News for hackers. Stuff that matters.

A comment on Designing the Scylla Userspace Disk I/O Scheduler (Part 1). Parent comment

Re:Designing the Scylla Userspace Disk I/O Scheduler (Part 1) by mtanski on Saturday April 16, 2016 @01:32PM (#11511457)
I'm going to guess that your next step to chase further speeds is going direct to nvme just levering the block layer (per core multiq) skipping the filesystem entirely.
[ Parent | on HN ]
Re:Designing the Scylla Userspace Disk I/O Scheduler (Part 1) by seastarer on Saturday April 16, 2016 @02:39PM (#11511725)
You're going to be right on that guess. It will take some time though.
[ Parent | on HN ]