Messages in this thread |  | | Date | Sun, 6 Jan 2013 19:38:35 -0800 (PST) | From | Hugh Dickins <> | Subject | Re: oops in copy_page_rep() |
| |
On Sun, 6 Jan 2013, Dave Jones wrote: > > investigating the huge page theory a little further I'm a bit confused. > The kernel on that machine has THP enabled, and the cpu supports it (an old amd64), but.. > > $ cat /sys/kernel/mm/hugepages/hugepages-2048kB/* > 0 > 0 > 0 > 0 > 0 > 0 > > I was expecting at least one of those to be non-zero. > > /sys/kernel/mm/transparent_hugepage/khugepaged/full_scans and pages_collapsed > are both non-zero, so it's been busy doing _something_. > > Is this expected behaviour ?
Yes. /sys/kernel/mm/hugepages/ is all about those dusty old opaque hugepages you might have got from fs/hugetlbfs and mm/hugetlb.c; whereas the splitting issue we suspect is peculiar to the dazzling new transparent hugepages you get from mm/huge_memory.c.
Hugh
|  |