[PATCH 1/2] mm: hugetlb: add hugetlb_alloc_threads cmdline option

[Thomas Prescher via B4 Relay <devnull+thomas.prescher.cyberus-technology.de@kernel.org>]

From: Thomas Prescher <thomas.prescher@cyberus-technology.de>

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

Allocating huge pages can take a very long time on servers
with terabytes of memory even when they are allocated at
boot time where the allocation happens in parallel.

The kernel currently uses a hard coded value of 2 threads per
NUMA node for these allocations.

This patch allows to override this value.

Signed-off-by: Thomas Prescher <thomas.prescher@cyberus-technology.de>
---
 Documentation/admin-guide/kernel-parameters.txt |  7 ++++
 Documentation/admin-guide/mm/hugetlbpage.rst    |  9 ++++-
 mm/hugetlb.c                                    | 50 +++++++++++++++++--------
 3 files changed, 49 insertions(+), 17 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index fb8752b42ec8582b8750d7e014c4d76166fa2fc1..812064542fdb0a5c0ff7587aaaba8da81dc234a9 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1882,6 +1882,13 @@
 			Documentation/admin-guide/mm/hugetlbpage.rst.
 			Format: size[KMG]
 
+	hugepage_alloc_threads=
+			[HW] The number of threads per NUMA node 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 2 threads per NUMA node.
+
 	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.
diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst
index f34a0d798d5b533f30add99a34f66ba4e1c496a3..c88461be0f66887d532ac4ef20e3a61dfd396be7 100644
--- a/Documentation/admin-guide/mm/hugetlbpage.rst
+++ b/Documentation/admin-guide/mm/hugetlbpage.rst
@@ -145,7 +145,14 @@ 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 per NUMA node 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 2 threads per NUMA node. Example to use 8 threads
+	per NUMA node::
+
+		hugepage_alloc_threads=8
 default_hugepagesz
 	Specify the default huge page size.  This parameter can
 	only be specified once on the command line.  default_hugepagesz can
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 163190e89ea16450026496c020b544877db147d1..b7d24c41e0f9d22f5b86c253e29a2eca28460026 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -68,6 +68,7 @@ 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 allocation_threads_per_node __initdata = 2;
 
 /*
  * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages,
@@ -3432,26 +3433,23 @@ static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h)
 	job.size	= h->max_huge_pages;
 
 	/*
-	 * job.max_threads is twice the num_node_state(N_MEMORY),
+	 * job.max_threads is twice the num_node_state(N_MEMORY) by default.
 	 *
-	 * Tests below indicate that a multiplier of 2 significantly improves
-	 * performance, and although larger values also provide improvements,
-	 * the gains are marginal.
+	 * On large servers with terabytes of memory, huge page allocation
+	 * can consume a considerably amount of time.
 	 *
-	 * Therefore, choosing 2 as the multiplier strikes a good balance between
-	 * enhancing parallel processing capabilities and maintaining efficient
-	 * resource management.
+	 * Tests below show how long it takes to allocate 1 TiB of memory with 2MiB huge pages.
+	 * 2MiB huge pages. Using more threads can significantly improve allocation time.
 	 *
-	 * +------------+-------+-------+-------+-------+-------+
-	 * | multiplier |   1   |   2   |   3   |   4   |   5   |
-	 * +------------+-------+-------+-------+-------+-------+
-	 * | 256G 2node | 358ms | 215ms | 157ms | 134ms | 126ms |
-	 * | 2T   4node | 979ms | 679ms | 543ms | 489ms | 481ms |
-	 * | 50G  2node | 71ms  | 44ms  | 37ms  | 30ms  | 31ms  |
-	 * +------------+-------+-------+-------+-------+-------+
+	 * +--------------------+-------+-------+-------+-------+-------+
+	 * | threads per node   |   2   |   4   |   8   |   16  |    32 |
+	 * +--------------------+-------+-------+-------+-------+-------+
+	 * | skylake 4node      |   44s |   22s |   16s |   19s |   20s |
+	 * | cascade lake 4node |   39s |   20s |   11s |   10s |    9s |
+	 * +--------------------+-------+-------+-------+-------+-------+
 	 */
-	job.max_threads	= num_node_state(N_MEMORY) * 2;
-	job.min_chunk	= h->max_huge_pages / num_node_state(N_MEMORY) / 2;
+	job.max_threads	= num_node_state(N_MEMORY) * allocation_threads_per_node;
+	job.min_chunk	= h->max_huge_pages / num_node_state(N_MEMORY) / allocation_threads_per_node;
 	padata_do_multithreaded(&job);
 
 	return h->nr_huge_pages;
@@ -4764,6 +4762,26 @@ static int __init default_hugepagesz_setup(char *s)
 }
 __setup("default_hugepagesz=", default_hugepagesz_setup);
 
+/* hugepage_alloc_threads command line parsing
+ * When set, use this specific number of threads per NUMA node for the boot
+ * allocation of hugepages.
+ */
+static int __init hugepage_alloc_threads_setup(char *s)
+{
+	unsigned long threads_per_node;
+
+	if (kstrtoul(s, 0, &threads_per_node) != 0)
+		return 1;
+
+	if (threads_per_node == 0)
+		return 1;
+
+	allocation_threads_per_node = threads_per_node;
+
+	return 1;
+}
+__setup("hugepage_alloc_threads=", hugepage_alloc_threads_setup);
+
 static unsigned int allowed_mems_nr(struct hstate *h)
 {
 	int node;

-- 
2.48.1