Guest

Cisco UCS C-Series Rack Servers

Deploy 200 Citrix XenDesktop 7.1 Hosted Virtual Desktops on Cisco UCS C240 M3 Rack Server with LSI Nytro MegaRAID and SAS Drives

  • Viewing Options

  • PDF (1.8 MB)
  • Feedback

March 2014


Contents

Overview...................................................................................................................................................................................... 3

Cisco UCS C-Series Rack Server....................................................................................................................................... 4

Cisco UCS C240 M3 Rack Server...................................................................................................................................... 5

Cisco UCS VIC 1225—10 Gigabit Ethernet Option......................................................................................................... 6

LSI Nytro MegaRAID Controller........................................................................................................................................... 8

Controller Cache.................................................................................................................................................................... 8

Read Policies.......................................................................................................................................................................... 8

Caching Policies.................................................................................................................................................................... 9

Write Policies.......................................................................................................................................................................... 9

Citrix XenServer......................................................................................................................................................................... 9

Citrix XenDesktop 7................................................................................................................................................................ 10

FlexCast Technology.......................................................................................................................................................... 11

High-Definition user experience (HDX) technology..................................................................................................... 12

Citrix XenDesktop 7 Desktop and Application Services............................................................................................... 13

Test Configuration................................................................................................................................................................... 14

Server Storage Volume Configuration............................................................................................................................ 15

Load Generation....................................................................................................................................................................... 17

User Workload Simulation—LoginVSI............................................................................................................................ 17

Test Run Protocol................................................................................................................................................................. 18

Success Criteria................................................................................................................................................................... 18

Performance Results............................................................................................................................................................. 19

Login VSImax....................................................................................................................................................................... 19

Recommended Workload.................................................................................................................................................. 20

Conclusion................................................................................................................................................................................. 24

References................................................................................................................................................................................ 24


Overview

One of the biggest barriers to entry for desktop virtualization (DV) is the capital expense for deploying proof of concept (PoC) and pilot environments for mid-size customers. For smaller customers, currently deployment of a DV system for fewer than 200 users is cost prohibitive.

To overcome the entry point barrier, Cisco has developed a self-contained DV solution that can host up to 200 Citrix XenDesktop Hosted Virtual Desktops on a single Cisco UCS® C240 M3 Rack Server and host the following required infrastructure:

Citrix XenServer 6.2 Hypervisor

Microsoft Active Directory Domain Controller (Optional)

Microsoft SQL Server 2012

Microsoft File Server for User Data and User Profiles (Optional)

Citrix XenCenter 6.2 (Optional)

Citrix XenDesktop 7.1 Desktop Broker

Citrix XenDesktop 7.1 Desktop Studio Administration Console

The Cisco UCS C240 M3 Rack Server server configuration used to validate the configuration is:

Intel Xeon Processor E5-2697 v2 12-core 2.7 GHz Processors (2)

384 GB 1866 MHz DIMMs (24 x 16GB)

Cisco® UCS Virtual Interface Card (VIC) 1225 Converged Network Adapter (Optional for 10GE)

LSI Nytro MegaRAID 200G Controller

Cisco 600GB 10K RPM Hot Swap SAS Drives (12)

Cisco 650 Watt Power Supply (2)

Note: Virtual machines and hardware components marked “(Optional)” can be hosted on existing infrastructure, deployed for management or performance enhancement or may be hosted on the Cisco UCS C240 M3. The tests performed in this study were performed with all optional components installed to validate system capability.

In this study the unique capabilities for the LSI Nytro MegaRAID 200G controller cache to support the Citrix XenDesktop 7.1 Machine Creation Service (MCS) differencing disks were used. These disposable disks incur high IOPS during the lifecycle of the Citrix MCS-provisioned virtual desktop.

Configuration of the controller flash and SAS drives is accomplished through the LSI Nytro MegaRAID BIOS Config Utility configuration wizard, which is accessed during the Cisco UCS C240 M3 Rack Server server’s boot sequence by pressing the CTRL-H key sequence when the controller BIOS loads. (See section 6 for details of the test configuration)

The tested configuration provides excellent virtual desktop end-user experience for 200 users as measured by our test tool, Login Virtual Session Indexer (Login VSI,) at a dramatically lower entry-level price.

Fault tolerance can be achieved by deploying a second server configured identically with redundant infrastructure and Citrix XenDesktop 7 virtual machines and by deploying a distributed file system.

With options to use lower bin processors, like the Intel Xeon processor E5-2680 v2, a lower entry point price can be achieved at a slightly lower Citrix XenDesktop virtual machine density.

As with any solution deployed to users with data storage requirements, a backup solution must be deployed to insure the integrity of the user data. Such a solution is outside the scope of this paper.

Cisco UCS C-Series Rack Server

Cisco UCS C-Series Rack Server keep pace with Intel Xeon processor innovation by offering the latest processors with an increase in processor frequency and improved security and availability features. With the increased performance provided by the Intel Xeon processor E5-2600 and E5-2600 v2 product families, Cisco UCS C-Series servers offer an improved price-to-performance ratio, extend Cisco Unified Computing System innovations to an industry standard Rack Server form factor, including a standards-based unified network fabric, Cisco VN-Link virtualization support, and Cisco Extended Memory Technology.

Designed to operate both in standalone environments and as part of the Cisco Unified Computing System, these servers enable organizations to deploy systems incrementally—using as many or as few servers as needed—on a schedule that best meets the organization’s timing and budget. Cisco UCS C-Series servers offer investment protection through the capability to deploy them either as standalone servers or as part of the Cisco Unified Computing System.

One compelling reason that many organizations prefer Rack Server servers is the wide range of I/O options available in the form of PCI Express (PCIe) adapters. Cisco UCS C-Series servers supports spectrum of I/O options, which includes interfaces supported by Cisco as well as adapters from third parties.

Figure 1. Cisco UCS Components

Cisco UCS C240 M3 Rack Server

The Cisco UCS C240 M3 Rack Server (Figure 2) is designed for both performance and expandability over a wide range of storage-intensive infrastructure workloads, from big data to collaboration. The enterprise-class Cisco UCS C240 M3 server further extends the capabilities of the Cisco UCS portfolio in a 2RU form factor with the addition of the Intel® Xeon processor E5-2600 and E5-2600 v2 product families, which deliver an outstanding combination of performance, flexibility, and efficiency gains. The Cisco UCS C240 M3 offers up to two Intel Xeon processor E5-2600 or E5-2600 v2 processors, 24 DIMM slots, 24 disk drives, and four 1 Gigabit Ethernet LAN-on-motherboard (LOM) ports to provide exceptional levels of internal memory and storage expandability and exceptional performance.

The Cisco UCS C240 M3 interfaces with the Cisco UCS Virtual Interface Card. The Cisco UCS Virtual Interface Card is a virtualization-optimized Fibre Channel over Ethernet (FCoE) PCI Express (PCIe) 2.0 x8 10-Gbps adapter designed for use with Cisco UCS C-Series Rack Servers. The VIC is a dual-port 10 Gigabit Ethernet PCIe adapter that can support up to 256 PCIe standards-compliant virtual interfaces, which can be dynamically configured so that both their interface type (network interface card [NIC] or host bus adapter [HBA]) and identity (MAC address and worldwide name [WWN]) are established using just-in-time provisioning. In addition, the Cisco UCS VIC 1225 can support network interface virtualization and Cisco® Data Center Virtual Machine Fabric Extender (VM-FEX) technology. An additional five PCIe slots are made available for certified third party PCIe cards. The server is equipped to handle 24 on board SAS drives or SSDs along with shared storage solutions offered by our partners.

Cisco UCS C240 M3 server's disk configuration delivers balanced performance and expandability to best meet individual workload requirements. With up to 12 LFF (Large Form Factor) or 24 SFF (Small Form Factor) internal drives, the Cisco UCS C240 M3 optionally offers 10,000-RPM and 15,000-RPM SAS drives to deliver a high number of I/O operations per second for transactional workloads such as database management systems. In addition, high-capacity SATA drives provide an economical, large-capacity solution. Superfast SSDs are a third option for workloads that demand extremely fast access to smaller amounts of data. A choice of RAID controller options also helps increase disk performance and reliability.

The Cisco UCS C240 M3 further increases performance and customer choice over many types of storage-intensive applications such as:

Collaboration

Small and medium-sized business (SMB) databases

Big data infrastructure

Virtualization and consolidation

Storage servers

High-performance appliances

This server caters to businesses that demand a large local storage capacity without compromising the user experience. A fast processor and large memory and storage footprints help meet these business needs.
http://www.cisco.com/en/US/prod/collateral/ps10265/ps10493/ps12370/data_sheet_c78-700629.html

Figure 2. Cisco UCS C240 M3 Rack Server

Cisco UCS VIC 1225—10 Gigabit Ethernet Option

A Cisco UCS Virtual Interface Card (VIC) 1225 (Figure 3) is a dual-port Enhanced Small Form-Factor Pluggable (SFP+) 10 Gigabit Ethernet and Fibre Channel over Ethernet (FCoE)-capable PCI Express (PCIe) card designed exclusively for Cisco UCS C-Series Rack Servers. With its half-height design, the card preserves full-height slots in servers for third-party adapters certified by Cisco. It incorporates next-generation converged network adapter (CNA) technology. The card enables a policy-based, stateless, agile server infrastructure that can present up to 256 PCIe standards-compliant interfaces to the host that can be dynamically configured as either network interface cards (NICs) or host bus adapters (HBAs). (Figure 4) In addition, the Cisco UCS VIC 1225 supports Cisco Data Center Virtual Machine Fabric Extender (VM-FEX) technology, which extends the Cisco UCS fabric interconnect ports to virtual machines, simplifying server virtualization deployment.

Figure 3. Cisco UCS VIC 1225 CNA

Figure 4. Cisco UCS VIC 1225 CNA Architecture


LSI Nytro MegaRAID Controller

Cisco UCS CSeries Rack Servers offer various raid/caching configuration options with LSI Nytro MegaRAID controllers. Base Cisco UCS C-Series servers come with an onboard controller, but customers can buy an LSI Nytro MegaRAID PCIe controller as an option. The Cisco MegaRAID Controller 8110-4i PCIe controller was used for this study.

The Cisco MegaRAID NMR 8110-4i combines a PCIe RAID controller and onboard Flash to optimize SAS/SATA storage into a single low latency, high performance, caching and data protected solution for internal storage systems (DAS) using up to 128 SATA and/or SAS hard drives with data transfer rates of up to 6Gb/s per port. The card complies with the PCI Express 3.0 x8 ports specification for high-bandwidth applications. All RAID levels are supported on this LSI controller.

Figure 5. Cisco Nytro MegaRAID Controller 8110-4i

Controller Cache

The LSI Nytro MegaRAID Controller NMR 8110-4i has enterprise multilevel-cell (eMLC) memory with a 200GB capacity and 1Gbps 1333MHz DDR3 SDRAM memory for RAID Cache assist. It provides a controller cache in read/write/caching versions which has an extra optional protection against power failure through Battery Backed unit (BBU). The controller cache is used to increase write and read performance which can be influenced by following three configurations parameters.

Read Policies

Adaptive Read Ahead—(Recommended for volume NOT associated with Nytro caching) This specifies that the controller uses read-ahead if the two most recent disk accesses occurred in sequential sectors. If all read requests are random, the algorithm reverts to No Read Ahead, however all requests are still evaluated for possible sequential operation. Data which are read-ahead of the current request are kept in the controller cache.

Read Ahead—The controller reads ahead all the data until the end of the stripe from the disk.

Normal—(Recommended for volumes associated with Nytro caching) Only the requested data is read and the controller does not read ahead any data.

Caching Policies

Direct IO—(Recommended for all volumes) All read data is transferred directly to host memory bypassing RAID controller cache. Any read-ahead data is cached. All write data is transferred directly from host memory bypassing RAID controller cache if Write-Through cache mode is set.

Cached IO—All read and write data passes through controller cache memory on its way to or from host memory. Includes write data in Write-Through mode.

Note: Recommended that Caching Policies are disabled.

Write Policies

Write-Through—Caching strategy where data is written to disks before a completion status is returned to the host operating system considered more secure since a power failure will be less likely to cause undetected drive write data loss with no battery-backed cache present. It is recommended using Write-Through for RAID 0, 1 and 10 to provide optimum performance for streaming/sequential access workloads as since data is moved directly from the host to the disks, controller avoids copying the data intermediary into cache which can improve overall performance for streaming workloads if Direct IO mode is set.

Note: Recommended for volumes associated with Nytro caching

Write-Back—A caching strategy where write operations result in a completion status being sent to the host operating system as soon as data is in written to the RAID cache. Data is written to the disk when it is forced out of controller cache memory. Write-Back is more efficient if the temporal and/or spatial locality of the requests is smaller than the controller cache size. Write-Back is more efficient in environments with “bursty” write activity. Battery-backed cache can be used to protect against data loss as a result of a power failure or system crash. Recommend Write-Back for RAID 0, 1, and 10 provides optimum performances for transactional (random real world) benchmarks. Recommend Write-Back for RAID 5 and 6 improves performance of RAID-5 and 6 data redundancy generation. Defaults to Write-Through if no BBU.

Note: Recommended for volumes NOT associated with Nytro caching.

Disk Cache—Enabling disk cache increases throughput/performance for write operation/access. It is always recommended to supply continuous power supply for hard disks by a UPS upstream. If the system is UPS-Protected then enabling disk cache for performance reason is recommended. In case there is no UPS to these disks – important data which has not been written from disk cache to hard disk may invariably be lost.

Citrix XenServer

In addition to the virtual desktop delivery options available with FlexCast, XenDesktop was intentionally designed to be hypervisor agnostic and therefore provide a choice when selecting a hypervisor to host virtual machine-based desktops. The open architecture of XenDesktop can utilize Citrix XenServer, Microsoft Hyper-V, and VMware vSphere hypervisors for the hosting virtual desktop infrastructure. For the purposes of the testing and validation represented in this paper only the Citrix XenServer bare-metal hypervisor was utilized to host virtual desktops.

Citrix XenServer is an enterprise-ready, cloud-proven virtualization platform with all the capabilities needed to create and manage a virtual infrastructure at half the cost of other solutions. Organizations of any size can install the free XenServer in less than ten minutes to virtualize even the most demanding workloads and automate management processes, which increases IT flexibility and agility, and lowers costs. To add a rich set of management and automation capabilities designed to help customers create a virtual computing center, simply upgrade to one of the enhanced versions of XenServer.

Citrix XenDesktop 7

Built on the Citrix Avalon™ architecture, Citrix XenDesktop 7 includes significant enhancements to help customers deliver Windows apps and desktops as mobile services while addressing management complexity and associated costs. Enhancements in this release include:

A new unified product architecture—the latest generation FlexCast architecture—and administrative interfaces designed to deliver both hosted-shared applications (RDS) and complete virtual desktops (VDI). Unlike previous software releases that required separate Citrix XenApp farms and XenDesktop infrastructures, this new release allows administrators to deploy a single infrastructure and employ a consistent set of management tools for mixed desktop and app workloads.

New and improved management interfaces. XenDesktop 7 includes two new purpose-built management consoles—one for automating workload provisioning and app publishing and the second for real-time monitoring of the infrastructure.

Enhanced HDX technologies. Since mobile technologies and devices are increasingly pervasive, Citrix has engineered new and improved HDX technologies to improve the user experience for hosted Windows apps and desktops delivered on laptops, tablets, and smartphones.

Unified App Store. The release includes a self-service Windows app store, implemented via Citrix StoreFront services, that provides a single, simple, and consistent aggregation point for all user services. IT can publish apps, desktops, and data services to the StoreFront, from which users can search and subscribe to services.


FlexCast Technology

In Citrix XenDesktop 7, FlexCast Management Architecture (FMA) is responsible for delivering and managing hosted-shared RDS apps and complete VDI desktops. By using Citrix Receiver with XenDesktop 7, users have adevice-native experience on endpoints including Windows, Mac, Linux, iOS, Android, Chrome OS, HTML5, andBlackberry.

Figure 6. Overview of the unified FlexCast architecture and components

The diagram above provides an overview of the unified FlexCast architecture and underlying components, which are also described below:

Citrix Receiver. Running on user endpoints, Receiver provides users with self-service access to resources published on XenDesktop servers. Receiver combines ease of deployment and use, supplying fast, secure access to hosted applications, desktops, and data. Receiver also provides on-demand access to Windows, Web, and Software-as-a-Service (SaaS) applications.

Citrix StoreFront. StoreFront authenticates users and manages catalogs of desktops and applications. Users can search StoreFront catalogs and subscribe to published services via Citrix Receiver.

Citrix Studio. Using the new and improved Studio interface, administrators can easily configure and manage XenDesktop deployments. Studio provides wizards to guide the process of setting up an environment, creating desktops, and assigning desktops to users, automating provisioning and application publishing. It also allows administration tasks to be customized and delegated to match site operational requirements.

Delivery Controller. The Delivery Controller is responsible for distributing applications and desktops, managing user access, and optimizing connections to applications. Each site has one or more deliverycontrollers.

Server OS Machines. These are virtual or physical machines (based on a Windows Server operating system) that deliver RDS applications or hosted shared desktops to users.

Desktop OS Machines. These are virtual or physical machines (based on a Windows Desktop operating system) that deliver personalized VDI desktops or applications that run on a desktop operating system.

Remote PC. XenDesktop with Remote PC allows IT to centrally deploy secure remote access to all Windows PCs on the corporate network. It is a comprehensive solution that delivers fast, secure remote access to all the corporate apps and data on an office PC from any device.

Virtual Delivery Agent. A Virtual Delivery Agent is installed on each virtual or physical machine (within the server or desktop OS) and manages each user connection for application and desktop services. The agent allows OS machines to register with the Delivery Controllers and governs the HDX connection between these machines and Citrix Receiver.

Citrix Director. Citrix Director is a powerful administrative tool that helps administrators quickly troubleshoot and resolve issues. It supports real-time assessment, site health and performance metrics, and end user experience monitoring. Citrix EdgeSight® reports are available from within the Director console and provide historical trending and correlation for capacity planning and service level assurance.

Citrix Provisioning Services 7.1. This new release of Citrix Provisioning Services (PVS) technology is responsible for streaming a shared virtual disk (vDisk) image to the configured Server OS or Desktop OS machines. This streaming capability allows VMs to be provisioned and re-provisioned in real-time from a single image, eliminating the need to patch individual systems and conserving storage. All patching is done in one place and then streamed at boot-up. PVS supports image management for both RDS and VDI-based machines, including support for image snapshots and rollbacks.

High-Definition user experience (HDX) technology

High-Definition User Experience (HDX) technology in this release is optimized to improve the user experience for hosted Windows apps on mobile devices. Specific enhancements include:

HDX Mobile technology, designed to cope with the variability and packet loss inherent in today’s mobile networks. HDX technology supports deep compression and redirection, taking advantage of advanced codec acceleration and an industry-leading H.264-based compression algorithm. The technology enables dramatic improvements in frame rates while requiring significantly less bandwidth. HDX technology offers users a rich multimedia experience and optimized performance for voice and video collaboration.

HDX Touch technology enables mobile navigation capabilities similar to native apps, without rewrites or porting of existing Windows applications. Optimizations support native menu controls, multi-touch gestures, and intelligent sensing of text-entry fields, providing a native application look and feel.

HDX 3D Pro uses advanced server-side GPU resources for compression and rendering of the latest OpenGL and DirectX professional graphics apps. GPU support includes both dedicated user and shared user workloads.


Citrix XenDesktop 7 Desktop and Application Services

IT departments strive to deliver application services to a broad range of enterprise users that have varying performance, personalization, and mobility requirements. Citrix XenDesktop 7 allows IT to configure and deliver any type of virtual desktop or application, hosted or local, and optimize delivery to meet individual user requirements, while simplifying operations, securing data, and reducing costs. (Figure 7)

Figure 7. Citrix XenDesktop and Application Services

With previous product releases, administrators had to deploy separate XenApp farms and XenDesktop sites to support both hosted shared RDS and VDI desktops. As shown above, the new XenDesktop 7 release allows administrators to create a single infrastructure that supports multiple modes of service delivery, including:

Application Virtualization and Hosting (RDS). Applications are installed on or streamed to Windows servers in the data center and remotely displayed to users’ desktops and devices.

Hosted Shared Desktops (RDS). Multiple user sessions share a single, locked-down Windows Server environment running in the datacenter and accessing a core set of apps. This model of service delivery is ideal for task workers using low intensity applications, and enables more desktops per host compared to VDI.

Pooled VDI Desktops. This approach leverages a single desktop OS image to create multiple thinly provisioned or streamed desktops. Optionally, desktops can be configured with a Personal vDisk to maintain user application, profile and data differences that are not part of the base image. This approach replaces the need for dedicated desktops, and is generally deployed to address the desktop needs of knowledge workers that run more intensive application workloads.

VM Hosted Apps (16 bit, 32 bit, or 64 bit Windows apps). Applications are hosted on virtual desktopsrunning Windows 7, XP, or Vista and then remotely displayed to users’ physical or virtual desktops and devices.

This white paper focuses on delivering a mixed workload consisting of hosted shared desktops (HSD or RDS) and hosted virtual desktops (HVD or VDI).


Test Configuration

The test configuration is represented by the hybrid logical/physical diagram shown below.

Figure 8. Reference Architecture

Hardware Components:

Cisco UCS C240-M3 Rack Server (2 x Intel Xeon processor E5-2697 v2 @ 2.70 GHz) with 384GB of memory (16 GB X 24 DIMMS @ 1866 MHz), Citrix XenServer 6.2 host

Cisco VIC 1225 Converged Network Adapter/Rack Server

2 x Cisco Nexus 5548UP Access Switches

12 x 600 Gbps SAS disks @ 10K RPM

LSI Nytro MegaRAID NMR 8110-4i controller

Software components:

Cisco UCS firmware release 2.2(1b)

Citrix XenServer 6.2

Citrix XenDesktop 7.1

Microsoft Windows 7 SP1 32 bit, 1 vCPU, 1 GB of memory, 18 GB/VM


Server Storage Volume Configuration

The key differentiator that allows this compact solution to perform so well, was the strategic use of the flash drives on the LSI Nytro MegaRAID NMR 8110-4i and 12 600GB 10K RPM SAS drives.

There are three high level operations that need to be performed to configure the controller card flash and the SAS drives for use in the solution.

Create Drive Groups

Add Drive Groups to Spans

Create Virtual Drives, setting RAID Level, controller settings and size

(Note: Multiple virtual drives can be configured on a single drive group)

We configured Drive Groups in the following way to support all infrastructure, user data, and Machine Creation Service Differencing disks.

Table 1. Virtual Drive Group Configuration

Physical Drive(s)

Drive Group

Span

Virtual Drive(s)

Capacity

Purpose

Backplane Flash Devices

Nytro Cache RAID-0

NA

Nytro Cache

180.7GB

Flash Caching

0-3

0 RAID-5

NA

VD0, VD1

20GB, 1.6TB

Boot, Infra

4-7

1 RAID-0

RAID-10

VD21

2.16TB

XD 7.1 MCS

8-11

2 RAID-0

Physical drives were allocated as follows:

Table 2. Physical Drive Group Configuration

Drive Groups

RAID Configuration

Physical Drives

Purpose

N/A

0

Backplane

Nytro MegaRAID NytroCache

0

5

0-3

Boot/Infrastructure Volumes

1

0

4-7

1st Group for RAID 10 Volume

2

0

8-11

2nd Group for RAID 10 Volume

Drive Groups were added to Spans as follows:

Table 3. Spans

Drive Group

Span

0

Nytro MegaRAID Cache Span

1

Boot/Infrastructure Span

2

Citrix XenDesktop 7.1 MCS Disks

3

Citrix XenDesktop 7.1 MCS Disks

Three Virtual Drives were created from the Drive Groups and Spans created above. Only Virtual Drive 2 utilizes the LSI Nytro MegaRAID NytroCache for Citrix XenDesktop 7.1 MCS disks.

Table 4. Virtual Drives

Drive Groups

RAID Configuration

Virtual Drive

Capacity

Purpose

0

5

0

20 GB

Boot

0

5

1

1.6 TB

Infrastructure/User Files

1,2

10

2

2.16 TB

Citrix XenDesktop 7.1 MCS disks

The final configuration looks like Figure 9 in the LSI NytroMegaRAID Bios Configuration Utility:

Figure 9. Nytro MegaRAID WebBIOS Configuration Utility

The testing results focused on the entire process of the virtual desktop lifecycle by capturing metrics during the desktop boot-up, user logon and virtual desktop acquisition (also referred to as ramp-up,) user workload execution (also referred to as steady state), and user logoff for the Hosted VDI model under test.

Test metrics were gathered from the hypervisor, virtual desktop, storage, and load generation software to assess the overall success of an individual test cycle. Each test cycle was not considered passing unless all of the planned test users completed the ramp-up and steady state phases (described later in this document) and unless all metrics were within the permissible thresholds as noted as success criteria. Three successfully completed test cycles were conducted for each hardware configuration and results were found to be relatively consistent from one test to the next.


Load Generation

Within each test environment, load generators were utilized to put demand on the system to simulate multiple users accessing the Citrix XenDesktop 7.1 environment and executing a typical end-user workflow. To generate load within the environment, an auxiliary software application was required to generate the end user connection to the Citrix XenDesktop 7.1 environment, to provide unique user credentials, to initiate the workload, and to evaluate the end user experience.

In the Hosted VDI test environment, sessions launchers were used simulate multiple users making a direct connection to Citrix XenDesktop 7.1 via a Citrix HDX protocol connection.

User Workload Simulation—LoginVSI

One of the most critical factors of validating a Citrix XenDesktop 7.1 deployment is identifying a real-world user workload that is easy for customers to replicate and standardized across platforms to allow customers to realistically test the impact of a variety of worker tasks. To accurately represent a real-world user workload, a third-party tool from Login Consultants was used throughout the Hosted VDI testing.

The tool has the benefit of taking measurements of the in-session response time, providing an objective way to measure the expected user experience for individual desktop throughout large scale testing, including login storms.

The Virtual Session Indexer (Login Consultants’ Login VSI 3.6) methodology, designed for benchmarking Server Based Computing (SBC) and Virtual Desktop Infrastructure (VDI) environments is completely platform and protocol independent and hence allows customers to easily replicate the testing results in their environment.

Note: In this testing, we utilized the tool to benchmark our VDI environment only.

Login VSI calculates an index based on the amount of simultaneous sessions that can be run on a single machine.

Login VSI simulates a medium workload user (also known as knowledge worker) running generic applications such as: Microsoft Office 2007 or 2010, Internet Explorer 8 including a Flash video applet and Adobe Acrobat Reader (Note: For the purposes of this test, applications were installed locally, not streamed nor hosted on Thin App).

Like real users, the scripted Login VSI session will leave multiple applications open at the same time. The medium workload is the default workload in Login VSI and was used for this testing. This workload emulated a medium knowledge working using Office, IE, printing and PDF viewing.

Once a session has been started the medium workload will repeat every 12 minutes.

During each loop the response time is measured every 2 minutes.

The medium workload opens up to 5 apps simultaneously.

The type rate is 160ms for each character.

Approximately 2 minutes of idle time is included to simulate real-world users.

Each loop will open and use:

Outlook 2007/2010, browse 10 messages.

Internet Explorer, one instance is left open (BBC.co.uk), one instance is browsed to Wired.com, Lonelyplanet.com and heavy

480 p Flash application gettheglass.com

Word 2007/2010, one instance to measure response time, one instance to review and edit document.

BullZip PDF Printer & Acrobat Reader, the word document is printed and reviewed to PDF.

Excel 2007/2010, a very large randomized sheet is opened.

PowerPoint 2007/2010, a presentation is reviewed and edited.

7-zip: using the command line version the output of the session is zipped.

You can obtain additional information on Login VSI from http://www.loginvsi.com.

Test Run Protocol

To simulate severe, real-world environments, Cisco requires the log-on and start-work sequence, known as Ramp Up, to complete in 30 minutes. Additionally, we require all sessions started, whether 170 single server users or 2000 full scale test users to become active within 2 minutes after the session is launched.

For each of the three consecutive runs on single blade (170 User) and 14-blade (2000 User) tests, the same process was followed:

1. Time 0:00:00 Started Logging on the following systems:

VDI Host servers used in test run

Profile Servers used in test run

SQL Servers used in test run

10 Launcher VMs

2. Time 0:05 Take 200 desktops out of maintenance mode Citrix XenDesktop Studio admin console

3. Time 0:06 First machines boot

4. Time 0:33 200 desktops booted on C240 M3.

5. Time 0:35 200 desktops available on C240 M3.

6. Time 0:50 Start Login VSI 3.6 Test with 200 desktops utilizing 10 Launchers

7. Time 1:20 200 desktops launched.

8. Time 1:22 200 desktops active.

9. Time 1:35 Login VSI Test Ends.

10. Time 1:50 200 desktops logged off.

11. Time 2:00 all logging terminated.

Success Criteria

There were multiple metrics that were captured during each test run, but the success criteria for considering a single test run as pass or fail was based on the key metric, VSImax. The Login VSImax evaluates the user response time during increasing user load and assesses the successful start-to-finish execution of all the initiated virtual desktop sessions.


Performance Results

The objective of the test case was to determine whether a UCS C240 M3 server equipped with 12 hot-swappable 10K RPM SAS drives and a Cisco Nytro MegaRAID controller could provide excellent end-user experience for up to 200 Citrix XenDesktop 7.1 Machine Creation Services provisioned Microsoft Windows 7 SP1 virtual desktops running on Citrix XenServer 6.2 and the required infrastructure to support them.

In order to determine the end-user experience with the hypervisor, infrastructure and virtual desktop users exercising the system simultaneously, we generated a Login VSImax score by loading the system with 250 virtual desktops and users.

Login VSI does not take into account the stress on the physical servers during the test (CPU, memory, network, nor storage.)

For that reason, we re-run the end-user experience tests taking into account those physical server factors to determine the maximum recommended virtual desktop workload for the system.

Login VSImax

Once we determined the Login VSImax, we perform three consecutive test runs generating the same result to insure integrity of the result.

To reach the Login VSImax, we ran 230 Medium Workload (with flash) Windows 7 SP1 sessions on a single server. The Login VSI score was confirmed by three consecutive runs and is shown in Figure 10 below.

Figure 10. Test with 230 Users: VSImax 214


Recommended Workload

To establish our recommended maximum workload, we ran the single server test at approximately 20% lower user density than prescribed by the Login VSImax to achieve a successful pass of the test with server hardware performance in a realistic range. Although a Login VSImax is not achieved at this load, the Login VSI Analyzer chart for the run shows very low response times over the entire run, confirming excellent end-user experience.

We have included graphs detailing the CPU, Memory utilization and network throughput during peak session load are also presented. Given adequate storage capability, the CPU utilization determined the maximum VM density per server.

Disks performance metrics are captured for Adapter Q depth, throughput rate (IOPS) and Read-Write rate in Mbps using XenServer logging tools.

The charts below present our recommended maximum Login VSI Medium workload loading on a single blade server with average and index response time below 2000 ms and maximum response times under 3000 ms.

Figure 11. 200 Citrix XenDesktop 7.1 Desktop Sessions on Citrix XenServer 6.2

Figure 12. 200 User Cisco UCS C240 M3 Memory Utilization–Test Phase

Figure 13. 200 User Cisco UCS C240 M3 VIC 1225 Network Utilization–Test Phase

Figure 14. 200 User Cisco UCS C240 M3 CPU Core Utilization–Test Phase

Figure 15. 200 User Cisco UCS C240 M3 disks throughput–Test Phase

Figure 16. 200 User Cisco UCS C240 M3 Total IOPS–Test Phase

Figure 17. 200 User C240 M3 Average Disk Queue Size–Test Phase


Conclusion

The cost barrier for mid-size to large organizations for Proofs of Concept has been shattered. For smaller organizations, there is now an entry point solution well within their reach for desktop virtualization for the first time.

The performance results demonstrate that a Cisco UCS C240 M3 Rack Server running Citrix XenServer 6.2 and XenDesktop 7.1 with a LSI Nytro MegaRAID NMR 8110-4i controller and 12 600 GB 10K RPM SAS drives provided impressive infratstructure and virtual desktop hosting density . The Cisco UCS solution delivered 200 concurrent virtual desktops with acceptable user response times and minimal bandwidth usage with an all direct-attached storage (DAS) configuration.

References

Cisco UCS C-Series Rack Server Servers

http://www.cisco.com/en/US/products/ps10265/

http://www.cisco.com/en/US/partner/products/ps12370/index.html

http://www.cisco.com/en/US/products/ps12571/index.html

LSI Mega RAID Controllers

http://www.lsi.com/downloads/Public/Nytro/docs/DB07-000134-06_LSI_Nytro_MegaRAID %28NMR r1.7%29_Application_Acceleration_RelNotes.pdf

http://www.lsi.com/downloads/Public/Nytro/downloads/Nytro XM/Tech Pubs/LSI_Nytro_MegaRAID_Application_Acceleration_Card_QIG.pdf

Citrix XenDesktop Reference Documents

http://support.citrix.com/proddocs/topic/xendesktop/cds-xendesktop-71-landing-page.html

Citrix XenDesktop–Windows 7 Optimization Guide:

http://support.citrix.com/servlet/KbServlet/download/25161-102-648285/XD - Windows 7 Optimization Guide.pdf

Citrix XenServer 6.2 Documentation:

http://support.citrix.com/proddocs/topic/xenserver/xs-wrapper-62.html