tracing, page-allocator: add trace event for page traffic related to the buddy lists

The page allocation trace event reports that a page was successfully
allocated but it does not specify where it came from.  When analysing
performance, it can be important to distinguish between pages coming from
the per-cpu allocator and pages coming from the buddy lists as the latter
requires the zone lock to the taken and more data structures to be
examined.

This patch adds a trace event for __rmqueue reporting when a page is being
allocated from the buddy lists.  It distinguishes between being called to
refill the per-cpu lists or whether it is a high-order allocation.
Similarly, this patch adds an event to catch when the PCP lists are being
drained a little and pages are going back to the buddy lists.

This is trickier to draw conclusions from but high activity on those
events could explain why there were a large number of cache misses on a
page-allocator-intensive workload.  The coalescing and splitting of
buddies involves a lot of writing of page metadata and cache line bounces
not to mention the acquisition of an interrupt-safe lock necessary to
enter this path.

[akpm@linux-foundation.org: fix build]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Ingo Molnar <mingo@elte.hu>
Cc: Larry Woodman <lwoodman@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Li Ming Chun <macli@brc.ubc.ca>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index aae16ee..eaf46bd 100644 (file)
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -299,6 +299,57 @@ TRACE_EVENT(mm_page_alloc,
                show_gfp_flags(__entry->gfp_flags))
 );
 
+TRACE_EVENT(mm_page_alloc_zone_locked,
+
+       TP_PROTO(struct page *page, unsigned int order, int migratetype),
+
+       TP_ARGS(page, order, migratetype),
+
+       TP_STRUCT__entry(
+               __field(        struct page *,  page            )
+               __field(        unsigned int,   order           )
+               __field(        int,            migratetype     )
+       ),
+
+       TP_fast_assign(
+               __entry->page           = page;
+               __entry->order          = order;
+               __entry->migratetype    = migratetype;
+       ),
+
+       TP_printk("page=%p pfn=%lu order=%u migratetype=%d percpu_refill=%d",
+               __entry->page,
+               page_to_pfn(__entry->page),
+               __entry->order,
+               __entry->migratetype,
+               __entry->order == 0)
+);
+
+TRACE_EVENT(mm_page_pcpu_drain,
+
+       TP_PROTO(struct page *page, int order, int migratetype),
+
+       TP_ARGS(page, order, migratetype),
+
+       TP_STRUCT__entry(
+               __field(        struct page *,  page            )
+               __field(        int,            order           )
+               __field(        int,            migratetype     )
+       ),
+
+       TP_fast_assign(
+               __entry->page           = page;
+               __entry->order          = order;
+               __entry->migratetype    = migratetype;
+       ),
+
+       TP_printk("page=%p pfn=%lu order=%d migratetype=%d",
+               __entry->page,
+               page_to_pfn(__entry->page),
+               __entry->order,
+               __entry->migratetype)
+);
+
 TRACE_EVENT(mm_page_alloc_extfrag,
 
        TP_PROTO(struct page *page,

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 77f517c..4c847cc 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -48,6 +48,7 @@
 #include <linux/page_cgroup.h>
 #include <linux/debugobjects.h>
 #include <linux/kmemleak.h>
+#include <trace/events/kmem.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -535,6 +536,7 @@ static void free_pages_bulk(struct zone *zone, int count,
                page = list_entry(list->prev, struct page, lru);
                /* have to delete it as __free_one_page list manipulates */
                list_del(&page->lru);
+               trace_mm_page_pcpu_drain(page, order, page_private(page));
                __free_one_page(page, zone, order, page_private(page));
        }
        spin_unlock(&zone->lock);
@@ -890,6 +892,7 @@ retry_reserve:
                }
        }
 
+       trace_mm_page_alloc_zone_locked(page, order, migratetype);
        return page;
 }