- 1. ESG Lab ReviewOracles Sun Storage 2500-M2 ArrayMixed Workload AnalysisDate: October 2012 Authors: Tony Palmer, Senior ESG Lab Analyst, and Vinny Choinski, Senior ESG Lab AnalystAbstract: This ESG Lab report explores the capabilities of Oracles Sun Storage 2500-M2 array deployed with a cost-effectively optimized, highly available virtual infrastructure thats built with an end-to-end combination of hardwareand software from Oracle.The ChallengesESG asked midmarket (under 1,000 employees) businesses to identify the IT initiatives they believed would be mostimportant to their organization over the next 12-18 months. As shown in Figure 1, 30% of respondents cited increaseduse of server virtualization, and 19% indicated deploying a private cloud infrastructure as their most importantpriorities.1Figure 1. Top Ten Most Important IT Priorities Which of the following would you consider to be your organizations most importantIT priorities over the next 12-18 months?(Percent of respondents, N=246, ten responses accepted)Improve data backup and recovery 37% Major application deployments or upgrades 31% Increased use of server virtualization30%Manage data growth26% Business continuity/disaster recovery programs 26% Desktop virtualization 25% Information security initiatives23% Use cloud infrastructure services20% Deploying a "private cloud" infrastructure 19% Mobile workforce enablement 18% 0%10%20%30%40% Source: Enterprise Strategy Group, 2012.1Source: ESG Research Report, 2012 IT Spending Intentions Survey, January 2012.The goal of ESG Lab reports is to educate IT professionals about data center technology products for companies of all types and sizes. ESG Lab reports are not meantto replace the evaluation process that should be conducted before making purchasing decisions, but rather to provide insight into these emerging technologies. Ourobjective is to go over some of the more valuable feature/functions of products, show how they can be used to solve real customer problems and identify any areasneeding improvement. ESG Labs expert third-party perspective is based on our own hands-on testing as well as on interviews with customers who use theseproducts in production environments. This ESG Lab report was sponsored by Oracle. 2012 by The Enterprise Strategy Group, Inc. All Rights Reserved.
2. ESG Lab Review: Oracles Sun Storage 2500-M2 Array-mixed Workload 2Despite the broad success of server virtualization, issues and challenges remain for IT. As a result, a low percentage ofthe potential workloads that could be virtualized have been migrated to virtual machines, and the consolidation ratios ofvirtual machines per physical servers remains relatively low. An ESG research survey explored the challenges associatedwith the next wave of server virtualization.2 Given the rapid growth in the number of virtual machines being deployed,its no surprise that scalability, performance, and the overall volume of storage capacity have been identified as keychallenges.The Solution: Oracles Sun Storage 2500-M2 ArrayThe Oracle Sun Storage 2500-M2 Array is designed to provide midrange storage functionality and performance, with anaffordable cost of entry. This technology brings together the latest Fibre Channel (FC) and SAS2 technologies withOracles intuitive Sun Storage Common Array Manager software to create a solution thats equally adept in a directattached storage (DAS) or storage area network (SAN) environment for the small or midsize business while integratinginto an existing enterprise storage network. In addition, the 2500-M2s resilient design is ideal for customers such asnetwork equipment providers (NEPs) who are looking for a rugged, NEBS Level 3 certified design.The Oracle integrated IT stack has been developed over a number of years and includes Sun servers and storagehardware. Because it uses an open architecture, its advantages are available even if customers dont use the entirestack. The 2500-M2 takes full advantage of any attached components of the Oracle stack. Organizations choosing theOracle stack can expect the confidence of single vendor support without compromising on performance and availability.Figure 2. The Oracle Sun Storage 2500-M2 Array * With Oracle Performance Enhancer software Oracle Sun Storage 2500-M2The key capabilities of the 2500-M2 Array include:Flexibility Support for direct attachment of up to eight servers via SAS2. Larger server environments can be accommodated with 8GFC SAN connectivity.Resilience2GB of mirrored, battery backed cache memory that is de-staged to flash if the controllers lose power and dual-ported SAS2 drive technology on the backend ensure availability of the array.Data ProtectionOptional software features such as snapshot and volume copy offer enhanced data management and protection.2Source: ESG Research Report, The Evolution of Server Virtualization, November 2010. 2012 by The Enterprise Strategy Group, Inc. All Rights Reserved. 3. ESG Lab Review: Oracles Sun Storage 2500-M2 Array-mixed Workload3 Enhanced Performance The processor has an integrated, high-speed RAID on-chip engine that performs RAID 5 XOR and RAID 6P + Q calculations with no performance penalty, enabling this compute-intensive task to be handled efficiently and effortlessly. Organizations can also realize up to a 2x performance improvement with Turbo models and Oracle Performance Enhancer software. ReliabilityAC/DC power options combined with NEBS Level 3 certification make Oracles Sun Storage 2500- M2 array ideal for network equipment providers (NEPs) and/or rugged environments. Ease of ManagementSun Storage Common Array Manager makes the 2500-M2 simple to deploy and manage with an intuitive user interface.ESG Lab TestedThe Oracle Sun Storage 2500-M2 storage system was tested by ESG Lab in Oracles Broomfield, Colorado facility. Themethodology presented in this report was designed to assess the mixed workload performance and manageability of a2500-M2 in virtual server and consolidated application environments.Getting StartedThe ESG Lab test bed is depicted in Figure 3. Two Sun X4470 servers were attached to an Oracle Sun Storage 2500-M2array via an 8GFC SAN. The servers were running Oracle VM Server 3.1.1 and hosted Windows Server 2008, OracleEnterprise Linux, and Oracle Solaris on eleven virtual machines. The 2500-M2 had 48 300GB 15K RPM SAS drivesinstalled. Figure 3. The ESG Lab Test BedESG Lab TestingESG Lab began with a look at the OVM Manager administration GUI, which gives a simple, high-level overview of servers,virtual machines, statuses, and component configurations. As shown in Figure 4, ten Windows and two Linux VMs wererunning in the environment. The Linux machines were used to emulate Oracle 11GB database servers, and the Windowsmachines were used to simulate e-mail, web, and virtual desktop servers. 2012 by The Enterprise Strategy Group, Inc. All Rights Reserved. 4. ESG Lab Review: Oracles Sun Storage 2500-M2 Array-mixed Workload 4Figure 4. Oracle VM ManagerNext, ESG Lab took a look at the Sun Storage Common Array Manager, and reviewed the LUNs created for testing. TheCommon Array Manager uses a tree-based presentation model when navigating systems, physical devices, volumes,snapshots, and virtual disks. The interface is clean and intuitive, providing easy access to all features and functionality, asshown in Figure 5Figure 5.Figure 5. Sun Storage Common Array ManagerVirtualizing Business-Critical ApplicationsConventional server benchmarks were designed to measure the performance of a single application running on a singleoperating system inside a single physical computer. SPEC CPU2000 and CPU2006 are well known examples of this typeof server benchmarking tool. Much like traditional server benchmarks, conventional storage system benchmarks weredesigned to measure the performance of a single storage system running a single application workload. The SPC-1benchmark, developed and managed by the Storage Performance Council, is a great example. 3 SPC-1 was designed toassess the performance capabilities of a single storage system as it services an online interactive database application.Traditional benchmarks running a single application workload cant help IT managers understand what happens when amix of applications are deployed together in a virtual server environment. The methodology developed by ESG Lab and3http://www.storageperformance.org 2012 by The Enterprise Strategy Group, Inc. All Rights Reserved. 5. ESG Lab Review: Oracles Sun Storage 2500-M2 Array-mixed Workload5presented in this report was designed to stress the storage system more than the servers. A tile-based concept wasused. Each tile is composed of a mixture of four application workloads. Two physical servers, each configured with sixvirtual machines, were used to measure performance in two tests, as the number of active tiles was increased from oneto three.WorkloadsIndustry standard benchmarks were used to emulate the I/O activity of four common business application workloads: E-mail: The Microsoft Jetstress 2010 utility was used to generate e-mail traffic. Similar to the MicrosoftLoadGen utility used in the VMmark benchmark, Jetstress simulates the activity of typical MicrosoftExchange users as they send and read e-mails, make appointments, and manage to-do lists. The Jetstressutility is, however, a more lightweight utility than LoadGen. Using the underlying Jet Engine database,Jetstress was designed to focus on storage performance. Database: The Orion utility from Oracle was used to generate database traffic. Much like Jetstress, Orion is alightweight tool that is ideally suited for measuring storage performance. Orion was designed to helpadministrators understand the performance capabilities of a storage system, either to uncover performanceissues or to size a new database installation without having to create and run an Oracle database. Orion istypically used to measure two types of databas