On Wed, Sep 16, 2020 at 10:24 AM Mikulas Patocka <mpatocka@xxxxxxxxxx> wrote: > > > > On Wed, 16 Sep 2020, Dan Williams wrote: > > > On Wed, Sep 16, 2020 at 3:57 AM Mikulas Patocka <mpatocka@xxxxxxxxxx> wrote: > > > > > > > > > > > > I'm submitting this patch that adds the required exports (so that we could > > > use __copy_from_user_flushcache on x86, arm64 and powerpc). Please, queue > > > it for the next merge window. > > > > Why? This should go with the first user, and it's not clear that it > > needs to be relative to the current dax_operations export scheme. > > Before nvfs gets included in the kernel, I need to distribute it as a > module. So, it would make my maintenance easier. But if you don't want to > export it now, no problem, I can just copy __copy_user_flushcache from the > kernel to the module. That sounds a better plan than exporting symbols with no in-kernel consumer. > > My first question about nvfs is how it compares to a daxfs with > > executables and other binaries configured to use page cache with the > > new per-file dax facility? > > nvfs is faster than dax-based filesystems on metadata-heavy operations > because it doesn't have the overhead of the buffer cache and bios. See > this: http://people.redhat.com/~mpatocka/nvfs/BENCHMARKS ...and that metadata problem is intractable upstream? Christoph poked at bypassing the block layer for xfs metadata operations [1], I just have not had time to carry that further. [1]: "xfs: use dax_direct_access for log writes", although it seems he's dropped that branch from his xfs.git
