5.5PB capacity in 90% less space. 70% more performance. 100% less headache. All-flash NVMe Storage Array.
Run everything from massive databases to cloud-native applications at the next level. Think faster transactions and more responsive customer experiences, with services always available and data always protected. Designed to be as easy to use as it is powerful, FlashArray//XL gives your business the freedom to innovate without storage as a constraint.
Consolidate more business services—bigger databases, more users, and more app workloads—on fewer arrays with FlashArray//XL. With an all-new 5U chassis, designed for the latest powerful CPUs, expect an up to 70% performance boost over FlashArray//X90.
Run business-critical apps, such as SAP HANA, Microsoft SQL Server, and Oracle, faster than ever. DirectFlash® Modules with Distributed NVRAM lift the limit on write throughput and reduce read latency to as low as 150µs, driving up to 20% improved density.
Protect your data from disasters and ensure business continuity with FlashArray//XL’s increased internal redundancy and new backplane for workload rebalancing and failover. Defend against ransomware attacks with immutable SafeMode™ snapshots.
Equip your data center for scale and agility with FlashArray//XL managed by Pure Fusion™. Deliver storage-as-a-service in a multi-cloud world and eliminate bottlenecks of traditional storage solutions.
We work with the best across all industries.
“The performance of Pure Storage was an immediate standout for us, but the simplicity of the offer made them absolutely different from the competition.”
“Pure has had a revolutionary impact on the business, completely changing our mindset and how the cloud infrastructure team functions.”
[1] Effective capacity assumes HA, RAID, and metadata overhead, GB-to-GiB conversion, and includes the benefit of data reduction with always-on inline deduplication, compression, and pattern removal. Average data reduction is calculated at 5-to-1 and does not include thin provisioning. Pure excludes thin provisioning from the data reduction calculation as it unrealistically doubles the claimed data reduction.
[2] Calculated using raw label capacity.
