On Mon, Apr 12, 2021 at 11:59:38AM +0100, Mel Gorman wrote: > > I don't understand this comment. Only alloc_flags_nofragment() sets this flag > > and we don't use it here? > > > > It's there as a reminder that there are non-obvious consequences > to ALLOC_NOFRAGMENT that may affect the bulk allocation success > rate. __rmqueue_fallback will only select pageblock_order pages and if that > fails, we fall into the slow path that allocates a single page. I didn't > deal with it because it was not obvious that it's even relevant but I bet > in 6 months time, I'll forget that ALLOC_NOFRAGMENT may affect success > rates without the comment. I'm waiting for a bug that can trivially trigger > a case with a meaningful workload where the success rate is poor enough to > affect latency before adding complexity. Ideally by then, the allocation > paths would be unified a bit better. > So this needs better clarification. ALLOC_NOFRAGMENT is not a problem at the moment but at one point during development, it was a non-obvious potential problem. If the paths are unified, ALLOC_NOFRAGMENT *potentially* becomes a problem depending on how it's done and it needs careful consideration. For example, it could be part unified by moving the alloc_flags_nofragment() call into prepare_alloc_pages because in __alloc_pages, it always happens and it looks like an obvious partial unification. Hence the comment "May set ALLOC_NOFRAGMENT" because I wanted a reminder in case I "fixed" this in 6 months time and forgot the downside. -- Mel Gorman SUSE Labs
