On Thu, Apr 27, 2023 at 8:03 PM Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> wrote: > > On Thu, Apr 27, 2023 at 3:33 PM Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> wrote: > > > > - Suren Baghdasaryan has improved mmap_lock scalability by switching to > > per-VMA locking. > > .. related to this, we have that new PER_VMA_LOCK_STATS config entry, > which is 'default y' and has basically no help test. > > Please don't do that. > > I don't think any of the VM debugging stuff should likely be 'default > y' in the first place, but if they are, they should most definitely > have a good *explanation* for why they should be on for a normal user. Understood. I wanted these stats enabled by default to be able to identify possible pathological cases and to also let users disable them if they can't tolerate even a small overhead in the pagefault path. Should I document this reasoning for the config option? > > Linus
