The portfolio of Dell EMC PowerEdge rack servers is designed to optimize application performance and ensure a stable, worry-free environment with intuitive tools that simplify and automate processes throughout the entire server life cycle. Every data center and virtual environment has unique requirements, and PowerEdge provides the flexibility that is needed to build scalable infrastructures that are tightly integrated with VMware vSphere.
The PowerEdge R640 is an ideal platform for dense scale-out data center computing. The R640 combines density, performance, and scalability to optimize application performance and data center density. The scalable architecture of the R640 is designed to maximize application performance and provide the flexibility to optimize configurations based on the application and use case. The PowerEdge R640 is a 1U, two-socket server platform, which supports up to 24 DIMM slots, ten 2.5 in. drives, and 3 PCIe cards.
Embedded in every PowerEdge server is iDRAC9 with Lifecycle Controller. iDRAC9 provides secure and remote server access for a multitude of common management functions. iDRAC with Lifecycle Controller operates regardless of the operating system state or the presence of a hypervisor. It offers a complete set of server management features including configuration, operating system deployment, firmware updates, health monitoring, and maintenance.
iDRAC9 provides a variety of remote connectivity interfaces and protocols, enabling administrators to securely configure, deploy, manage, monitor, and update the server. IPMI, Redfish, SMASH-CLP, and WS-Man are some of the common standard management interfaces that iDRAC9 supports.
The iDRAC9 HTML5 web UI provides for secure connectivity through HTTPS. With the Group Manager feature in iDRAC9 Enterprise, administrators can create a one-to-many console experience, which enables them to view and manage a set of servers rather than visually inspecting servers for faults and manually managing the servers.
The Ready Stack architecture network design consists of these functional groups:
The key building block of the OOB network is the Dell EMC PowerSwitch S4148T-ON switch, which provides forty-eight 10GBASE-T ports and multiple uplink port options.
The Dell EMC PowerSwitch S5248F-ON switch provides LAN connectivity. This switch provides up to forty-eight 25 GbE ports and six 100 GbE ports. Using two S5248F-ON switches—referred to as top-of-rack (ToR) switches—provides redundancy. Integrated NICs directly connect the ToR switches to the rackmount servers. Isilon nodes connect to these switches to provide data services.
The Dell EMC Isilon storage array in this Ready Stack design uses LAN networking. Its front-end network consists of the two Dell EMC PowerSwitch S5248F-ON switches.
For FC storage traffic to and from the Dell EMC Unity XT array, Ready Stack uses Dell EMC Connectrix DS-6620B switches. The DS-6620B switch delivers up to 32 Gbps FC performance in a 1U form factor and, by default, has twenty-four 32 Gbps ports enabled. You can add more ports—up to 48 ports per chassis—through Ports on Demand upgrade kits. Brocade Web Tools, the embedded UI on the Connectrix DS-6620B switches, facilitates the monitoring and management of single or small fabrics, switches, and ports.
The back-end network for Isilon storage consists of two Dell EMC PowerSwitch Z9100-ON switches. The back-end switches enable the Isilon nodes to remain in full communication with each other to take advantage of the full performance and benefits of the Isilon OneFS operating system. The network is 40 GbE, but 10 GbE is also supported.
These switches are used solely for Isilon and are not physically connected to the LAN network. For more information, see the Dell EMC Isilon Ethernet Backend Network Overview.
Dell EMC PowerSwitch components support the OS10 network operating system. Standard in OS10 is Dell EMC SmartFabric Services, which enables you to accelerate IT transformation by providing more agile and simplified central management across both virtual and physical network infrastructures. Dell EMC Open Networking Switching Fabrics and Dell EMC Isilon NAS provide an intelligent and capable architecture that can scale on demand to increase the efficiency of the data center. Dell EMC PowerSwitch switches significantly reduce the deployment complexity and time to value for Isilon node inter-networking.
For more information about using Dell EMC Open Networking Switching fabrics with Isilon storage, see the Scalable Dell EMC Isilon Storage Solutions with Dell EMC Open Network Fabrics Solution Brief.
In this Ready Stack design, the Dell EMC Unity XT Series array provides the primary FC storage. To complement Unity XT, for managing the challenge of high volumes of unstructured data, we also provide Dell EMC Isilon storage.
Both Unity XT and Isilon arrays support the Dell EMC CloudIQ application—a no-cost, cloud-native software-as-a-service solution that enables you to proactively monitor your Dell EMC storage systems. The CloudIQ solution provides intelligent, comprehensive, and predictive analytics. These analytics enable storage administrators to monitor their Dell EMC storage proactively and in detail to help eliminate risks in their environment, such as unused capacity, overused capacity, and system component health.
The CloudIQ solution provides password-protected access. It is easy to use and designed to help you achieve higher uptime, increased performance, and effective capacity planning.
On an ongoing basis, the CloudIQ application performs the following proactive system health checks:
At the highest level, the CloudIQ application combines these five metrics into an overall health score. The health score provides a useful visual indicator of the health of each storage system you have configured to use the CloudIQ solution, as shown in the following figure:
Figure 2. Dell EMC CloudIQ Health Score panel
Dell EMC Unity XT All-Flash storage systems implement an integrated architecture for block, file, and vSphere Virtual Volumes, with concurrent support for native NAS, iSCSI, and FC protocols. Each system uses dual storage processors, full 12 Gb SAS back-end connectivity, and Dell EMC’s patented multicore architected operating environment to deliver performance and efficiency. Disk array enclosures (DAEs) provide more storage capacity, and, for additional performance, online controller upgrades are available. Dell EMC Unity XT All-Flash systems support:
Dell EMC Unity Data Reduction includes deduplication and compression logic within a space-savings algorithm. Data reduction features are available for block LUNs and VMFS datastores in an all-flash pool. You can enable Unity Data Reduction at the resource level, so that storage resources with and without the Data Reduction feature enabled can exist in the same pool on a system. Also, data reduction savings occur at multiple levels, including system level, pool level, and resource level, providing varying levels of reporting granularity.
Dynamic pools increase the flexibility of configuration options within a Dell EMC Unity system. In Unity XT All-Flash systems, dynamic pools replace the existing pool technology as the default pool type within Dell EMC Unisphere storage management. As with traditional pools, you can create, expand, and delete dynamic pools. You can expand a dynamic pool with as little as a single drive to increase the pool’s capacity. This flexible deployment model improves the planning and provisioning process and reduces the total cost of ownership.
The Host I/O Limits feature enables you to limit the amount of I/O activity that is serviced by the Unity XT system. This ability is useful when specific LUNs, vSphere VMFS datastores, thin clones, and their associated attached snapshots are consuming a large portion of the system’s resources and reducing the performance of other resources on the system. You can use the Host I/O Limits feature to limit incoming host activity based on IOPS, bandwidth, or both.
A related feature allows you to set burst policies for host I/O limits. This option is available for any host I/O limit policy and allows host activity/traffic to exceed the base policy limit by a user-specified percentage. The user specifies parameters of amount (percentage), duration, and frequency of the I/O limit burst allowance.
vSphere Storage APIs - Array Integration (VAAI) enables the Unity XT system to handle offloaded VMware operations, improve performance, and reduce network overhead. VAAI improves the utilization rates of ESXi hosts in a VMware environment by offloading tasks to the Unity XT system. The Unity XT system processes various operations—including clone and snapshot operations as well as hardware-assisted moves—for both block and file datastores and for Virtual Volumes.
vSphere Storage APIs for Storage Awareness (VASA) enables intercommunication between the storage and virtualization layers so that administration of one layer can be performed from the other. This capability can enable more efficient workflows for administrators who are familiar with one interface. VASA enables VMware administrators to access storage technologies and features from within the familiar vCenter management console, such as the creation of vSphere Virtual Volumes, and surfaces array-specific details to vCenter. This capability eliminates the need to manage a VMware storage environment from multiple management consoles.
HTML-based Unisphere storage management for the Unity XT array provides a dedicated page for accessing VMware, which allows for the end-to-end discovery of a vSphere environment. Unisphere imports and displays information about vCenter, ESXi hosts, virtual machines (VMs), and virtual disks. It also registers the VMware hosts on the Unity system so that they can be granted access to LUNs, VMFS datastores, NFS file systems or datastores, and vSphere Virtual Volumes datastores. Unisphere storage management can also display system status and performance information, including a graphical representation of the Unity XT system that highlights areas of interest, such as for drive faults and network link failures.
Dell EMC Isilon storage has a wide variety of applications in various vertical markets, including oil and gas, medical imaging, and astrophysical data. However, most Isilon customers use Isilon arrays as tier 2 storage, typically for:
Therefore, this design guide focuses less on building a design for a specific use case than on describing a general NAS environment and the Dell Technologies tools that help speed design and deployment, including iDRAC, OpenManage Integration for VMware vCenter, and the Dell EMC Fabric Design Center.
Heterogeneous Isilon clusters can be architected with a wide variety of node styles and capacities to meet the needs of a varied dataset and wide spectrum of workloads. These node styles encompass several hardware generations and fall loosely into four main categories or tiers. The following figure illustrates these tiers and the associated hardware models:
Figure 3. Isilon hardware tiers and node generations
In this Ready Stack design, we provide a hybrid/utility midsize reference architecture. You can easily expand an Isilon implementation of any size, scaling up or scaling out, by adding Isilon nodes.
Isilon scale-out storage solutions are designed for enterprises of all sizes. Isilon NAS, driven by the OneFS operating system, enables you to eliminate storage silos by consolidating all your unstructured data and to store petabytes of file data in a single data lake.
The Isilon portfolio includes the following platform types:
This Ready Stack design describes the Isilon H500 Hybrid array. The Hybrid-class storage platforms, which are powered by the OneFS operating system, use a dense, modular architecture. The architecture provides a powerful, yet simple, scale-out storage platform to speed access to unstructured data while reducing cost and complexity.
Isilon Hybrid-class storage platforms provide:
In addition, SmartDedupe data deduplication software enhances storage efficiency to reduce physical storage requirements by up to 35 percent. Both SFSE and SmartDedupe use shadow stores (file system containers that allow data to be stored in a shareable manner).
In Isilon scale-out NAS, the OneFS operating system combines the three layers of traditional storage architectures—file system, volume manager, and data protection—into one software layer. This unified layer provides a single intelligent distributed file system that runs on an Isilon storage cluster.
Figure 4. OneFS: One unified software layer
The OneFS operating system provides enterprises with the ability to successfully use scale-out NAS in their environments today by adhering to the key principles of scale-out: intelligent software, commodity hardware, and distributed architecture. The system stores and manages data in the Isilon storage cluster by providing a single file system that operates outside the constraints of traditional scale-up constructs such as RAID groups. This file system enables the placement of data anywhere on the cluster to accommodate a variety of levels of performance and protection.
Each Isilon cluster operates within a single volume and namespace within the file system that is distributed across all nodes. There is no partitioning, and clients have a coherent view of their data from any node in the cluster. Because all information is shared among nodes across the internal network, data can be written to or read from any node. This capability optimizes performance when multiple users are concurrently reading and writing to the same set of data.
Because the storage has been virtualized for the users and administrator, all capacity is available from an application or user perspective. The file system can grow organically without requiring significant planning or oversight. The administrator does not have to manage tiering files to the appropriate disk because the SmartPools feature handles that automatically. Also, because the Isilon SyncIQ service automatically parallelizes the transfer of the data to one or more alternate clusters, replicating such a large file system requires no special considerations.