This series moves the boot time initialization of tail struct pages of a
gigantic page to after HVO is attempted. If HVO is successful, only
HUGETLB_VMEMMAP_RESERVE_SIZE / sizeof(struct page) struct pages need to
be initialized. For a 1G hugepage, this series avoid initialization of
262144 - 63 = 262081 struct pages per hugepage.
When tested on a 512G system (which can allocate max 500 1G hugepages), the
kexec-boot time with HVO and DEFERRED_STRUCT_PAGE_INIT enabled without this
patchseries to running init is 3.9 seconds. With this patch it is 1.2 seconds.
This represents an approximately 70% reduction in boot time and will
significantly reduce server downtime when using a large number of
gigantic pages.
Thanks,
Usama
[v2->v3]:
- (Muchun Song) skip prep of struct pages backing gigantic hugepages
at boot time only.
- (Muchun Song) move initialization of tail struct pages to after
HVO is attempted. This also means that the hugetlb command line parsing
does not need to be changed.
[v1->v2]:
- (Mike Rapoport) Code quality improvements (function names, arguments,
comments).
[RFC->v1]:
- (Mike Rapoport) Change from passing hugepage_size in
memblock_alloc_try_nid_raw for skipping struct page initialization to
using MEMBLOCK_RSRV_NOINIT flag
Usama Arif (4):
mm: hugetlb_vmemmap: Use nid of the head page to reallocate it
memblock: pass memblock_type to memblock_setclr_flag
memblock: introduce MEMBLOCK_RSRV_NOINIT_VMEMMAP flag
mm: hugetlb: Skip initialization of gigantic tail struct pages if
freed by HVO
include/linux/memblock.h | 10 ++++++++
mm/hugetlb.c | 52 ++++++++++++++++++++++++++++++++--------
mm/hugetlb_vmemmap.c | 2 +-
mm/hugetlb_vmemmap.h | 8 +++----
mm/internal.h | 3 +++
mm/memblock.c | 47 ++++++++++++++++++++++++++----------
mm/mm_init.c | 2 +-
7 files changed, 95 insertions(+), 29 deletions(-)
--
2.25.1
