Consolidate Everything on Flash

The efficiency and consistency of all-flash storage provides enormous opportunities for workload consolidation. Now there’s Pure Storage Policy QoS to ensure that your consolidation includes full mixed workload performance – all the time.

Seeing Is Believing

In its simplest form, our Policy QoS is always-on and automatic. Nothing to configure, no knobs to turn. We’ve prepared a demonstration that’s sure to bring joy to the hearts of storage admins everywhere. Watch.

Delivering Service Assurance

Consolidation of previously siloed workloads is a critical aspect of the journey to Cloud Era IT. Organizations want to know that their storage solution can maintain and protect workload performance 24/7/365. Without this assurance, organizations must accept either lower levels of consolidation – increasing costs – or higher levels of disruption risk. Pure Storage Policy QoS delivers complete service assurance.

A QoS SOLUTION FOR EVERYONE

Whether it’s the automatic protection of your workloads through zero configuration, always-on QoS, or you choose to manage your workloads with performance classes or individual limits, our Policy QoS will ensure that all your applications run smoothly and disruption-free.

Always-On QoS

No knobs, and nothing to configure: Always-On QoS protects against noisy neighbors.

Policy QoS – Classes

Assure the performance of your mission-critical workloads with performance classes.

Policy QoS – Limits

Use performance consumption limits to ensure a consistent experience for tenants.


DO NOTHING. LET ALWAYS-ON QoS TAKE CARE OF EVERYTHING

Always-On QoS prevents workloads from using more than their fair share of resources on the array by efficiently throttling noisy neighbors. With no artificial limits on workloads, however, maximum utilization of the array is always possible, and you’re assured of full performance for all your workloads.


Play Favorites with your workloads

To assure performance for mission-critical workloads, Policy QoS with performance classes allocates more performance to higher priority classes while throttling workloads in lower priority classes when the array is under contention. However, when the system is not under contention, any workload from any class can burst, ensuring maximum utilization of the array is always possible. The division of performance between classes is optionally user-configurable.


Give Everyone a Sandbox to Play In

Policy QoS with limits ensures a “consistent” experience for all tenants of the array by offering one performance limit setting (MB/s) to configure for each tenant. Simple – and this also ensures that tenants receive consistent performance as new tenants are added.

SERVICE PROTECTION IS COMPLICATED, UNLESS YOU BUILD IT TO BE SIMPLE

Among our competitors, service protection is limited by a number of factors. The performance of disk-based arrays is fundamentally constrained by IOPS per disk, and while other vendors’ AFAs offer adequate nominal performance, their fixed metadata means they have a linear performance drop-off as mixed workloads are running, or when the arrays reach capacity. And competitors’ QoS – when available – has often been complex enough to require a PhD to regularly configure all the knobs. With Pure Storage, all these issues disappear.

Featured Technology Partners