On Wed, Apr 27, 2022 at 10:33:31AM -0700, Andrew Morton wrote: > On Wed, 27 Apr 2022 14:08:39 +0000 Liam Howlett <liam.howlett@xxxxxxxxxx> wrote: > > The benchmarks are around the same as they have always been. > > So it's presently a wash. > > That makes "the plan" (below) really critical, otherwise there seems > little point in merging this code at this time? > > Please send me many very soothing words about how confident we should > be that the plan will be implemented and that it shall be good? Yes, performance-wise it's a wash. However, Davidlohr was very impressed that it was a wash because we're actually getting rid of three data structures here; the linked list, the rbtree and the vmacache. His opinion was that we should push the maple tree in now, in advance of the future RCU uses. We also have other users waiting in the wings. Dave Howells has something he's working on that uses the maple tree directly. I have a couple of XArray users that are using it inappropriately that I want to convert ... I just didn't want to do that work before all this lands. The current LSFMM schedule has very many words about the Maple tree scheduled for 13:30-15:00 on Monday. Hopefully we'll have a better idea after that how confident we are that RCU VMA walking is going to work.
