Roman Mamedov posted on Sat, 28 Jun 2014 16:13:47 +0600 as excerpted: > Also depending on what you consider "fully works", RAID1 may not qualify > too, > as neither the read-balancing, nor write-submission algorithms are ready > for production use, performance-wise. > > (RAID1 writes to two disks sequentially, not at the same time; and reads > are satisfied from in effect a random device, not from the least-busy > device).
Good point. The current algorithms were designed as "good enough" stand- ins for testing. They were /not/ designed as highly efficient parallel-I/O on parallel devices and cores implementations, as that was to come later. Of course part of /that/ problem is that often enough, the I/O channel is /not/ the bottleneck, the bottleneck is still the horrible scaling issues due to calculating the interplay between all those snapshots and quotas and massive internal-rewrite-pattern-VM-images, thus the reason we have snapshot-aware-defrag disabled ATM, so arguably focusing on the most efficient I/O queues algorithm at this point would be premature optimization, which would mean it's a /good/ thing they haven't focused on updating them yet. Once these horrible scaling issues are addressed and snapshot-aware-defrag and the like can be enabled again without triggering week-going-and-it's-still-not-half-done issues, /then/ perhaps it's time to look at the parallel I/O queuing and balancing algorithms. -- Duncan - List replies preferred. No HTML msgs. "Every nonfree program has a lord, a master -- and if you use the program, he is your master." Richard Stallman -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
