On Fri, Jan 17, 2025 at 10:26:34AM +0000, John Garry wrote: > On 14/01/2025 23:57, Darrick J. Wong wrote: > > > i.e. RWF_ATOMIC as implemented by a COW capable filesystem should > > > always be able to succeed regardless of IO alignment. In these > > > situations, the REQ_ATOMIC block layer offload to the hardware is a > > > fast path that is enabled when the user IO and filesystem extent > > > alignment matches the constraints needed to do a hardware atomic > > > write. > > > > > > In all other cases, we implement RWF_ATOMIC something like > > > always-cow or prealloc-beyond-eof-then-xchg-range-on-io-completion > > > for anything that doesn't correctly align to hardware REQ_ATOMIC. > > > > > > That said, there is nothing that prevents us from first implementing > > > RWF_ATOMIC constraints as "must match hardware requirements exactly" > > > and then relaxing them to be less stringent as filesystems > > > implementations improve. We've relaxed the direct IO hardware > > > alignment constraints multiple times over the years, so there's > > > nothing that really prevents us from doing so with RWF_ATOMIC, > > > either. Especially as we have statx to tell the application exactly > > > what alignment will get fast hardware offloads... > > Ok, let's do that then. Just to be clear -- for any RWF_ATOMIC direct > > write that's correctly aligned and targets a single mapping in the > > correct state, we can build the untorn bio and submit it. For > > everything else, prealloc some post EOF blocks, write them there, and > > exchange-range them. > > I have some doubt about this, but I may be misunderstanding the concept: > > So is there any guarantee that what we write into is aligned (after the > exchange-range routine)? If not, surely every subsequent write with > RWF_ATOMIC to that logical range will require this exchange-range routine > until we get something aligned (and correct granularity) - correct? Correct, you'd still need forcealign to make sure that the new allocations for exchange-range are aligned to awumin. --D > I know that getting unaligned blocks continuously is unlikely, unless a > heavily fragmented disk. However, databases prefer guaranteed performance > (which HW offload gives). > > We can use extszhint to hint at granularity, but that does not help with > alignment (AFAIK). > > > > > Tricky questions: How do we avoid collisions between overlapping writes? > > I guess we find a free file range at the top of the file that is long > > enough to stage the write, and put it there? And purge it later? > > > > Also, does this imply that the maximum file size is less than the usual > > 8EB? > > > > (There's also the question about how to do this with buffered writes, > > but I guess we could skip that for now.) > >
