The patch titled
Subject: mm/mm_init: use node's number of cpus in deferred_page_init_max_threads
has been added to the -mm mm-unstable branch. Its filename is
mm-mm_init-use-nodes-number-of-cpus-in-deferred_page_init_max_threads.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-mm_init-use-nodes-number-of-cpus-in-deferred_page_init_max_threads.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Eric Chanudet <echanude@xxxxxxxxxx>
Subject: mm/mm_init: use node's number of cpus in deferred_page_init_max_threads
Date: Wed, 22 May 2024 16:38:01 -0400
x86_64 is already using the node's cpu as maximum threads. Make that the
default for all archs setting DEFERRED_STRUCT_PAGE_INIT.
This returns to the behavior prior making the function arch-specific with
commit ecd096506922 ("mm: make deferred init's max threads
arch-specific").
Setting DEFERRED_STRUCT_PAGE_INIT and testing on a few arm64 platforms
shows faster deferred_init_memmap completions:
| | x13s | SA8775p-ride | Ampere R137-P31 | Ampere HR330 |
| | Metal, 32GB | VM, 36GB | VM, 58GB | Metal, 128GB |
| | 8cpus | 8cpus | 8cpus | 32cpus |
|---------|-------------|--------------|-----------------|--------------|
| threads | ms (%) | ms (%) | ms (%) | ms (%) |
|---------|-------------|--------------|-----------------|--------------|
| 1 | 108 (0%) | 72 (0%) | 224 (0%) | 324 (0%) |
| cpus | 24 (-77%) | 36 (-50%) | 40 (-82%) | 56 (-82%) |
Link: https://lkml.kernel.org/r/20240522203758.626932-4-echanude@xxxxxxxxxx
Signed-off-by: Eric Chanudet <echanude@xxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Baoquan He <bhe@xxxxxxxxxx>
Cc: Borislav Petkov (AMD) <bp@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Mike Rapoport (IBM) <rppt@xxxxxxxxxx>
Cc: Nicholas Piggin <npiggin@xxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/x86/mm/init_64.c | 12 ------------
mm/mm_init.c | 2 +-
2 files changed, 1 insertion(+), 13 deletions(-)
--- a/arch/x86/mm/init_64.c~mm-mm_init-use-nodes-number-of-cpus-in-deferred_page_init_max_threads
+++ a/arch/x86/mm/init_64.c
@@ -1354,18 +1354,6 @@ void __init mem_init(void)
preallocate_vmalloc_pages();
}
-#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask)
-{
- /*
- * More CPUs always led to greater speedups on tested systems, up to
- * all the nodes' CPUs. Use all since the system is otherwise idle
- * now.
- */
- return max_t(int, cpumask_weight(node_cpumask), 1);
-}
-#endif
-
int kernel_set_to_readonly;
void mark_rodata_ro(void)
--- a/mm/mm_init.c~mm-mm_init-use-nodes-number-of-cpus-in-deferred_page_init_max_threads
+++ a/mm/mm_init.c
@@ -2126,7 +2126,7 @@ deferred_init_memmap_chunk(unsigned long
__weak int __init
deferred_page_init_max_threads(const struct cpumask *node_cpumask)
{
- return 1;
+ return max_t(int, cpumask_weight(node_cpumask), 1);
}
/* Initialise remaining memory on a node */
_
Patches currently in -mm which might be from echanude@xxxxxxxxxx are
mm-mm_init-use-nodes-number-of-cpus-in-deferred_page_init_max_threads.patch
