The Intel/Micron announcement of XPoint 3D in July 2015 really got my attention: finally, a vendor will start shipping a form of nonvolatile memory (NVM) that’s not NAND flash. XPoint 3D promises to be byte addressable, faster, more durable, and require lower power than any form of flash today. The downsides (there are always downsides) will be that XPoint 3D will be more expensive and have less storage capacity when it appears in early 2016.
Having byte-addressable NVM will have impacts on the way computers are designed and operating systems and software are written. If this technology proves to be everything that Intel and Micron are promising, it might change everything about the systems we are familiar with. At the very least, XPoint 3D would become a new tier in the storage hierarchy.
I asked around, trying to find someone I knew in our community who could address this topic from a file system and storage perspective. The timing was terrible, as all of the people I asked (who responded) were busy preparing FAST ’16 papers for submission, and with two deadlines at about the same time, you can guess which one is the more important.
Darrell Long, a professor at UCSC, took up my challenge, even though he too was busy on an overseas trip, as well as supervising papers to be submitted to FAST ’16. Long has experience in both storage systems and operating systems, and seemed like the right person to talk to about this development.
