On Thu, Apr 04, 2019 at 07:57:37PM +0300, Amir Goldstein wrote: > This patch improves performance of mixed random rw workload > on xfs without relaxing the atomic buffered read/write guaranty > that xfs has always provided. > > We achieve that by calling generic_file_read_iter() twice. > Once with a discard iterator to warm up page cache before taking > the shared ilock and once again under shared ilock. This will race with thing like truncate, hole punching, etc that serialise IO and invalidate the page cache for data integrity reasons under the IOLOCK. These rely on there being no IO to the inode in progress at all to work correctly, which this patch violates. IOWs, while this is fast, it is not safe and so not a viable approach to solving the problem. FYI, I'm working on a range lock implementation that should both solve the performance issue and the reader starvation issue at the same time by allowing concurrent buffered reads and writes to different file ranges. IO range locks will allow proper exclusion for other extent manipulation operations like fallocate and truncate, and eventually even allow truncate, hole punch, file extension, etc to run concurrently with other non-overlapping IO. They solve more than just the performance issue you are seeing.... Cheers, Dave. -- Dave Chinner david@xxxxxxxxxxxxx
