> > in the examples below we presume that the basic page size is 4K and > > @@ -463,6 +463,10 @@ fields for each mapping. (Note that AnonHugePages only applies to traditional > > PMD-sized THP for historical reasons and should have been called > > AnonHugePmdMapped). > > +The number of PMD-sized transparent huge pages currently used by > > +filesystem data (page cache) is available by reading the FileHugePages field > > +in ``/proc/meminfo``. > > + > > These changed look good. Do we also want to talk about FilePmdMapped? > (PMD-sized THPs in the page cache that are mapped in to user space using a > PMD ?) I am a bit new to this subsystem, and it took some time to wrap around all the different terminology used :) But sure, I will add a new commit to talk about FilePmdMapped. I can give it a shot with what I understand about FilePmdMapped, but please feel free to add your input. > > Do we have to distinguish it from below? (shmem also uses the page cache) > > > The number of file transparent huge pages mapped to userspace is available > > by reading ShmemPmdMapped and ShmemHugePages fields in ``/proc/meminfo``. > > To identify what applications are mapping file transparent huge pages, it > > Previously here, but: this reads rather odd. "file transparent huge pages". > "PMD-sized THPs specific to shmem are tracked separately ..." ? > I totally agree. Reading "file transparent huge pages" confused me even more. I will fold these changes as well. Thanks, David. -- Pankaj
