Easier - Faster - Better



Similar documents
An Alternative Storage Solution for MapReduce. Eric Lomascolo Director, Solutions Marketing

The Benefit of Migrating from 4Gb to 8Gb Fibre Channel

Xyratex Update. Michael K. Connolly. Partner and Alliances Development

MaxDeploy Ready. Hyper- Converged Virtualization Solution. With SanDisk Fusion iomemory products

Make the Most of Big Data to Drive Innovation Through Reseach

Flash Memory Arrays Enabling the Virtualized Data Center. July 2010

Complete Storage and Data Protection Architecture for VMware vsphere

SQL Server 2012 Parallel Data Warehouse. Solution Brief

Microsoft Private Cloud Fast Track

ANY SURVEILLANCE, ANYWHERE, ANYTIME

Reducing Storage TCO With Private Cloud Storage

HadoopTM Analytics DDN

SYMANTEC NETBACKUP APPLIANCE FAMILY OVERVIEW BROCHURE. When you can do it simply, you can do it all.

Hitachi Adaptable Modular Storage 2000 Family and Microsoft Exchange Server 2007: Monitoring and Management Made Easy

Fabrics that Fit Matching the Network to Today s Data Center Traffic Conditions

How Solace Message Routers Reduce the Cost of IT Infrastructure

Business-centric Storage FUJITSU Hyperscale Storage System ETERNUS CD10000

Dell s SAP HANA Appliance

Clusters: Mainstream Technology for CAE

Understanding Storage Virtualization of Infortrend ESVA

Netapp HPC Solution for Lustre. Rich Fenton UK Solutions Architect

Maximum performance, minimal risk for data warehousing

Quick Reference Selling Guide for Intel Lustre Solutions Overview

STORNEXT PRO SOLUTIONS. StorNext Pro Solutions

Integration of Microsoft Hyper-V and Coraid Ethernet SAN Storage. White Paper

Hadoop Cluster Applications

INCREASING EFFICIENCY WITH EASY AND COMPREHENSIVE STORAGE MANAGEMENT

IBM System Storage DS5020 Express

SAP HANA - an inflection point

Solution Brief Network Design Considerations to Enable the Benefits of Flash Storage

Cisco Unified Data Center Solutions for MapR: Deliver Automated, High-Performance Hadoop Workloads

STORNEXT PRO SOLUTIONS. StorNext Pro Solutions

EMC XtremSF: Delivering Next Generation Performance for Oracle Database

Scaling Objectivity Database Performance with Panasas Scale-Out NAS Storage

New Storage System Solutions

IBM Storwize V7000 Unified and Storwize V7000 storage systems

Data Sheet FUJITSU Storage ETERNUS CD10000

IBM Storwize Rapid Application Storage solutions

PRIMERGY server-based High Performance Computing solutions

MaxDeploy Hyper- Converged Reference Architecture Solution Brief

Nondisruptive Operations and Clustered Data ONTAP

IBM Storwize Rapid Application Storage

Top Ten Questions. to Ask Your Primary Storage Provider About Their Data Efficiency. May Copyright 2014 Permabit Technology Corporation

Microsoft Private Cloud Fast Track Reference Architecture

TOP FIVE REASONS WHY CUSTOMERS USE EMC AND VMWARE TO VIRTUALIZE ORACLE ENVIRONMENTS

EMC ISILON OneFS OPERATING SYSTEM Powering scale-out storage for the new world of Big Data in the enterprise

Integrated Grid Solutions. and Greenplum

How To Write An Article On An Hp Appsystem For Spera Hana

I D C T E C H N O L O G Y S P O T L I G H T. I m p r o ve I T E f ficiency, S t o p S e r ve r S p r aw l

EMC XtremSF: Delivering Next Generation Storage Performance for SQL Server

Using EonStor FC-host Storage Systems in VMware Infrastructure 3 and vsphere 4

Clustering Windows File Servers for Enterprise Scale and High Availability

Data Center Performance Insurance

Optimizing Large Arrays with StoneFly Storage Concentrators

ioscale: The Holy Grail for Hyperscale

An Oracle White Paper November Backup and Recovery with Oracle s Sun ZFS Storage Appliances and Oracle Recovery Manager

Unlock the value of data with smarter storage solutions.

Scala Storage Scale-Out Clustered Storage White Paper

IBM Enterprise Linux Server

Introduction. Need for ever-increasing storage scalability. Arista and Panasas provide a unique Cloud Storage solution

Microsoft SQL Server 2014 Fast Track

The PHI solution. Fujitsu Industry Ready Intel XEON-PHI based solution. SC Denver

Elasticsearch on Cisco Unified Computing System: Optimizing your UCS infrastructure for Elasticsearch s analytics software stack

Modernizing Hadoop Architecture for Superior Scalability, Efficiency & Productive Throughput. ddn.com

All-Flash Arrays Weren t Built for Dynamic Environments. Here s Why... This whitepaper is based on content originally posted at

EMC s Enterprise Hadoop Solution. By Julie Lockner, Senior Analyst, and Terri McClure, Senior Analyst

Five Essential Components for Highly Reliable Data Centers

Milestone Solution Partner IT Infrastructure MTP Certification Report Scality RING Software-Defined Storage

Colgate-Palmolive selects SAP HANA to improve the speed of business analytics with IBM and SAP

Technology Insight Series

POWER ALL GLOBAL FILE SYSTEM (PGFS)

Four Ways High-Speed Data Transfer Can Transform Oil and Gas WHITE PAPER

An Oracle White Paper. Oracle Database Appliance X4-2

Introduction. Scalable File-Serving Using External Storage

A Dell Technical White Paper Dell Compellent

Realizing the True Potential of Software-Defined Storage

Open-E Data Storage Software and Intel Modular Server a certified virtualization solution

Why is the V3 appliance so effective as a physical desktop replacement?

Nexenta Performance Scaling for Speed and Cost

WHITE PAPER. Building Blocks of the Modern Data Center

Software-defined Storage Architecture for Analytics Computing

OPTIMIZING SERVER VIRTUALIZATION

EMC VPLEX FAMILY. Continuous Availability and data Mobility Within and Across Data Centers

Storage Technologies for Video Surveillance

ScaleArc for SQL Server

REDEFINE SIMPLICITY TOP REASONS: EMC VSPEX BLUE FOR VIRTUALIZED ENVIRONMENTS

Einsatzfelder von IBM PureData Systems und Ihre Vorteile.

Unified Computing Systems

SIP-Based Solutions in the Contact Center: Using Dialogic Media Gateways with the Genesys Voice Platform

Symantec NetBackup Appliances

SAN Conceptual and Design Basics

Transcription:

Highest reliability, availability and serviceability ClusterStor gets you productive fast with robust professional service offerings available as part of solution delivery, including quality controlled installation, comprehensive early-stage support, personalized training, as well as data migration, configuration and architecture services. Instead of spending weeks gathering separate hardware and software, resolving interoperability issues and testing to get your Lustre environment into production, you can be productive with ClusterStor in hours. ClusterStor includes pre- Easier - Faster - Better installation of all internal software components, configuration of the integrated system and intensive system reliability tests before it ships from the factory. Rather than fight complexity, let the highly The Ultimate in Scale-Out Storage efficient, factory tested and seamlessly integrated ClusterStor solution do the work for you. for HPC and Big Data ClusterStor maximizes your operation time and application availability. Keeping your storage and file system running through scheduled maintenance or production operation upgrades means that you can stay productive. A key aspect to keeping you up and running is ClusterStor s built-in high availability design and comprehensive set of distributed management services. ClusterStor has been designed from the ground up as a highly available enterprise class storage solution with resiliency engineered into all primary subsystems. Meta-data and management server operations are resident on a high availability Cluster Management Unit. Each Scalable Storage Unit includes active/active embedded server modules, redundant and independent system interconnects. ClusterStor Manager removes the management burden of administering tens of petabytes and their traditional complement of deployed Lustre Object Storage Servers. Consolidated and detailed health monitoring and error reporting enables administrators to quickly view and diagnose file system and hardware assets. Software and firmware upgrades across an entire ClusterStor system are executed through ClusterStor Manager, removing the administrative burden and risks that come with large complex Lustre implementations. Xyratex removes all of the pre-upgrade work and testing effort normally associated with upgrades and gives you an ability to roll-back upgrades, if necessary. ClusterStor Manager is a comprehensive system management application that is part of ClusterStor s distributed management framework and is responsible for pulling everything together as a single managed system. ClusterStor Manager consolidates The ClusterStor family of high management of the storage infrastructure, RAID data protection layer, scale-out operating system and the Lustre file system into a performance scale-out storage for single, easy-to-use, administrator interface. From initial installation, creation of file systems, ongoing monitoring and management, HPC and Big Data provides unmatched to expansion and software upgrades, ClusterStor Manager brings the entire storage cluster solution to a single pane. This brings file system performance, optimized unprecedented system visibility to the Lustre system administrator. time to productivity and the HPC Conclusion industry s highest levels in integrated Our attention to architectural balance and keen eye to detail has resulted in the ClusterStor scale-out data storage solution, exactly solution reliability, availability and serviceability. matching the linear file system processing scalability needs for state of the art HPC and Big Data scale-out compute architectures. USA Sales & Support While alternative scale-out data storage designs have appeared on the market, none match the degree of linear scalability and performance-capacity density delivered by the ClusterStor family of integrated high performance scale-out storage solutions for HPC and Big Data. T: +1 877 997 2839 www.xyratex.com Issue 3.0 06/13 UK HQ T: +1 877 XYRATEX T: +44(0)23 9249 6000 Lustre is a registered trademark of Xyratex. Other names may be trademarks of their respective owners. 2013 Xyratex (The trading name of Xyratex Technology Limited). Registered in England & Wales. Company no: 03134912. Registered Office: Langstone Road, Havant, Hampshire PO9 1SA, England. The information given in this brochure is for marketing purposes and is not intended to be a specification nor to provide the basis for a warranty. The products and their details are subject to change. For a detailed specification or if you need to meet a specific requirement please contact Xyratex: www.xyratex.com. Departmental Storage Scale ClusterStor Manager Supercomputing Storage Scale

ClusterStor integrated high performance scale-out storage for HPC and Big Data ClusterStor Architecture ClusterStor A family of integrated high performance scale-out storage solutions ClusterStor makes the solution paradigm clear. ClusterStor utilizes high performance, distributed computing How does the ClusterStor architecture deliver unmatched yet predictable file system performance? There is a feeling you get when you experience fine engineering. The feeling starts when you first lay eyes data storage elements that have been designed and built from the enclosure and application platform all the Taking a deeper look into the distributed scale-out data storage on the product and becomes more evident every time you use it. There are so many facets of your experience way up to the operating system, file system and advanced User Interface (UI) management functions. Four high architecture, one of the unique characteristics users experience level solution components (storage hardware, operating system, is ClusterStor s performance density. This means the highest file system and management application) have been synergistically performance in the smallest amount of space. that tell you someone knows exactly what you need; innovative thought is evident behind every detail. Xyratex has taken its 25 years experience in designing and delivering enterprise class storage, along with the bonded together to create the most reliable and best performing Lustre high performance file system, to create ClusterStor, an integrated family of high performance scale- integrated high performance scale-out storage in the industry out storage solutions for HPC and Big Data. Designed to provide unmatched file system today. performance and optimized time to productivity, ClusterStor provides the HPC industry s highest levels of integration solution reliability, availability and serviceability. Lustre is the front running file system for the top HPC systems in the world and is continuing to gain momentum in emerging Big Data This achievement is the direct result of a fresh ground-breaking design approach that deployments as organizations such as OpenSFS invest heavily in its meets the specific needs of high performance computing and its ever expanding scale. future. ClusterStor s software architecture tightly integrates Lustre The ClusterStor architecture is not merely an exercise of repackaging separate legacy into a performance and capacity optimized solution that removes storage hardware and file system software components. headaches that have historically been associated with deploying, Overcoming Bottlenecks Looking back, traditional storage designs offer two storage servers per rack of storage, and frequently offer the same Take one look at ClusterStor; you will see up to 14 embedded storage servers per rack. two storage servers for two racks of storage. Unfortunately, this has been widely noted as one of the principle pain- ClusterStor has not only been designed with a massively parallel points within the industry: storage IO performance degree of embedded storage servers per rack volume of storage bottleneck. Clearly, traditional storage design with too few capacity, but looking deeper into individual SSU building blocks, storage servers per rack volume are out of balance with the users see the latest generation of server-class processors and file system performance and capacity needs of modern HPC the same design approach as contained in the latest HPC and Big and Big Data scale-out compute architectures. Data scale-out compute nodes. ClusterStor is the result of state of the art optimization of the Lustre file system embedded managing and maintaining traditional Lustre environments using In a ClusterStor system, Scalable Storage Units (SSUs) act as independent I/O processing engines that work in parallel. Each SSU has its within a modular scale-out hardware architecture to address a wide spectrum of HPC off the shelf components from different vendors. own set of resources that includes densely packed disk storage and dual embedded server modules, which also carry their own set of and Big Data application needs. ClusterStor offers solutions to best match your most challenging linear performance and capacity scalability requirements. When you get up close, you can see that ClusterStor is not only innovative in its approach but also delivers a level of quality that translates into higher availability to meet your productivity requirements today and into the future. Problem: Legacy storage metrics are not meaningful at the HPC and Big Data user level. Traditional Lustre file system solutions have typically used a mix of off-the-shelf components from different vendors leveraging legacy storage. Difficulties and roadblocks have been widely reported within the industry due to variances in vendor components Lustre s future is directly tied to its quality and end user productivity success. This is why Xyratex makes significant contributions into Lustre testing, support and community involvement, and why we have honed the processing, memory and I/O network resources. This provides the most efficient use of each resource in a compact design that reduces the space required to deliver each gigabyte of file system performance. best attributes into our tightly optimized environment, eliminating variations and complexity. Broad Applications - Flexible Planning - Easy Deployment The resilient ClusterStor operating environment introduces a scale-out storage and management architecture No matter how small or large your high performance application plan, the ClusterStor family specifically designed to take full advantage of the performance and capacity scaling capabilities of the Lustre provides a wide range of solutions and design methods to best match the file system performance file system. ClusterStor doesn t have to utilize special block-storage algorithms to predict how to provide and/or data storage capacity growth projected throughout the lifetime of your installation. optimal performance, the ClusterStor operating environment knows. In ClusterStor, the operating environment - Delivers best in class ROI acceleration for department level environments is integrated into distributed data storage elements called the Scalable Storage Unit. To best address commercial scientific high resolution simulation and engineering Introducing the Scalable Storage Unit modeling applications, enables parallel data access to attain The Scalable Storage Unit (SSU) is at the heart of ClusterStor s scale-out storage architecture. The ClusterStor limitations associated to legacy midrange solutions relying solely upon serial data SSU consolidates and integrates traditional block storage, network and file system components into a single access Network File System (NFS). specifically enables commercial This traditional approach burdens HPC and Big Data environments with unacceptable program risk due to building block that delivers a linear scaling unit in file system performance and data storage capacity. There is and industrial technical computing users to attain faster job completion, higher the excessive time, expense and non-productive work that constantly disrupts system productivity. What no need to guess at how to scale your Lustre file system: each unit is a balanced performance building block job iteration rates and more precise application insights with higher resolution has previously been considered maintenance is actually waste. Increasing HPC and Big Data productivity delivering a predictable level of performance and/or data storage capacity that scales linearly without storage requirements demand that waste be eliminated. or network degradation. The future of HPC and Big Data data storage requires a paradigm shift from legacy storage systems that focus on Scalable Storage Unit building blocks provide a purpose-built, appliance interacting with separate file system servers and software packages, as well as the constant need to tune and retune file system parameters when attempting to add or even adjust file system processing capacity. attributes like raw block storage capacity, controller cache size, or raw block data transfers. Solution: like method to plan, build and deploy small, medium, or extensively large HPC data storage systems. HPC and Big Data user productivity is the only meaningful metric. File system storage productivity End users simply add SSUs to satisfy their is best measured in sustained end to end file system throughput delivery, as well as reduced datacenter floor performance and/or data capacity needs, space utilization, cooling, power and administrative time. Unfortunately, traditional storage systems on their own all while using built-in optimization, are not able to address these user level attributes. A comprehensive solution paradigm is needed. resilient ClusterStor operating ClusterStor introduces a new standard in end-to-end file system performance and efficiency, at the user level. Truly scaling file system performance efficiently means aggressively reducing the space, power, cooling and time consumed to achieve the HPC and Big Data performance and results users seek. Xyratex has proven that performance, efficiency and end-to-end solution management gains can be realized by consolidating system components closely together within an efficient, reliable and highly integrated scale-out data storage solution. environment, end-to-end solution quality and ease of management. significantly enhanced data processing throughput efficiency, far exceeding accuracy. Highest Concentrated Performance Density Best in Class ROI Acceleration Proven Efficiency, Reliability and Ease of Management Affordable Midrange Solution Maximum Supercomputing Scale Compact and Easy to Use Turnkey Lustre Solution As an easy to use complete turnkey engineered Lustre solution for midrange technical computing users, is designed to deliver no compromise performance and data capacity scalability in an affordable and remarkably compact integrated scale-out solution. - Delivers maximum performance scale for supercomputing environments To best address maximum file system through-put, delivers highest performance and data capacity density per SSU, achieving more concentrated performance per unit data storage capacity, while delivering excellent efficiency, reliability and ease of management. As demonstrated among the industry s largest and fastest supercomputing installations, is designed to collapse and consolidate Lustre file system hardware and software into modular, easy-to-use building blocks, enabling unprecedented linear performance scalability via proven methodical deployment methods with predictable solution results. Compared to legacy Lustre designs, this translates into saving in storage hardware, resulting in lower latencies, higher reliability and reduced power and cooling costs.

ClusterStor integrated high performance scale-out storage for HPC and Big Data ClusterStor Architecture ClusterStor A family of integrated high performance scale-out storage solutions ClusterStor makes the solution paradigm clear. ClusterStor utilizes high performance, distributed computing How does the ClusterStor architecture deliver unmatched yet predictable file system performance? There is a feeling you get when you experience fine engineering. The feeling starts when you first lay eyes data storage elements that have been designed and built from the enclosure and application platform all the Taking a deeper look into the distributed scale-out data storage on the product and becomes more evident every time you use it. There are so many facets of your experience way up to the operating system, file system and advanced User Interface (UI) management functions. Four high architecture, one of the unique characteristics users experience level solution components (storage hardware, operating system, is ClusterStor s performance density. This means the highest file system and management application) have been synergistically performance in the smallest amount of space. that tell you someone knows exactly what you need; innovative thought is evident behind every detail. Xyratex has taken its 25 years experience in designing and delivering enterprise class storage, along with the bonded together to create the most reliable and best performing Lustre high performance file system, to create ClusterStor, an integrated family of high performance scale- integrated high performance scale-out storage in the industry out storage solutions for HPC and Big Data. Designed to provide unmatched file system today. performance and optimized time to productivity, ClusterStor provides the HPC industry s highest levels of integration solution reliability, availability and serviceability. Lustre is the front running file system for the top HPC systems in the world and is continuing to gain momentum in emerging Big Data This achievement is the direct result of a fresh ground-breaking design approach that deployments as organizations such as OpenSFS invest heavily in its meets the specific needs of high performance computing and its ever expanding scale. future. ClusterStor s software architecture tightly integrates Lustre The ClusterStor architecture is not merely an exercise of repackaging separate legacy into a performance and capacity optimized solution that removes storage hardware and file system software components. headaches that have historically been associated with deploying, Overcoming Bottlenecks Looking back, traditional storage designs offer two storage servers per rack of storage, and frequently offer the same Take one look at ClusterStor; you will see up to 14 embedded storage servers per rack. two storage servers for two racks of storage. Unfortunately, this has been widely noted as one of the principle pain- ClusterStor has not only been designed with a massively parallel points within the industry: storage IO performance degree of embedded storage servers per rack volume of storage bottleneck. Clearly, traditional storage design with too few capacity, but looking deeper into individual SSU building blocks, storage servers per rack volume are out of balance with the users see the latest generation of server-class processors and file system performance and capacity needs of modern HPC the same design approach as contained in the latest HPC and Big and Big Data scale-out compute architectures. Data scale-out compute nodes. ClusterStor is the result of state of the art optimization of the Lustre file system embedded managing and maintaining traditional Lustre environments using In a ClusterStor system, Scalable Storage Units (SSUs) act as independent I/O processing engines that work in parallel. Each SSU has its within a modular scale-out hardware architecture to address a wide spectrum of HPC off the shelf components from different vendors. own set of resources that includes densely packed disk storage and dual embedded server modules, which also carry their own set of and Big Data application needs. ClusterStor offers solutions to best match your most challenging linear performance and capacity scalability requirements. When you get up close, you can see that ClusterStor is not only innovative in its approach but also delivers a level of quality that translates into higher availability to meet your productivity requirements today and into the future. Problem: Legacy storage metrics are not meaningful at the HPC and Big Data user level. Traditional Lustre file system solutions have typically used a mix of off-the-shelf components from different vendors leveraging legacy storage. Difficulties and roadblocks have been widely reported within the industry due to variances in vendor components Lustre s future is directly tied to its quality and end user productivity success. This is why Xyratex makes significant contributions into Lustre testing, support and community involvement, and why we have honed the processing, memory and I/O network resources. This provides the most efficient use of each resource in a compact design that reduces the space required to deliver each gigabyte of file system performance. best attributes into our tightly optimized environment, eliminating variations and complexity. Broad Applications - Flexible Planning - Easy Deployment The resilient ClusterStor operating environment introduces a scale-out storage and management architecture No matter how small or large your high performance application plan, the ClusterStor family specifically designed to take full advantage of the performance and capacity scaling capabilities of the Lustre provides a wide range of solutions and design methods to best match the file system performance file system. ClusterStor doesn t have to utilize special block-storage algorithms to predict how to provide and/or data storage capacity growth projected throughout the lifetime of your installation. optimal performance, the ClusterStor operating environment knows. In ClusterStor, the operating environment - Delivers best in class ROI acceleration for department level environments is integrated into distributed data storage elements called the Scalable Storage Unit. To best address commercial scientific high resolution simulation and engineering Introducing the Scalable Storage Unit modeling applications, enables parallel data access to attain The Scalable Storage Unit (SSU) is at the heart of ClusterStor s scale-out storage architecture. The ClusterStor limitations associated to legacy midrange solutions relying solely upon serial data SSU consolidates and integrates traditional block storage, network and file system components into a single access Network File System (NFS). specifically enables commercial This traditional approach burdens HPC and Big Data environments with unacceptable program risk due to building block that delivers a linear scaling unit in file system performance and data storage capacity. There is and industrial technical computing users to attain faster job completion, higher the excessive time, expense and non-productive work that constantly disrupts system productivity. What no need to guess at how to scale your Lustre file system: each unit is a balanced performance building block job iteration rates and more precise application insights with higher resolution has previously been considered maintenance is actually waste. Increasing HPC and Big Data productivity delivering a predictable level of performance and/or data storage capacity that scales linearly without storage requirements demand that waste be eliminated. or network degradation. The future of HPC and Big Data data storage requires a paradigm shift from legacy storage systems that focus on Scalable Storage Unit building blocks provide a purpose-built, appliance interacting with separate file system servers and software packages, as well as the constant need to tune and retune file system parameters when attempting to add or even adjust file system processing capacity. attributes like raw block storage capacity, controller cache size, or raw block data transfers. Solution: like method to plan, build and deploy small, medium, or extensively large HPC data storage systems. HPC and Big Data user productivity is the only meaningful metric. File system storage productivity End users simply add SSUs to satisfy their is best measured in sustained end to end file system throughput delivery, as well as reduced datacenter floor performance and/or data capacity needs, space utilization, cooling, power and administrative time. Unfortunately, traditional storage systems on their own all while using built-in optimization, are not able to address these user level attributes. A comprehensive solution paradigm is needed. resilient ClusterStor operating ClusterStor introduces a new standard in end-to-end file system performance and efficiency, at the user level. Truly scaling file system performance efficiently means aggressively reducing the space, power, cooling and time consumed to achieve the HPC and Big Data performance and results users seek. Xyratex has proven that performance, efficiency and end-to-end solution management gains can be realized by consolidating system components closely together within an efficient, reliable and highly integrated scale-out data storage solution. environment, end-to-end solution quality and ease of management. significantly enhanced data processing throughput efficiency, far exceeding accuracy. Highest Concentrated Performance Density Best in Class ROI Acceleration Proven Efficiency, Reliability and Ease of Management Affordable Midrange Solution Maximum Supercomputing Scale Compact and Easy to Use Turnkey Lustre Solution As an easy to use complete turnkey engineered Lustre solution for midrange technical computing users, is designed to deliver no compromise performance and data capacity scalability in an affordable and remarkably compact integrated scale-out solution. - Delivers maximum performance scale for supercomputing environments To best address maximum file system through-put, delivers highest performance and data capacity density per SSU, achieving more concentrated performance per unit data storage capacity, while delivering excellent efficiency, reliability and ease of management. As demonstrated among the industry s largest and fastest supercomputing installations, is designed to collapse and consolidate Lustre file system hardware and software into modular, easy-to-use building blocks, enabling unprecedented linear performance scalability via proven methodical deployment methods with predictable solution results. Compared to legacy Lustre designs, this translates into saving in storage hardware, resulting in lower latencies, higher reliability and reduced power and cooling costs.

ClusterStor integrated high performance scale-out storage for HPC and Big Data ClusterStor Architecture ClusterStor A family of integrated high performance scale-out storage solutions ClusterStor makes the solution paradigm clear. ClusterStor utilizes high performance, distributed computing How does the ClusterStor architecture deliver unmatched yet predictable file system performance? There is a feeling you get when you experience fine engineering. The feeling starts when you first lay eyes data storage elements that have been designed and built from the enclosure and application platform all the Taking a deeper look into the distributed scale-out data storage on the product and becomes more evident every time you use it. There are so many facets of your experience way up to the operating system, file system and advanced User Interface (UI) management functions. Four high architecture, one of the unique characteristics users experience level solution components (storage hardware, operating system, is ClusterStor s performance density. This means the highest file system and management application) have been synergistically performance in the smallest amount of space. that tell you someone knows exactly what you need; innovative thought is evident behind every detail. Xyratex has taken its 25 years experience in designing and delivering enterprise class storage, along with the bonded together to create the most reliable and best performing Lustre high performance file system, to create ClusterStor, an integrated family of high performance scale- integrated high performance scale-out storage in the industry out storage solutions for HPC and Big Data. Designed to provide unmatched file system today. performance and optimized time to productivity, ClusterStor provides the HPC industry s highest levels of integration solution reliability, availability and serviceability. Lustre is the front running file system for the top HPC systems in the world and is continuing to gain momentum in emerging Big Data This achievement is the direct result of a fresh ground-breaking design approach that deployments as organizations such as OpenSFS invest heavily in its meets the specific needs of high performance computing and its ever expanding scale. future. ClusterStor s software architecture tightly integrates Lustre The ClusterStor architecture is not merely an exercise of repackaging separate legacy into a performance and capacity optimized solution that removes storage hardware and file system software components. headaches that have historically been associated with deploying, Overcoming Bottlenecks Looking back, traditional storage designs offer two storage servers per rack of storage, and frequently offer the same Take one look at ClusterStor; you will see up to 14 embedded storage servers per rack. two storage servers for two racks of storage. Unfortunately, this has been widely noted as one of the principle pain- ClusterStor has not only been designed with a massively parallel points within the industry: storage IO performance degree of embedded storage servers per rack volume of storage bottleneck. Clearly, traditional storage design with too few capacity, but looking deeper into individual SSU building blocks, storage servers per rack volume are out of balance with the users see the latest generation of server-class processors and file system performance and capacity needs of modern HPC the same design approach as contained in the latest HPC and Big and Big Data scale-out compute architectures. Data scale-out compute nodes. ClusterStor is the result of state of the art optimization of the Lustre file system embedded managing and maintaining traditional Lustre environments using In a ClusterStor system, Scalable Storage Units (SSUs) act as independent I/O processing engines that work in parallel. Each SSU has its within a modular scale-out hardware architecture to address a wide spectrum of HPC off the shelf components from different vendors. own set of resources that includes densely packed disk storage and dual embedded server modules, which also carry their own set of and Big Data application needs. ClusterStor offers solutions to best match your most challenging linear performance and capacity scalability requirements. When you get up close, you can see that ClusterStor is not only innovative in its approach but also delivers a level of quality that translates into higher availability to meet your productivity requirements today and into the future. Problem: Legacy storage metrics are not meaningful at the HPC and Big Data user level. Traditional Lustre file system solutions have typically used a mix of off-the-shelf components from different vendors leveraging legacy storage. Difficulties and roadblocks have been widely reported within the industry due to variances in vendor components Lustre s future is directly tied to its quality and end user productivity success. This is why Xyratex makes significant contributions into Lustre testing, support and community involvement, and why we have honed the processing, memory and I/O network resources. This provides the most efficient use of each resource in a compact design that reduces the space required to deliver each gigabyte of file system performance. best attributes into our tightly optimized environment, eliminating variations and complexity. Broad Applications - Flexible Planning - Easy Deployment The resilient ClusterStor operating environment introduces a scale-out storage and management architecture No matter how small or large your high performance application plan, the ClusterStor family specifically designed to take full advantage of the performance and capacity scaling capabilities of the Lustre provides a wide range of solutions and design methods to best match the file system performance file system. ClusterStor doesn t have to utilize special block-storage algorithms to predict how to provide and/or data storage capacity growth projected throughout the lifetime of your installation. optimal performance, the ClusterStor operating environment knows. In ClusterStor, the operating environment - Delivers best in class ROI acceleration for department level environments is integrated into distributed data storage elements called the Scalable Storage Unit. To best address commercial scientific high resolution simulation and engineering Introducing the Scalable Storage Unit modeling applications, enables parallel data access to attain The Scalable Storage Unit (SSU) is at the heart of ClusterStor s scale-out storage architecture. The ClusterStor limitations associated to legacy midrange solutions relying solely upon serial data SSU consolidates and integrates traditional block storage, network and file system components into a single access Network File System (NFS). specifically enables commercial This traditional approach burdens HPC and Big Data environments with unacceptable program risk due to building block that delivers a linear scaling unit in file system performance and data storage capacity. There is and industrial technical computing users to attain faster job completion, higher the excessive time, expense and non-productive work that constantly disrupts system productivity. What no need to guess at how to scale your Lustre file system: each unit is a balanced performance building block job iteration rates and more precise application insights with higher resolution has previously been considered maintenance is actually waste. Increasing HPC and Big Data productivity delivering a predictable level of performance and/or data storage capacity that scales linearly without storage requirements demand that waste be eliminated. or network degradation. The future of HPC and Big Data data storage requires a paradigm shift from legacy storage systems that focus on Scalable Storage Unit building blocks provide a purpose-built, appliance interacting with separate file system servers and software packages, as well as the constant need to tune and retune file system parameters when attempting to add or even adjust file system processing capacity. attributes like raw block storage capacity, controller cache size, or raw block data transfers. Solution: like method to plan, build and deploy small, medium, or extensively large HPC data storage systems. HPC and Big Data user productivity is the only meaningful metric. File system storage productivity End users simply add SSUs to satisfy their is best measured in sustained end to end file system throughput delivery, as well as reduced datacenter floor performance and/or data capacity needs, space utilization, cooling, power and administrative time. Unfortunately, traditional storage systems on their own all while using built-in optimization, are not able to address these user level attributes. A comprehensive solution paradigm is needed. resilient ClusterStor operating ClusterStor introduces a new standard in end-to-end file system performance and efficiency, at the user level. Truly scaling file system performance efficiently means aggressively reducing the space, power, cooling and time consumed to achieve the HPC and Big Data performance and results users seek. Xyratex has proven that performance, efficiency and end-to-end solution management gains can be realized by consolidating system components closely together within an efficient, reliable and highly integrated scale-out data storage solution. environment, end-to-end solution quality and ease of management. significantly enhanced data processing throughput efficiency, far exceeding accuracy. Highest Concentrated Performance Density Best in Class ROI Acceleration Proven Efficiency, Reliability and Ease of Management Affordable Midrange Solution Maximum Supercomputing Scale Compact and Easy to Use Turnkey Lustre Solution As an easy to use complete turnkey engineered Lustre solution for midrange technical computing users, is designed to deliver no compromise performance and data capacity scalability in an affordable and remarkably compact integrated scale-out solution. - Delivers maximum performance scale for supercomputing environments To best address maximum file system through-put, delivers highest performance and data capacity density per SSU, achieving more concentrated performance per unit data storage capacity, while delivering excellent efficiency, reliability and ease of management. As demonstrated among the industry s largest and fastest supercomputing installations, is designed to collapse and consolidate Lustre file system hardware and software into modular, easy-to-use building blocks, enabling unprecedented linear performance scalability via proven methodical deployment methods with predictable solution results. Compared to legacy Lustre designs, this translates into saving in storage hardware, resulting in lower latencies, higher reliability and reduced power and cooling costs.

Highest reliability, availability and serviceability ClusterStor gets you productive fast with robust professional service offerings available as part of solution delivery, including quality controlled installation, comprehensive early-stage support, personalized training, as well as data migration, configuration and architecture services. Instead of spending weeks gathering separate hardware and software, resolving interoperability issues and testing to get your Lustre environment into production, you can be productive with ClusterStor in hours. ClusterStor includes pre- Easier - Faster - Better installation of all internal software components, configuration of the integrated system and intensive system reliability tests before it ships from the factory. Rather than fight complexity, let the highly The Ultimate in Scale-Out Storage efficient, factory tested and seamlessly integrated ClusterStor solution do the work for you. for HPC and Big Data ClusterStor maximizes your operation time and application availability. Keeping your storage and file system running through scheduled maintenance or production operation upgrades means that you can stay productive. A key aspect to keeping you up and running is ClusterStor s built-in high availability design and comprehensive set of distributed management services. ClusterStor has been designed from the ground up as a highly available enterprise class storage solution with resiliency engineered into all primary subsystems. Meta-data and management server operations are resident on a high availability Cluster Management Unit. Each Scalable Storage Unit includes active/active embedded server modules, redundant and independent system interconnects. ClusterStor Manager removes the management burden of administering tens of petabytes and their traditional complement of deployed Lustre Object Storage Servers. Consolidated and detailed health monitoring and error reporting enables administrators to quickly view and diagnose file system and hardware assets. Software and firmware upgrades across an entire ClusterStor system are executed through ClusterStor Manager, removing the administrative burden and risks that come with large complex Lustre implementations. Xyratex removes all of the pre-upgrade work and testing effort normally associated with upgrades and gives you an ability to roll-back upgrades, if necessary. ClusterStor Manager is a comprehensive system management application that is part of ClusterStor s distributed management framework and is responsible for pulling everything together as a single managed system. ClusterStor Manager consolidates The ClusterStor family of high management of the storage infrastructure, RAID data protection layer, scale-out operating system and the Lustre file system into a performance scale-out storage for single, easy-to-use, administrator interface. From initial installation, creation of file systems, ongoing monitoring and management, HPC and Big Data provides unmatched to expansion and software upgrades, ClusterStor Manager brings the entire storage cluster solution to a single pane. This brings file system performance, optimized unprecedented system visibility to the Lustre system administrator. time to productivity and the HPC Conclusion industry s highest levels in integrated Our attention to architectural balance and keen eye to detail has resulted in the ClusterStor scale-out data storage solution, exactly solution reliability, availability and serviceability. matching the linear file system processing scalability needs for state of the art HPC and Big Data scale-out compute architectures. USA Sales & Support While alternative scale-out data storage designs have appeared on the market, none match the degree of linear scalability and performance-capacity density delivered by the ClusterStor family of integrated high performance scale-out storage solutions for HPC and Big Data. T: +1 877 997 2839 www.xyratex.com Issue 3.0 06/13 UK HQ T: +1 877 XYRATEX T: +44(0)23 9249 6000 Lustre is a registered trademark of Xyratex. Other names may be trademarks of their respective owners. 2013 Xyratex (The trading name of Xyratex Technology Limited). Registered in England & Wales. Company no: 03134912. Registered Office: Langstone Road, Havant, Hampshire PO9 1SA, England. The information given in this brochure is for marketing purposes and is not intended to be a specification nor to provide the basis for a warranty. The products and their details are subject to change. For a detailed specification or if you need to meet a specific requirement please contact Xyratex: www.xyratex.com. Departmental Storage Scale ClusterStor Manager Supercomputing Storage Scale

Highest reliability, availability and serviceability ClusterStor gets you productive fast with robust professional service offerings available as part of solution delivery, including quality controlled installation, comprehensive early-stage support, personalized training, as well as data migration, configuration and architecture services. Instead of spending weeks gathering separate hardware and software, resolving interoperability issues and testing to get your Lustre environment into production, you can be productive with ClusterStor in hours. ClusterStor includes pre- Easier - Faster - Better installation of all internal software components, configuration of the integrated system and intensive system reliability tests before it ships from the factory. Rather than fight complexity, let the highly The Ultimate in Scale-Out Storage efficient, factory tested and seamlessly integrated ClusterStor solution do the work for you. for HPC and Big Data ClusterStor maximizes your operation time and application availability. Keeping your storage and file system running through scheduled maintenance or production operation upgrades means that you can stay productive. A key aspect to keeping you up and running is ClusterStor s built-in high availability design and comprehensive set of distributed management services. ClusterStor has been designed from the ground up as a highly available enterprise class storage solution with resiliency engineered into all primary subsystems. Meta-data and management server operations are resident on a high availability Cluster Management Unit. Each Scalable Storage Unit includes active/active embedded server modules, redundant and independent system interconnects. ClusterStor Manager removes the management burden of administering tens of petabytes and their traditional complement of deployed Lustre Object Storage Servers. Consolidated and detailed health monitoring and error reporting enables administrators to quickly view and diagnose file system and hardware assets. Software and firmware upgrades across an entire ClusterStor system are executed through ClusterStor Manager, removing the administrative burden and risks that come with large complex Lustre implementations. Xyratex removes all of the pre-upgrade work and testing effort normally associated with upgrades and gives you an ability to roll-back upgrades, if necessary. ClusterStor Manager is a comprehensive system management application that is part of ClusterStor s distributed management framework and is responsible for pulling everything together as a single managed system. ClusterStor Manager consolidates The ClusterStor family of high management of the storage infrastructure, RAID data protection layer, scale-out operating system and the Lustre file system into a performance scale-out storage for single, easy-to-use, administrator interface. From initial installation, creation of file systems, ongoing monitoring and management, HPC and Big Data provides unmatched to expansion and software upgrades, ClusterStor Manager brings the entire storage cluster solution to a single pane. This brings file system performance, optimized unprecedented system visibility to the Lustre system administrator. time to productivity and the HPC Conclusion industry s highest levels in integrated Our attention to architectural balance and keen eye to detail has resulted in the ClusterStor scale-out data storage solution, exactly solution reliability, availability and serviceability. matching the linear file system processing scalability needs for state of the art HPC and Big Data scale-out compute architectures. USA Sales & Support While alternative scale-out data storage designs have appeared on the market, none match the degree of linear scalability and performance-capacity density delivered by the ClusterStor family of integrated high performance scale-out storage solutions for HPC and Big Data. T: +1 877 997 2839 www.xyratex.com Issue 3.0 06/13 UK HQ T: +1 877 XYRATEX T: +44(0)23 9249 6000 Lustre is a registered trademark of Xyratex. Other names may be trademarks of their respective owners. 2013 Xyratex (The trading name of Xyratex Technology Limited). Registered in England & Wales. Company no: 03134912. Registered Office: Langstone Road, Havant, Hampshire PO9 1SA, England. The information given in this brochure is for marketing purposes and is not intended to be a specification nor to provide the basis for a warranty. The products and their details are subject to change. For a detailed specification or if you need to meet a specific requirement please contact Xyratex: www.xyratex.com. Departmental Storage Scale ClusterStor Manager Supercomputing Storage Scale