Ethernet White Papers
SX1036: The Ideal 40GbE Aggregation Switch (May 2013)
As new data center applications are used, new solutions are required to meet the demand for higher throughput, without increasing the power consumption or cost. Mellanox’s SX1036 36-Port 40/56GbE Switch System provides the highest-performing fabric solution in a 1U form factor by delivering over 4Tb/s of non-blocking throughput. It can be configured to provide 36 4X ports running at 40GbE or 56GbE, or provide up to 64 1GbE or 10GbE ports. The SX1036 switch system is also ready for Mellanox Open Ethernet, which provides the ability to terminate the dependency on the operating system and protocol stack of the switch vendor.
Highly Accurate Time Synchronization with ConnectX®-3 and TimeKeeper® (March 2013)
Upgrading your trading platforms to reliable and precise time is achievable at a low cost and a rapid deployment model via the combination of Mellanox's ConnectX®-3 network adapter cards and TimeKeeper® Client software. TimeKeeper can assure sub-microsecond time precision from both the newer IEEE 1588 Precision Time Protocol (PTP) or the standard Network Time Protocol (NTP) over shared (not dedicated) network links. Flexibility in time sources and automatic adapability to network quality allows for incremental changes to enterprise systems, and immediate high precision timing in critical components while less critical components see incremental performance improvement. For high quality links and time feeds, applications can see time locked to reference well within 500 nanoseconds of variation.
Deploying Apache™ Hadoop® with Colfax and Mellanox VPI Solutions (March 2013)
Hadoop® has become the “go-to” framework for Map-Reduce systems. Increasing in popularity, Map-Reduce brings current and future users to look for systems which can deploy their application and framework’s in a scalable manner. While more data is helpful for understanding a problem, the challenge is whether the infrastructure used to process the data provides the expected return. In this white paper we describe the build of a Hadoop cluster, using Mellanox InfiniBand FDR interconnect and highly powerful and reliable servers from Colfax International. The Hadoop version described is the Apache™ community Hadoop.
Power Saving Features in Mellanox Products (January 2013)
The growth in Cloud and Web 2.0 storage and compute requirements in recent years has led to an increase in demand for larger, stronger, and more cost efficient data centers.
- Tolly Report: Mellanox SX1016 & SX1036 10/40GbE Switches
As data center demands continually increase, network architects seeks out the best performance combined with operational efficiency and scalability. Mellanox is focused on meeting these needs by developing L2/L3 Ethernet switches that offer high throughput, extremely low latency and ultra low power consumption.
- Introduction to Cloud Design
Cloud computing is a collection of technologies and practices used to abstract the provisioning and management of computer hardware. The goal is to simplify the users experience so they can get the benefit of compute resources on demand; or in the language of cloud computing "as a service".
- Deploying Hadoop® with Mellanox End-to-End 10/40Gb Ethernet Solutions
The Apache™ Hadoop® project develops open-source software for reliable, scalable, distributed computing. The described configurations and settings are used in the following CDH (Cloudera's Distribution, including Apache™ Hadoop®)
TIBCO, HP and Mellanox High Performance Extreme Low Latency Messaging
With the recent release of TIBCO FTL™, TIBCO is once again changing the game when it comes to providing high performance messaging middleware. Many solutions have emerged to try and provide next generation systems with extreme low latency but they are doing this by sacrificing the traditional features and functions that mission critical middleware solutions require. TIBCO's approach is to offer a middleware solution that offers extreme low latency without sacrifice, allowing for the scalability not only to meet the demands for low latency data distribution but also to meet the demands as the application grows from a few instances to thousands of instances.
Achieving Data Center Networking Efficiency
Data centers have been designed for years with the same hierarchical and expensive network design. But as the modern data center evolves to a scale-out, dynamic and virtualized shared services platform, it's time to re-evaluate the old architecture and see if there is a more efficient way.
The Next Phase of Datacenter Network Resource Management and Automation (March 2011)
Executives want to undertake an "operational" transformation of IT to boost the effective use of IT assets and make it easier for organizations to react quickly to major positive or negative changes in the business environment.
Scaling-out Ethernet for the Data Center (February 2011)
Computation infiltrates all aspects of our lives. More content and services are now digitized, requiring more storage and associated computation and network resources. As a result, data center capacities are constantly growing at a fast pace while budgets and available power remain at the same levels.
Informatica, HP, and Mellanox/Voltaire Benchmark Report: Ultra Messaging accelerated across three supported interconnects
The securities trading market is experiencing rapid growth in volume and complexity with a greater reliance on trading software, which is supported by sophisticated algorithms. As this market grows, so do the trading volumes, bringing existing IT infrastructure systems to their limits.
Virtual Machine Migration Acceleration using Mellanox ConnectX-2 EN 40Gb/s IO Adapter (December 2010)
Large virtualized environments including those found in cloud computing increase I/O performance requirements for applications such as VM migration. With high-performance and efficient networking, data center managers can migrate VMs to different servers faster, allowing them to meet stringent service level agreements (SLA) and lower total cost of ownership (TCO).
RoCE vs. iWARP Competitive Analysis Brief (November 2010)
Over Ethernet, RoCE provides a superior solution compared to iWARP. Many latency-sensitive applications have been ported to run over RoCE and RoCE has been already deployed in mainstream Data Centers.
IBM WebSphere MQ Low Latency Messaging Software Tested With Arista 10 Gigabit Ethernet Switch and Mellanox®
ConnectX®-2 EN with RoCE Adapter Delivers Reliable Multicast Messaging With Ultra Low Latency And High Throughput
Microseconds matter in the ultra-competitive world of High Frequency Trading (HFT). Trading architectures that deliver the lowest latency solution are the difference between profit and loss for these financial firms. IBM, Mellanox and Arista have combined to demonstrate a low latency messaging transport solution that facilitates the high-speed delivery of market, trade, reference and event data, in or between front-, middle and back-office operations.
Red Hat Enterprise MRG with Mellanox ConnectX-2 10GigE NIC Deliver Determinism in Performance and Profitability (June 2010)
Demanding datacenter applications require network infrastructures that can deliver reliable and deterministic performance. High-performance, low-latency networking solutions — combined with low-latency and deterministic performance-oriented software platforms — help deliver mission-critical application performance in the face of growing data and transaction volumes, and are able to handle sudden usage spikes without compromising performance. Red Hat Enterprise MRG with Mellanox ConnectX-2 EN with RoCE delivers the performance, reliability, and guaranteed application response times demanded by today’s datacenters.
- ConnectX®-2 with RoCE
ConnextX-2 with RoCE comes with many advantages and holds the promise to enable widespread deployment of RDMA technologies in mainstream data center applications.
Cisco Nexus Switches and UCS Servers with Mellanox ConnectX®-2 EN with RoCE for a Reliable and Low-Latency Data Center
Infrastructure (April 2010)
Demanding data center applications require network infrastructures that can deliver reliable and deterministic performance. High performance, low latency and lossless Ethernet fabrics serve as cornerstones in the delivery of mission critical application performance in the face of growing data and transaction volumes, and their ability to handle sudden usage spike without compromising performance.
- Delivering Unmatched Messaging Performance with IBM
WebSphere LLM and Mellanox ConnectX 10 Gigabit Ethernet Products (April 2010)
WebSphere MQ Low Latency Messaging running over low-latency Ethernet can be used to implement the high-performance, highly available messaging infrastructure needed for the next generation implementations of exchange systems.
Exegy Ticker Plant & Mellanox ConnectX® EN with RoCE Delivers Breakthrough for Co-located Trading
Exegy’s Ticker Plant and its clients can ingest millions of messages per second from today’s extremely busy stock, option and futures markets. With the incorporation of the latest Mellanox ConnectX-2 EN with RoCE adapters, customers need not hesitate to adopt this ground breaking technology since they can easily accommodate it over their familiar Ethernet networks.
RNA Networks Memory Virtualization Solution Using RNA MVX and Mellanox ConnectX®-2 EN with RoCE Accelerates Business
Analytics by 10 Times
ConnectX-2 EN with RoCE enables RNA MVX to achieve 1/3rd the latency using other 10GigE NICs using TCP/IP (that is not using RDMA and kernel bypass enabled by RoCE).
The Case for Low-Latency Ethernet (March 2009)
The industry momentum behind Fibre over Ethernet (FCoE) sets some significant precedence that raises questions about what is the best approach for server to server messaging (or inter process communication or IPC) using zero-copy send/receive and remote DMA (RDMA) technologies over Ethernet.
ARISTA and Mellanox: Improving Application Performance While Reducing Complexity
Advances in server virtualization, network storage, and compute clusters have driven the need for faster network throughput to address application latency and availability problems in the Enterprise. Yet today’s economic demands require the Enterprise maintain reasonable or reduced capital and operational cost parameters. This white paper will address how Mellanox and Arista Networks substantially improve application performance while reducing network complexity.
The Case for InfiniBand over Ethernet (April 2008)
Advances in server virtualization, network storage, and compute clusters have driven the need for faster network throughput to address application latency and vailability problems in the Enterprise. Yet today’s economic demands require the Enterprise maintain reasonable or reduced capital and operational cost parameters. This white paper will address how Mellanox and Arista Networks substantially improve application performance while reducing network complexity.
7 Reasons to deploy a Mellanox ConnectX 10GbE (October 2008)
Mellanox, the leader in the high performance interconnect technology has introduced the most compelling 10 Gigabit Ethernet silicon and adapter providing leading storage, virtualization and networking features. Mellanox dominates the 10 Gigabit Ethernet market by supporting several leading-edge technologies providing the utmost investment protection to data centers worldwide.