[PATCH] mm/vmscan: add balance_pgdat begin/end tracepoints

[PATCH] mm/vmscan: add balance_pgdat begin/end tracepoints

[Bunyod Suvonov]

Vmscan has six main reclaim entry points: try_to_free_pages() for
direct reclaim, try_to_free_mem_cgroup_pages() for memcg reclaim,
mem_cgroup_shrink_node() for memcg soft limit reclaim, node_reclaim()
for node reclaim, shrink_all_memory() for hibernation reclaim, and
balance_pgdat() for kswapd reclaim.

All of them, except for shrink_all_memory() and balance_pgdat(), already
have begin/end tracepoints. This makes it harder to trace which reclaim
path is responsible for memory reclaim activity, because kswapd reclaim
cannot be identified as cleanly as other reclaim entry points, even
though it is the main background reclaim path under memory pressure.
There may be no need to trace shrink_all_memory() as it is primarily
used during hibernation. So this patch adds the missing tracepoint pair
for balance_pgdat().

The begin tracepoint records the node id, requested reclaim order, and
highest_zoneidx. The end tracepoint records the node id, reclaim order
that balance_pgdat() finished with, highest_zoneidx, and nr_reclaimed.
Together, they show the requested reclaim order and zone bound, whether
reclaim fell back to a lower order, and how much reclaim work was done.

Signed-off-by: Bunyod Suvonov <b.suvonov@sjtu.edu.cn>
---
 include/trace/events/vmscan.h | 52 +++++++++++++++++++++++++++++++++++
 mm/vmscan.c                   |  5 ++++
 2 files changed, 57 insertions(+)

diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 4445a8d9218d..b4bf7b8def1f 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -96,6 +96,58 @@ TRACE_EVENT(mm_vmscan_kswapd_wake,
 		__entry->order)
 );
 
+TRACE_EVENT(mm_vmscan_balance_pgdat_begin,
+
+	TP_PROTO(int nid, int order, int highest_zoneidx),
+
+	TP_ARGS(nid, order, highest_zoneidx),
+
+	TP_STRUCT__entry(
+		__field(int, nid)
+		__field(int, order)
+		__field(int, highest_zoneidx)
+	),
+
+	TP_fast_assign(
+		__entry->nid = nid;
+		__entry->order = order;
+		__entry->highest_zoneidx = highest_zoneidx;
+	),
+
+	TP_printk("nid=%d order=%d highest_zoneidx=%-8s",
+		__entry->nid,
+		__entry->order,
+		__print_symbolic(__entry->highest_zoneidx, ZONE_TYPE))
+);
+
+TRACE_EVENT(mm_vmscan_balance_pgdat_end,
+
+	TP_PROTO(int nid, int order, int highest_zoneidx,
+		 unsigned long nr_reclaimed),
+
+	TP_ARGS(nid, order, highest_zoneidx, nr_reclaimed),
+
+	TP_STRUCT__entry(
+		__field(int, nid)
+		__field(int, order)
+		__field(int, highest_zoneidx)
+		__field(unsigned long, nr_reclaimed)
+	),
+
+	TP_fast_assign(
+		__entry->nid = nid;
+		__entry->order = order;
+		__entry->highest_zoneidx = highest_zoneidx;
+		__entry->nr_reclaimed = nr_reclaimed;
+	),
+
+	TP_printk("nid=%d order=%d highest_zoneidx=%-8s nr_reclaimed=%lu",
+		__entry->nid,
+		__entry->order,
+		__print_symbolic(__entry->highest_zoneidx, ZONE_TYPE),
+		__entry->nr_reclaimed)
+);
+
 TRACE_EVENT(mm_vmscan_wakeup_kswapd,
 
 	TP_PROTO(int nid, int zid, int order, gfp_t gfp_flags),
diff --git a/mm/vmscan.c b/mm/vmscan.c
index bd1b1aa12581..b2d89ed69d22 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -7121,6 +7121,8 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
 		.may_unmap = 1,
 	};
 
+	trace_mm_vmscan_balance_pgdat_begin(pgdat->node_id, order,
+					    highest_zoneidx);
 	set_task_reclaim_state(current, &sc.reclaim_state);
 	psi_memstall_enter(&pflags);
 	__fs_reclaim_acquire(_THIS_IP_);
@@ -7314,6 +7316,9 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
 	psi_memstall_leave(&pflags);
 	set_task_reclaim_state(current, NULL);
 
+	trace_mm_vmscan_balance_pgdat_end(pgdat->node_id, sc.order,
+					  highest_zoneidx, sc.nr_reclaimed);
+
 	/*
 	 * Return the order kswapd stopped reclaiming at as
 	 * prepare_kswapd_sleep() takes it into account. If another caller
-- 
2.53.0