On Wed, Nov 10, 2021 at 06:37:46PM +0100, David Hildenbrand wrote: > It will be if we somewhat frequent when reclaim an empty PTE page table > as soon as it turns empty. What do you think is the frequency of unlocked page table walks that this would have to block on? > Also, it adds complexity for something that is only a problem in some > corner cases -- sparse memory mappings, especially relevant for some > memory allocators after freeing a lot of memory or running VMs with > memory ballooning after inflating the balloon. Some of these use cases > might be good with just triggering page table reclaim manually from user > space. Right, this is why it would be nice if the complexity could address more than one problem, like the existing complex locking around the thp stuff.. Jason
