Redefine Mission Critical Storage with HPE Primera
Bashar Younis
Enterprise and Storage Consultant
27/05/2021

In June 2019, HPE launched its new storage product line, the HPE Primera. HPE describes it as the new TIER 0 data platform which will redefine mission-critical storage. It is architected for high availability with multi-node design, business continuity with peer persistence and data replication.

HPE Primera facilitates business continuity with automatic site failover and also modernises and extends data protection to the cloud.  HPE Primera uses artificial intelligence (AI) and machine learning (ML), powered by HPE InfoSight, to predict and prevent failures across storage, servers, and virtual machines. Leading IT experts describe it as a storage system that combines the InfoSight Based AI intelligence technology from the HPE Nimble family of arrays with the reliability and efficient scalability of the 3PAR family.

HPE Primera is built to deliver three experiences:

  1. On-demand availability. This can be described in three words: Simple, Automated and Fully predictive.
  2. High performance. Predictive acceleration using real-time analysis to ensure applications run fast all the time.
  3. Application-aware resilience. Deep application-aware intelligence built into the storage platform, focusing on maximum uptime of your critical services – VMware, Hyper-V, Oracle, SQL Server, SAP and more.

Why HPE Primera?

Here are some reasons why HPE Primera should be your storage of choice:

  • HPE InfoSight: HPE Primera has Infosight built-in for intelligent optimisation, with insight exposure for self-diagnostics.
  • Operating System: Simple with enhanced resiliency. This reduces the need to reboot after upgrades, reducing disruption to business operation.
  • Timeless:
    • No upfront payment for software features.
    • Data reduction ratio guaranteed.
    • Flat support model.
    • 100% Data availability for applications guaranteed.
    • Investment protection.
    • Technology refreshes every three years without additional cost.
    • Technology that is always current.
  • Integrated Management: Simple management tools that reduce installation time from days to minutes.
  • Scalability: HPE Primera is designed to scale without downtime or disruption.
  • Hybrid Cloud Mobility: Built-in data protection, copy data management and data mobility built for the cloud.
  • Performance: HPE Primera has an all-active architecture that brings parallel processing together with a multi-node system. The result is massive application performance.

 

HPE Primera Hardware

There are three Primera models, the 630, 650 and 670.

 

HPE Primera Models Comparison table

Here is a comparison table for HPE Primera different models and hardware capabilities:

HPE Primera Hardware Building Blocks

The process of configuring the HPE Primera that is suitable for your organisation starts with going through the following building process:

  1. We start with choosing the Chassis. This will be dependent on Enterprise requirements, power and rack space, plus required disk capacity. The A630/C630 2U Chassis includes 2 node slots and 24 Small Form Factor drives.  The A650/A670/C650/C670 4U Chassis includes 4 node slots and 48 Small Form Factor drives.
  2. Controllers: Then, select the compute element of the HPE Primera. These controllers will be responsible for the connectivity and functionality of the storage array.
  3. Select the PCIe adaptor: This will provide the front and back-end connectivity options.
  4. Drive enclosures can be considered the primary building block for storage capacity.  A 2U add-on enclosure can host 24 SFF drives or 12 LFF drives.
  5. Drives: HPE Primera supports SAS and NVMe SSD, SAS 10K HDD and SAS 7.2K HDD. The NVMe SSD is only supported on HPE Primera A-Series Models.
  6. Rack: Finally, you chose the type of rack that will accommodate the storage unit.

HPE Primera Peer Persistence

Primera Peer Performance is a high availability data centre solution for providing highly resilient storage volumes across multiple Primera systems.  These can be located in the same data centre or even different locations in a “Metro Cluster” setup for zero-downtime DR.

Peer persistence is provided with HPE Primera without purchasing any extra hardware or software licences.

For the first time in an HPE Storage solution, HPE Primera supports Active peer persistence, where the secondary Primera system provides not only seamless resilience but actively services I/O requests, giving the ability to architect ultra-high throughput storage for the most demanding applications.

Requirements

  • FC or iSCSI cross-site connectivity.
  • A minimum of two synchronous remote copy RCIP or RCFC links.

How does it work?

In case of an array failure on one site (Primera 1 shown in the above image):

  • When the Quorum is lost, and this failure is detected by the Quorum Witness and the secondary storage array at Data Center-2.
  • Peer Persistence software on the array at Data Centre-2 makes the peer volumes and cross-connected paths from hosts on Data Center-1  to the array at Data Center-2.
  • Data Center-1 Hosts, Virtual Machines and Applications access peer volumes on Data Center-2 and continue normal operation.
  • The failover from the Primary to Secondary site is Automated.

Here are Scenarios of failure tests carried out by VMware with HPE Primera behaviour:

Scenario

HPE Primera Storage System Behaviour

VMware HA Behaviour

Single Array-Host Path Failure

Hosts use alternate paths to maintain volume access.

No effect observed

Single Array Node Failure

Hosts use alternate paths to the surviving array node(s) at the site and maintain volume access.

No effect observed

Single Storage Inter-Site Link Failure

No effect. Inter-site connectivity is maintained by the alternate link

No effect observed

All Storage Inter-Site Links fail

Peer volume synchronization is disabled, and Automated Transparent Failover is disabled.

No effect observed

Quorum Witness Failure

Automated Transparent Failover is disabled

No effect observed

Simultaneous Quorum Witness and Storage Inter-site Links Fail

Peer volume synchronization is disabled and Automated Transparent Failover is disabled.

No effect observed

Single Site Storage Array Failure

Automated Failover occurs and Peer volumes and paths are made active on the surviving site.

No effect observed

Complete Site Failure

Automated Failover occurs and Peer volumes and paths are made active on the surviving site.

Virtual machines are restarted on ESXi hosts on the surviving site

Conclusion

HPE Primera is a high-end storage system built on the foundations of the reliable and resilient HPE 3PAR platform and well-known, tried-and-tested technologies.  In addition, it incorporates HPE InfoSight, the latest in SSD technologies, containerised OS and a very advanced parallel architecture. The result is a self-managing and advanced system that can meet today's Enterprise SLA demands, in addition to the highest levels of data security and availability.

Contact us today to get started.

Ultima’s HPE Partnership

As an HPE Gold Partner, we have wide ranging capabilities from pre-sales advice and design through to installation. With experience across multiple areas within HPE’s portfolio, we can provide you with a bespoke end-to-end solution, or platform for specific products. We have been recognised as the Top Value Partner 2019 as well as Intelligent Edge Partner of the Year for 2018.


Full Name