1 Microsoft SharePoint Server 2010 Medium Farm Solution Performance Study Dell SharePoint Solutions Ravikanth Chaganti and Quocdat Nguyen August 2010
2 THIS WHITE PAPER IS FOR INFORMATIONAL PURPOSES ONLY, AND MAY CONTAIN TYPOGRAPHICAL ERRORS AND TECHNICAL INACCURACIES. THE CONTENT IS PROVIDED AS IS, WITHOUT EXPRESS OR IMPLIED WARRANTIES OF ANY KIND Dell Inc. All rights reserved. Reproduction of this material in any manner whatsoever without the express written permission of Dell Inc. is strictly forbidden. For more information, contact Dell. Dell, the DELL logo, PowerEdge, and EqualLogic are trademarks of Dell Inc. Microsoft, Windows, Windows Server, Visual Studio and SharePoint are either trademarks or registered trademarks of Microsoft Corporation in the United States and/or other countries. Intel and Xeon are registered trademarks of Intel Corporation. Other trademarks and trade names may be used in this document to refer to either the entities claiming the marks and names or their products. Dell Inc. disclaims any proprietary interest in trademarks and trade names other than its own. August
3 Executive Summary A Microsoft SharePoint Server 2010 farm hosts the core platform services and applications that provide many different functions for its users. A classical three-tier (Web, Application, Database) model, or farm, architecture is usually used for SharePoint Server Understanding sizing of each of the tiers of a SharePoint farm requires a comprehensive study of the workload requirements and performance capabilities of each hardware component. This white paper includes such a comprehensive study and describes how a medium SharePoint farm, built using Dell PowerEdge blade servers and Dell EqualLogic storage, performed under load testing. It is a priority for Dell to be able to provide accurate guidance to customers when recommending infrastructure elements of a SharePoint implementation. Through our testing, we have provided guidance on how to increase performance and help keep client response times under one second. Dell s SharePoint engineering team developed a load generation framework to perform this load testing so that we would be able to share these results with our customers. This data is being provided to our customers to help them understand the performance impact of several SharePoint workloads, and how to size and design the best farm architecture to support these workloads. The paper details information on how the farm was configured, some of the factors considered while designing the farm, how Dell performs SharePoint load testing, and finally provides several performance metrics of various farm components. This paper also details information on how the recommended farm architectures could support more than users and achieve sub one second response times. Performance benefits of the new generation of full-height blade servers Dell PowerEdge M910 and its Nehalem EX series processors are also highlighted. A companion paper, SharePoint Server 2010: An Introduction, is available from This paper offers an overview of SharePoint Server 2010, and provides common concepts and definitions that form a good basis for understanding the reference architecture presented in this paper. Another companion paper, SharePoint 2010: Designing and Implementing a Medium Farm, is also available from This companion paper provides the reference architecture and infrastructure best practices for implementing a SharePoint 2010 medium farm. These reference architectures formed the basis of the performance study described in this paper. 3
4 Table of Contents Executive Summary... 3 Introduction... 5 SharePoint 2010 Farm Topologies... 5 Medium Farm Topology... 6 Dell PowerEdge M1000e Blade Enclosure... 8 Dell PowerEdge M Dell PowerEdge M Dell PowerEdge M Dell EqualLogic PS6000XV Storage Arrays Farm Architecture and Configuration of Farm Roles Configuration of Web Front-end and Application Servers HTTP Request Throttling Search Service Application Configuration Network Configuration Configuration of Database Servers SQL Server Memory Configuration DB Server Network Configuration Performance Study of a Medium Farm Dell SharePoint Load Generation Framework Content Population Tool VSTS Load Testing Framework Load Testing Workload Test Mix Test Methodology Performance Results & Analysis Summary References
5 Introduction Microsoft SharePoint Server 2010 builds on the capabilities that were offered in Microsoft Office SharePoint Server 2007 to provide a rich platform for collaboration, information sharing, and document management. SharePoint 2010 adds several new features and introduces important architectural changes and product improvements. Capacity planning for a SharePoint farm deployment needs a thorough study of the existing requirements and future growth. A SharePoint implementation can be used in several ways including custom developed applications. This brings in the complexity factor while sizing the servers and storage for a SharePoint implementation. There are, however, the six pillars 1 that can be used to create clarity around how SharePoint will be used. This performance study paper intends to provide performance capacity details of two SharePoint 2010 medium farms configured with Dell PowerEdge blade servers and Dell EqualLogic iscsi storage in the context of SharePoint collaboration 2. SharePoint 2010 Farm Topologies A SharePoint server farm is a set of servers which collectively provide the services needed by a SharePoint deployment. Some of these services, or sets of services, comprise predefined roles and must be configured within the solution. Other services and components are optional, but they provide additional features and functionality that are often desirable. These optional components may include some of the service applications such as managed meta data service, Excel services, and etc. There are some constraints and best practices that help determine which components should be located on each server in the farm. Also, by considering how the components are distributed, the farm can be designed to more easily accommodate later growth. NOTE: In SharePoint Server 2010, components generally provide functionality for a given service application. As a result, this paper may use the terms role and component interchangeably. In this context, SharePoint roles refer to one or more components that provide a farm service, and should not be confused with Windows Server roles, which generally include one or more Windows services to provide operating system functionality. The size and capacity of a SharePoint 2010 implementation can vary based on several factors such as number of concurrent users, service application in the farm, the expected uptime service level agreement (SLA), and etc. These factors dictate how many servers are needed in the SharePoint farm and how the overall farm architecture looks. Based on the these factors, SharePoint 2010 farm implementations can be classified in to small farm 3, medium farm and a large farm 4 deployments. 1 SharePoint capabilities SharePoint collaboration capabilities SharePoint 2010 Designing and Implementing a Small Server Farm 4 SharePoint 2010 Designing and Implementing a Large Farm 5
6 Medium Farm Topology A typical SharePoint medium server farm 5 consists of three tiers: Web front-end, application, and database. Dedicated servers are used to host each tier to provide process isolation and to allow for future growth. A server farm deployment model helps ensure that the solution infrastructure is scalable, flexible, and resilient to hardware failures. To achieve these goals, a medium farm implementation uses multiple servers at all tiers of the farm deployment. The farm model uses a dedicated database server, employs one or more application servers, and generally distributes Web front-end server roles across multiple hosts. This performance study paper used the SharePoint 2010 medium farm architecture to understand how several components of a farm perform at incrementing user loads. Within the scope of this paper, two farm configurations were used to study the performance characteristics of SharePoint 2010 on Dell servers and storage. Figures 1 and 2 depict the reference architecture of the two farms used in this performance study. Figure 1 Farm Configuration 1 M710 as DB Server (For Illustration Only) 5 SharePoint 2010 Designing and Implementing a Medium Farm 6
7 Figure 2 Farm Configuration 2 M910 as DB Server (For Illustration Only) As shown in Figures 1 and 2, the two farm configuration used in the performance study employed Dell PowerEdge blade servers in a Dell PowerEdge M1000e blade enclosure at all tiers and Dell EqualLogic storage arrays for the database backend. These two SharePoint farms are identical at all tiers except the database tier. Farm configuration 1 (Figure 1) used Dell PowerEdge M710 for the DB backend and Dell PowerEdge M910 server was used in farm configuration 2 (Figure 2) for the DB backend. The choice of two server models for database tier provides an opportunity to compare the performance differences when using Dell PowerEdge M710 and Dell PowerEdge M910. These two are full-height blade servers designed for performance intensive applications and compute-intensive business critical applications. In addition, the M910 blade server is equipped with 4 socket Intel Xeon 7500/6500 Series processors which include up to 8 cores per CPU. This provides great scalability for future growth of the farm. Table 1 provides an overview of server and storage hardware used in these two farm deployments. Table 2 provides complete configuration details of each server used within the two farm configurations shown in Table 1. 7
8 Table 1 Overview of Farm Configuration Blade Chassis (1) M1000e with (2) Ethernet pass-through modules Farm Configuration 1 Farm Configuration 2 (1) M1000e with (2) Ethernet pass-through modules Web front-end Servers Application Servers Database Servers Storage Arrays Three Dell PowerEdge M710 Servers Two Dell PowerEdge M610 Servers Two Dell PowerEdge M710 Servers Two Dell EqualLogic PS6000XV Arrays Three Dell PowerEdge M710 Servers Two Dell PowerEdge M610 Servers Two Dell PowerEdge M910 Servers Two Dell EqualLogic PS6000XV Arrays Table 2 Blade Server Configuration Details Blade Server Configuration Server Role Web front-end Application Server Database Server (Farm Database Server (Farm 2) 1) Server M710 M610 M710 M910 Model Processor Two Intel Xeon X GHz, Two Intel Xeon X GHz, 12MB cache Two Intel Xeon X GHz, 12MB cache Two Intel Xeon L GHz, 18MB cache (Nehalem EX, 4S) 12MB cache Memory 12GB (6 x 2GB, DDR3) 12GB (6 x 2GB, DDR3) 24GB (6 x 4GB, DDR3) 32GB (8 x 4GB, DDR3) Local storage Drives 2 x RAID 1 connected to SAS 6i 4 x 146GB, 15K RPM SAS Drives 1 x RAID 1 connected to SAS 6i 2 x 146GB, 15K RPM drives 2 x RAID 1 connected to SAS 6i 4 x 146GB, 15K RPM SAS Drives 1 x RAID 1 connected to SAS 6i 2 x 146GB, 15K RPM SAS Drives Network Controller Two Broadcom LOMs in a load balancing team Two Broadcom LOMs in a load balancing team 2 x Two Broadcom LOMs for Public and iscsi network connections 2 x Two Broadcom LOMs for Public and iscsi network connections The following sections describe the servers chosen for each of the farm roles and provide a technical overview of the servers used in this performance study. Dell PowerEdge M1000e Blade Enclosure The PowerEdge M1000e modular blade enclosure is the foundation for Dell s blade server architecture, providing one of the most energy efficient, extremely reliable, flexible, and manageable blade server platforms in the market for building any IT infrastructure. Flexible and scalable, the M1000e is designed to support future generations of blade technologies regardless of processor/chipset architecture. The M1000e is optimized for use with all Dell PowerEdge Blades including the M610, M710 and M910 blades servers. Features include: 8
9 Energy Efficiency: M1000e is built on Dell s energy smart technology which can help customers to increase capacity and to lower operating costs while delivering better performance/watt. Effortless Scalability: with scale on-demand switch design and additional I/O slots and switch options, the M1000e provides a flexibility to meet the increasing demand for I/O consumption. Plus, Dell s FlexIO modular switch technology offers a great scalability. Powerful Management Tool: M1000e includes centralized management controllers, dynamic power management, and real-time reporting service for IT administrators to manage and monitor multiple enclosures and blades from a single console. As shown in Figure 1, this performance study paper used a PowerEdge M1000e blade enclosure with five PowerEdge M710 full-height blades, two PowerEdge M610 half-height blades, and two Dell Ethernet pass-through IO modules for network connectivity. Figure 3, which is not an actual representation of blade server, shows how the network connections map from the blade servers to the I/O modules at the rear of the chassis. Figure 3 Blade Server to I/O Module Mapping As shown in Figure 3, two network connections from each blade were configured in a team to increase the overall network bandwidth and to provide failover. The database server used two LOM connections with MPIO for the iscsi storage network and two more LOMs in a team for the farm network. Dell PowerEdge M610 The PowerEdge M610 6 is a two-socket, half-height blade server that supports up to 192GB of physical RAM with 12 x 16GB DDR3 DIMMs. The M610 blade server supports the latest quad-core and six-core Intel Xeon processors and up to two internal SAS disk drives. This server supports a maximum internal disk storage capacity of 600GB when using 2 x 300GB, 10K RPM SAS drives in a RAID 0 configuration. 6 Dell PowerEdge M610 blade server spec sheet - 9
10 Within the scope of this performance study paper, the M610 blade server was used for the application server role running the crawler service. Both the farm configurations (as shown in Figures 1 and 2) used 2 x 146GB, 15K RPM SAS drives connected to a SAS 6iR controller and configured in a RAID 1 for the OS disk. With the new search architecture, SharePoint 2010 does not store the index content on the application server and hence reduces the needs for disk space on the application server. This along with higher processor and memory capacity makes the PowerEdge M610 the best choice for an application server running crawler role. Dell PowerEdge M710 The PowerEdge M710 7 is a two-socket, full-height blade server with support for up to 192GB of physical RAM and the latest quad-core and six-core Intel Xeon processors. The M710 supports a maximum internal disk storage capacity of 1.2TB when using 4 x 300GB, 10K RPM SAS drives in a RAID 0 configuration. The PowerEdge M710 has more PCIe expansion slots (4) than M610 (2). This server supports up to four 1GB network connections without using any additional expansion cards. Within the scope of this performance study paper, the PowerEdge M710 server was used at the web front-end, database tiers of farm configuration 1 (Figure 1) and web front-end tier of farm configuration 2 (Figure 2). At all tiers and in both farm configurations, 4 x 146GB, 15K RPM drives were used and configured as two RAID 1 volumes. Dell PowerEdge M910 The PowerEdge M910 8 is a four-socket, full-height blade server with support of up to 512GB of physical RAM (32 x 16GB DDR3 DIMMs) and the latest quad, six and eight core Intel Xeon 7500/6500 series processors. This server supports maximum of 2 internal SAS disk drives and hence the maximum internal storage capacity is 600GB when using 2 x 300GB, 10K RPM SAS drives in a RAID 0 configuration. Similar to the PowerEdge M710, the M910 also supports four 1GB network ports without any additional I/O expansion cards. Within the scope of this performance study paper, the PowerEdge M910 server was used at the database tier of farm configuration 2 (Figure 2). The enormous processing power and physical memory capacity makes this server the best choice for a database server. Dell EqualLogic PS6000XV Storage Arrays The Dell EqualLogic PS6000XV is a virtualized iscsi storage area network (SAN) that combines intelligence and automation with fault tolerance to provide simplified administration, enterprise performance and reliability, and seamless scalability. A PS Series array provides the following features: No-single-point-of-failure hardware: o Redundant, hot-swappable hardware components disks, control modules, fans, and power supplies. o Component failover and disk sparing occur automatically without user intervention or disrupting data availability. o RAID technology provides data protection in each array. 7 Dell PowerEdge M710 blade server spec sheet Dell PowerEdge M910 blade server spec sheet
11 High-performance control modules: The PS6000 control module has four 1 Gigabit Ethernet interfaces. Support for standard Gigabit Ethernet networks. 9.In this SharePoint 2010 farm configuration, two PS6000XV arrays each with sixteen 15K RPM, 300GB SAS drives were used. These 32 drives in a single RAID10 storage pool provide sufficient I/O bandwidth and capacity for the SharePoint databases 9 in a medium SharePoint farm. Farm Architecture and Configuration of Farm Roles Both the experimental farms used the same physical architecture, as shown in Figures 1 and 2, with three WFEs, two application servers and two database servers in a failover cluster. Both farms were configured to use Windows authentication and hence all the requests during the load test were authenticated requests. The farm servers at all tiers used teamed network connections to provide load balancing and failover capabilities. Table 3 lists the OS and software editions used in the above farm configurations. The rationale for choosing this matrix is explained in the later sections of this paper. Table 3 OS and Software Editions Used in This Study Operating System Windows Server 2008 R2 Enterprise Edition SharePoint Server Web front-ends Application Servers Database Servers SharePoint Server 2010 Standard Edition Windows Server 2008 R2 Enterprise Edition SharePoint Server 2010 Standard Edition Windows Server 2008 R2 Enterprise Edition Database Server NA NA SQL Server 2008 R2 x64 Standard Edition NA Note: Step-by-step instructions for installing and configuring a SharePoint farm and any service applications used in this performance study are outside the scope of this performance study paper. For more information and resources, refer to the References section at the end of this paper. Configuration of Web Front-end and Application Servers The SharePoint 2010 farm design includes three web front-end servers. The software matrix for these web front-end servers is shown in Table 3. SharePoint 2010 Standard edition used in the performance study included only out-of-the-box features of SharePoint and a collaboration workload only. As a part of the collaboration workload, only search service application was deployed and no other service applications such as Excel services or Visio Services were deployed. All the web front-end servers were configured in an Network Load Balancing (NLB) cluster 10. Using NLB, stateless applications like SharePoint web front-end can be made scalable by adding additional servers 9 SharePoint Database types NLB Deployment guide
12 when the load increases. Since the network connections were redundant by using Broadcom NIC teaming, NLB was configured to use multicast mode to avoid IP address conflicts 11 in the farm. On both the PowerEdge M710 and M610 blade servers, simultaneous multi-threading or logical processor support was enabled for increased performance. This option is disabled by default in the system BIOS and needs to be enabled manually. HTTP Request Throttling SharePoint 2010 offers resource throttling features that can be configured to help increase server performance and protect server resources during peak usage times. SharePoint 2010 has a default timer job that checks server resources compared to configured throttle levels. By default, Server CPU, Memory, Request in Queue, and Request Wait Time are monitored. After three unsuccessful checks, the server enters a throttling period and remains in this state until a successful check is completed. Requests generated prior to the server's entering throttling mode are completed. Any new HTTP GET and Search Robot requests generate a error message and are logged in the event viewer. The throttle settings can be modified to increase the overall load supported by the farm servers. However, this itself requires a complete study to be able to determine accurate throttle setting recommendations for any given user load or requests per second. The default HTTP throttle monitor settings prevent an extensive load testing to find out the real capacity of the farm servers. Hence, HTTP request throttling was turned off during the load testing of SharePoint. Search Service Application Configuration SharePoint 2010 changed the search architecture and introduced high availability at the application tier or crawler. The new search service application architecture in SharePoint 2010 includes greater redundancy. The new design provides flexibility and allows the query and crawler roles to be scaledout separately on an as-needed basis. Search crawlers are now stateless; they do not store a copy of the index. The index does, however, still propagate and is stored locally on the query servers. Two application servers hosting the crawler role were used in this performance study. The query role was hosted on two web front-end servers to provide better availability and improved search performance. Both farm configurations used the same search service application configuration as shown in Figure 4. Two application servers hosted the crawler role and the index partitions from these two crawlers were placed on two web front-end servers. On all web front-ends, a dedicated RAID 1 volume stored the index content. The two servers at the application tier provide redundancy for the crawler role and improve the overall crawl performance during content indexing. 11 Using teaming adapters with network load balancing may cause network problems Throttling starts alert- Events
13 Figure 4 Search Service Application Configuration As shown in Figure 4, the first two web front-ends provide redundant search index and the third frontend was used to increase the overall user load supported by the farm configuration. This also brings in high availability at the web front-end tier. However, in case of a front-end failure, the overall capacity and performance of the farm would degrade. Network Configuration On the PowerEdge M1000e blade chassis, two Dell Ethernet pass-through modules were used. For both the web front-end servers and applications servers, teamed network connections were used. These teamed connections (shown in Figure 3) were configured to be in the smart load balancing mode (SLB) which supports both load balancing and failover. Configuration of Database Servers As shown in Figures 1 and 2, this performance study paper deployed PowerEdge M710 and M910 blade servers as the database servers in the two farm configurations described earlier. Two DB servers were deployed in a fail-over cluster to enable redundancy at the database tier of the SharePoint farm. A SharePoint farms performance depends on the performance of the database server and the database backend. The PowerEdge M710 and M910 blade servers are the best choice for hosting the SQL database. The PowerEdge M710 supports four internal disk drives and in farm configuration 1; two drives in a RAID 1 configuration were dedicated to host the SQL instance. However, in the case of farm configuration 2, the PowerEdge M910 supports only 2 internal drives; therefore, the SQL instance had to be hosted on external EqualLogic storage arrays. In both the farm configurations to add performance and storage capacity, two EqualLogic PS6000XV storage arrays were used. These arrays were configured to be in the same storage pool and provided 32 SAS drives configured in a RAID 10 for storing the SharePoint content. 13
14 Figure 5 SharePoint 2010 Database Layout SQL Server Memory Configuration By default, SQL Server uses all available physical memory 13 since SQL Server dynamically grows and shrinks the size of its buffer pool depending on the physical memory reported by the operating system. This behavior can be adjusted to limit the amount of physical memory used by SQL Server. Within the scope of this paper, SQL server memory was limited to 80% of the actual physical memory available in the system. For example, on the PowerEdge M710 blade server used at the DB tier, out of 24GB of physical memory, 19.6GB was allocated to SQL server. DB Server Network Configuration Similar to the web front-end and application tiers, the database tier also used teamed network connections for the farm network as shown in Figure 3. For the iscsi storage network, two LOM connections were dedicated and MPIO was configured to provide load balancing and fail-over. Performance Study of a Medium Farm Microsoft SharePoint 2010 is a versatile platform that can be used in a large variety of ways. Some SharePoint workloads work almost out of the box, others require or allow significant customization, and still others are the result of completely custom developed applications. This flexibility results in thousands of possible ways of using SharePoint which makes it nearly impossible to accurately size servers and storage for a SharePoint farm. Also, there is no standard benchmark for sizing SharePoint workloads as of yet. It is very important to be able to provide accurate guidance to customers when recommending infrastructure elements of a SharePoint implementation. This led to the development of the Dell SharePoint Load Generation framework used to perform load testing of a SharePoint farm. Dell SharePoint Load Generation Framework An internally developed load generation framework was used to understand the performance characteristics of the SharePoint farm. This framework includes load testing of SharePoint out of the box usage profiles such as collaboration and publishing. The Dell SharePoint load generation framework has two components a content population tool and Visual Studio Team Suite (VSTS) web test framework. Content Population Tool The content population tool is designed to prepare the SharePoint farm for load testing. This content population tool distributes the SharePoint content across multiple site collections. Figure 6 shows the user interface for the content population tool. 13 SQL Server memory options
15 Figure 6 SharePoint Content Population Tool The content population tool performs the following functions: Creates SharePoint web applications Creates site collections Adds web parts to home pages Creates document libraries Creates SharePoint list items Uploads documents/images, etc. This utility is capable of populating hundreds of gigabytes of SharePoint content within few hours. The size of SharePoint content DB and other aspects such as number of site collections, etc., vary based on the usage profile selection. A usage profile is a collection of use cases closely mapped to real world SharePoint usage. To some extent, these usage profiles were mapped into the SharePoint Capacity Planner 14 and other Microsoft recommendations. Although SharePoint Capacity Planner was intended for MOSS 2007, there are several aspects of these recommendations 15 that still apply to SharePoint 2010 out of the box workloads. The content generated and uploaded by the content population tool serves as a baseline for SharePoint 2010 load testing using Visual Studio test framework. VSTS Load Testing Framework Dell s SharePoint load generation framework uses VSTS 2008 to perform load testing. Within VSTS, each load test maps directly into a SharePoint usage profile and each usage profile defines a list of use cases and how may use cases are run per hour per connected user. Using VSTS 2008 helps in rapid creation of use cases and to parameterize those use cases. SharePoint load testing is performed using a test rig (shown in Figure 7) of several physical test agents and the results are captured in to a SQL database on the test controller. 14 SharePoint capacity planner - e71493b2fd87&displaylang=en 15 Microsoft SharePoint 2010 performance and capacity management
16 VSTS Test Rig Test Controller Start Test Agent 1 Agent 2 Agent 3 Agent 4 Agent 5 Agent 6 Agent 7 Agent 8 Agent 9 Agent 10 Run Test NLB Cluster Web Server Web Server Web Server SharePoint Farm Application Server Database Server Figure 7 VSTS Test Rig for SharePoint Load Testing Load Testing Workload Test Mix As mentioned earlier, the load test usage profiles were based on the SharePoint Capacity Planner (SCP) and other Microsoft recommendations for SharePoint System Center SharePoint capacity planner defines several usage profiles for both collaboration and publishing workloads. These usage profiles are categorized in to low, medium and heavy usage profiles. These categories define several aspects of a usage profile such as how many requests are sent per hour per connected user, what use cases constitute a load test, and what percentage (test mix) of each use case is used within each load test. Within the scope of this performance study, heavy collaboration usage profile was used. Table 4 shows the heavy collaboration test mix as suggested by SCP. Table 4 SCP Usage Profile Definition SCP Usage Profiles Heavy Collaboration Home Page Access (%) 30 List Page Access (%) 20 Document/Picture Download (%) 15 Document/Picture Upload (%) 8 Search (%) 15 Total requests/hour/connected user 60 As shown in Table 4, SCP defines only a high-level test mix for each usage profile. Table 5 shows a more granular translation of this SCP heavy collaboration usage profile. Several use cases were mapped 16
17 in to each of the categories described by SCP and the number of use cases per hour per connected user has been assigned. Table 5 Dell's Test Mix for a Heavy Collaboration Profile Heavy Collaboration Test Mix Home Page Access Number of tests/hr/user Read Site Home Page 18 List Page Access Read Survey 6 Read Lists 6 Document/Picture Download Read Document Library 2 Read Home to Document Library 1 Read Wiki Page 2 Read Picture Library 1 Read Home to Wiki Page 2 Read Home to Picture Library 1 Document/Picture Upload Search Create Wiki Page 3 Upload Document 2 Search Site 10 List Item Insertion/Deletion Respond to Survey 2 Reply to Discussion Topic 1 Edit Wiki Page 2 Comment home to blog post 1 Total tests/hour/connected user 60 It is important to note that Dell s test mix (shown in Table 5) is not a one-to-one mapping into the SCP and Microsoft recommendations stated above. For example, SCP defines total requests per hour per connected user. Within Dell s test mix for the heavy collaboration profile, this translates into more requests than 60 per hour as the usage profile uses 60 tests per hour per connected user. And, each test could mean more than one request. Hence, the results published in this paper may or may not map directly in to SCP recommendations directly and are specific to the workload mix defined in Table 5. Test Methodology The intent of the experiments conducted as a part of this performance study was to understand the capacity of a medium SharePoint farm as shown in Figures 1 and 2 with configurations described in Table 2. Several load test iterations were conducted with incrementing user load. Initially, a user load of 500 virtual users was used and then it was incremented by 500 users until the farm resources reached an optimal level of utilization. The overall goal of the load test was to ensure that the 17
18 processor utilization remained below 60% and the average farm response time was less than one second. The data set used to build the content database included several different types of files including Microsoft Office documents, Adobe PDF documents and several image formats. Table 6 shows a distribution of file content sizes used in this performance study. Average File size Table 6 File Content Sizes Number of files 1KB to 500KB KB to 1MB MB to 10MB MB to 70MB 125 The aggregated SharePoint content database size was around 53GB. During the load test duration, this content DB grew by almost 20%. This performance study involved load testing of out-of-the-box SharePoint deployment using a test mix shown in Table 5. A full content crawl was performed once at the beginning of the load tests. There were no subsequent crawls after load test or during the load test duration. The performance data shown in this paper was a result of load testing on the final configuration of a SharePoint farm as described in Table 2. The following sections of this paper described the performance data and how several components within the farm performed at increment user loads. Performance Results & Analysis As a part of this performance study, several performance metrics were collected and analyzed. Based on the results, the farm configurations were tweaked to reach the final farm configuration shown in Figures 1 and 2. This section describes the performance data and how the two farm configurations differ in overall performance. As mentioned earlier, this study included only collaboration workload. All the results shown here are relative to the workload and may differ with any other implementation outside of the test mix shown in Table 5.Table 7 shows how the two farm configurations differed in performance metrics such as overall concurrent user load and requests per second. 18
19 Table 7 Farm Performance Comparison Farm Configuration 1 Farm Configuration 2 Maximum concurrent user load supported Requests per second 16 at Max concurrent user load 5,000 7, Farm configuration 1 with the PowerEdge M710 as DB server could support up to 5,000 concurrent users; farm configuration 2 with the PowerEdge M910 as DB server could scale up to 7,000 concurrent users. As mentioned earlier, one of the goals of this performance study was to build a farm with average SharePoint farm response time below one second. The following figures show the farm response time for both configurations and the average response time metrics for several user loads. ` Figure 8 Average Response Time - Farm 1 16 This number indicates the average requests per second generate during the load test duration. This is a VSTS reported metric. 19
20 Figure 9 Average Response time - Farm 2 The average processor utilization on the web front-end servers in both farm configurations was below 50% even at the maximum user load. Since NLB was used at the web front-end tier, all WFEs were more or less equally loaded. Figure 10 Percentage of Processor Utilization - Farm 1 20
21 Figure 11 Percentage of Processor Utilization - Farm 2 As shown in the above charts, there is enough capacity available for future growth. However, in a heavily loaded scenario, even though the average processor utilization is below 50%, farm configurations 1 and 2 may not support more number of users than shown here. This is mainly because of the ASP.NET and IIS request queue length limitations. In such a scenario, adding a fourth web frontend can resolve the bottleneck. The application tier servers were hosting only the crawler role and therefore, these servers were not used during load testing. The servers mainly were employed for content crawling which usually occurs during non-peak hours. The overall network utilization was well within 50% of the total available bandwidth, in this case 2 GBs. The following charts capture the network utilization at web front-end and database tiers of the farm. Figure 12 Network Utilization - Farm 1 21
22 Figure 13 Network Utilization - Farm 2 In addition, performance results show that the maximum memory utilization on the web front-end servers at the maximum user load was within 50% of the available physical memory. This indicates that there is enough room for future growth and scalability. Overall, farm configurations 1 and 2 were capable of supporting approximately 50,000 users with a minimum of 10 percent concurrency. Summary A companion paper, SharePoint Server 2010: An Introduction, is available on That paper provides a high-level overview of SharePoint Server 2010, and introduces key concepts and terminology that are helpful for understanding the reference architectures presented in this paper. A medium SharePoint 2010 farm consists of several servers, each of which is provisioned with different SharePoint components. Three-tier architectures are recommended featuring a presentation tier that provides Web and search query functions, an application tier that provides search indexing and service application functions and a database tier that hosts the SQL Server databases for the farm. SharePoint 2010 can be used in many different ways and each implementation needs an in-depth study of requirements such as expected user load, requests per second and future growth. This performance study paper was intended to understand the performance capacity of SharePoint medium farm configurations built using Dell PowerEdge blade servers and Dell EqualLogic iscsi storage. This study showed that both the configurations, as illustrated above, could support approximately 50,000 users with a minimum concurrency of 10 percent. Also, in both the farm configurations, the average farm response time was well below one second. The farm configuration that used the PowerEdge M910 at the database tier could support more number of users, almost 70,000 users with minimum 10 percent 22
23 concurrency, than the farm with M710 as the DB server. This is essentially because of the performance benefits of a four socket Nehalem EX and the memory architecture improvements in Dell PowerEdge M910. References Dell SharePoint solutions: Microsoft SharePoint page: Microsoft SharePoint Technet: For EqualLogic documents: For PowerEdge blade server documents: Updates for SharePoint 2010 products: Deploying multiple servers in a three-tier farm: 23
Best Practices for Deploying SSDs in a Microsoft SQL Server 2008 OLTP Environment with Dell EqualLogic PS-Series Arrays Database Solutions Engineering By Murali Krishnan.K Dell Product Group October 2009
Microsoft SharePoint Server 2010 Designing and Implementing a Medium Farm Dell Solutions Engineering Ravikanth Chaganti and Kevin Guinn May 2010 Executive Summary A SharePoint Server 2010 farm hosts service
Microsoft SharePoint Server 2010 Designing and Implementing a Small Server Farm Dell Solutions Engineering Ravikanth Chaganti and Kevin Guinn May 2010 Executive Summary A Microsoft SharePoint Server 2010
Dell EqualLogic Best Practices Series Reference Architecture for a Virtualized SharePoint 2010 Document Management Solution A Dell Technical White Paper Storage Infrastructure and Solutions Engineering
Reference Architecture EMC PERFORMANCE OPTIMIZATION FOR MICROSOFT FAST SEARCH SERVER 2010 FOR SHAREPOINT Optimize scalability and performance of FAST Search Server 2010 for SharePoint Validate virtualization
Microsoft SharePoint Server 2010 Designing and Implementing a Large Farm Dell Solutions Engineering Ravikanth Chaganti and Kevin Guinn May 2010 Executive Summary A Microsoft SharePoint Server 2010 farm
Dell Virtualization Solution for Microsoft SQL Server 2012 using PowerEdge R820 This white paper discusses the SQL server workload consolidation capabilities of Dell PowerEdge R820 using Virtualization.
Dell High Availability Solutions Guide for Microsoft Hyper-V www.dell.com support.dell.com Notes and Cautions NOTE: A NOTE indicates important information that helps you make better use of your computer.
DELL Dell Microsoft Windows Server 2008 Hyper-V TM Reference Architecture VIRTUALIZATION SOLUTIONS ENGINEERING September 2008 1 THIS WHITE PAPER IS FOR INFORMATIONAL PURPOSES ONLY, AND MAY CONTAIN TYPOGRAPHICAL
Dell Compellent Storage Center SAN & VMware View 1,000 Desktop Reference Architecture Dell Compellent Product Specialist Team THIS WHITE PAPER IS FOR INFORMATIONAL PURPOSES ONLY, AND MAY CONTAIN TYPOGRAPHICAL
Reference Architecture for Dell VIS Self-Service Creator and VMware vsphere 4 Solutions for Large Environments Virtualization Solutions Engineering Ryan Weldon and Tom Harrington THIS WHITE PAPER IS FOR
CUTTING-EDGE SOLUTIONS FOR TODAY AND TOMORROW Dell PowerEdge M-Series Blade Servers Simplifying IT The Dell PowerEdge M-Series blade servers address the challenges of an evolving IT environment by delivering
White Paper Dell Microsoft Business Intelligence and Data Warehousing Reference Configuration Performance Results Phase III Performance of Microsoft SQL Server 2008 BI and D/W Solutions on Dell PowerEdge
Optimizing SQL Server Storage Performance with the PowerEdge R720 Choosing the best storage solution for optimal database performance Luis Acosta Solutions Performance Analysis Group Joe Noyola Advanced
EMC Unified Storage for Microsoft SQL Server 2008 Enabled by EMC CLARiiON and EMC FAST Cache Reference Copyright 2010 EMC Corporation. All rights reserved. Published October, 2010 EMC believes the information
High Performance Tier Implementation Guideline A Dell Technical White Paper PowerVault MD32 and MD32i Storage Arrays THIS WHITE PAPER IS FOR INFORMATIONAL PURPOSES ONLY, AND MAY CONTAIN TYPOGRAPHICAL ERRORS
Technical white paper HP ProLiant BL660c Gen9 and Microsoft SQL Server 2014 technical brief Scale-up your Microsoft SQL Server environment to new heights Table of contents Executive summary... 2 Introduction...
Building robust private cloud services infrastructures By Brian Gautreau and Gong Wang Private clouds optimize utilization and management of IT resources to heighten availability. Microsoft Private Cloud
SYSTEM X SERVERS SOLUTION BRIEF Maximum performance, minimal risk for data warehousing Microsoft Data Warehouse Fast Track for SQL Server 2014 on System x3850 X6 (95TB) The rapid growth of technology has
DELL Virtual Desktop Infrastructure Study END-TO-END COMPUTING Dell Enterprise Solutions Engineering 1 THIS WHITE PAPER IS FOR INFORMATIONAL PURPOSES ONLY, AND MAY CONTAIN TYPOGRAPHICAL ERRORS AND TECHNICAL
Dell Virtual Remote Desktop Reference Architecture Technical White Paper Version 1.0 July 2010 THIS WHITE PAPER IS FOR INFORMATIONAL PURPOSES ONLY, AND MAY CONTAIN TYPOGRAPHICAL ERRORS AND TECHNICAL INACCURACIES.
Microsoft Exchange Server 2007 and Hyper-V high availability configuration on HP ProLiant BL680c G5 server blades Executive summary... 2 Introduction... 2 Exchange 2007 Hyper-V high availability configuration...
Evaluation of Dell PowerEdge VRTX Shared PERC8 in Failover Scenario Evaluation report prepared under contract with Dell Introduction Dell introduced its PowerEdge VRTX integrated IT solution for remote-office
EMC Virtual Infrastructure for Microsoft Applications Data Center Solution Enabled by EMC Symmetrix V-Max and Reference Architecture EMC Global Solutions Copyright and Trademark Information Copyright 2009
Capacity Planning for Microsoft SharePoint Technologies Capacity Planning The process of evaluating a technology against the needs of an organization, and making an educated decision about the configuration
White Paper Dell Microsoft - Reference Configurations Deploying Microsoft SQL Server 2005 Business Intelligence and Data Warehousing Solutions on Dell PowerEdge Servers and Dell PowerVault Storage Abstract
HP recommended configuration for Microsoft Exchange Server 2010: HP LeftHand P4000 SAN Table of contents Executive summary... 2 Introduction... 2 Solution criteria... 3 Hyper-V guest machine configurations...
DVS Enterprise Reference Architecture VMware Horizon View Reference THIS DOCUMENT IS FOR INFORMATIONAL PURPOSES ONLY, AND MAY CONTAIN TYPOGRAPHICAL ERRORS AND TECHNICAL INACCURACIES. THE CONTENT IS PROVIDED
DELL s Oracle Database Advisor Underlying Methodology A Dell Technical White Paper Database Solutions Engineering By Roger Lopez Phani MV Dell Product Group January 2010 THIS WHITE PAPER IS FOR INFORMATIONAL
Using Red Hat Network Satellite Server to Manage Dell PowerEdge Servers Enterprise Product Group (EPG) Dell White Paper By Todd Muirhead and Peter Lillian July 2004 Contents Executive Summary... 3 Introduction...
Virtualizing SQL Server 2008 Using EMC VNX Series and Microsoft Windows Server 2008 R2 Hyper-V Copyright 2011 EMC Corporation. All rights reserved. Published February, 2011 EMC believes the information
Dell High Availability Solutions Guide for Microsoft Hyper-V R2 A Dell Technical White Paper THIS WHITE PAPER IS FOR INFORMATIONAL PURPOPERATING SYSTEMS ONLY, AND MAY CONTAIN TYPOGRAPHICAL ERRORS AND TECHNICAL
Estimate Performance and Capacity Requirements for Workflow in SharePoint Server 2010 This document is provided as-is. Information and views expressed in this document, including URL and other Internet
Virtualizing Microsoft SQL Server 2008 on the Hitachi Adaptable Modular Storage 2000 Family Using Microsoft Hyper-V Implementation Guide By Eduardo Freitas and Ryan Sokolowski February 2010 Summary Deploying
Accelerate SQL Server 2014 AlwaysOn Availability Groups with Seagate Nytro Flash Accelerator Cards Technology Paper Authored by: Mark Pokorny, Database Engineer, Seagate Overview SQL Server 2014 provides
The Methodology Behind the Dell SQL Server Advisor Tool Database Solutions Engineering By Phani MV Dell Product Group October 2009 Executive Summary The Dell SQL Server Advisor is intended to perform capacity
Pivot3 Reference Architecture for VMware View Version 1.03 January 2012 Table of Contents Test and Document History... 2 Test Goals... 3 Reference Architecture Design... 4 Design Overview... 4 The Pivot3
Dell EqualLogic Best Practices Series Dell EqualLogic PS Series Reference Architecture for Cisco Catalyst 3750X Two-Switch SAN Reference Storage Infrastructure and Solutions Engineering Dell Product Group
Dell PowerVault Backup to Disk Appliance Interoperability Guide This document provides information about the supported hardware and software versions for the Dell PowerVault Backup to Disk Appliance system.
Dell Reference Configuration for Hortonworks Data Platform A Quick Reference Configuration Guide Armando Acosta Hadoop Product Manager Dell Revolutionary Cloud and Big Data Group Kris Applegate Solution
Performance benefit of MAX5 for databases The MAX5 Advantage: Clients Benefit running Microsoft SQL Server Data Warehouse (Workloads) on IBM BladeCenter HX5 with IBM MAX5 Vinay Kulkarni Kent Swalin IBM
Dell EqualLogic Best Practices Series Sizing and Best Practices for Deploying Microsoft Exchange Server 2010 on VMware vsphere and Dell EqualLogic Storage A Dell Technical Whitepaper Ananda Sankaran Storage
White Paper MS Exchange Server Acceleration Using virtualization to dramatically maximize user experience for Microsoft Exchange Server Allon Cohen, PhD Scott Harlin OCZ Storage Solutions, Inc. A Toshiba
Dell Desktop Virtualization Solutions Simplified All-in-one VDI appliance creates a new level of simplicity for desktop virtualization Executive summary Desktop virtualization is a proven method for delivering
Dell EqualLogic Best Practices Series Sizing and Best Practices for Deploying Oracle 11g Release 2 Based Decision Support Systems with Dell EqualLogic 10GbE iscsi SAN A Dell Technical Whitepaper Storage
Cisco Unified Computing System and EMC VNXe3300 Unified Storage System An Ideal Solution for SMB Server Consolidation White Paper January 2011, Revision 1.0 Contents Cisco UCS C250 M2 Extended-Memory Rack-Mount
MS Exchange Server Acceleration Maximizing Users in a Virtualized Environment with Flash-Powered Consolidation Allon Cohen, PhD OCZ Technology Group Introduction Microsoft (MS) Exchange Server is one of
Scaling out a SharePoint Farm and Configuring Network Load Balancing on the Web Servers Steve Smith Combined Knowledge MVP SharePoint Server Scaling out a SharePoint Farm and Configuring Network Load Balancing
WHITE PAPER Improve Business Productivity and User Experience with a SanDisk Powered SQL Server 2014 In-Memory OLTP Database 951 SanDisk Drive, Milpitas, CA 95035 www.sandisk.com Table of Contents Executive
Open-E Data Storage Software and Intel Modular Server a certified virtualization solution Contents 1. New challenges for SME IT environments 2. Open-E DSS V6 and Intel Modular Server: the ideal virtualization
Business white paper HP Process Automation Version 7.0 Server performance Table of contents 3 Summary of results 4 Benchmark profile 5 Benchmark environmant 6 Performance metrics 6 Process throughput 6
Converged Networking Solution for Dell M-Series Blades Authors: Reza Koohrangpour Spencer Wheelwright. THIS SOLUTION BRIEF IS FOR INFORMATIONAL PURPOSES ONLY, AND MAY CONTAIN TYPOGRAPHICAL ERRORS AND TECHNICAL
Performance Study Microsoft Office SharePoint Server 2007 Performance on VMware vsphere 4.1 VMware vsphere 4.1 One of the key benefits of virtualization is the ability to consolidate multiple applications
HP recommended configurations for Microsoft Exchange Server 2013 and HP ProLiant Gen8 with direct attached storage (DAS) Building blocks at 1000, 3000, and 5000 mailboxes Table of contents Executive summary...
White Paper Cisco Prime Home 5.0 Minimum System Requirements (Standalone and High Availability) White Paper July, 2012 2012 Cisco and/or its affiliates. All rights reserved. This document is Cisco Public
Cisco, Citrix, Microsoft, and NetApp Deliver Simplified High-Performance Infrastructure for Virtual Desktops Greater Efficiency and Performance from the Industry Leaders Citrix XenDesktop with Microsoft
IT@Intel White Paper Intel IT IT Best Practices: Data Center Solutions Server Virtualization August 2010 Analyzing the Virtualization Deployment Advantages of Two- and Four-Socket Server Platforms Executive
Load Balancing for Microsoft Office Communication Server 2007 Release 2 A Dell and F5 Networks Technical White Paper End-to-End Solutions Team Dell Product Group Enterprise Dell/F5 Partner Team F5 Networks
Technical white paper HP high availability solutions for Microsoft SQL Server Fast Track Data Warehouse using SQL Server 2012 failover clustering Table of contents Executive summary 2 Fast Track reference
HP Asset Manager Asset Manager 5.10 Sizing Guide Using the Oracle Database Server, or IBM DB2 Database Server, or Microsoft SQL Server Legal Notices... 2 Introduction... 3 Asset Manager Architecture...
White Paper Cisco Unified Computing System: Meet the Challenges of Microsoft SharePoint Server Workloads What You Will Learn Occam s razor (according to Wikipedia) is a principle that generally recommends,
Dell EqualLogic Best Practices Series Sizing and Best Practices for Deploying Microsoft Exchange Server 2010 on VMware vsphere and Dell EqualLogic Storage A Dell Technical Whitepaper Ananda Sankaran Storage
Dell PowerVault MD32xx Deployment Guide for VMware ESX4.1 Server A Dell Technical White Paper PowerVault MD32xx Storage Array www.dell.com/md32xx THIS WHITE PAPER IS FOR INFORMATIONAL PURPOSES ONLY, AND
Dragon NaturallySpeaking and citrix A White Paper from Nuance Communications March 2009 Introduction As the number of deployed enterprise applications increases, organizations are seeking solutions that
Cisco for SAP HANA Scale-Out Solution Solution Brief December 2014 With Intelligent Intel Xeon Processors Highlights Scale SAP HANA on Demand Scale-out capabilities, combined with high-performance NetApp
Improved Virtualization Performance with 9th Generation Servers David J. Morse Dell, Inc. August 2006 Contents Introduction... 4 VMware ESX Server 3.0... 4 SPECjbb2005... 4 BEA JRockit... 4 Hardware/Software
White Paper Recording Server Virtualization Prepared by: Mike Sherwood, Senior Solutions Engineer Milestone Systems 23 March 2011 Table of Contents Introduction... 3 Target audience and white paper purpose...
vce.com DATA SHEET VXRACK SYSTEM 1032 Product Overview VCE adds rackscale hyper-converged offerings to the industry s broadest converged infrastructure system portfolio. The VxRack System 1000 series is
1 Deploying a 48,000-user Exchange Server 2010 Environment with Hitachi Compute Blade 2000 and Hitachi Adaptable Modular Storage 2500 Reference Architecture Guide Leo Nguyen April 2011 Month Year Feedback
IBM DS5020 Express Manage growth, complexity, and risk with scalable, high-performance storage Highlights Mixed host interfaces support (Fibre Channel/iSCSI) enables SAN tiering Balanced performance well-suited
Microsoft Exchange Server 3 Deployment Considerations for Small and Medium Businesses A Dell PowerEdge server can provide an effective platform for Microsoft Exchange Server 3. A team of Dell engineers
WITH A FUSION POWERED SQL SERVER 2014 IN-MEMORY OLTP DATABASE 1 W W W. F U S I ON I O.COM Table of Contents Table of Contents... 2 Executive Summary... 3 Introduction: In-Memory Meets iomemory... 4 What
WHITE PAPER HP ProLiant DL580 Gen8 and HP LE PCIe Workload WHITE PAPER Accelerator 90TB Microsoft SQL Server Data Warehouse Fast Track Reference Architecture Based on Microsoft SQL Server 2014 Data Warehouse
An evaluation of blade server power efficiency for the, Dell PowerEdge M600, and IBM BladeCenter HS21 using the SPECjbb2005 Benchmark The HP Difference The ProLiant BL260c G5 is a new class of server blade
TEST REPORT MARCH 2009 Server management solution comparison on Dell PowerEdge R710 and HP Executive summary Dell Inc. (Dell) commissioned Principled Technologies (PT) to compare server management solutions
SYSTEM X SERVERS SOLUTION BRIEF Minimize cost and risk for data warehousing Microsoft Data Warehouse Fast Track for SQL Server 2014 on System x3850 X6 (55TB) Highlights Improve time to value for your data
N8103-149/150/151/160 RAID Controller N8103-156 MegaRAID CacheCade Feature Overview April 2012 Rev.1.0 NEC Corporation Contents 1 Introduction... 3 2 Types of RAID Controllers... 3 3 New Features of RAID
Dell High Availability and Disaster Recovery Solutions Using Microsoft SQL Server 2012 AlwaysOn Availability Groups Dell servers and storage options available for AlwaysOn Availability Groups deployment.
Handling Multimedia Under Desktop Virtualization for Knowledge Workers Wyse TCX Multimedia capabilities deliver the applications and performance required, for less A white paper by Wyse Technology Inc.
A Dell white paper Howard Shoobe, Storage Enterprise Technologist John Shirley, Product Management Dan Bock, Product Management Table of contents Executive summary... 3 What is different about Dell Compellent
White Paper Power Efficiency Comparison: Cisco UCS 5108 Blade Server Chassis and Dell PowerEdge M1000e Blade Enclosure White Paper March 2014 2014 Cisco and/or its affiliates. All rights reserved. This
EMC Virtual Infrastructure for Microsoft Applications Data Center Solution Enabled by EMC Symmetrix V-Max and Reference Architecture EMC Global Solutions Copyright and Trademark Information Copyright 2009