From: Kemi Wang <kemi.wang@xxxxxxxxx> Subject: mm: consider the number in local CPUs when reading NUMA stats To avoid deviation, the per cpu number of NUMA stats in vm_numa_stat_diff[] is included when a user *reads* the NUMA stats. Since NUMA stats does not be read by users frequently, and kernel does not need it to make a decision, it will not be a problem to make the readers more expensive. Link: http://lkml.kernel.org/r/1503568801-21305-4-git-send-email-kemi.wang@xxxxxxxxx Signed-off-by: Kemi Wang <kemi.wang@xxxxxxxxx> Reported-by: Jesper Dangaard Brouer <brouer@xxxxxxxxxx> Acked-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx> Cc: Aaron Lu <aaron.lu@xxxxxxxxx> Cc: Andi Kleen <andi.kleen@xxxxxxxxx> Cc: Christopher Lameter <cl@xxxxxxxxx> Cc: Dave Hansen <dave.hansen@xxxxxxxxx> Cc: Johannes Weiner <hannes@xxxxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxxx> Cc: Tim Chen <tim.c.chen@xxxxxxxxx> Cc: Ying Huang <ying.huang@xxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/vmstat.h | 6 +++++- mm/vmstat.c | 9 +++++++-- 2 files changed, 12 insertions(+), 3 deletions(-) diff -puN include/linux/vmstat.h~mm-consider-the-number-in-local-cpus-when-reads-numa-stats include/linux/vmstat.h --- a/include/linux/vmstat.h~mm-consider-the-number-in-local-cpus-when-reads-numa-stats +++ a/include/linux/vmstat.h @@ -125,10 +125,14 @@ static inline unsigned long global_numa_ return x; } -static inline unsigned long zone_numa_state(struct zone *zone, +static inline unsigned long zone_numa_state_snapshot(struct zone *zone, enum numa_stat_item item) { long x = atomic_long_read(&zone->vm_numa_stat[item]); + int cpu; + + for_each_online_cpu(cpu) + x += per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item]; return x; } diff -puN mm/vmstat.c~mm-consider-the-number-in-local-cpus-when-reads-numa-stats mm/vmstat.c --- a/mm/vmstat.c~mm-consider-the-number-in-local-cpus-when-reads-numa-stats +++ a/mm/vmstat.c @@ -897,6 +897,10 @@ unsigned long sum_zone_node_page_state(i return count; } +/* + * Determine the per node value of a numa stat item. To avoid deviation, + * the per cpu stat number in vm_numa_stat_diff[] is also included. + */ unsigned long sum_zone_numa_state(int node, enum numa_stat_item item) { @@ -905,7 +909,7 @@ unsigned long sum_zone_numa_state(int no unsigned long count = 0; for (i = 0; i < MAX_NR_ZONES; i++) - count += zone_numa_state(zones + i, item); + count += zone_numa_state_snapshot(zones + i, item); return count; } @@ -1536,7 +1540,7 @@ static void zoneinfo_show_print(struct s for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) seq_printf(m, "\n %-12s %lu", vmstat_text[i + NR_VM_ZONE_STAT_ITEMS], - zone_numa_state(zone, i)); + zone_numa_state_snapshot(zone, i)); #endif seq_printf(m, "\n pagesets"); @@ -1792,6 +1796,7 @@ static bool need_update(int cpu) #ifdef CONFIG_NUMA BUILD_BUG_ON(sizeof(p->vm_numa_stat_diff[0]) != 2); #endif + /* * The fast way of checking if there are any vmstat diffs. * This works because the diffs are byte sized items. _ -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
