On Mon, Mar 22, 2021 at 06:03:21PM +0900, Sergey Senozhatsky wrote: > On (21/03/22 08:15), Matthew Wilcox wrote: > > > > What's the scenario for which your allocator performs better than slub > > > > IIRC request and reply buffers can be up to 4M in size. So this stuff > just allocates a number of fat buffers and keeps them around so that > it doesn't have to vmalloc(4M) for every request and every response. That makes a lot more sense; I was thrown off by the kvmalloc, which is usually used for allocations that might be smaller than PAGE_SIZE. So what this patch is really saying is that vmalloc() should include some caching, so it can defer freeing until there's memory pressure or it's built up a large (percpu) backlog of freed areas. Vlad, have you thought about this?
