White Papers

vStart 1000v for Enterprise Virtualization using VMware vSphere: Reference Architecture
Page 11
4 Design Principles
The following principles are central to the design and architecture of the vStart 1000v Solution.
1. Redundancy with no single point-of-failure: Redundancy is incorporated in the critical
aspects
1
of the solution, including server high availability features, networking, and storage.
2. Management: Provide integrated management using VMware vCenter, Dell Management Plug-in
VMware vCenter, Dell OpenManage Essentials, and Compellent plug-in for VMware vCenter.
3. Cloud Enabled: The solution includes VIS Creator, which enables customers to manage their
virtualization infrastructure as a private cloud. The private cloud can in turn be connected to
Dell vCloud using VMware vCloud Connector.
4. Integration into an existing data center: This architecture assumes that there is an existing
10 Gb Ethernet infrastructure with which to integrate.
5. Hardware configuration for virtualization: This solution is designed for virtualization for most
general cases. Each blade server is configured with appropriate processor, memory, host bus,
and network adapters as required for virtualization.
6. Racked, Cabled, and Ready to be deployed: vStart is available partially 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.
7. Power, Cooling, and Weight Considerations: vStart 1000v 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.
8. Flexible configurations: vStart 1000v 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 high-level reference architecture for the solution. The figure
shows high-level logical connectivity between various components. Subsequent sections provide more
detailed connectivity information.
1
Out of band management is not considered critical to user workload and does not have redundancy.