High-performance computing applications, web-scale storage systems, and modern enterprises increasingly have the need for a data architecture that will unify at the edge, and in data centers, and clouds. These organizations with massive-scale data requirements need the performance of a parallel file system coupled with a standards-based solution that will be easy to deploy on machines with diverse security and build environments.

Standards-Based Parallel Global File System - No Proprietary Clients

One of the goals of HPE’s Spaceborne Computer program is proving the value of edge computing. Spaceborne Computer-1 (SBC-1) was launched in August of 2017 with the latest available COTS (Commercial off the Shelf) hardware, including twenty solid state disks (SSDs) for storage. The disappointing durability of those SSDs will be covered; the Failure Analysis (FA) of them upon Return To Earth (RTE) will be presented and the mitigation done in Spaceborne Computer-2 will be detailed. HPE’s Spaceborne Computer-2 (SBC-2) launched in February of 2021 with over 6 TB of internal SSD storage.

With the increasing amount of network throughput, we'll reach a point where a data copies are too much for a single cpu core to handle. This talk gives an overview about how the io_uring infrastructure of the Linux kernel could be used in order to avoid copying data, as well as spreading the load between cpu cores. A prototype for this exists for quite some time and shows excellent results.

In this presentation, I will delve into the world of NVMe RAID and present a comprehensive analysis and comparison of various NVMe RAID engines. Through comparative testing and performance analysis using state-of-the-art performance analysis tools, I have identified bottlenecks in these engines when handling different workloads. During the presentation, I will provide valuable insights and comparisons, showcasing significant figures that highlight the performance differences among the tested NVMe RAID solutions.

In recent years, zoned storage has become pervasive across the storage software ecosystem, including file systems, cloud storage, and end-to-end application integrations. Zoned storage overcomes the drawbacks of write amplification by enabling the host to collaborate with the storage device when submitting writes. The ecosystem seamlessly integrates support for shingled magnetic drives (SMR HDDs), SSDs with Zoned Namespaces (ZNS SSDs), and UFS-enabled mobile devices through a single storage abstraction.

The demand for data storage continues to grow exponentially with the overall data storage temperature cooling down with most data becoming cold after one month and subsequently infrequently accessed. Given the evolving storage pyramid and the growth of the overall storage ecosystem, especially cold storage, demand for significant capacity, longevity and sustainability scaling is increasing.

Hyperscale deployments are using Serial Attached SCSI (SAS) today, to solve capacity and cost challenges within their large-scale storage infrastructure. Specific features within SAS address these problems and offer developers real solutions. This presentation will discuss how SAS addresses the scaling, reliability, cost and flexibility requirements of modern hyperscale architectures and show how this maps to Meta's Grand Canyon architecture.