mm/mm_init: use node's number of cpus in deferred_page_init_max_threads
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 ecd0965069
("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%) |
Michael Ellerman reported:
: On a machine here (1TB, 40 cores, 4KB pages) the existing code gives:
:
: [ 0.500124] node 2 deferred pages initialised in 210ms
: [ 0.515790] node 3 deferred pages initialised in 230ms
: [ 0.516061] node 0 deferred pages initialised in 230ms
: [ 0.516522] node 7 deferred pages initialised in 230ms
: [ 0.516672] node 4 deferred pages initialised in 230ms
: [ 0.516798] node 6 deferred pages initialised in 230ms
: [ 0.517051] node 5 deferred pages initialised in 230ms
: [ 0.523887] node 1 deferred pages initialised in 240ms
:
: vs with the patch:
:
: [ 0.379613] node 0 deferred pages initialised in 90ms
: [ 0.380388] node 1 deferred pages initialised in 90ms
: [ 0.380540] node 4 deferred pages initialised in 100ms
: [ 0.390239] node 6 deferred pages initialised in 100ms
: [ 0.390249] node 2 deferred pages initialised in 100ms
: [ 0.390786] node 3 deferred pages initialised in 110ms
: [ 0.396721] node 5 deferred pages initialised in 110ms
: [ 0.397095] node 7 deferred pages initialised in 110ms
:
: Which is a nice speedup.
[echanude@redhat.com: v3]
Link: https://lkml.kernel.org/r/20240528185455.643227-4-echanude@redhat.com
Link: https://lkml.kernel.org/r/20240522203758.626932-4-echanude@redhat.com
Signed-off-by: Eric Chanudet <echanude@redhat.com>
Tested-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
Reviewed-by: Baoquan He <bhe@redhat.com>
Acked-by: Alexander Gordeev <agordeev@linux.ibm.com>
Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov (AMD) <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
parent
3577dbb192
commit
188f87f264
@ -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)
|
||||
|
@ -335,8 +335,6 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone,
|
||||
for (; i != U64_MAX; \
|
||||
__next_mem_pfn_range_in_zone(&i, zone, p_start, p_end))
|
||||
|
||||
int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask);
|
||||
|
||||
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
|
||||
|
||||
/**
|
||||
|
@ -2122,11 +2122,10 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
|
||||
}
|
||||
}
|
||||
|
||||
/* An arch may override for more concurrency. */
|
||||
__weak int __init
|
||||
static unsigned int __init
|
||||
deferred_page_init_max_threads(const struct cpumask *node_cpumask)
|
||||
{
|
||||
return 1;
|
||||
return max(cpumask_weight(node_cpumask), 1U);
|
||||
}
|
||||
|
||||
/* Initialise remaining memory on a node */
|
||||
|
Loading…
Reference in New Issue
Block a user