Our Blog

July 15, 2024

In today’s AI world, powerful storage is key for many GPUs working together on large datasets. These workflows involve an initial data load at high speeds, followed by data loading during training and periodic checkpoints, all at tens of gigabytes per second. Storage must handle many GPUs accessing massive datasets (hundreds of terabytes to petabytes) […]

July 9, 2024

Boosting virtual machine performance in Proxmox environments has always been a challenge due to inherent limitations in the existing I/O architecture. Xinnor’s latest solution xiRAID Opus, a software RAID engine operating in user space, addresses this issue head-on.

June 20, 2024

This is the second part of our High Availability post series started with introduction into High Availability challenges some time ago. Today we will look at the practical example and see how xiRAID 4.1.0 can be configured within existing Pacemaker cluster.

April 12, 2024

SSDs continue to advance in speed, particularly with the market shift to NVMe™ PCIe® 5.0 SSDs. With this technology, a single SSD can now achieve remarkable sequential read speeds of up to 14GB/s and sequential write speeds of 7GB/s, along with handling millions of Input/Output per second (IOps).

March 16, 2024

What is a high availability cluster and why it is important. Nowadays, data are the foundation for almost every business; the biggest threat to successful organizations is the loss of their data or the inability to access them.

March 14, 2024

Modern AI innovations require proper infrastructure, especially concerning data throughput and storage capabilities. While GPUs drive faster results, legacy storage solutions often lag behind, causing inefficient resource utilization and extended times in completing the project.

March 1, 2024

In this document, we’ll look at the optimal way to provide high performance to PostgreSQL in a virtualized environment. With this goal, we are comparing the performance of vHOST Kernel Target with Mdadm against SPDK vhost-blk target protected by Xinnor’s xiRAID Opus.

February 7, 2024

In our new blog post, we had the opportunity to speak with Sergey Platonov, our VP of Product Strategy, who brings a deep understanding of RAID technologies to the table. Throughout the interview, Sergey discusses the significant challenges and limitations inherent in hardware RAID solutions, from the constraints of PCI-Express lanes to logistical issues highlighted […]

September 20, 2023

This is the third and the final part of the Performance Guide. The first two parts were about performance characteristics, the ways to measure it and optimal hardware and software configurations. Now, in this concluding section, we’ll be focusing entirely on RAID.

September 14, 2023

This is the second part of our Performance Guide blog post series. In the previous part, we’ve covered the fundamentals of system performance, its basic units and methods for measurement.

September 11, 2023

Just like when the NVMe protocol first appeared on the scene, the advent of server platforms and storage devices supporting the PCI-E Gen5 interface has brought forth a new layer of complexity and challenge.

September 5, 2023

We’re excited to introduce a new blog post series focused on testing and enhancing storage performance. Throughout this series, we’ll walk you through the entire process, from defining objectives and preparing the necessary hardware and software to optimizing performance using a software RAID engine.

September 3, 2023

Erasure coding and RAID are both data protection technologies that are used to improve the reliability and performance of storage systems. While erasure coding is sometimes seen as a more advanced technology than RAID, it is important to understand that they are actually two sides of the same coin.

September 2, 2023

Solid-State Drives (SSDs) have revolutionized storage technology with their transformative impact. They offer blazing speed, minimal latency, and high throughput, making data access lightning-fast and critical for applications requiring real-time processing.