Get Started Here
Solution Forums
Connect with peers on today's solutions.
Product Forums
Learn and collaborate about the Everpure Platform.
Node Navigation
Featured Content
Start Here
Recent Discussions
How much more inference could you get from the GPUs you already have?
As inference workloads grow, it’s not always the GPU compute that becomes the bottleneck. Recomputing tokens of a known context vs reloading from KV cache can take up a lot of GPU bandwidth and limit how many workloads you can run in a given amount of time. That’s one of the things we’ve been working on with PureKVA, reusing KV cache so you can get more out of the GPU capacity you already have. With v1.2, we’ve also added a 3-tier memory architecture, TurboQuant KV cache support, along with things like multi-tenancy and storage isolation. We’re seeing some of the benefits internally as well, particularly around reducing throttling when usage spikes. Curious what others are seeing. Is GPU compute the bigger constraint for you, or GPU memory?09222026 - Demo Recap - From CSI to Snapshots—Seamless VM Management on Red Hat OpenShift
If you missed our latest Expert Led Demo, Matt Webb and I walked through how teams can manage virtual machines on Red Hat OpenShift while using Everpure FlashArray through CSI. The goal was not to turn every VMware administrator into a Kubernetes expert overnight. It was to connect the dots: many familiar VM operations still exist, but the platform uses different objects, policies, and automation to get the job done. What you missed 👇 🗺️ A familiar operating model with new terminology. Worker nodes, StorageClasses, PersistentVolumeClaims, live migration, and VirtualMachine objects map closely to concepts many VMware administrators already know. ⚙️ CSI automates the storage plumbing. A StorageClass defines the storage policy, while the CSI driver provisions volumes, maps them to the right node, and handles the day-to-day attachment work. 🔀 Choose the right storage-consumption model. Teams can use Portworx Enterprise volumes for flexible, software-defined storage services across mixed infrastructure, or FlashArray Direct Access when they want array-level data services and visibility in Purity. 🚀 Keep VM operations simple. In the demo, we showed a live compute migration, created a VM from a template, and used the OpenShift console to work through familiar virtualization tasks. 📸 Use array-based snapshots for fast recovery. With CSI configured, snapshots are FlashArray-based. The demo showed taking a snapshot, deleting data, restoring the VM, and bringing the data back quickly. 🧳 Plan migrations around your environment. Migration Toolkit for Virtualization can support cold migrations, while storage-offload migration can use SCSI XCOPY when source VMware storage and OpenShift storage share the same FlashArray. The practical takeaway: storage policies and automation remove much of the manual LUN, mapping, rescan, and multipathing work. That gives virtualization and platform teams more time to focus on the workload—not the plumbing behind it. 🎥Catch up on the demo HERE 🎥 💬 What is the biggest question your team has about running VMs on OpenShift: migration, storage policy, snapshots, or day-two operations? Share it in the comments.10012026 - TechTalk Recap - Oracle Resiliency—Choosing the Right Data Protection Approach🛡️
If you missed our latest TechTalks session, Lester Wells and I explored an important reality for Oracle teams: there is no single data-protection feature that covers every failure scenario. Keeping Oracle resilient means looking beyond a simple “backup or HA” decision. The right approach layers protection for local failures, site failures, operational recovery, and logical corruption—then aligns each layer to the application’s business requirements. What you missed 👇 🧭 HA and DR are different problems. High availability helps applications continue through infrastructure failures; disaster recovery protects against a broader site-level event. Both matter, but not every database needs the same RPO or RTO. ⚡ Snapshots improve operational recovery. Fast, space-efficient snapshots can help reduce backup and recovery pressure, refresh dev/test environments, support reporting copies, and provide recovery points for ransomware or user errors. 🏢 ActiveCluster is designed for continuous availability. For metro-distance deployments that meet latency requirements, synchronous replication can provide zero RPO and zero RTO protection against array or site failure. 🌍 ActiveDR extends protection across distance. Continuous, asynchronous replication supports disaster recovery where synchronous replication is not practical—and enables non-disruptive DR testing. 🧩 Layered protection covers more failure modes. Oracle RAC, ActiveCluster, ActiveDR, Data Guard, Flashback, and snapshots each address different risks. Combining the right layers helps protect both availability and recoverability. 🔎 Replication does not replace logical recovery. A bad write, accidental delete, or corruption can replicate correctly. Point-in-time snapshots and database-level recovery tools remain important parts of the plan. One of the best practical examples was using ActiveDR to bring up and validate a DR environment without disrupting production. That makes it easier to test your recovery plan more often—before you need it. 🎥 Catch up on the session HERE🎥 💬 Which Oracle resilience challenge is top of mind for your team: backup windows, recovery time, site-level availability, DR testing, or protection from logical errors? Share your perspective in the comments.
Simplify mounting volumes on Azure VM with EC Mount VM Extension
Managing external storage on Azure VMs no longer has to involve repetitive guest OS configuration or custom scripts. The Everpure Cloud Mount VM Extension is now generally available across Azure regions. It automates iSCSI configuration, enables and optimizes MPIO, establishes target connectivity, and mounts storage volumes according to Everpure best practices. With support for both Linux and Windows VMs, the extension can be deployed during provisioning or added to existing VMs. It also integrates with ARM templates, Azure Bicep, and Terraform, making storage connectivity part of your infrastructure-as-code workflows. For Everpure Cloud Azure Native, a one-click mount workflow from the Azure Portal makes attaching storage even simpler. Everpure Cloud Dedicated customers can automate guest-side setup and reduce manual configuration at scale. Less scripting. Less configuration drift. A faster, more consistent path to usable storage on Azure VMs. Learn more: https://blog.everpuredata.com/news-events/announcing-general-availability-of-everpure-cloud-vm-extension/
Featured Places
Introductions
Welcome! Please introduce yourself to the Pure Storage Community.Pure User Groups
Explore groups and meetups near you./CODE
The Everpure /Code community is where collaboration thrives and everyone, from beginners taking their first steps to experts honing their craft, comes together to learn, share, and grow. In this inclusive space, find support, inspiration, and opportunities to elevate your automation, scripting, and coding skills, no matter your starting point or career position. The goal is to break barriers, solve challenges, and most of all, learn from each other.Career Growth
A forum to discuss career growth and skill development for technology professionals.
Featured Content
Fleet Security Assessment
The Pure1 Fleet Security Assessment provides a fleet-wide view of the security posture of FlashArray and FlashBlade systems by correlating each asset's current software ve...
1 month ago
If you are moving Oracle databases off Exadata, the first sizing mistake is usually looking at only one database at a time.
Exadata is not a traditional Oracle architecture. Some of the work that w...
1 month ago If you missed last week’s TechTalks, Ashish Gupta and I dug into a practical question many teams are working through right now: before you ask AI to make decisions with your data, do you really know ...
27 days ago What happens when you take the enterprise storage capabilities IT teams rely on and deliver them as a fully managed, Azure-native experience?
That question was at the heart of our latest Ask Us Eve...
27 days ago
