The patch titled
memcg: break out event counters from other stats
has been added to the -mm tree. Its filename is
memcg-break-out-event-counters-from-other-stats.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: memcg: break out event counters from other stats
From: Johannes Weiner <hannes@xxxxxxxxxxx>
For increasing and decreasing per-cpu cgroup usage counters it makes sense
to use signed types, as single per-cpu values might go negative during
updates. But this is not the case for only-ever-increasing event
counters.
All the counters have been signed 64-bit so far, which was enough to count
events even with the sign bit wasted.
This patch:
- divides s64 counters into signed usage counters and unsigned
monotonically increasing event counters.
- converts unsigned event counters into 'unsigned long' rather than
'u64'. This matches the type used by the /proc/vmstat event counters.
The next patch narrows the signed usage counters type (on 32-bit CPUs,
that is).
Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Signed-off-by: Greg Thelen <gthelen@xxxxxxxxxx>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Acked-by: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Cc: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memcontrol.c | 49 ++++++++++++++++++++++++++++++++++------------
1 file changed, 37 insertions(+), 12 deletions(-)
diff -puN mm/memcontrol.c~memcg-break-out-event-counters-from-other-stats mm/memcontrol.c
--- a/mm/memcontrol.c~memcg-break-out-event-counters-from-other-stats
+++ a/mm/memcontrol.c
@@ -93,19 +93,22 @@ enum mem_cgroup_stat_index {
MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */
MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */
- MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */
- MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */
MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */
MEM_CGROUP_STAT_DATA, /* end of data requires synchronization */
- /* incremented at every pagein/pageout */
- MEM_CGROUP_EVENTS = MEM_CGROUP_STAT_DATA,
MEM_CGROUP_ON_MOVE, /* someone is moving account between groups */
-
MEM_CGROUP_STAT_NSTATS,
};
+enum mem_cgroup_events_index {
+ MEM_CGROUP_EVENTS_PGPGIN, /* # of pages paged in */
+ MEM_CGROUP_EVENTS_PGPGOUT, /* # of pages paged out */
+ MEM_CGROUP_EVENTS_COUNT, /* # of pages paged in/out */
+ MEM_CGROUP_EVENTS_NSTATS,
+};
+
struct mem_cgroup_stat_cpu {
s64 count[MEM_CGROUP_STAT_NSTATS];
+ unsigned long events[MEM_CGROUP_EVENTS_NSTATS];
};
/*
@@ -577,6 +580,22 @@ static void mem_cgroup_swap_statistics(s
this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_SWAPOUT], val);
}
+static unsigned long mem_cgroup_read_events(struct mem_cgroup *mem,
+ enum mem_cgroup_events_index idx)
+{
+ unsigned long val = 0;
+ int cpu;
+
+ for_each_online_cpu(cpu)
+ val += per_cpu(mem->stat->events[idx], cpu);
+#ifdef CONFIG_HOTPLUG_CPU
+ spin_lock(&mem->pcp_counter_lock);
+ val += mem->nocpu_base.events[idx];
+ spin_unlock(&mem->pcp_counter_lock);
+#endif
+ return val;
+}
+
static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
bool file, int nr_pages)
{
@@ -589,13 +608,13 @@ static void mem_cgroup_charge_statistics
/* pagein of a big page is an event. So, ignore page size */
if (nr_pages > 0)
- __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGIN_COUNT]);
+ __this_cpu_inc(mem->stat->events[MEM_CGROUP_EVENTS_PGPGIN]);
else {
- __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGOUT_COUNT]);
+ __this_cpu_inc(mem->stat->events[MEM_CGROUP_EVENTS_PGPGOUT]);
nr_pages = -nr_pages; /* for event */
}
- __this_cpu_add(mem->stat->count[MEM_CGROUP_EVENTS], nr_pages);
+ __this_cpu_add(mem->stat->events[MEM_CGROUP_EVENTS_COUNT], nr_pages);
preempt_enable();
}
@@ -617,9 +636,9 @@ static unsigned long mem_cgroup_get_loca
static bool __memcg_event_check(struct mem_cgroup *mem, int event_mask_shift)
{
- s64 val;
+ unsigned long val;
- val = this_cpu_read(mem->stat->count[MEM_CGROUP_EVENTS]);
+ val = this_cpu_read(mem->stat->events[MEM_CGROUP_EVENTS_COUNT]);
return !(val & ((1 << event_mask_shift) - 1));
}
@@ -1747,6 +1766,12 @@ static void mem_cgroup_drain_pcp_counter
per_cpu(mem->stat->count[i], cpu) = 0;
mem->nocpu_base.count[i] += x;
}
+ for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) {
+ unsigned long x = per_cpu(mem->stat->events[i], cpu);
+
+ per_cpu(mem->stat->events[i], cpu) = 0;
+ mem->nocpu_base.events[i] += x;
+ }
/* need to clear ON_MOVE value, works as a kind of lock. */
per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) = 0;
spin_unlock(&mem->pcp_counter_lock);
@@ -3699,9 +3724,9 @@ mem_cgroup_get_local_stat(struct mem_cgr
s->stat[MCS_RSS] += val * PAGE_SIZE;
val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_FILE_MAPPED);
s->stat[MCS_FILE_MAPPED] += val * PAGE_SIZE;
- val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_PGPGIN_COUNT);
+ val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGPGIN);
s->stat[MCS_PGPGIN] += val;
- val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_PGPGOUT_COUNT);
+ val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGPGOUT);
s->stat[MCS_PGPGOUT] += val;
if (do_swap_account) {
val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_SWAPOUT);
_
Patches currently in -mm which might be from hannes@xxxxxxxxxxx are
mm-vmscan-stop-reclaim-compaction-earlier-due-to-insufficient-progress-if-__gfp_repeat.patch
mm-introduce-delete_from_page_cache.patch
mm-hugetlbfs-change-remove_from_page_cache.patch
mm-shmem-change-remove_from_page_cache.patch
mm-truncate-change-remove_from_page_cache.patch
mm-good-bye-remove_from_page_cache.patch
mm-change-__remove_from_page_cache.patch
mm-batch-free-pcp-list-if-possible.patch
mm-batch-free-pcp-list-if-possible-fix.patch
epoll-fix-compiler-warning-and-optimize-the-non-blocking-path-fix.patch
memcg-res_counter_read_u64-fix-potential-races-on-32-bit-machines.patch
memcg-fix-ugly-initialization-of-return-value-is-in-caller.patch
memcg-soft-limit-reclaim-should-end-at-limit-not-below.patch
memcg-simplify-the-way-memory-limits-are-checked.patch
memcg-remove-unused-page-flag-bitfield-defines.patch
memcg-remove-impossible-conditional-when-committing.patch
memcg-remove-null-check-from-lookup_page_cgroup-result.patch
memcg-add-memcg-sanity-checks-at-allocating-and-freeing-pages.patch
memcg-add-memcg-sanity-checks-at-allocating-and-freeing-pages-update.patch
memcg-add-memcg-sanity-checks-at-allocating-and-freeing-pages-update-fix.patch
memcg-no-uncharged-pages-reach-page_cgroup_zoneinfo.patch
memcg-change-page_cgroup_zoneinfo-signature.patch
memcg-fold-__mem_cgroup_move_account-into-caller.patch
memcg-condense-page_cgroup-to-page-lookup-points.patch
memcg-remove-direct-page_cgroup-to-page-pointer.patch
memcg-remove-direct-page_cgroup-to-page-pointer-fix.patch
memcg-remove-direct-page_cgroup-to-page-pointer-fix-fix.patch
memcg-charged-pages-always-have-valid-per-memcg-zone-info.patch
memcg-remove-memcg-reclaim_param_lock.patch
memcg-keep-only-one-charge-cancelling-function.patch
memcg-keep-only-one-charge-cancelling-function-fix.patch
memcg-convert-per-cpu-stock-from-bytes-to-page-granularity.patch
memcg-convert-uncharge-batching-from-bytes-to-page-granularity.patch
memcg-unify-charge-uncharge-quantities-to-units-of-pages.patch
memcg-break-out-event-counters-from-other-stats.patch
memcg-use-native-word-page-statistics-counters.patch
crash_dump-export-is_kdump_kernel-to-modules-consolidate-elfcorehdr_addr-setup_elfcorehdr-and-saved_max_pfn.patch
crash_dump-export-is_kdump_kernel-to-modules-consolidate-elfcorehdr_addr-setup_elfcorehdr-and-saved_max_pfn-fix.patch
crash_dump-export-is_kdump_kernel-to-modules-consolidate-elfcorehdr_addr-setup_elfcorehdr-and-saved_max_pfn-fix-fix.patch
--
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
