On Mon, Mar 17, 2025 at 6:42 AM Harry Yoo <harry.yoo@xxxxxxxxxx> wrote: > If we allow reclaiming per-cpu stuff only biut do not reclaim > the slab object that contains it... > > Does that mean the users of the cache need to check if the percpu > memory has been reclaimed and if so, should call init routines (e.g., > mm_init())? > see the other mail (about to be written) e-mail. > > I'm happy to split the churn and add some 'return 0;' myself. > > Fortunately, there were only a handful users of of constructor ;-) > Never mind, I converted all of them in an hour (splitting the work + ping > pong-ing seemed like unnecessary overhead). > cool and apologies again :) > Will send the patch series before too late. > But please be patient—since LSFMM is next week, > I'm expecting to be busier than usual :) > there is zero time pressure here mate I appreciate you looking into this. -- Mateusz Guzik <mjguzik gmail.com>
