Latest Release of StorPool Storage Adds NVMe/TCP Support

StorPool Distributed Storage

The 20th major version of StorPool Storage, a storage platform for large-scale cloud infrastructure supporting a variety of mission-critical applications, has been officially released. With the addition of various new capabilities that would future-proof the storage software and broaden its potential applications, the company claims it to be a significant turning point in the evolution of StorPool.

“With each iteration of StorPool Storage, we build more ways for users to maximize the value and productivity of their data,” said Boyan Ivanov, CEO at StorPool Storage. “These upgrades offer substantial advantages to customers dealing with large data volumes and high-performance applications, especially in complex hybrid and multi-cloud environments.”

StorPool Storage v20 would offer the following new capabilities:

NVMe/TCP Support

NVMe/TCP (NVMe over Fabrics, TCP transport), the next-generation block storage system that makes use of TCP/IP, this most widely used set of communication protocols in data centers with standard Ethernet networking and controllers, is now supported by StorPool Storage.

Customers can access standalone NVMe SSD-based StorPool storage systems with NVMe/TCP at high performance and low latency by using the standard NVMe/TCP initiators found in VMware vSphere, Linux-based hypervisors, container nodes, and bare-metal hosts.

Modern workloads demand high throughput and quick response times, which the StorPool NVMe/TCP implementation can provide without the use of specialist hardware. NVMe/TCP targets are highly available; in the event of a node loss, StorPool switches over the targets on the failed storage node to a node in the cluster that is currently operating.

StorPool on AWS

Boyan Ivanov, CEO at StorPool Storage
“These upgrades offer substantial advantages to customers dealing with large data volumes and high-performance applications, especially in complex hybrid and multi-cloud environments,” said Boyan Ivanov, CEO at StorPool Storage.

Extremely low latency and high IOPS are supplied to single-instance workloads including massive transactional databases, voluminous SaaS applications, and massively used e-commerce websites when using StorPool on AWS, according to the company.

Now, AWS allows the deployment of StorPool Storage on groups of three or more i3en.metal instances. Fast 1.3M+ balanced random read/write IOPS are delivered by the solution to EC2 r5n and other suitable compute instances (m5n, c6i, r6i, etc.). With enough network bandwidth, StorPool can give this level of performance to any suitable instance type, freeing users from the restrictions placed on per-instance storage. According to StorPool, these results are achieved with less than a fifth of client CPU resources being used for storage operations, leaving more than 80 percent for user application(s) and database(s).

Clients of StorPool who use AWS would receive the same white-glove service offered to customers on-premises, giving them confidence that the core of their application is functioning properly in the cloud. Each StorPool storage system on AWS is designed, deployed, tuned, monitored, and maintained by the StorPool expert team. The whole StorPool Storage solution would make it possible for anyone to quickly and affordably deploy complex corporate applications to AWS.

NFS File Storage on StorPool

For specific use cases, StorPool is adding support for hosting highly available NFS Servers inside StorPool storage clusters. NFS services provided by StorPool are appropriate for file workloads with high throughput shared by internal and external end users (video rendering, video editing, heavily loaded web applications). They can also enable cloud platform operations and handle moderate-load use cases (configuration files, scripts, pictures, and email hosting) (secondary storage for Apache CloudStack, NFS storage for OpenStack Glance). For IOPS-intensive file applications like virtual disks for virtual machines, NFS file storage on StorPool is unsuitable.

The ability of StorPool Storage to operate hyper-converged with other workloads and the minimal resource consumption of StorPool software components are both taken advantage of when NFS Servers are deployed on StorPool storage nodes. NFS Servers can run in virtual machines supported by StorPool volumes and administered by the StorPool operations team. The cumulative provisioned storage of all shares exposed from each NFS Server can be up to 50TB. By distributing NFS service data across all cluster nodes and ensuring that StorPool maintains data and service integrity in the event of hardware failures, StorPool would ensure the high availability of each NFS service.

“High performance access to data is essential wherever applications live,” said Scott Sinclair, Practice Director at Enterprise Strategy Group. “Adding NVMe/TCP support, StorPool on AWS and NFS file storage to an already robust storage platform enables StorPool to better help their customers achieve a high level of productivity with their primary workloads.”