RDMA/rtrs-clt: Add a minimum latency multipath policy

This patch adds new multipath policy: min-latency.  Client checks the
latency of each path when it sends the heart-beat.  And it sends IO to the
path with the minimum latency.

Link: https://lore.kernel.org/r/20210407113444.150961-2-gi-oh.kim@ionos.com
Signed-off-by: Gioh Kim <gi-oh.kim@ionos.com>
Signed-off-by: Jack Wang <jinpu.wang@ionos.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

1 files changed, 56 insertions, 1 deletions

diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index cb1731a4483d..8139c790ba7d 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -628,6 +628,8 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 		} else if (imm_type == RTRS_HB_ACK_IMM) {
 			WARN_ON(con->c.cid);
 			sess->s.hb_missed_cnt = 0;
+			sess->s.hb_cur_latency =
+				ktime_sub(ktime_get(), sess->s.hb_last_sent);
 			if (sess->flags & RTRS_MSG_NEW_RKEY_F)
 				return  rtrs_clt_recv_done(con, wc);
 		} else {
@@ -826,6 +828,57 @@ static struct rtrs_clt_sess *get_next_path_min_inflight(struct path_it *it)
 	return min_path;
 }
 
+/**
+ * get_next_path_min_latency() - Returns path with minimal latency.
+ * @it:	the path pointer
+ *
+ * Return: a path with the lowest latency or NULL if all paths are tried
+ *
+ * Locks:
+ *    rcu_read_lock() must be hold.
+ *
+ * Related to @MP_POLICY_MIN_LATENCY
+ *
+ * This DOES skip an already-tried path.
+ * There is a skip-list to skip a path if the path has tried but failed.
+ * It will try the minimum latency path and then the second minimum latency
+ * path and so on. Finally it will return NULL if all paths are tried.
+ * Therefore the caller MUST check the returned
+ * path is NULL and trigger the IO error.
+ */
+static struct rtrs_clt_sess *get_next_path_min_latency(struct path_it *it)
+{
+	struct rtrs_clt_sess *min_path = NULL;
+	struct rtrs_clt *clt = it->clt;
+	struct rtrs_clt_sess *sess;
+	ktime_t min_latency = INT_MAX;
+	ktime_t latency;
+
+	list_for_each_entry_rcu(sess, &clt->paths_list, s.entry) {
+		if (unlikely(READ_ONCE(sess->state) != RTRS_CLT_CONNECTED))
+			continue;
+
+		if (unlikely(!list_empty(raw_cpu_ptr(sess->mp_skip_entry))))
+			continue;
+
+		latency = sess->s.hb_cur_latency;
+
+		if (latency < min_latency) {
+			min_latency = latency;
+			min_path = sess;
+		}
+	}
+
+	/*
+	 * add the path to the skip list, so that next time we can get
+	 * a different one
+	 */
+	if (min_path)
+		list_add(raw_cpu_ptr(min_path->mp_skip_entry), &it->skip_list);
+
+	return min_path;
+}
+
 static inline void path_it_init(struct path_it *it, struct rtrs_clt *clt)
 {
 	INIT_LIST_HEAD(&it->skip_list);
@@ -834,8 +887,10 @@ static inline void path_it_init(struct path_it *it, struct rtrs_clt *clt)
 
 	if (clt->mp_policy == MP_POLICY_RR)
 		it->next_path = get_next_path_rr;
-	else
+	else if (clt->mp_policy == MP_POLICY_MIN_INFLIGHT)
 		it->next_path = get_next_path_min_inflight;
+	else
+		it->next_path = get_next_path_min_latency;
 }
 
 static inline void path_it_deinit(struct path_it *it)