achieving 8 Gbps, which is 20% of its advertised throughput.
Read More »
Tags: 802.11ac, aruba, Cisco, controller, Miercom, network, performance, QoS, technology, wireless
Cisco continues its cloud computing performance leadership with the announcement of VMware® VMmark™ 2.5 benchmark result published on May 9th 2013. The Cisco UCS C240 M3 Rack Server’s score of 12.00@10 tiles on the VMware VMmark 2.5 benchmark represents the best cloud computing performance of any 2-socket server in a 2-node configuration as measured by the VMware VMmark 2.5 benchmark
The VMware VMmark 2.5 benchmark uses a tiled design that incorporates six real-world workloads to calculate a virtualization score. Then it includes VMware vMotion, Storage vMotion, and virtual machine provisioning times to calculate an infrastructure score. The combination of these scores is the total benchmark score.
The system used to achieve this performance included the Cisco UCS C240 M3 Rack Server powered by Intel® Xeon® processors and an industry-leading approach to storage: a Cisco UCS server-based Fusion‑io ION Data Accelerator solution that turns the server into a storage system. The Fusion-io ION Data Accelerator turns Cisco UCS servers equipped with Fusion-io ioMemory into highly available, transparently scalable, shared storage appliances.
For additional insights on the benchmark configuration check the “Cisco UCS C240 M3 Rack Server Delivers World-Record Cloud Computing Performance” Performance Brief. You can also download the official VMware® VMmark™ V 2.5 benchmark disclosure and configuration details at http://www.vmware.com/a/assets/vmmark/pdf/2013-05-09-Cisco-C240M3.pdf
With this world-record-setting VMmark 2.5 benchmark score of 12.00@10 tiles Cisco UCS has delivered the best cloud computing performance of any 2-socket server in a 2-node configuration as measured by the VMware VMmark 2.5 benchmark outperforming solutions from AMD, Dell, Fujitsu, and HP. Whether a virtualized data center or a public or private cloud is needed, this VMware VMmark 2.5 benchmark result indicates the degree to which the Cisco UCS can accelerate applications while delivering virtualization and infrastructure performance and agility for cloud computing environments
Better infrastructure yields better performance. With innovations such as unified fabric, large memory capacity, expansion capabilities, and the low-latency performance of Fusion-io ioMemory and ION Data Accelerator software, Cisco’s results demonstrate the architectural advantages of a system built for virtualized environments.
VMware VMmark is a product of VMware, Inc. The comparative results cited in this document were available at http://www.vmmark.com and were valid as of May 9th, 2013..
Senior Marketing Manager
Unified Computing System
Tags: Benchmark Performance, Cisco UCS, cloud_computing, performance, virtualization, VMmark
On March 19th, 2013 Cisco announced the best 2-socket virtualized SAP Sales and Distribution (SD) Benchmark result in a Linux environment with the Cisco Unified Computing System™ (Cisco UCS®) delivering high scalability and low latency in virtualized SAP Business Suite deployments.
Cisco’s benchmark result for the Cisco UCS B200 M3 Blade Server show support for up to 5530 concurrent users and a SAP Application Performance Standard (SAPS) score of 30,270 derived from the processing of 605,330 order line items per hour and 1,816,000 dialog steps per hour. This result demonstrates that a Cisco UCS B200 M3 Blade Server configured with a LSI 400-GB SLC WarpDrive can deliver high scalability and low latency in virtualized SAP Business Suite deployments.
The tested configuration consisted of a Cisco UCS chassis equipped with one Cisco UCS B200 M3 Blade Server running Red Hat Enterprise Linux (RHEL) 6.4 on KVM. The server was configured with two 2.90-GHz, 8-core Intel Xeon processor E5-2690 CPUs and 256 GB of 1600-MHz memory. The blade server ran both the SAP Business Suite application software and the 64-bit Sybase ASE 15.7 in a single virtual machine. SAP Enhancement Package 5 for SAP Enterprise Resource Planning (ERP) 6.0 was used in this scenario. The Cisco UCS B200 M3 Blade Server recorded the best two-way virtualized SAP SD Benchmark result on SAP Enhancement Package 5 for SAP ERP 6.0 and Sybase ASE 15.7. In the test, 5530 SAP SD Benchmark users were supported while a consistent application response of less than one second was maintained.
The “Cisco UCS B200 M3 Blade Server: High Performance and Flexibility for Virtualized SAP Business Suite Deployment” Performance Brief provides additional benchmark configuration details.Official Benchmark Certification is available at the SAP® Standard Application Benchmarks certification web site.
Many business organizations currently struggle with the cost of maintaining RISC processor–based servers running proprietary operating systems and third-party database management systems. Cisco UCS enables organizations to use lower-cost industry-standard x86-architecture servers, open source operating systems, database management systems, and allows organizations to run SAP Business Suite applications in virtualized environments. With Cisco UCS, organizations can easily balance workloads across a pool of servers to manage service levels according to business priorities, scale environments up and down as needed, and contain costs by consolidating workloads onto a smaller number of servers.
Using the Cisco UCS, IT departments can run virtualized SAP Business Suite applications with the flexibility, scalability, and lower cost of virtualized environments. These innovations delivering high scalability and low latency in virtualized SAP Business Suite deployments and the dramatic reduction in the number of physical components required illustrates the value created by Cisco UCS solution for customers planning migration away from proprietary RISC/Unix based systems to open source operating system software and standards-based computing infrastructure.
For additional information on Cisco UCS and Cisco UCS solutions please visit www.cisco.com/go/ucs
Sr. Product Marketing Manager
Unified Computing System
Tags: Benchmark Performance, Benchmark results, Cisco UCS, performance, SAP, virtualization
One part of my job involves designing the virtualization model for our internal unified communications (UC) system deployments around the world. A critical task in this design is specifying which UC virtual machines (VMs) can share a Cisco Unified Computing System (Cisco UCS) server chassis or blade and which ones can’t. When migrating UC servers to a shared virtual environment, we need to make sure we carefully balance each VM’s needs for CPU, storage, network and memory. Read More »
Tags: coc-collaboration, coc-data-center, performance, server, UC on UCS, UCS, unified communications, virtualization, VM
Cisco continues a tradition of enterprise application performance leadership with four new world records on Oracle E-Business Suite benchmarks, demonstrating that Cisco Unified Computing System™ (Cisco UCS®) powers business-critical software better than any other server vendor.
In four of the Oracle E-Business Suite Standard Benchmarks, the Cisco UCS B200 M3 Blade Server delivered the best performance of any server, regardless of configuration or number of processor cores.
The benchmarks were run in a two-tier configuration with a single Cisco UCS B200 M3 Blade Server hosting both the database and the application server instances, all running on a single Oracle Linux image.
Read More »
Tags: benchmark, Cisco UCS, Oracle E-Business Suite, performance