IB/rdmavt, staging/rdma/hfi1: use qps to dynamically scale timeout value

A busy_jiffies variable is maintained and updated when rc qps are
created and deleted. busy_jiffies is a scaled value of the number
of rc qps in the device. busy_jiffies is incremented every rc qp
scaling interval. busy_jiffies is added to the rc timeout
in add_retry_timer and mod_retry_timer. The rc qp scaling interval
is selected based on extensive performance evaluation of targeted
workloads.

Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Vennila Megavannan <vennila.megavannan@intel.com>
Signed-off-by: Jubin John <jubin.john@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

4 files changed, 32 insertions, 3 deletions

diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 439213c..7dc837c 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -685,6 +685,19 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
 	}
 
 	rdi->n_qps_allocated++;
+	/*
+	 * Maintain a busy_jiffies variable that will be added to the timeout
+	 * period in mod_retry_timer and add_retry_timer. This busy jiffies
+	 * is scaled by the number of rc qps created for the device to reduce
+	 * the number of timeouts occurring when there is a large number of
+	 * qps. busy_jiffies is incremented every rc qp scaling interval.
+	 * The scaling interval is selected based on extensive performance
+	 * evaluation of targeted workloads.
+	 */
+	if (init_attr->qp_type == IB_QPT_RC) {
+		rdi->n_rc_qps++;
+		rdi->busy_jiffies = rdi->n_rc_qps / RC_QP_SCALING_INTERVAL;
+	}
 	spin_unlock(&rdi->n_qps_lock);
 
 	if (qp->ip) {
@@ -1223,6 +1236,10 @@ int rvt_destroy_qp(struct ib_qp *ibqp)
 
 	spin_lock(&rdi->n_qps_lock);
 	rdi->n_qps_allocated--;
+	if (qp->ibqp.qp_type == IB_QPT_RC) {
+		rdi->n_rc_qps--;
+		rdi->busy_jiffies = rdi->n_rc_qps / RC_QP_SCALING_INTERVAL;
+	}
 	spin_unlock(&rdi->n_qps_lock);
 
 	if (qp->ip)
diff --git a/drivers/staging/rdma/hfi1/rc.c b/drivers/staging/rdma/hfi1/rc.c
index ba2a2cc..a4a44d3 100644
--- a/drivers/staging/rdma/hfi1/rc.c
+++ b/drivers/staging/rdma/hfi1/rc.c
@@ -68,9 +68,13 @@
  */
 static inline void hfi1_add_retry_timer(struct rvt_qp *qp)
 {
+	struct ib_qp *ibqp = &qp->ibqp;
+	struct rvt_dev_info *rdi = ib_to_rvt(ibqp->device);
+
 	qp->s_flags |= RVT_S_TIMER;
 	/* 4.096 usec. * (1 << qp->timeout) */
-	qp->s_timer.expires = jiffies + qp->timeout_jiffies;
+	qp->s_timer.expires = jiffies + qp->timeout_jiffies +
+			      rdi->busy_jiffies;
 	add_timer(&qp->s_timer);
 }
 
@@ -99,9 +103,13 @@ void hfi1_add_rnr_timer(struct rvt_qp *qp, u32 to)
  */
 static inline void hfi1_mod_retry_timer(struct rvt_qp *qp)
 {
+	struct ib_qp *ibqp = &qp->ibqp;
+	struct rvt_dev_info *rdi = ib_to_rvt(ibqp->device);
+
 	qp->s_flags |= RVT_S_TIMER;
 	/* 4.096 usec. * (1 << qp->timeout) */
-	mod_timer(&qp->s_timer, jiffies + qp->timeout_jiffies);
+	mod_timer(&qp->s_timer, jiffies + qp->timeout_jiffies +
+		  rdi->busy_jiffies);
 }
 
 /**
diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h
index 4242fea..5ccf683 100644
--- a/include/rdma/rdma_vt.h
+++ b/include/rdma/rdma_vt.h
@@ -318,7 +318,9 @@ struct rvt_dev_info {
 	/* QP */
 	struct rvt_qp_ibdev *qp_dev;
 	u32 n_qps_allocated;    /* number of QPs allocated for device */
-	spinlock_t n_qps_lock; /* keep track of number of qps */
+	u32 n_rc_qps;		/* number of RC QPs allocated for device */
+	u32 busy_jiffies;	/* timeout scaling based on RC QP count */
+	spinlock_t n_qps_lock;	/* protect qps, rc qps and busy jiffy counts */
 
 	/* memory maps */
 	struct list_head pending_mmaps;
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index aed13e1..b3ea745 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -225,6 +225,8 @@ struct rvt_ack_entry {
 	};
 };
 
+#define	RC_QP_SCALING_INTERVAL	5
+
 /*
  * Variables prefixed with s_ are for the requester (sender).
  * Variables prefixed with r_ are for the responder (receiver).