On 17/04/2025 01:02, Nico Pache wrote: > Now that we can collapse to mTHPs lets update the admin guide to > reflect these changes and provide proper guidence on how to utilize it. > > Signed-off-by: Nico Pache <npache@xxxxxxxxxx> > --- > Documentation/admin-guide/mm/transhuge.rst | 10 +++++++++- > 1 file changed, 9 insertions(+), 1 deletion(-) > > diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst > index dff8d5985f0f..06814e05e1d5 100644 > --- a/Documentation/admin-guide/mm/transhuge.rst > +++ b/Documentation/admin-guide/mm/transhuge.rst > @@ -63,7 +63,7 @@ often. > THP can be enabled system wide or restricted to certain tasks or even > memory ranges inside task's address space. Unless THP is completely > disabled, there is ``khugepaged`` daemon that scans memory and > -collapses sequences of basic pages into PMD-sized huge pages. > +collapses sequences of basic pages into huge pages. > > The THP behaviour is controlled via :ref:`sysfs <thp_sysfs>` > interface and using madvise(2) and prctl(2) system calls. > @@ -144,6 +144,14 @@ hugepage sizes have enabled="never". If enabling multiple hugepage > sizes, the kernel will select the most appropriate enabled size for a > given allocation. > > +khugepaged uses max_ptes_none scaled to the order of the enabled mTHP size to > +determine collapses. When using mTHPs it's recommended to set max_ptes_none > +low-- ideally less than HPAGE_PMD_NR / 2 (255 on 4k page size). This will > +prevent undesired "creep" behavior that leads to continuously collapsing to a > +larger mTHP size. max_ptes_shared and max_ptes_swap have no effect when > +collapsing to a mTHP, and mTHP collapse will fail on shared or swapped out > +pages. > + Hi Nico, Could you add a bit more explanation of the creep behaviour here in documentation. I remember you explained in one of the earlier versions that if more than half of the collapsed mTHP is zero-filled, it for some reason becomes eligible for collapsing to larger order, but if less than half is zero-filled its not eligible? I cant exactly remember what the reason was :) Would be good to have it documented more if possible. Thanks > It's also possible to limit defrag efforts in the VM to generate > anonymous hugepages in case they're not immediately free to madvise > regions or to never try to defrag memory and simply fallback to regular
