[dpdk-dev] [PATCH] net/bonding: ensure fairness among slaves

Chas Williams 3chas3 at gmail.com
Wed Sep 19 17:48:25 CEST 2018


From: Chas Williams <chas3 at att.com>

Some PMDs, especially ones with vector receives, require a minimum number
of receive buffers in order to receive any packets.  If the first slave
read leaves less than this number available, a read from the next slave
may return 0 implying that the slave doesn't have any packets which
results in skipping over that slave as the next active slave.

To fix this, implement round robin for the slaves during receive that
is only advanced to the next slave at the end of each receive burst.
This should also provide some additional fairness in processing in
bond_ethdev_rx_burst as well.

Fixes: 2efb58cbab6e ("bond: new link bonding library")
Cc: stable at dpdk.org

Signed-off-by: Chas Williams <chas3 at att.com>
---
 drivers/net/bonding/rte_eth_bond_pmd.c | 50 ++++++++++++++++++++++------------
 1 file changed, 32 insertions(+), 18 deletions(-)

diff --git a/drivers/net/bonding/rte_eth_bond_pmd.c b/drivers/net/bonding/rte_eth_bond_pmd.c
index b84f32263..f25faa75c 100644
--- a/drivers/net/bonding/rte_eth_bond_pmd.c
+++ b/drivers/net/bonding/rte_eth_bond_pmd.c
@@ -58,28 +58,33 @@ bond_ethdev_rx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 {
 	struct bond_dev_private *internals;
 
-	uint16_t num_rx_slave = 0;
 	uint16_t num_rx_total = 0;
-
+	uint16_t slave_count;
+	uint16_t active_slave;
 	int i;
 
 	/* Cast to structure, containing bonded device's port id and queue id */
 	struct bond_rx_queue *bd_rx_q = (struct bond_rx_queue *)queue;
-
 	internals = bd_rx_q->dev_private;
+	slave_count = internals->active_slave_count;
+	active_slave = internals->active_slave;
 
+	for (i = 0; i < slave_count && nb_pkts; i++) {
+		uint16_t num_rx_slave;
 
-	for (i = 0; i < internals->active_slave_count && nb_pkts; i++) {
 		/* Offset of pointer to *bufs increases as packets are received
 		 * from other slaves */
-		num_rx_slave = rte_eth_rx_burst(internals->active_slaves[i],
+		num_rx_slave = rte_eth_rx_burst(
+				internals->active_slaves[active_slave],
 				bd_rx_q->queue_id, bufs + num_rx_total, nb_pkts);
-		if (num_rx_slave) {
-			num_rx_total += num_rx_slave;
-			nb_pkts -= num_rx_slave;
-		}
+		num_rx_total += num_rx_slave;
+		nb_pkts -= num_rx_slave;
+		if (++active_slave == slave_count)
+			active_slave = 0;
 	}
 
+	if (++internals->active_slave == slave_count)
+		internals->active_slave = 0;
 	return num_rx_total;
 }
 
@@ -258,25 +263,32 @@ bond_ethdev_rx_burst_8023ad_fast_queue(void *queue, struct rte_mbuf **bufs,
 	uint16_t num_rx_total = 0;	/* Total number of received packets */
 	uint16_t slaves[RTE_MAX_ETHPORTS];
 	uint16_t slave_count;
-
-	uint16_t i, idx;
+	uint16_t active_slave;
+	uint16_t i;
 
 	/* Copy slave list to protect against slave up/down changes during tx
 	 * bursting */
 	slave_count = internals->active_slave_count;
+	active_slave = internals->active_slave;
 	memcpy(slaves, internals->active_slaves,
 			sizeof(internals->active_slaves[0]) * slave_count);
 
-	for (i = 0, idx = internals->active_slave;
-			i < slave_count && num_rx_total < nb_pkts; i++, idx++) {
-		idx = idx % slave_count;
+	for (i = 0; i < slave_count && nb_pkts; i++) {
+		uint16_t num_rx_slave;
 
 		/* Read packets from this slave */
-		num_rx_total += rte_eth_rx_burst(slaves[idx], bd_rx_q->queue_id,
-				&bufs[num_rx_total], nb_pkts - num_rx_total);
+		num_rx_slave = rte_eth_rx_burst(slaves[active_slave],
+						bd_rx_q->queue_id,
+						bufs + num_rx_total, nb_pkts);
+		num_rx_total += num_rx_slave;
+		nb_pkts -= num_rx_slave;
+
+		if (++active_slave == slave_count)
+			active_slave = 0;
 	}
 
-	internals->active_slave = idx;
+	if (++internals->active_slave == slave_count)
+		internals->active_slave = 0;
 
 	return num_rx_total;
 }
@@ -459,7 +471,9 @@ bond_ethdev_rx_burst_8023ad(void *queue, struct rte_mbuf **bufs,
 			idx = 0;
 	}
 
-	internals->active_slave = idx;
+	if (++internals->active_slave == slave_count)
+		internals->active_slave = 0;
+
 	return num_rx_total;
 }
 
-- 
2.14.4



More information about the dev mailing list