On Mon, Sep 23, 2024 at 12:07:24PM GMT, Linus Torvalds wrote: > On Mon, 23 Sept 2024 at 10:18, Linus Torvalds > <torvalds@xxxxxxxxxxxxxxxxxxxx> wrote: > > > > On Sat, 21 Sept 2024 at 12:28, Kent Overstreet > > <kent.overstreet@xxxxxxxxx> wrote: > > > > > > We're now using an rhashtable instead of the system inode hash table; > > > this is another significant performance improvement on multithreaded > > > metadata workloads, eliminating more lock contention. > > > > So I've pulled this, but I reacted to this issue - what is the load > > where the inode hash table is actually causing issues? > > Oh, and I also only now noticed that a third of the commits are fairly > recent and from after the merge window even started. > > Maybe there's a good reason for that, but it sure wasn't explained in > the pull request. Grr. I rebased to drop a patch that conflicts with Andrew's tree (the PF_MEMALLOC_NORECLAIM stuff, which I would still like to chat with him about since I missed him at Plumbers...)
