Skip to content

storage

Demystifying NetApp Adaptive QoS in OpenStack Genestack

Configuring multi-tenant Quality of Service (QoS) for enterprise storage in OpenStack sounds straightforward on paper: define standard and high-performance tiers, specify IOPS per gigabyte, and let the storage backend handle enforcement. In practice, our journey implementing NetApp ONTAP Adaptive QoS (AQoS) across Rackspace OpenStack Flex and Genestack production environments revealed sharp discrepancies between early published deployment specifications and storage reality.

Putting Swift's S3 API to Work for AI Workloads on OpenStack Flex

I'll be honest. When someone says "object storage for AI" the picture in most people's heads is a purpose-built S3 appliance with a six-figure invoice attached, or a hyperscaler bucket with an egress meter running. Swift, the OpenStack object store that has been quietly holding petabytes since 2010, rarely makes the list. It's old. It doesn't have a launch video. It speaks S3 through a middleware rather than natively.

Our team has been leaning on that middleware harder every month. Model weights, training shards, and lately the KV cache that vLLM spills out of GPU memory all land in Swift buckets through the S3 API, and at some point "it seems fine" stops being an acceptable answer to "how fast is it." So we did what you're supposed to do. We picked an open source benchmark, built a container around it, ran the object sizes that AI workloads actually produce, and kept the numbers.

Running Longhorn on OpenStack Flex

Longhorn logo

Longhorn is a distributed block storage system for Kubernetes that is designed to be easy to deploy and manage. In this guide, we will walk through deploying Longhorn on an OpenStack Flex instance. As operators, we will need to create a new instance, install the Longhorn software, and configure the service to run on the instance. This setup will allow us to access the Longhorn web interface and create new volumes, snapshots, and backups. The intent of this guide is to provide a simple example of how to deploy Longhorn on an OpenStack Flex instance.