Address issues slowing memory init
Get series with b4
b4 am [email protected]Versions newest first · linked by author and title
- v2 Latest2 patches 17 repliesIn review
- v12 patches 14 repliesSuperseded
Patches in v2 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/2 | mm: Move page struct poisoning to CONFIG_DEBUG_VM_PAGE_INIT_POISONinclude/ lib/ mm/ +1 more | +25 | 16 replies | |
| 2/2 | mm: Create non-atomic version of SetPageReserved for init useinclude/ mm/ | +12 | 1 reply |
Reviews trailers per patch
1 of 2 patches has a Reviewed-by or Acked-by.
| Patch | Michal Hocko |
|---|---|
| 1/2 | |
| 2/2 | A-b |
Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.
Cover letter [PATCH v2 0/2] Address issues slowing memory init
This patch series is meant to address some issues I consider to be low-hanging fruit in regards to memory initialization optimization.
With these two changes I am able to cut the hot-plug memory initialization times in my environment in half.
v2: Added comments about why we are using __SetPageReserved
Added new config and updated approach used for page init poisoning
---
Alexander Duyck (2):
mm: Move page struct poisoning to CONFIG_DEBUG_VM_PAGE_INIT_POISON
mm: Create non-atomic version of SetPageReserved for init use
include/linux/page-flags.h | 9 +++++++++ lib/Kconfig.debug | 14 ++++++++++++++ mm/memblock.c | 5 ++--- mm/page_alloc.c | 13 +++++++++++-- mm/sparse.c | 4 +--- 5 files changed, 37 insertions(+), 8 deletions(-)
--