From f19298b9516c1a031b34b4147773457e3efe743b Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 28 Jun 2021 19:41:44 -0700 Subject: mm/vmstat: convert NUMA statistics to basic NUMA counters NUMA statistics are maintained on the zone level for hits, misses, foreign etc but nothing relies on them being perfectly accurate for functional correctness. The counters are used by userspace to get a general overview of a workloads NUMA behaviour but the page allocator incurs a high cost to maintain perfect accuracy similar to what is required for a vmstat like NR_FREE_PAGES. There even is a sysctl vm.numa_stat to allow userspace to turn off the collection of NUMA statistics like NUMA_HIT. This patch converts NUMA_HIT and friends to be NUMA events with similar accuracy to VM events. There is a possibility that slight errors will be introduced but the overall trend as seen by userspace will be similar. The counters are no longer updated from vmstat_refresh context as it is unnecessary overhead for counters that may never be read by userspace. Note that counters could be maintained at the node level to save space but it would have a user-visible impact due to /proc/zoneinfo. [lkp@intel.com: Fix misplaced closing brace for !CONFIG_NUMA] Link: https://lkml.kernel.org/r/20210512095458.30632-4-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Peter Zijlstra (Intel) Cc: Chuck Lever Cc: Ingo Molnar Cc: Jesper Dangaard Brouer Cc: Michal Hocko Cc: Sebastian Andrzej Siewior Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/node.c b/drivers/base/node.c index 2c36f61d30bc..9db297431b97 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -482,6 +482,7 @@ static DEVICE_ATTR(meminfo, 0444, node_read_meminfo, NULL); static ssize_t node_read_numastat(struct device *dev, struct device_attribute *attr, char *buf) { + fold_vm_numa_events(); return sysfs_emit(buf, "numa_hit %lu\n" "numa_miss %lu\n" @@ -489,12 +490,12 @@ static ssize_t node_read_numastat(struct device *dev, "interleave_hit %lu\n" "local_node %lu\n" "other_node %lu\n", - sum_zone_numa_state(dev->id, NUMA_HIT), - sum_zone_numa_state(dev->id, NUMA_MISS), - sum_zone_numa_state(dev->id, NUMA_FOREIGN), - sum_zone_numa_state(dev->id, NUMA_INTERLEAVE_HIT), - sum_zone_numa_state(dev->id, NUMA_LOCAL), - sum_zone_numa_state(dev->id, NUMA_OTHER)); + sum_zone_numa_event_state(dev->id, NUMA_HIT), + sum_zone_numa_event_state(dev->id, NUMA_MISS), + sum_zone_numa_event_state(dev->id, NUMA_FOREIGN), + sum_zone_numa_event_state(dev->id, NUMA_INTERLEAVE_HIT), + sum_zone_numa_event_state(dev->id, NUMA_LOCAL), + sum_zone_numa_event_state(dev->id, NUMA_OTHER)); } static DEVICE_ATTR(numastat, 0444, node_read_numastat, NULL); @@ -512,10 +513,11 @@ static ssize_t node_read_vmstat(struct device *dev, sum_zone_node_page_state(nid, i)); #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) + fold_vm_numa_events(); + for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) len += sysfs_emit_at(buf, len, "%s %lu\n", numa_stat_name(i), - sum_zone_numa_state(nid, i)); + sum_zone_numa_event_state(nid, i)); #endif for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { -- cgit v1.2.3