[PATCH v4 4/5] mm/compaction: more trace to understand when/why compaction start/finish

From: Joonsoo Kim
Date: Mon Jan 19 2015 - 01:11:33 EST


It is not well analyzed that when/why compaction start/finish or not. With
these new tracepoints, we can know much more about start/finish reason of
compaction. I can find following bug with these tracepoint.

http://www.spinics.net/lists/linux-mm/msg81582.html

Change from v2: omit alloc_flag, classzone_idx from tracepoint output

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
---
include/linux/compaction.h | 3 ++
include/trace/events/compaction.h | 74 +++++++++++++++++++++++++++++++++++++
mm/compaction.c | 38 +++++++++++++++++--
3 files changed, 111 insertions(+), 4 deletions(-)

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 9363c08..648d183 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -12,6 +12,9 @@
#define COMPACT_PARTIAL 3
/* The full zone was compacted */
#define COMPACT_COMPLETE 4
+/* For more detailed tracepoint output */
+#define COMPACT_NO_SUITABLE_PAGE 5
+#define COMPACT_NOT_SUITABLE_ZONE 6
/* When adding new state, please change compaction_status_string, too */

/* Used to signal whether compaction detected need_sched() or lock contention */
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index 139020b..d465358 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -164,6 +164,80 @@ TRACE_EVENT(mm_compaction_end,
compaction_status_string[__entry->status])
);

+TRACE_EVENT(mm_compaction_try_to_compact_pages,
+
+ TP_PROTO(
+ int order,
+ gfp_t gfp_mask,
+ enum migrate_mode mode),
+
+ TP_ARGS(order, gfp_mask, mode),
+
+ TP_STRUCT__entry(
+ __field(int, order)
+ __field(gfp_t, gfp_mask)
+ __field(enum migrate_mode, mode)
+ ),
+
+ TP_fast_assign(
+ __entry->order = order;
+ __entry->gfp_mask = gfp_mask;
+ __entry->mode = mode;
+ ),
+
+ TP_printk("order=%d gfp_mask=0x%x mode=%d",
+ __entry->order,
+ __entry->gfp_mask,
+ (int)__entry->mode)
+);
+
+DECLARE_EVENT_CLASS(mm_compaction_suitable_template,
+
+ TP_PROTO(struct zone *zone,
+ int order,
+ int ret),
+
+ TP_ARGS(zone, order, ret),
+
+ TP_STRUCT__entry(
+ __field(int, nid)
+ __field(char *, name)
+ __field(int, order)
+ __field(int, ret)
+ ),
+
+ TP_fast_assign(
+ __entry->nid = zone_to_nid(zone);
+ __entry->name = (char *)zone->name;
+ __entry->order = order;
+ __entry->ret = ret;
+ ),
+
+ TP_printk("node=%d zone=%-8s order=%d ret=%s",
+ __entry->nid,
+ __entry->name,
+ __entry->order,
+ compaction_status_string[__entry->ret])
+);
+
+DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_finished,
+
+ TP_PROTO(struct zone *zone,
+ int order,
+ int ret),
+
+ TP_ARGS(zone, order, ret)
+);
+
+DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_suitable,
+
+ TP_PROTO(struct zone *zone,
+ int order,
+ int ret),
+
+ TP_ARGS(zone, order, ret)
+);
+
#endif /* _TRACE_COMPACTION_H */

/* This part must be outside protection */
diff --git a/mm/compaction.c b/mm/compaction.c
index 70af2b1..8248a53 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -41,6 +41,8 @@ static const char const *compaction_status_string[] = {
"continue",
"partial",
"complete",
+ "no_suitable_page",
+ "not_suitable_zone",
};
#endif

@@ -1049,7 +1051,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE;
}

-static int compact_finished(struct zone *zone, struct compact_control *cc,
+static int __compact_finished(struct zone *zone, struct compact_control *cc,
const int migratetype)
{
unsigned int order;
@@ -1104,7 +1106,20 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
return COMPACT_PARTIAL;
}

- return COMPACT_CONTINUE;
+ return COMPACT_NO_SUITABLE_PAGE;
+}
+
+static int compact_finished(struct zone *zone, struct compact_control *cc,
+ const int migratetype)
+{
+ int ret;
+
+ ret = __compact_finished(zone, cc, migratetype);
+ trace_mm_compaction_finished(zone, cc->order, ret);
+ if (ret == COMPACT_NO_SUITABLE_PAGE)
+ ret = COMPACT_CONTINUE;
+
+ return ret;
}

/*
@@ -1114,7 +1129,7 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
* COMPACT_PARTIAL - If the allocation would succeed without compaction
* COMPACT_CONTINUE - If compaction should run now
*/
-unsigned long compaction_suitable(struct zone *zone, int order,
+static unsigned long __compaction_suitable(struct zone *zone, int order,
int alloc_flags, int classzone_idx)
{
int fragindex;
@@ -1158,11 +1173,24 @@ unsigned long compaction_suitable(struct zone *zone, int order,
*/
fragindex = fragmentation_index(zone, order);
if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
- return COMPACT_SKIPPED;
+ return COMPACT_NOT_SUITABLE_ZONE;

return COMPACT_CONTINUE;
}

+unsigned long compaction_suitable(struct zone *zone, int order,
+ int alloc_flags, int classzone_idx)
+{
+ unsigned long ret;
+
+ ret = __compaction_suitable(zone, order, alloc_flags, classzone_idx);
+ trace_mm_compaction_suitable(zone, order, ret);
+ if (ret == COMPACT_NOT_SUITABLE_ZONE)
+ ret = COMPACT_SKIPPED;
+
+ return ret;
+}
+
static int compact_zone(struct zone *zone, struct compact_control *cc)
{
int ret;
@@ -1378,6 +1406,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
if (!order || !may_enter_fs || !may_perform_io)
return COMPACT_SKIPPED;

+ trace_mm_compaction_try_to_compact_pages(order, gfp_mask, mode);
+
/* Compact each zone in the list */
for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
nodemask) {
--
1.7.9.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/