Active System 800v Reference Architecture

Reference Architecture for an Active
System 800 with VMware vSphere
Release 1.0 for Dell PowerEdge 12th Generation Blade Servers, Dell
Force10 Switches, and Dell EqualLogic iSCSI SAN with Dell Active System
Manager
Dell Virtualization Solutions Engineering
Revision: A00
Active System 800v with VMware vSphere: Reference Architecture
This document 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.
© 2012 Dell Inc. All rights reserved. Dell and its affiliates cannot be responsible for errors or omissions
in typography or photography. Dell, the Dell logo, OpenManage, Force10, Kace, EqualLogic,
PowerVault, PowerConnect, and PowerEdge are trademarks of Dell Inc. Intel and Xeon are registered
trademarks of Intel Corporation in the U.S. and other countries. Microsoft, Windows, Hyper-V, and
Windows Server are either trademarks or registered trademarks of Microsoft Corporation in the United
States and/or other countries. VMware, vSphere, ESXi, vMotion, vCloud, and vCenter are registered
trademarks or trademarks of VMware, Inc. in the United States and/or other jurisdictions. Linux is the
registered trademark of Linus Torvalds in the U. S. and other countries. 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 disclaims proprietary interest in the marks and names of others.
Page ii
Active System 800v with VMware vSphere: Reference Architecture
Revision History
Revision
A00
Description
Initial Version
Page iii
Contents
1
Introduction .......................................................................................................... 2
2
Audience .............................................................................................................. 2
3
Overview .............................................................................................................. 2
4
Design Principles .................................................................................................. 10
5
Reference Architecture .......................................................................................... 11
6
Dell Blade Network Architecture ............................................................................... 12
7
Converged Network Architecture .............................................................................. 13
8
Storage Architecture ............................................................................................. 20
9
Management Infrastructure ..................................................................................... 22
10
Scalability .......................................................................................................... 26
11
Delivery Model ..................................................................................................... 27
12
Reference ........................................................................................................... 30
Figures
Figure 1: Active System 800v Overview ............................................................................... 3
Figure 2: Active System 800v Network Topology (Logical View) ................................................ 11
Figure 3: I/O Connectivity for PowerEdge M620 Blade Server................................................... 12
Figure 4: Converged Network Logical Connectivity ............................................................... 15
Figure 5: Conceptual View of Converged Traffic Using DCB ..................................................... 16
Figure 6: vSwitch and NPAR Configuration for the hypervisor hosts ........................................... 19
Figure 7: Management Components .................................................................................. 23
Figure 8: Active System 800v Single Chassis: Rack Overview .................................................... 28
Figure 9: Active System 800v Two Chassis and Maximum Storage: Rack Overview .......................... 29
Page 1
1 Introduction
Dell Active Infrastructure is a family of converged infrastructure solutions that combine servers,
storage, networking, and infrastructure management into an integrated and optimized system that
provides general purpose virtualized resource pools. Active Infrastructure leverages Dell innovations
including unified management (Active System Manager), converged LAN/SAN fabrics, and modular
server architecture for the ultimate converged infrastructure solution. Active Infrastructure helps IT
rapidly respond to dynamic business demands, maximize data center efficiency, and strengthen IT
service quality.
The Active System 800 solution, a member of Dell Active Infrastructure family, is a converged
infrastructure solution that has been designed and validated by Dell™ Engineering. It is available to be
racked, cabled, and delivered to your site to speed deployment. Dell Services will deploy and configure
the solution tailored for business needs, so that the solution is ready to be integrated into your
datacenter. Active System 800 is offered in configurations with either VMware® vSphere® (Active
System 800v) or Microsoft® Windows Server® 2012 with Hyper-V® role enabled (Active System 800m)
hypervisors. This paper defines the Reference Architecture for the VMware vSphere based Active
System 800v solution.
Active System 800v offers converged LAN & SAN fabric design to enable a converged infrastructure
solution. The end-to-end converged network architecture in Active System 800v is based upon Data
Center Bridging (DCB) technologies that enable convergence of all LAN and iSCSI SAN traffic into a
single fabric. The converged fabric design of Active System 800v reduces complexity and cost while
bringing greater flexibility to the infrastructure solution.
Active System 800v includes Dell PowerEdgeTM M1000e blade chassis with Dell PowerEdgeTM M I/O
Aggregator, Dell PowerEdgeTM M620 blades, Dell EqualLogic™ Storage, Dell Force10™ network switches,
and VMware vSphere 5.1. The solution also includes Dell PowerEdgeTM R620 servers as management
servers. Dell Active System Manager, VMware vCenter Server, EqualLogic Virtual Storage Manager for
VMware, and Dell OpenManage™ Essentials, are included with the solution.
One of the key components of Active System 800v is Dell Active System Manager. Active System
Manager simplifies complex and error-prone infrastructure lifecycle management activities like
discovery, inventory, deployment, configuration, and on-going monitoring and management through
automation and collapsing the management interfaces into a highly optimized guided workflow. By
simplifying and automating these activities through a wizard-driven graphical user interface, Dell
Active System manager enables IT to respond rapidly to business needs, maximize data center
efficiency, and strengthen quality of IT service delivery.
2 Audience
IT administrators and IT managers — who have purchased, or are planning to purchase an Active System
configuration — can use this document to understand the design elements, hardware and software
components, and the overall architecture of the solution.
3 Overview
This section provides a high-level product overview of VMware vSphere, Dell PowerEdge blade servers,
Dell PowerEdge M I/O Aggregator, Dell Force10 S4810 switch, Dell Force10 S55 switch, and Dell
Page 2
EqualLogic Storage, as illustrated in Figure 1. Readers can skip the sections of products with which they
are familiar.
Figure 1: Active System 800v Overview
Page 3
Table 1 below describes the key solution components and the roles served.
Table 1: Solution Components
Component
Details
Hypervisor Server

Up to 2x Dell PowerEdge M1000e chassis with up to 32x
Dell PowerEdge M620 Blade Servers and embedded
VMware vSphere 5.1
Converged Fabric Switch

2xDell Force10 S4810

2x Dell PowerEdge M I/O Aggregator in each Dell
PowerEdge M1000e chassis
Storage

Up to 8x Dell EqualLogic PS6110 series arrays
Management Infrastructure

2x Dell PowerEdge R620 servers with embedded VMware
vSphere 5.1 hosting management VMs.

1x Dell Force10 S55 used as a 1Gb out-of-band
management switch

Dell Active System Manager

VMware vCenter Server

Dell Management Plug-in for VMware vCenter

Dell OpenManage Essentials

Dell EqualLogic Virtual Storage Manager (VSM) for VMware

Dell EqualLogic SAN HeadQuarters (HQ)

VMware vCloud Connector

Dell Repository Manager
Management components
hosted in the management
infrastructure
3.1 VMware vSphere 5.1
VMware vSphere 5.1 includes the ESXi™ hypervisor as well as vCenter™ Server which is used to
configure and manage VMware hosts. Key capabilities for the ESXi Enterprise Plus license level include:

VMware vMotion™: VMware vMotion technology provides real-time migration of running virtual
machines (VM) from one host to another with no disruption or downtime.

VMware High Availability (HA): VMware HA provides high availability at the virtual machine
(VM) level. Upon host failure, VMware HA automatically re-starts VMs on other physical hosts
running ESXi. VMware vSphere 5.1 uses Fault Domain Manager (FDM) for High Availability.

VMware Distributed Resource Scheduler (DRS) and VMware Distributed Power Management
(DPM): VMware DRS technology enables vMotion to automatically achieve load balancing
according to resource requirements. When VMs in a DRS cluster need fewer resources, such as
during nights and weekends, DPM consolidates workloads onto fewer hosts and powers off the
rest to reduce power consumption.
Page 4

VMware vCenter Update Manager: VMware vCenter Update Manager automates patch
management, enforcing compliance to patch standards for VMware ESXi hosts.

VMware Storage vMotion™: VMware Storage vMotion enables real-time migration of running VM
disks from one storage array to another with no disruption or downtime. It minimizes service
disruptions due to planned storage downtime previously incurred for rebalancing or retiring
storage arrays.

Host Profiles: Host Profiles standardize and simplify the deployment and management of
VMware ESXi host configurations. They capture and store validated configuration information,
including host compliance, networking, storage, and security settings.
For more information on VMware vSphere, see www.vmware.com/products/vsphere.
3.2 Dell Active System Manager
Dell Active System Manager is the Active Infrastructure management software that is part of the Active
System 800v. Active System Manager addresses key factors that impact service levels, namely
infrastructure configuration errors, incorrect problem troubleshooting, and slow recovery from failures.
Active System Manager dramatically improves the accuracy of infrastructure configuration by reducing
manual touch points.
The key capabilities of Dell Active System Manager are:

Template-based provisioning: Workload specific infrastructure requirements are encapsulated
in the form of a template which can be repeatedly applied on-demand as needed. This brings
efficiency, accuracy, and consistency in the infrastructure configuration process.

Automated configuration: Active System Manager enables simplified discovery, inventory, and
configuration of modular infrastructure. This results in better visibility and resource allocation
through efficient pooling of available resources.

Infrastructure lifecycle management: Active System Manager provides the capability to
manage the entire lifecycle of infrastructure, from discovery and on-boarding through
provisioning, on-going management, and decommissioning.

Workload failover: Active System Manager provides immediate alerting in case of a hardware
fault, and enables rapid and easy migration of the workload to other infrastructure resources.
Multiple warnings and errors are aggregated into a single console.

Guided user workflows and multi-level views: Active System Manager presents a wizarddriven graphical user interface with feature-guided, step-by-step work-flows. It provides a
graphical logical network topology view for better decision making through improved visibility.
For more information on Dell Active System Manager, see Dell Active System Manager.
3.3 Dell PowerEdge Blade Servers
Blade Modular Enclosure: The Dell PowerEdge M1000e is a high-density, energy-efficient blade chassis
that supports up to sixteen half-height blade servers, or eight full-height blade servers, and six I/O
modules. A high-speed passive mid-plane connects the server modules to the I/O modules,
management, and power in the rear of the chassis. The enclosure includes a flip-out LCD screen (for
Page 5
local configuration), six hot-pluggable/redundant power supplies, and nine hot-pluggable N+1
redundant fan modules.
Blade Servers: The PowerEdge M620 blade server is the Dell 12th generation PowerEdge half height
blade server offering:

New high-efficiency Intel® Xeon® E5-2600 family processors for more advanced processing
performance, memory, and I/O bandwidth.

Greater memory density than any previous PowerEdge server. Each PowerEdge M620 can deploy
up to 24x 32GB DIMMs, or 768GB of RAM per blade – 12TB of RAM in a single M1000e chassis.

‗Agent Free‘ management with the new iDRAC7 with Lifecycle Controller allows customers to
deploy, update, maintain, and monitor their systems throughout the system lifecycle without a
software management agent, regardless of the operating system.

The PowerEdge Select Network Adapter (formerly NDC) on the PowerEdge M620 offers three
modular choices for embedded fabric capability. With 10Gb CNA offerings from Broadcom,
QLogic & Intel, our customers can choose the networking vendor and technology that‘s right for
them and their applications, and even change in the future as those needs evolve over time.
The Broadcom and QLogic offerings offer Switch Independent Partitioning technology,
developed in partnership with Dell, which allows for virtual partitioning of the 10Gb ports.
I/O Modules: The Dell blade chassis has three separate fabrics referred to as A, B, and C. Each fabric
can have two I/O modules, for a total of six I/O module slots in the chassis. The I/O modules are A1,
A2, B1, B2, C1, and C2. Each I/O module can be an Ethernet physical switch, an Ethernet pass-through
module, FC switch, or FC pass-through module. InfiniBand™ switch modules are also supported. Each
half-height blade server has a dual-port network daughter card (NDC) and two optional dual-port
mezzanine I/O cards. The NDC connects to Fabric A. One mezzanine I/O card attaches to Fabric B, with
the remaining mezzanine I/O card attached to Fabric C.
Chassis Management: The Dell PowerEdge M1000e has integrated management through a redundant
Chassis Management Controller (CMC) module for enclosure management and integrated Keyboard,
Video, and Mouse (iKVM) modules. Through the CMC, the enclosure supports FlexAddress Plus
technology, which enables the blade enclosure to lock the World Wide Names (WWN) of the FC
controllers and Media Access Control (MAC) addresses of the Ethernet controllers to specific blade
slots. This enables seamless swapping or upgrading of blade servers without affecting the LAN or SAN
configuration.
Embedded Management with Dell’s Lifecycle Controller: The Lifecycle Controller is the engine for
advanced embedded management and is delivered as part of iDRAC Enterprise in 12th-generation Dell
PowerEdge blade servers. It includes 1GB of managed and persistent storage that embeds systems
management features directly on the server, thus eliminating the media-based delivery of system
management tools and utilities previously needed for systems management. Embedded management
includes:

Unified Server Configurator (USC) aims at local 1-to-1 deployment via a graphical user interface
(GUI) for operating system install, updates, configuration, and for performing diagnostics on
single, local servers. This eliminates the need for multiple option ROMs for hardware
configuration.
Page 6

Remote Services are standards-based interfaces that enable consoles to integrate, for example,
bare-metal provisioning and one-to-many OS deployments, for servers located remotely. Dell‘s
Lifecycle Controller takes advantage of the capabilities of both USC and Remote Services to
deliver significant advancement and simplification of server deployment.

Lifecycle Controller Serviceability aims at simplifying server re-provisioning and/or replacing
failed parts, and thus reduces maintenance downtime.
For more information on Dell Lifecycle Controllers and blade servers, see
http://content.dell.com/us/en/enterprise/dcsm-embedded-management and Dell.com/blades.
3.4 Dell PowerEdge M I/O Aggregator
The Dell PowerEdge M I/O Aggregator (IOA) is a flexible 1/10GbE aggregation device that is automated
and pre-configured for easy deployment into converged iSCSI and FCoE networks. The key feature of
the PowerEdge M I/O Aggregator is that all VLANs are allowed as a default setting. This allows the topof-rack (ToR) managed switch to perform all VLAN management related tasks. The external ports of the
PowerEdge M I/O Aggregator are automatically all part of a single link aggregation group (LAG), and
thus there is no need for Spanning-tree. The PowerEdge M I/O Aggregator can use Data Center Bridging
(DCB) and Data Center Bridging Exchange (DCBX) to support converged network architecture.
The PowerEdge M I/O Aggregator provides connectivity to the CNA/Network adapters internally and
externally to upstream network devices. Internally the PowerEdge M I/O Aggregator provides thirty-two
(32) connections. The connections are 10 Gigabit Ethernet connections for basic Ethernet traffic, iSCSI
storage traffic, or FCoE storage traffic. In a typical PowerEdge M1000e configuration with 16 halfheight blade server ports, 1-16 are used and 17-32 are disabled. If quad port CAN/Network adapters or
quarter-height blade servers are used, then ports 17-32 will be enabled.
The PowerEdge M I/O Aggregator includes two integrated 40Gb Ethernet ports on the base module.
These ports can be used in a default configuration with a 4 X 10Gb breakout cable to provide four 10Gb
links for network traffic. Alternatively these ports can be used as 40Gb links for stacking. The Dell
PowerEdge M I/O Aggregator also supports three different types of add-in expansion modules, which
are called FlexIO Expansion modules. The modules available are: 4-port 10Gbase-T FlexIO module, 4port 10G SFP+ FlexIO module, and the 2-port 40G QSFP+ FlexIO module.
The PowerEdge M I/O Aggregator modules can be managed through the PowerEdge M1000e Chassis
Management Controller (CMC) GUI. Also, the out-of-band management port on the PowerEdge M I/O
Aggregator is reached by connection through the CMC‘s management port. This one management port
on the CMC allows for management connections to all I/O modules within the PowerEdge M1000e
chassis.
For more information on Dell PowerEdge M I/O Aggregator, see
http://www.dell.com/us/business/p/poweredge-m-io-aggregator/pd
3.5 OpenManage Essentials
The Dell OpenManage™ Essentials (OME) Console provides a single, easy-to-use, one-to-many interface
through which to manage resources in multivendor operating system and hypervisor environments. It
automates basic repetitive hardware management tasks — like discovery, inventory, and monitoring—
for Dell servers, storage, and network systems. OME employs the embedded management of
Page 7
PowerEdge™ servers — Integrated Dell Remote Access Controller 7 (iDRAC7) with Lifecycle Controller —
to enable agent-free remote management and monitoring of server hardware components like storage,
networking, processors, and memory.
OpenManage Essentials helps you maximize IT performance and uptime with capabilities like:

Automated discovery, inventory and monitoring of Dell PowerEdge™ servers, Dell EqualLogic™
and Dell PowerVault™ storage, and Dell PowerConnect™ switches

Server health monitoring, as well as BIOS, firmware, and driver updates for Dell PowerEdge
servers, blade systems, and internal storage

Control of PowerEdge servers within Microsoft® Windows®, Linux®, VMware®, and Hyper-V®
environments
For more information on OpenManage Essentials, see the Data Center Systems Management page.
3.6 Dell Force10 S4810 Switches
The Force10 S-Series S4810 is an ultra-low-latency 10/40 GbE Top-of-Rack (ToR) switch purpose-built
for applications in high-performance data center and computing environments. Leveraging a nonblocking, cut-through switching architecture, the S4810 delivers line-rate L2 and L3 forwarding
capacity with ultra-low latency to maximize network performance. The compact Force10 S4810 design
provides industry leading density of 48 dual-speed 1/10 GbE (SFP+) ports, as well as four 40GbE QSFP+
uplinks to conserve valuable rack space and simplify the migration to 40Gbps in the data center core.
(Each 40GbE QSFP+ uplink can support four 10GbE ports with a breakout cable).
Powerful Quality of Service (QoS) features coupled with Data Center Bridging (DCB) support to make
the Force10 S4810 ideally suited for iSCSI storage environments. In addition, the S4810 incorporates
multiple architectural features that optimize data center network flexibility, efficiency, and
availability, including Force10‘s stacking technology, reversible front-to-back or back-to-front airflow
for hot/cold aisle environments, and redundant, hot-swappable power supplies and fans.
For more information on Force10 switches, see Dell.com/force10.
3.7 Dell Force10 S55
The Dell Force10 S-Series S55 1/10 GbE ToR switch is designed for high-performance data center
applications. The S55 leverages a non-blocking architecture that delivers line-rate, low-latency L2 and
L3 switching to eliminate network bottlenecks. The high-density Force10 S55 design provides 48GbE
access ports with up to four modular 10GbE uplinks in 1-RU to conserve valuable rack space. The
Force10 S55 switch incorporates multiple architectural features that optimize data center network
efficiency and reliability, including reversible front-to-back or back-to-front airflow for hot/cold aisle
environments and redundant, hot-swappable power supplies and fans.
For more information on Force10 switches, see Dell.com/force10.
3.8 Dell EqualLogic PS6110 Series iSCSI SAN Arrays
The Dell EqualLogic PS6110 series arrays are 10GbE iSCSI SAN arrays. The EqualLogic PS6110 arrays
provide 10GbE connectivity using SPF+ or lower-cost 10GBASE-T. A dedicated management port allows
better utilization of the 10GbE ports for the storage network I/O traffic by segmenting the
Page 8
management traffic. The PS6110 Series 10GbE arrays can use Data Center Bridging (DCB) to improve
Ethernet quality of service and greatly reduce dropped packets for an end-to-end iSCSI over DCB
solution, from host adapters to iSCSI target.
The key features of the EqualLogic PS6110 series arrays are:

Dedicated 10GbE ports that enable you to use SFP+ or 10GBASE-T cabling options

Simplified network storage management with a dedicated management port

2.5" drives in 2U or 3.5" drives in 4U form factors

SAS, NL-SAS and solid state drive and hybrid options available

Supports DCB and DCBX technologies for use in a converged LAN & iSCSI SAN network

Efficient data protection and simplified management and operation of the EqualLogic SAN
through tight integration with Microsoft®, VMware® and Linux® host operating platforms

Includes a full-featured array monitoring and analysis tool to help strengthen your ability to
analyze and optimize storage performance and resource allocation
For more information on EqualLogic storage, see Dell.com/equallogic.
3.9 PowerEdge R620 Management Server
The Dell PowerEdge R620 uses Intel Xeon E5-2600 series processors and Intel chipset architecture in a
1U rack mount form factor. These servers support up to ten 2.5‖ drives and provide the option for an
LCD located in the front of the server for system health monitoring, alerting, and basic management
configuration. An AC power meter and ambient temperature thermometer are built into the server,
both of which can be monitored on this display without any software tools. The server features two
CPU sockets and 24 memory DIMM slots.
For more information, see the PowerEdge R620 guides at Dell.com/PowerEdge.
3.10 Dell Management Plug-in for VMware vCenter
Dell Management Plug-in for VMware vCenter is included in the solution. This enables customers to:

Get deep-level detail from Dell servers for inventory, monitoring, and alerting — all from
within vCenter

Apply BIOS and Firmware updates to Dell servers from within vCenter

Automatically perform Dell-recommended vCenter actions based on Dell hardware alerts

Access Dell hardware warranty information online

Rapidly deploy new bare metal hosts using Profile features
For more information, see the web page for Dell Management Plug-in for VMware vCenter.
Page 9
3.11 Dell Cloud Connectivity using VMware vCloud Connector
VMware vCloud Connector lets you view, operate on, and transfer your computing resources across
vSphere and vCloud Director in your private cloud environment, as well as Dell vCloud public cloud.

Expand your view across hybrid clouds. Use a "single pane of glass" management interface that
seamlessly spans your private vSphere and public Dell vCloud environment.

Extend your datacenter. Move VMs, vApps, and templates from private vSphere to a Dell
vCloud to free up your on-premise datacenter resources as needed.

Consume cloud resources with confidence. Run Development, QA, and production workloads
using Dell vCloud, a VMware technology-based public cloud.
The Dell Cloud with VMware vCloud™ Datacenter is an enterprise-class, multi-tenant infrastructure-asa-service (IaaS) public cloud solution that is hosted in secured Dell data centers. Utilizing VMware
vCloud Connector, Dell Cloud provides you with unique hybrid cloud capabilities to extend your internal
data center with Dell and VMware by transitioning your VMware virtualized workloads into our vCloud
data center. vCloud hosting provides you with a secure, manageable, and flexible public cloud
application.
For more information, see Dell vCloud website.
4 Design Principles
The following principles are central to the design and architecture of Active System 800v Solution.
1. Converged Network: The infrastructure is designed to achieve end-to-end LAN and SAN
convergence.
2. Redundancy with no single point-of-failure: Redundancy is incorporated in every critical
aspect1 of the solution, including server high availability features, networking, and storage.
3. Management: Provide integrated management using VMware vCenter, Dell Management Plug-in
for VMware vCenter, Dell OpenManage Essentials, and Equallogic Virtual Storage Manager (VSM)
for VMware plug-in.
4. Cloud Enabled: The solution also includes connectivity to Dell vCloud using VMware vCloud
Connector.
5. Integration into an existing data center: This architecture assumes that there is an existing
10 Gb Ethernet infrastructure with which to integrate.
6. Hardware configuration for virtualization: This solution is designed for virtualization for most
general cases. Each blade server is configured with appropriate processor, memory, and
network adapters, as required for virtualization.
7. Racked, Cabled, and Ready to be deployed: Active System 800v is available racked, cabled,
and delivered to the customer site, ready for deployment. Components are configured and
racked to optimize airflow and thermals. Based on customer needs, different rack sizes and
configurations are available to support various datacenter requirements.
1
Out of band management is not considered critical to user workload and does not have redundancy.
Page 10
8. Power, Cooling, and Weight Considerations: Active System 800v solution is configured with
Power Distribution Units (PDUs) to meet the power requirements of the components as well as
regional constraints. Power consumed, cooling required, and information regarding rack weight
are provided to enable customers to plan for the solution.
9. Flexible configurations: Active System 800v is pre-configured to suit most customer needs for
a virtualized infrastructure. The solution also supports additional options, such as configuring
racks, server processors, server memory, and storage, based on customer needs.
5 Reference Architecture
This solution consists of a PowerEdge M1000e chassis populated with PowerEdge M620 blade servers
running VMware ESXi. Figure 2 provides the high-level reference architecture for the solution.
Figure 2: Active System 800v Network Topology (Logical View)
Page 11
The figure shows high-level logical connectivity between various components. Subsequent sections of
this document provide more detailed connectivity information.
6 Dell Blade Network Architecture
In Active System 800v, the Fabric A in PowerEdge M1000e blade chassis contains two Dell PowerEdge M
I/O Aggregator modules, one in I/O module slot A1 and the other in slot A2, and is used for converged
LAN and SAN traffic. Fabric B and Fabric C (I/O Module slot B1, B2, C1, and C2) are not used.
The PowerEdge M620 blade servers use the Broadcom 57810-k Dual port 10GbE KR Blade NDC to
connect to the Fabric A. Dell PowerEdge M I/O Aggregator modules uplink to Dell Force10 S4810
network switches providing LAN AND SAN connectivity.
Figure 3 below illustrates how the fabrics are populated in the PowerEdge M1000e blade server chassis
and how the I/O modules are utilized.
Figure 3: I/O Connectivity for PowerEdge M620 Blade Server
Network Interface Card Partition (NPAR): NPAR allows splitting the 10GbE pipe on the NDC with no
specific configuration requirements in the switches. With NPAR, administrators can split each 10GbE
port of an NDC into four separate partitions, or physical functions, and allocate the desired bandwidth
and resources as needed. Each of these partitions is enumerated as a PCI Express function that appears
as a separate physical NIC in the server, operating systems, BIOS, and hypervisor. Active System 800v
solution takes advantage of NPAR. Partitions are created for various traffic types and bandwidth is
allocated, as described in the following section.
Page 12
7 Converged Network Architecture
One of the key attributes of the Active System 800v is the convergence of SAN and LAN over the same
network infrastructure. LAN and iSCSI SAN traffic share the same physical connections from servers to
storage. The converged network is designed using Data Center Bridging (IEEE 802.1) and Data Center
Bridging Exchange (IEEE 802.1AB) technologies and features. The converged network design drastically
reduces cost and complexity by reducing the components and physical connections and the associated
efforts in deploying, configuring, and managing the infrastructure.
Data Center Bridging is a set of related standards to achieve enhance Ethernet capabilities, especially
in datacenter environments, through converge network connectivity. The functionalities provided by
DCB and DCBX are:

Priority Flow Control (PFC): This capability provides zero packet loss under congestion by
providing a link level flow control mechanism that can be controlled independently for each
priority.

Enhanced Transmission Selection (ETS): This capability provides a framework and mechanism
for bandwidth management for different traffic types by assigning bandwidth to different
frame priorities.

Data Center Bridging Exchange (DCBX): This functionality is used for conveying the
capabilities and configuration of the above features between neighbors to ensure consistent
configuration across the network.
Dell Force10 S4810 switches, Dell PowerEdge M I/O Aggregator modules, Broadcom 57810-k Dual port
10GbE KR Blade NDCs, and EqualLogic PS6110 iSCSI SAN arrays enable Active System 800v to utilize
these technologies, features, and capabilities to support converged network architecture.
7.1 Converged Network Connectivity
The Active System 800v design is based upon a converged network. All LAN and iSCSI traffic within the
solution share the same physical connections. The following section describes the converged network
architecture of Active System 800v.
Connectivity between hypervisor hosts and converged network switches: The compute cluster
hypervisor hosts, PowerEdge M620 blade servers, connect to the Force10 S4810 switches through the
PowerEdge M I/O Aggregator I/O Modules in the PowerEdge M1000e blade chassis. The management
cluster hypervisor hosts, PowerEdge R620 rack servers, directly connect to the Force10 S4810 switches.

Connectivity between the Dell PowerEdge M620 blade servers and Dell PowerEdge M I/O
Aggregators: The internal architecture of PowerEdge M1000e chassis provides connectivity
between the Broadcom 57810-k Dual port 10GbE KR Blade NDC in each PowerEdge M620 blade
server and the internal ports of the PowerEdge M I/O Aggregator. The PowerEdge M I/O
Aggregator has 32 x 10GbE internal ports. With one Broadcom 57810-k Dual port 10GbE KR
Blade NDC in each PowerEdge M620 blade, blade servers 1-16 connect to the internal ports 1-16
of each of the two PowerEdge M I/O Aggregator. Internal ports 17-32 of each PowerEdge M I/O
Aggregator are disabled and not used.
Page 13

Connectivity between the Dell PowerEdge M I/O Aggregator and Force10 S4810 switches:
The two PowerEdge M I/O Aggregator modules are configured to operate as a port aggregator
for aggregating 16 internal ports to eight external ports.
The two fixed 40GbE QSFP+ ports on each PowerEdge M I/O Aggregator are used for network
connectivity to the two Force10 S4810 switches. These two 40GbE ports on each PowerEdge M
I/O Aggregator are used with a 4 x 10Gb breakout cable to provide four 10Gb links for network
traffic from each 40GbE port. Out of the 4 x 10Gb links from each 40GbE port on each
PowerEdge M I/O Aggregator, two links connect to one of the Force10 S4810 switches and the
other two links connect to the other Force10 S4810 switch. Due to this design, each PowerEdge
M1000e chassis with two PowerEdge M I/O Aggregator modules will have total of 16 x 10Gb
links to the two Force10 S4810 switches. This design ensures load balancing while maintaining
redundancy.

Connectivity between the Dell PowerEdge R620 rack servers and Force10 S4810 switches:
Both of the PowerEdge R620 servers have two 10Gb connections to the Force10 S4810 switches
through one Broadcom 57810 Dual Port 10Gb Network Adapter in each of the PowerEdge R620
servers.
Connectivity between the two converged network switches: The two Force10 S4810 switches are
connected using Inter Switch Links (ISLs) using two 40 Gbps QSFP+ links. Virtual Link Trunking (VLT) is
configured between the two Force10 S4810 switches. This design eliminates the need for Spanning
Tree-based networks; and also provides redundancy as well as active-active full bandwidth utilization
on all links.
Connectivity between the converged network switches and iSCSI storage arrays: Each EqualLogic
PS6110 array in Active System 800v uses two controllers. The 10Gb SFP+ port on each EqualLogic
controller is connected to the Force10 S4810 switches. This dual controller configuration provides high
availability and load balancing.
Figure 4 below illustrates the resultant logical converged network connectivity within the Active
System 800v solution.
Page 14
Figure 4: Converged Network Logical Connectivity
7.2 Converged Network Configuration
This section provides details of the different configurations in the Active System 800v that enable the
converged network in the solution.
DCB Configuration: Data Center Bridging (DCB) and Data Center Bridging Exchange (DCBX) technologies
are used in Active System 800v to enable converged networking. The Force10 S4810 switches,
PowerEdge M I/O Aggregator modules, Broadcom 57810-k Dual port 10GbE KR Blade NDCs, Broadcom
57810 Dual Port 10Gb Network Adapters, and EqualLogic PS6110 iSCSI SAN arrays support DCB and
DCBX.
Within the Active System 800v environment, DCB settings are configured within the Force10 S4810
switches. Utilizing the DCBX protocol, these settings are then automatically propagated to the
PowerEdge M I/O Aggregator modules. Additionally, the DCB settings are also propagated to the
network end nodes, including the Broadcom Network Adapters in PowerEdge R620 rack servers, the
Page 15
Broadcom NDCs in the PowerEdge M620 blade servers, and the EqualLogic PS6110 storage controllers.
The DCB settings are not propagated to the Force10 S55 out-of-band management switch and the
associated out-of-band management ports but the out-of-band management traffic going to the core
from Force10 S55 switch traverses through the Force10 S4810 switches. When the out-of-band
management traffic traverses through the Force10 S4810 switches, it obeys the DCB settings.
DCB technologies enable each switch-port and each network device-port in the converged network to
simultaneously carry multiple traffic classes, while guaranteeing performance and QoS. In case of
Active System 800v, DCB settings are used for the two traffic classes: (i) Traffic class for iSCSI traffic,
and (ii) Traffic class for all non-iSCSI traffic, which, in the case of Active System 800v, are different
LAN traffic types. DCB ETS settings are configured to assign bandwidth limits to the two traffic classes.
These bandwidth limitations are effective during periods of contention between the two traffic classes.
The iSCSI traffic class is also configured with Priority Flow Control (PFC), which guarantees lossless
iSCSI traffic.
The Broadcom Network Adapters and the Broadcom NDCs support DCB and DCBX. This capability, along
with iSCSI hardware offload, allows Active System 800v solution to include an end-to-end converged
network design, without requiring support from the VMware vSphere hypervisor for DCB.
Figure 5 below provides a conceptual view of converged traffic with Data Center Bridging in Active
System 800v.
Figure 5: Conceptual View of Converged Traffic Using DCB
Virtual Link Trunking (VLT) for S4810s: Inside each Active System 800v, a Virtual Link Trunking
interconnect (VLTi) is configured between the two Force10 S4810 switches using the Virtual Link
Trunking (VLT) technology. VLT peer LAGs are configured between the PowerEdge M I/O Aggregator
modules and Force10 S4810 switches, and also between the Force10 S4810 switch and the Force10
S4810 switches.
Virtual Link Trunking technology allows a server or bridge to uplink a single trunk into more than one
Force10 S4810 switch, and to remain unaware of the fact that the single trunk is connected to two
different switches. The switches, a VLT-pair, make themselves appear as a single switch for a
Page 16
connecting bridge or server. Both links from the bridge network can actively forward and receive
traffic. VLT provides a replacement for Spanning Tree-based networks by providing both redundancy
and active-active full bandwidth utilization.
Major benefits of VLT technology are:
1. Dual control plane on the access side that lends resiliency.
2. Full utilization of the active LAG interfaces.
3. Rack-level maintenance is hitless and one switch can be kept active at all times.
Note that the two switches can also be stacked together. However, this is not recommended, as this
configuration will incur downtime during firmware updates of the switch or failure of stack links.
NPAR configuration:
In Active System 800v, each port of the Broadcom 57810-k Dual port 10GbE KR Blade NDCs in the
PowerEdge M620 blade servers, and the Broadcom 57810 Dual Port 10Gb Network Adapters in
PowerEdge R620 rack servers is partitioned into four ports using NPAR to obtain a total of eight I/O
ports on each server. As detailed in the subsequent sections, one partition each on every physical I/O
port is assigned to management traffic, vMotion traffic, VM traffic and iSCSI traffic.
The Broadcom NDC and the Broadcom Network Adapter allow setting a maximum bandwidth limitation
to each partition. Setting maximum bandwidth at 100 will prevent the artificial capping of any
individual traffic type during periods of non-contention. For customers with specific requirements,
NPAR maximum bandwidth settings may be modified to limit the maximum bandwidth available to a
specific traffic type, regardless of contention.
The Broadcom NDC and the Broadcom Network Adapter also allow setting relative bandwidth
assignments for each partition. While utilizing NPAR in conjunction with Data Center Bridging (DCB) and
Data Center Bridging Exchange (DCBX), the relative bandwidth settings of the partitions are not
enforced. Due this fact, the relative bandwidth capability of the Broadcom NDCs and the Broadcom
Network Adapters are not utilized in Active System 800v.
iSCSI hardware offload: In Active System 800v, iSCSI hardware offload functionality is used in the
Broadcom 57810-k Dual port 10GbE KR Blade NDCs in the PowerEdge M620 blade servers, and also in
the Broadcom 57810 Dual Port 10Gb Network Adapters in the PowerEdge R620 rack servers. The iSCSI
offload protocol is enabled on one of the partitions on each port of the NDC or the Network Adapter.
With iSCSI hardware offload, all iSCSI sessions are terminated on the Broadcom NDC or on the
Broadcom Network Adapter.
Traffic isolation using VLANs: Within the converged network, the LAN traffic is separated into four
unique VLANs; one VLAN each for management, vMotion, VM traffic, and out-of-band management. The
iSCSI traffic also uses a unique VM. Network traffic is tagged with the respective VLAN ID for each
traffic type in the virtual switch. Routing between the management and out-of-band management
VLANs is required to be configured in the core or the Force10 S4810 switches. Additionally, the Force10
S4810 switch ports that connect to the blade servers are configured in VLAN trunk mode to pass traffic
with different VLANs on a given physical port. The table 2 below provides an overview of different
traffic types segregated by VLANs in the Active System 800v, and which edge devices with which they
are associated.
Page 17
Table 2: VLAN Overview
Traffic Type
(VLAN segregation)
Management
Description
Associated Network Device
vSphere management traffic and
Broadcom NDC and
Broadcom Network Adapter
Active System 800v management services
vMotion
VMware vMotion traffic
Broadcom NDC and
Broadcom Network Adapter
VM
LAN traffic generated by compute cluster
VMs
Broadcom NDC and
Broadcom Network Adapter
iSCSI
iSCSI SAN traffic
Broadcom NDC and
Broadcom Network Adapter
Out-of-Band
Management
Out-of-Band Management traffic
iDRAC, CMC, and EqualLogic
Management Ports
Hypervisor network configuration for LAN and iSCSI SAN traffic: VMware ESXi hypervisor is configured
for the LAN and iSCSI SAN traffic that are associated with the blade servers. LAN traffic in Active
System 800v solution is categorized into four traffic types: VM traffic, management traffic, vMotion
traffic, and Out-of-Band (OOB) management traffic. OOB management traffic is associated with CMC,
iDRAC, and EqualLogic SAN management traffic. VM traffic, management traffic, and vMotion traffic
are associated with the blade servers in the compute cluster and the rack servers in the management
servers. Similarly, iSCSI SAN traffic is also associated with the blade servers and the rack servers. On
each hypervisor host within the compute cluster and the management cluster, a virtual switch is
created for each of the three LAN traffic types associated with the blade and the rack servers, and also
for the iSCSI traffic.
On the compute cluster hosts (the PowerEdge M620 blade servers), one vSwitch each is created for VM
traffic, vSphere management traffic, vMotion traffic, and iSCSI traffic. Two partitions, one from each
physical network port, are connected as uplinks to each of the virtual switches. This creates a team of
two network ports, enabling NIC failover and load balancing for each vSwitch. On the management
cluster hosts (the PowerEdge R620 rack servers), one vSwitch each is created for management traffic,
vMotion traffic, and iSCSI traffic. In this case, all VMs are management VMs, so the VM traffic and the
vSphere management traffic are on the same management VLAN. Due to this fact, the VM traffic port
group and the vSphere management traffic port group are on the same vSwitch.
The resultant compute cluster and management cluster hypervisor host configuration is illustrated in
Figure 6.
Page 18
Figure 6: vSwitch and NPAR Configuration for the Hypervisor Hosts
Page 19
Load Balancing and Failover: This solution uses Route based on the originating virtual switch port ID
configuration at the vSwitch for load balancing the LAN traffic. Any given virtual network adapter will
use only one physical adapter port at any given time. In other words, if a VM has only one virtual NIC, it
will use only one physical adapter port at any given time. The reason for choosing this option is that it
is easy to configure and provides load balancing across VMs, especially in the case of a large number of
VMs.
Uplinks: There are several options to uplink the Force10 switches to the core network. Selecting the
uplink option depends on the customer core network and customer requirements. One simple option is
to create multiple uplinks on each switch and connect them to the core network switches. Uplink LAGs
can then be created from the Force10 S4810 switches to the core network.
8 Storage Architecture
EqualLogic PS6110 provides capabilities essential to the Active System 800v design, like 10Gb
connectivity, flexibility in configuring RAID arrays and creating volumes, thin provisioning, and storage
tiering, while providing tight integration with VMware vSphere for better performance and
manageability through the use of EqualLogic MEM and EqualLogic VSM for VMware.
8.1 EqualLogic Group and Pool Configuration
Each EqualLogic array (or member) is assigned to a particular group. Groups help in simplifying
management by enabling management of all members in a group from a single interface. Each group
contains one or more storage pools. Each pool must contain one or more members and each member is
associated with only one storage pool.
The iSCSI volumes are created at the pool level. In the case where multiple members are placed in a
single pool, the data is distributed amongst the members of the pool. With data being distributed over
a larger number of disks, the potential performance of iSCSI volumes within the pool is increased with
each member added.
8.2 RAID Array Design
The storage array RAID configuration is highly dependent on the workload in your virtual environment.
The EqualLogic PS series storage arrays support four RAID types: RAID 6, RAID 10, and RAID 50. The
RAID configuration will depend on workloads and customer requirements. In general, RAID 10 provides
the best performance at the expense of storage capacity, especially in random I/O situations. RAID 50
generally provides more usable storage, but has less performance than RAID 10. RAID 6 provides better
data protection than RAID 50.
For more information on configuring RAID in EqualLogic, refer to the white paper, How to Select the
Correct RAID for an EqualLogic SAN.
8.3 Volume Size Considerations
Volumes are created in the storage pools. Volume sizes depend on the customer environment and the
type of workloads. Volumes must be sized to accommodate not only the VM virtual hard drive, but also
the size of the virtual memory of the VM and additional capacity for any snapshots of the VM.
Page 20
It is important to include space for the guest operating system memory cache, snapshots, and VMware
configuration files when sizing these volumes. Additionally, you can configure thin-provisioned volumes
to grow on demand only when additional storage is needed for those volumes. Thin provisioning can
increase the efficiency of storage utilization.
With each volume created and presented to the servers, additional iSCSI sessions are initiated. When
planning the solution, it is important to understand that group and pool limits exist for the number of
simultaneous iSCSI sessions that can created.
For more information, refer to the current EqualLogic Firmware (FW) Release Notes available at the
EqualLogic Support site.
8.4 Drive Types and Automated Tiered Storage
Dell EqualLogic PS6110 arrays, with the 10Gb dual-controller configuration, provide high bandwidth for
data flows. This bandwidth is complemented with a large variety of drives in multiple speeds and sizes,
including 10K RPM and 15K RPM SAS drives, 7.2K RPM NL-SAS drives and solid-state disks. The reference
architecture presented in this document shows EqualLogic PS6110X arrays with 24 x 10K RPM SAS drives
in each array. The disk and array type should be selected by carefully considering the workload
requirements. Active System 800v supports a maximum of 8 x PS6110 arrays.
EqualLogic PS arrays provide IT organizations numerous techniques for storage tiering as a standard
part of their all-inclusive feature set. These techniques extend the automation at the core of the PS
Series design philosophy, while allowing broad customization of storage tiers to suit a wide range of
business and organizational requirements.
8.5 Multipath Configuration
The Dell EqualLogic PS Series storage array supports multiple iSCSI SAN connections for performance
and reliability. Multi-Path I/O (MPIO) provides multiple paths from servers to storage, delivering fault
tolerance, high availability, and improved performance. Active System 800v uses EqualLogic Multipath
Extension Module (MEM) for VMware vSphere to enable MPIO for the iSCSI storage.
EqualLogic MEM offers:

Ease of installation and iSCSI configuration in ESXi servers

Increased bandwidth

Reduced network latency

Automatic load balancing across multiple active paths

Automatic connection management

Automatic failure detection and failover

Multiple connections to a single iSCSI target
Once installed, the EqualLogic MEM will automatically create iSCSI sessions to each member that a
volume spans. As the storage environment changes, the MEM will respond by automatically adding or
removing iSCSI sessions as needed.
Page 21
As storage I/O requests are generated on the ESXi hosts, the MEM plug-in will intelligently route these
requests to the array member best suited to handle the request. This results in efficient load balancing
of the iSCSI storage traffic, reduced network latency and increased bandwidth.
For more information on EqualLogic MEM, refer to white-paper, Configuring and Installing the
EqualLogic Multipathing Extension Module for VMware vSphere 5.1, 5.0 and 4.1 and PS Series SANs.
9 Management Infrastructure
Within the Active System 800v solution, two Dell PowerEdge R620 servers and one Dell Force10 S55
1/10GbE Ethernet switch are used for the management infrastructure. The Force10 S55 switch is used
for out-of-band management connectivity for Dell CMC, Dell iDRAC, and the management ports on Dell
EqualLogic arrays. The management cluster infrastructure imitates the compute cluster in using
converge network infrastructure and configuration. The PowerEdge R620 servers are connected to the
Force10 S4810 switches using Broadcom 57810 Dual Port 10Gb network adapters. The management
servers are connected to the EqualLogic storage through the two Force10 S4810 switches.
Note that the EqualLogic storage is shared between the management cluster and the compute cluster.
The EqualLogic storage must be sized so that sufficient capacity and bandwidth are allocated for both
the management VMs and compute VMs.
The PowerEdge R620 servers run VMware ESXi 5.1 hypervisor and are a part of the unique vSphere
Cluster for management. VMware High Availability is enabled in that cluster to provide HA for virtual
machines. Admission control is disabled in the VMware HA Cluster. If admission control is enabled,
VMware HA would prevent putting one of the management servers in maintenance mode, since this
would violate HA policy of having more than one active server in the cluster.
The Active System 800v solution includes the necessary management components required to manage
the Active System 800v infrastructure, including the Converged Infrastructure management software,
Dell Active System Manager. The following management components are included in the Active System
800v solution.

Dell Active System Manager

VMware vCenter Server

Dell Management Plug-in for VMware vCenter

Dell OpenManage Essentials (OME)

Dell EqualLogic Virtual Storage Manager (VSM) for VMware

Dell EqualLogic SAN HeadQuarters (HQ)

Dell Repository Manager

VMware vCloud Connector
These components are installed in virtual machines installed as virtual machines in the management
infrastructure as illustrated in Figure 7.
Page 22
Figure 7: Management Components
The remainder of this section will provide an introduction to each component and how they are
integrated into the Active System 800v solution.
9.1 Dell Active System Manager
As described in section 3.2, ―Dell Active System Manager‖, the Dell Active System Manager is the Active
Infrastructure management software that is part of the Active System 800v solution. The Dell Active
System Manager virtual appliance is deployed on the management cluster. For fullest functionality,
direct internet access, or access through a proxy, is recommended.
Active System Manager addresses key factors that impact service levels, namely infrastructure
configuration errors, incorrect problem troubleshooting, and slow recovery from failures. Active System
Manager dramatically improves the accuracy of infrastructure configuration by reducing manual touch
points.
As highlighted in section 3.2, Dell Active System Manager provides capabilities like, template-based
infrastructure provisioning, automated infrastructure configuration, infrastructure lifecycle
management, workload failover, and provides a guided user workflow through its wizard driven
graphical interface.
For more information on Dell Active System Manager, see Dell Active System Manager.
9.2 Dell OpenManage Essentials (OME)
In the Active System 800v, Dell OpenManage Essentials (OME) is sized and configured to monitor the
Active System 800v solution components. It is deployed on a Windows 2008 R2 virtual machine within
the management cluster. High availability of the OME virtual machine is provided by VMware High
Page 23
Availability service. OME utilized a local SQL Express database. For fullest functionality, direct internet
access, or through a proxy, is recommended.
Within the Active System 800v, OME is utilized for discovery, inventory, and hardware level monitoring
of blade & Rack servers, blade chassis, PowerEdge M I/O Aggregator modules, EqualLogic storage, and
Force10 network switches. Each of these components are configured to send SNMP traps to the
centralized OME console to provide a single pane of glass monitoring interface for major hardware
components. OME provides a comprehensive inventory of solution component thought WS-MAN and
SNMP inventory calls. For instance, reporting is available to provide blade and rack server firmware
versions or solution warranty status. OME can be used as the single point of monitoring for all hardware
components within an enterprise.
For more information on OpenManage Essentials, see the Data Center Systems Management page.
9.3 Dell Repository Manager (DRM)
Within the Active System 800v solution, Dell Repository Manager (DRM) is installed on the same
Windows 2008 R2 VM as Dell OpenManage Essentials. DRM is an application that allows IT Admins to
more easily manage system updates. DRM provides a searchable interface used to create custom
collections known as bundles and repositories of Dell Update Packages (DUPs). These bundles and
repositories allow for the deployment of multiple firmware, BIOS, driver, and software updates at
once. Additionally, Dell Repository Manager makes it easier to locate specific updates for a particular
platform, which saves you time. For example, in Repository Manager you can create a bundle with the
latest updates for a Dell PowerEdge M620. DRM can be used in conjunction with other OpenManage
tools helps to ensure that your PowerEdge server is kept up to date.
For more information on Dell Repository Manager, see
http://content.dell.com/us/en/enterprise/d/solutions/repository-manager.
9.4 Dell Management Plug-in for VMware vCenter (DMPVV)
Dell Management Plug-in for VMware vCenter is deployed as a virtual appliance within the management
cluster, and is attached to the VMware vCenter Server within the Active System 800v stack. DMPVV
communicates with the VMware vCenter Server, the hypervisor management interfaces, and server outof-band management interfaces (iDRAC). For ease of appliance, firmware updates and warranty
information, it is recommend that the DMPVV appliance has access to an internet connect either
directly, or thought a proxy. Dell Management Plug-in for VMware vCenter enables customers to:

Get deep-level detail from Dell servers for inventory, monitoring, and alerting — all from
within vCenter

Apply BIOS and Firmware updates to Dell servers from within vCenter

Automatically perform Dell-recommended vCenter actions based on Dell hardware alerts

Access Dell hardware warranty information online

Rapidly deploy new bare metal hosts using Profile features
For more information, see the web page for Dell Management Plug-in for VMware vCenter.
Page 24
9.5 Dell EqualLogic Virtual Storage Manager (VSM) for VMware
Within Active System 800v, the Dell EqualLogic Virtual Storage Manager (VSM) for VMware is deployed
as a virtual appliance within the management cluster and is attached to the VMware vCenter Server
within the Active System 800v stack. VSM communicates with the dedicated management interfaces of
the EqualLogic storage enclosures over the out-of-band network. VSM enables customers to preform
many storage administrative tasks from vSphere client including:

Create Smart Copy snapshots, replicas, and clones of various types of VMware Infrastructure
(VI) objects.

Restore the state of virtual machines using saved Smart Copy snapshots and replicas.

Setup replication of data stores and sets of data stores stored on one PS Series group to a
secondary PS Series group (potentially at a remote location) for disaster tolerance.

Recover from replicas on the secondary site, including failover and failback of virtual machines
and their data.

Create Virtual Desktop Infrastructure (VDI) manual desktop pools.

Provision of data stores on EqualLogic iSCSI volumes.
9.6 Dell EqualLogic SAN HQ
Within the Active System 800, Dell EqualLogic SAN HQ is installed on the same Windows 2008 R2 VM as
OpenManage Essentials. SAN HQ communicates with the dedicated management interface of the
EqualLogic storage enclosure to gather performance and event logs.
Dell EqualLogic SAN HQ provides consolidated performance and robust event monitoring across multiple
groups. The key benefits of EqualLogic SAN HQ include:

Multi-Group Management: EqualLogic SAN HQ enables centralized monitoring of multiple
EqualLogic PS Series groups from a single graphical interface.

Comprehensive information about the EqualLogic PS Series arrays: EqualLogic SAN HQ
provides comprehensive information on configuration, capacity, I/O performance and network
performance for EqualLogic PS Series groups, pools, members, disks, volumes and volume
collections. These in depth analytical tools, enable flexible, granular views of SAN resources
and provide quick notification of hardware, capacity, and performance-related problems.

Experimental analysis: EqualLogic SAN HQ collects information on current hardware
configuration and distribution of reads and writes and provides information about PS Series
group performance, relative to a specific workload. Customers can perform experimental
analysis to determine if a group has reached its full capabilities, or whether they can increase
the group workload with no impact on performance. This helps in identifying requirements for
storage growth and future planning.

Events and alerts: EqualLogic SAN HQ provides performance related and email alerts and
hardware alarms on multiple parameters. This feature ensures users take timely action to make
data more available and more secure.
Page 25

Formatted reports, graphs and archives: Customizable reports and graphs are available on
performance, capacity utilization and trending, group configuration with alerts, replication,
status, host connections, and more.
9.7 VMware vCloud Connector
VMware vCloud Connector is an optional component of the Active System 800v solution. When included,
it is deployed upon the management stack, alongside other management VMs. For the base
functionality, three VMs are necessary, a single ‗server‘ VM and two ‗node‘ VMs. The node VMs are
responsibility for the physical transfer of VM workloads. Within the Active System 800v, two of these
components, the server and the local node, are installed. The third component, ‗remote‘ node VM,
should be installed outside of the Active System 800v solution, near the infrastructure to which it
provides connectivity.
After deploying the VMware vCloud Connector ‗node‘ VMs, the size of the virtual disk may have to be
increased based on the size of expected VM to be transferred and the number of concurrent transfers
anticipated.
As described in the section 3.11 of this document, ―Dell Cloud Connectivity using VMware vCloud
Connector‖, VMware vCloud Connector lets you view, operate on, and transfer your computing
resources across vSphere and vCloud Director in your private cloud environment, as well as Dell vCloud
public cloud. The key capabilities provided by VMware vCloud Connector are:

Expand your view across hybrid clouds. Use a "single pane of glass" management interface that
seamlessly spans your private vSphere and public Dell vCloud environment.

Extend your datacenter. Move VMs, vApps, and templates from private vSphere to a Dell
vCloud to free up your on-premise datacenter resources as needed.

Consume cloud resources with confidence. Run Development, QA, and production workloads
using Dell vCloud, a VMware technology-based public cloud.
The Dell Cloud with VMware vCloud™ Datacenter is an enterprise-class, multi-tenant infrastructure-asa-service (IaaS) public cloud solution that is hosted in secured Dell data centers. Utilizing VMware
vCloud Connector, Dell Cloud provides you with unique hybrid cloud capabilities to extend your internal
data center with Dell and VMware by transitioning your VMware virtualized workloads into our vCloud
data center. vCloud hosting provides you with a secure, manageable, and flexible public cloud
application.
10 Scalability
As workloads increase, the solution can be scaled to provide additional compute and storage resources
independently.
Scaling Compute and Network Resources: This solution is configured with two Force10 S4810 network
switches. Up to two PowerEdge M1000e chassis can be added to the two Force10 S4810 switches. In
order to scale the compute nodes beyond two chassis, new Force10 S4810 switches need to be added.
Additional switches can either be stacked together and/or connected to this distribution switch based
on customer needs.
Scaling Storage Resources: EqualLogic storage can be scaled seamlessly and independent of the
compute and network architectures. Additional EqualLogic PS6110 arrays of same or different
Page 26
configuration can be added to the existing PS 6110 arrays. New volumes can be created or existing
volumes can be expanded to utilize the capacity in the added enclosures. Active System 800v solution
can scale up to maximum of 8 arrays. To scale beyond this, additional racks can be added which may
require additional switches and networking.
11 Delivery Model
This Reference Architecture can be purchased as a complete solution, the Dell Active System 800v.
This solution is available to be racked, cabled, and delivered to the customer site, to speed
deployment. Dell Services will deploy and configure the solution tailored to the business needs of the
customer and based on the architecture developed and validated by Dell Engineering. For more details
or questions about the delivery model, please consult with your Dell Sales representative.
Figure 8 below shows the Active System 800v solution with a single chassis. Figure 9 shows Active
System 800v with two chassis and maximum storage enclosures. Note that all EqualLogic arrays shown
in the figures are PS6110X. If a different PS6110 array type is ordered, the actual rack configuration
may be different from the one shown below. Also note that the switches shown in figures are shown
mounted forward for representation. In actual use, ports face the back of the rack. The PDUs are not
shown in the illustration because they will vary by region or customer power requirements.
Page 27
Figure 8: Active System 800v Single Chassis: Rack Overview
Page 28
Figure 9: Active System 800v Two Chassis and Maximum Storage: Rack Overview
Page 29
12 Reference
Dell Active Infrastructure reference:

Dell Active System Manager

Dell Active Infrastructure Wiki
VMware references:

VMware vSphere Edition Comparisons

VMware vSphere Compatibility Matrixes

VMware High Availability (HA): Deployment Best Practices

VMware Virtual Networking Concepts
Dell PowerEdge References:

Dell PowerEdge M1000e Technical Guide

Dell PowerEdge M I/O Aggregator Configuration Quick Reference

NIC Partitioning (NPAR)
Dell EqualLogic references:

EqualLogic Technical Content

Dell EqualLogic PS Series Architecture Whitepaper

Configuring iSCSI Connectivity with VMware vSphere 5 and Dell EqualLogic PS Series Storage

Configuring and Installing the EqualLogic Multipathing Extension Module for VMware vSphere
5.1, 5.0 and 4.1 and PS Series SANs

How to Select the Correct RAID for an EqualLogic SAN

Using Tiered Storage in a PS Series SAN

Monitoring your PS Series SAN with SAN HQ
Dell Management reference:

Dell Management Plug-In for VMware vCenter references – Solution Brief
Page 30