Home > Workload Solutions > SAP > Guides > SAP HANA TDI Guides > Business Continuity and Disaster Recovery with Dell PowerMax Storage for SAP HANA TDI Deployments > PowerMax storage arrays
The PowerMax array is the first enterprise data-services platform that is built to deliver and manage predictable service levels at scale for hybrid clouds. It is based on Dell’s Dynamic Virtual Matrix software, which delivers agility and efficiency at scale by pooling hundreds of CPU cores and allocating them on demand to meet performance requirements for dynamic mixed workloads. The PowerMax array provides up to three times the performance of previous-generation arrays with twice the density.
The following figure shows the PowerMax array family of storage arrays:
Both PowerMax arrays, 2000 and 8000, have at their foundation the trusted Dynamic Virtual Matrix architecture and internal system software that is written for the NVMe platform called PowerMaxOS 5978. PowerMaxOS can run natively on PowerMax systems and on legacy VMAX All Flash systems (250F, 450F, 850F, or 950F) as an upgrade. As with VMAX All Flash systems, PowerMax systems are true all-flash arrays. This means PowerMax products are targeted to meet the storage capacity and performance requirements of the all-flash enterprise data center. The PowerMax products are feature-rich, all-flash offerings that are designed to take advantage of ultrahigh-performing Storage Class Memory (SCM) and higher capacity NVMe flash drives to create the densest storage configuration possible. PowerMax storage offers enterprise customers trusted data services, along with the simplicity, capacity, and performance that their highly virtualized environments demand, while still meeting the economic needs of more traditional storage workloads. PowerMax now also enables customers to deploy applications such as real-time analytics, machine learning, and big data—applications that demand the lower storage latency and higher IOPS densities that were unattainable with previous all-flash offerings.
PowerMax arrays also offer several technologies to protect customer data and maintain business continuity if unexpected failures occur within the data center and across data centers. These technologies include SRDF, consolidation of block and file storage using eNAS, Non-Disruptive Migration (NDM) online data migrations, and SnapVX.
Note: For information about configuring PowerMaxarrays in an SAP HANA TDI environment, see Validation Guide—PowerMax Storage Configuration Best Practices for SAP HANA TDI | Dell Technologies Info Hub.
SRDF is a family of DR, parallel processing, and data migration solutions. SRDF configurations require at least two arrays—a primary array and at least one secondary array. The arrays can be in the same room, in different buildings on the same campus, or even hundreds or thousands of kilometers apart.
In the open-systems host environment:
Note: An SRDF device pair is a logical device that is paired with another logical device residing in a second array. An R1 device is the member of the device pair at the source (production) site. R1 devices are generally read/write-accessible to the application host. An R2 device is the member of the device pair at the target (remote) site. During normal operations, host I/O writes to the R1 device are replicated over the SRDF links to the R2 device. In general, data on R2 devices is not available to the application host while the SRDF relationship is active, aside from SRDF/Metro or SRDF Smart DR active/active configurations.
SRDF supports the following primary modes of operation:
For more information, see Dell EMC PowerMax and VMAX All Flash: SRDF/Metro Overview and Best Practices
For more information about SRDF configurations and operations, see Dell EMC Solutions Enabler SRDF Family: CLI User Guide.
Embedded NAS (eNAS) data service extends the value of PowerMax to file storage by enabling customers to make the most of vital enterprise features such as flash-level performance for both block and file storage while also simplifying management and reducing deployment costs. PowerMax with the eNAS data service becomes a unified block and file platform using a multi-controller, transactional NAS solution. It is designed for Dell EMC PowerMax: Family Overview customers who want hyper consolidation for block storage combined with moderate-capacity, high-performance file storage in mission-critical environments. Common eNAS use cases include running Oracle on NFS, VMware on NFS, and Microsoft SQL on SMB 3.0; home directories, and Windows server consolidation. eNAS uses the hypervisor that is provided in PowerMaxOS to create and run a set of containers in the PowerMax array. These containers host two major elements of eNAS: software data movers and control stations. The embedded data movers and control stations have access to shared system resource pools to ensure PowerMax resources are evenly consumed for both performance and capacity. Aside from performance and consolidation, PowerMax with eNAS provides the following benefits:
Data migrations have always been challenging in an enterprise environment. The complexity and size of large data storage environments makes planning for, scheduling, and performing migrations extremely difficult. Migrations also often involve applications that cannot be taken offline, even briefly, for cutover to a new data storage array. Dell Non-Disruptive Migration (NDM) enables customers to perform online data migrations that are simple and nondisruptive to the host and application.
NDM is designed to help automate the process of migrating hosts and applications to a new PowerMax array with no downtime. NDM uses SRDF replication technologies to move the application data to the new array. It also uses auto provisioning combined with PowerPath or a supported host multipathing solution to manage host access to the data during the migration process.
NDM gives PowerMax customers the following benefits:
Note: Migrations should take place during low I/O activity to minimize performance impact. NDM does not currently support mainframe CKD devices.
Every PowerMax array comes with the local replication data service TimeFinder SnapVX, which is included in the default Essentials and zEssentials packages. SnapVX creates low-impact snapshots and supports up to 256 snapshots per source volume, up to 1,024 snapshots per source using Snapshot Policies or zDP, and up to 65 million total snapshots per array. Users can assign names to identify their snapshots and set automatic expiration dates on each snapshot.
SnapVX provides the ability to manage consistent point-in-time copies for storage groups with a single operation. Up to 1,024 target devices can be linked per source volume, providing read/write access.
Local replication with SnapVX starts out as efficiently as possible by creating a snapshot: a pointer-based structure that preserves a point-in-time view of a source volume. Snapshots do not require target devices. They share back-end allocations with the source volume and other snapshots of the source volume, and only consume additional space when the source volume is changed.
Each snapshot has a user-defined name and can optionally have an expiration date, both of which can be modified later. Management interfaces provide the user with the ability to take a snapshot of an entire storage group using a single command.
Note: Expiration is optional. However, it is considered a best practice to ensure that snaps do not get forgotten, thus continuing to consume resources.
You can access a point-in-time snapshot from a host by linking it to a host-accessible volume called a target. Target devices are standard thin devices. Up to 1,024 target devices can be linked to the snapshot or snapshots of a single source volume. This limit can be achieved either by linking all 1,024 target devices to the same snapshot from the source volume, or by linking multiple target devices to multiple snapshots from the same source volume. A target volume may only be linked to a single snapshot at a time.
By default, targets are linked in a no-copy mode. This no-copy linked target functionality significantly reduces the number of writes to the back-end flash media because it eliminates the requirement to perform a full copy of the source device.
This functionality provides an easy way for you to check different points in time if you are unsure of which one to access, as illustrated in the following figure: