Scaling ZFS for NVMe - Allan Jude - EuroBSDcon 2022

Allan Jude explains how ZFS was optimized for low-latency NVMe storage by removing bottlenecks in task queues and reducing lock contention.

Learn about how ZFS is being adapted to the ways the rules of storage are being changed by NVMe. In the past, storage was slow relative to the CPU so requests were preprocessed, sorted, and coalesced to improve performance. Modern NVMe is so low latency that we must avoid as much of this preprocessing as possible to maintain the performance this new storage paradigm has to offer. An overview of the work Klara has done to improve performance of multiple ZFS pools of large numbers of NVMe disks on high thread count machines. - Fixing the scaling of the TaskQueue interface - Removing bottlenecks to synchronous writes - Reducing contention on the TaskQueues - Reducing contention on the vdev queue lock A walkthrough of how we improved performance from 3 GB/sec to over 7 GB/sec of writes.