mm: hugetlb: add hugetlb_alloc_threads cmdline option

Add a command line option that enables control of how many threads should
be used to allocate huge pages.

[akpm@linux-foundation.org: tidy up a comment]
Link: https://lkml.kernel.org/r/20250227-hugepage-parameter-v2-2-7db8c6dc0453@cyberus-technology.de
Signed-off-by: Thomas Prescher <thomas.prescher@cyberus-technology.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Muchun Song <muchun.song@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Thomas Prescher 2025-02-27 23:45:06 +01:00 committed by Andrew Morton
parent c34b3eceea
commit 71f7456889
3 changed files with 48 additions and 4 deletions

View File

@ -1882,6 +1882,15 @@
Documentation/admin-guide/mm/hugetlbpage.rst.
Format: size[KMG]
hugepage_alloc_threads=
[HW] The number of threads that should be used to
allocate hugepages during boot. This option can be
used to improve system bootup time when allocating
a large amount of huge pages.
The default value is 25% of the available hardware threads.
Note that this parameter only applies to non-gigantic huge pages.
hugetlb_cma= [HW,CMA,EARLY] The size of a CMA area used for allocation
of gigantic hugepages. Or using node format, the size
of a CMA area per node can be specified.

View File

@ -145,7 +145,17 @@ hugepages
It will allocate 1 2M hugepage on node0 and 2 2M hugepages on node1.
If the node number is invalid, the parameter will be ignored.
hugepage_alloc_threads
Specify the number of threads that should be used to allocate hugepages
during boot. This parameter can be used to improve system bootup time
when allocating a large amount of huge pages.
The default value is 25% of the available hardware threads.
Example to use 8 allocation threads::
hugepage_alloc_threads=8
Note that this parameter only applies to non-gigantic huge pages.
default_hugepagesz
Specify the default huge page size. This parameter can
only be specified once on the command line. default_hugepagesz can

View File

@ -85,6 +85,7 @@ static unsigned long __initdata default_hstate_max_huge_pages;
static bool __initdata parsed_valid_hugepagesz = true;
static bool __initdata parsed_default_hugepagesz;
static unsigned int default_hugepages_in_node[MAX_NUMNODES] __initdata;
static unsigned long hugepage_allocation_threads __initdata;
static char hstate_cmdline_buf[COMMAND_LINE_SIZE] __initdata;
static int hstate_cmdline_index __initdata;
@ -3607,8 +3608,6 @@ static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h)
.numa_aware = true
};
unsigned int num_allocation_threads = max(num_online_cpus() / 4, 1);
job.thread_fn = hugetlb_pages_alloc_boot_node;
job.start = 0;
job.size = h->max_huge_pages;
@ -3629,9 +3628,13 @@ static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h)
* | cascade lake 192 cpus | 39s | 20s | 11s | 10s | 9s |
* +-----------------------+-------+-------+-------+-------+-------+
*/
if (hugepage_allocation_threads == 0) {
hugepage_allocation_threads = num_online_cpus() / 4;
hugepage_allocation_threads = max(hugepage_allocation_threads, 1);
}
job.max_threads = num_allocation_threads;
job.min_chunk = h->max_huge_pages / num_allocation_threads;
job.max_threads = hugepage_allocation_threads;
job.min_chunk = h->max_huge_pages / hugepage_allocation_threads;
padata_do_multithreaded(&job);
return h->nr_huge_pages;
@ -5000,6 +5003,28 @@ void __init hugetlb_bootmem_alloc(void)
__hugetlb_bootmem_allocated = true;
}
/*
* hugepage_alloc_threads command line parsing.
*
* When set, use this specific number of threads for the boot
* allocation of hugepages.
*/
static int __init hugepage_alloc_threads_setup(char *s)
{
unsigned long allocation_threads;
if (kstrtoul(s, 0, &allocation_threads) != 0)
return 1;
if (allocation_threads == 0)
return 1;
hugepage_allocation_threads = allocation_threads;
return 1;
}
__setup("hugepage_alloc_threads=", hugepage_alloc_threads_setup);
static unsigned int allowed_mems_nr(struct hstate *h)
{
int node;