From 734c15700cdf9062ae98d8b131c6fe873dfad26d Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Tue, 22 Mar 2022 14:47:37 -0700 Subject: mm: only re-generate demotion targets when a numa node changes its N_CPU state Abhishek reported that after patch [1], hotplug operations are taking roughly double the expected time. [2] The reason behind is that the CPU callbacks that migrate_on_reclaim_init() sets always call set_migration_target_nodes() whenever a CPU is brought up/down. But we only care about numa nodes going from having cpus to become cpuless, and vice versa, as that influences the demotion_target order. We do already have two CPU callbacks (vmstat_cpu_online() and vmstat_cpu_dead()) that check exactly that, so get rid of the CPU callbacks in migrate_on_reclaim_init() and only call set_migration_target_nodes() from vmstat_cpu_{dead,online}() whenever a numa node change its N_CPU state. [1] https://lore.kernel.org/linux-mm/20210721063926.3024591-2-ying.huang@intel.com/ [2] https://lore.kernel.org/linux-mm/eb438ddd-2919-73d4-bd9f-b7eecdd9577a@linux.vnet.ibm.com/ [osalvador@suse.de: add feedback from Huang Ying] Link: https://lkml.kernel.org/r/20220314150945.12694-1-osalvador@suse.de Link: https://lkml.kernel.org/r/20220310120749.23077-1-osalvador@suse.de Fixes: 884a6e5d1f93b ("mm/migrate: update node demotion order on hotplug events") Signed-off-by: Oscar Salvador Reviewed-by: Baolin Wang Tested-by: Baolin Wang Reported-by: Abhishek Goel Cc: Dave Hansen Cc: "Huang, Ying" Cc: Abhishek Goel Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmstat.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'mm/vmstat.c') diff --git a/mm/vmstat.c b/mm/vmstat.c index d5cc8d739fac..b75b1a64b54c 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -28,6 +28,7 @@ #include #include #include +#include #include "internal.h" @@ -2049,7 +2050,12 @@ static void __init init_cpu_node_state(void) static int vmstat_cpu_online(unsigned int cpu) { refresh_zone_stat_thresholds(); - node_set_state(cpu_to_node(cpu), N_CPU); + + if (!node_state(cpu_to_node(cpu), N_CPU)) { + node_set_state(cpu_to_node(cpu), N_CPU); + set_migration_target_nodes(); + } + return 0; } @@ -2072,6 +2078,8 @@ static int vmstat_cpu_dead(unsigned int cpu) return 0; node_clear_state(node, N_CPU); + set_migration_target_nodes(); + return 0; } @@ -2103,6 +2111,9 @@ void __init init_mm_internals(void) start_shepherd_timer(); #endif +#if defined(CONFIG_MIGRATION) && defined(CONFIG_HOTPLUG_CPU) + migrate_on_reclaim_init(); +#endif #ifdef CONFIG_PROC_FS proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op); proc_create_seq("pagetypeinfo", 0400, NULL, &pagetypeinfo_op); -- cgit v1.2.3