Online / 6 & 7 February 2021


Starting Over

A FOSS proposal for a new type of OS for a new type of computer

A possible next evolutionary step for computers is persistent memory: large capacity non-volatile main memory. With a few terabytes of nonvolatile RAM, who needs an SSD any more? I will sketch out a proposal for how to build an versatile, general-purpose OS for a computer that doesn't need or use filesystems or files, and how such a thing could be built from existing FOSS code and techniques, using lessons from systems that existed decades ago and which inspired the computers we use today.

Since the era of the mainframe, all computers have used hard disks and at least two levels of storage: main memory, or RAM, and secondary or auxiliary storage: disk drives, accessed over some form of disk controller using a file system to index the contents of secondary storage for retrieval.

Technology such as Intel's 3D Xpoint -- sold under the brand name Optane -- and HP's future memristor storage will render this separation obsolete. When a computer's permanent storage is all right there in the processors' memory map, there is no need for disk controllers or filesystems. It's all just RAM.

It is very hard to imagine how existing filesystem-centric OSes such as Unix could be adapted to take full advantage of this, so fundamental are files and directories and metadata to how they operate. I will present the outline of an idea how to build an OS that natively uses such a computer architecture, based on existing technology and software, that the FOSS community is ideally situated to build and develop.


Photo of Liam Proven Liam Proven