True Active/Active Metro Stretch Cluster

How’s this for raising the bar on enterprise storage: Purity ActiveCluster does away with decades of cost and complexity in business continuity by delivering a true Active/Active cluster that’s simple and built-in.

RTO Zero, RPO Zero, no third site

Achieve RTO & RPO Zero – across your data center, metro region, or globally via async across three data centers – with Purity ActiveCluster. Pure1™ Cloud Mediator means you don’t need a third site, and setup takes minutes. ActiveCluster is included with Purity//FA 5.

ActiveCluster – Ultra-simple, ultra-Included

An Active/Active metro stretch cluster without the traditional expense or complexity? Yep. It’s included in your Evergreen® subscription. Check it out.

ESG: ActiveCluster is Transparent and Effortless

Market intelligence firm ESG put ActiveCluster through a battery of business continuity tests. They found that “Purity ActiveCluster takes the cost and complexity barriers out of business continuity, making it simple, cost-effective, and provable for any organization—and relieving the minds of IT administrators.” 

What are we talking about, exactly?

Pure Storage ActiveCluster is a fully symmetric Active/Active bidirectional replication solution that provides synchronous replication for RPO zero and automatic transparent failover for RTO zero. ActiveCluster enables clustered arrays and hosts in multiple sites to be used in flexible Active/Active data center configurations.

Business Continuity for Clustered Apps Business Continuity for Clustered Apps

Synchronous Replication

Writes are synchronized between arrays and protected in NVRAM on both arrays before host acknowledgement.

Symmetric Active/Active

Read and write to the same volumes at either side of the mirror, with optional host-to-array site awareness.

Transparent Failover

Automatic non-disruptive failover between arrays and sites with automatic resync and recovery.

Nothing else required

No third site, no extra hardware, and no software licenses. Just a simple, non-disruptive Purity upgrade.

Performance Optimized, Always Available

ActiveCluster uses a preferred array setting to ensure that hosts have the best possible performance. This ensures that writes from the host only use one round trip to be synchronously replicated between arrays and that reads are always serviced by the local path. However, ActiveCluster still allows the host simply to access data directly from the remote array, should the local array become unavailable.


Multi-site, Active/Active design is fundamental to the effortless experience of Purity ActiveCluster. Unlike Active/Passive implementations, ActiveCluster serves I/O on a given volume from both sites simultaneously. You don’t have to worry about the complexity of managing VM or database instance affinity to a site, and application latency is optimized with reads served locally.

Designed to be Easy and Automatic

Managing an ActiveCluster stretch cluster is as simple as managing a single array: snapshot and clone operations can be performed from either array, and volumes and snapshots are synchronously maintained on both arrays. Failovers are transparent, and the arrays automatically resynchronize.

ActiveCluster Stretch Cluster for Business Continuity ActiveCluster Stretch Cluster for Business Continuity

Get started with Just Four Steps

Stretch cluster deployments have typically been intimidating from the customer’s point of view. Look at the length in pages of the manuals from some of our major competitiors: 769 pages; 1,360 pages. It doesn’t have to be that way. You can launch ActiveCluster in minutes – with just four steps.


About the time it takes to brew coffee. Watch the entire process – in 7 minutes.

The Foundation is Purity

ActiveCluster leverages Purity’s simple, built-in, data reduction-aware snapshots and replication to deliver synchronous replication and metro stretch cluster for mainstream enterprise deployments.


Purity ActiveCluster uses Pure1 Cloud Mediator, a SaaS-based quorum witness, which eliminates the need for a customer-managed third site. Failovers happen safely, automatically, and transparently within standard host I/O timeouts. If an array fails, the Cloud Mediator ensures your hosts simply access data on the other array.

Management is Simple as SaaS

Nothing to install onsite or configure and support, no hardware or software to maintain, no security patch updates.

Third Site

An integrated, cloud-based mediator is inherently a separate failure domain, and not subject to human error.

Automatic Configuration

Arrays configured for ActiveCluster will automatically connect to and use the Pure1 Cloud Mediator.

Mediation Can Be Passive

Continuous access to the mediator is not required for normal synchronous replication operations.


If array communication is broken, both arrays briefly pause I/O and query the mediator. The first array to reach the mediator keeps its synchronously replicated pods online. The second array must stop servicing I/O to its synchronously replicated volumes in order to prevent split brain. The entire operation occurs within standard host I/O timeouts to ensure that applications experience no more than a pause and resume I/O.

The Game Changers

What’s made us a 2017 IDC MarketScape leader?
A strategy for the future that includes being the only enterprise storage vendor today to offer stretch cluster at no additional charge. 

Featured Technology Partners

Gartner names Pure Storage a Leader in the 2018 Magic Quadrant Solid-State Arrays 5 Years in a Row

Get the analysis you need to choose the best Solid-State Arrays for your business.

By downloading the report, we believe you'll gain insights into:

  • The flash storage futures market overview
  • Gartner’s evaluation of vision, strengths and cautions for each vendor
  • Why Pure Storage was named a LEADER