Technical Activities White Papers

The following are technical white papers produced by various SNIA Technical Work Groups and the SNIA Technical Council.

Hyperscaler Storage

Hyperscaler storage customers typically build their own storage systems from commodity components. They have requirements for drives (SSDs and Hard drives) that are in some cases being put into standard interfaces. This paper explores that trend and highlights features of existing and new standards that will meet those requirements.

Persistent Memory Hardware Threat Model 

This SNIA Technical White Paper discusses approaches for securing persistent memory (PM), particularly considering unique characteristics of PM.  This work includes a threat model and potential responses to threats.

NVM PM Remote Access for High Availability

This paper explores the requirements that High Availability extensions to the NVM.PM.FILE mode of the SNIA NVM Programming Model might place on high speed networking, such as RDMA.

Architectural Model for Data Integrity

This document describes a model for how data integrity can be protected between an Application client and a storage device. If all nodes in an implementation follow this model then there will be end-to-end data protection for the following class of data integrity errors: silent data corruption, wrong address on device and buffer corruption.

Hypervisor Storage Interfaces for Storage Optimization White Paper

To assist with the management and operation of Hypervisor Storage, the SNIA HSI TWG is clarifying the use of, extending, and/or developing standard Hypervisor Storage Interfaces for storage interactions with hypervisors. These interfaces enable the hypervisor to offload certain storage intensive tasks to the underlying storage systems to achieve performance and functional improvements.

It is the purpose of this document to describe use cases where it is desirable to have the storage array perform offload operations and/or have some visibility into virtual disk constructs while maintaining the necessary and appropriate abstractions and isolation.

The first revision of this document focuses on optimizing copy operations and space reclamation operations in block storage environments.