On Tue, Dec 12, 2023 at 3:27 PM Yosry Ahmed <yosryahmed@xxxxxxxxxx> wrote: > > Let's split the rbtree breakdown into a separate series. This series > has irrelevant (and very nice) cleanups and optimizations, let's get > them separately and defer the rbtree breakdown part until we get data > about the xarray implementation. Perhaps the tree breakdown is not > needed as much with an xarray, or at the very least the implementation > would look different on top of an xarray. Actually, kinda agree - I quite like the cleanup/optimization done w.r.t dstmem reuse :)
