Hi Christopher, On Tue, Aug 07, 2018 at 02:12:06PM +0000, Christopher Lameter wrote: > On Mon, 6 Aug 2018, Dennis Zhou wrote: > > show_val_kb(m, "VmallocUsed: ", 0ul); > > show_val_kb(m, "VmallocChunk: ", 0ul); > > + show_val_kb(m, "PercpuPopulated:", pcpu_nr_populated_pages()); > > Populated? Can we avoid this for simplicities sake: "Percpu"? Yeah, I've dropped populated. > > We do not count pages that are not present elsewhere either and those > counters do not have "populated" in them. I see, that makes sense. I think I was trying to keep an external distinction between what we reserve and what we actually have populated that really isn't useful outside of playing with the allocator itself. > > int pcpu_nr_empty_pop_pages; > > > > +/* > > + * The number of populated pages in use by the allocator, protected by > > + * pcpu_lock. This number is kept per a unit per chunk (i.e. when a page gets > > + * allocated/deallocated, it is allocated/deallocated in all units of a chunk > > + * and increments/decrements this count by 1). > > + */ > > +static int pcpu_nr_populated; > > pcpu_nr_pages? > I'd rather keep it as pcpu_nr_populated because internally in pcpu_chunk we maintain nr_pages and nr_populated. That way we keep the same meaning at the chunk and global level. Thanks, Dennis
