From 629484ae73754243917e06d8d5e5f37c26e99399 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 25 Feb 2021 17:16:51 -0800 Subject: [PATCH] mm: vmstat: add some comments on internal storage of byte items Byte-accounted items are used for slab object accounting at the cgroup level, because the objects in a slab page can belong to different cgroups. At the global level these items always change in multiples of whole slab pages. The vmstat code exploits this and stores these items as pages internally, which allows for more compact per-cpu data. This optimization isn't self-evident from the asserts and the division in the stat update functions. Provide the reader with some context. Link: https://lkml.kernel.org/r/20210202184411.118614-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 6 ++++++ mm/vmstat.c | 12 ++++++++++++ 2 files changed, 18 insertions(+) diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 773135f..506d6251 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -313,6 +313,12 @@ static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { if (vmstat_item_in_bytes(item)) { + /* + * Only cgroups use subpage accounting right now; at + * the global level, these items still change in + * multiples of whole pages. Store them as pages + * internally to keep the per-cpu counters compact. + */ VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } diff --git a/mm/vmstat.c b/mm/vmstat.c index 0b0fc3b..e60b36f5 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -342,6 +342,12 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, long t; if (vmstat_item_in_bytes(item)) { + /* + * Only cgroups use subpage accounting right now; at + * the global level, these items still change in + * multiples of whole pages. Store them as pages + * internally to keep the per-cpu counters compact. + */ VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } @@ -551,6 +557,12 @@ static inline void mod_node_state(struct pglist_data *pgdat, long o, n, t, z; if (vmstat_item_in_bytes(item)) { + /* + * Only cgroups use subpage accounting right now; at + * the global level, these items still change in + * multiples of whole pages. Store them as pages + * internally to keep the per-cpu counters compact. + */ VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } -- 2.7.4