netdev-dpdk: Remove vhost send retries when no packets have been sent.

If the guest is connected but not servicing the virt queue, this leads
to vhost send retries until timeout. This is fine in isolation but if
there are other high rate queues also being serviced by the same PMD
it can lead to a performance hit on those queues. Change to only retry
when at least some packets have been successfully sent on the previous
attempt.

Also, limit retries to avoid a similar delays if packets are being sent
at a very low rate due to few available descriptors.

Reported-by: Bhanuprakash Bodireddy <bhanuprakash.bodireddy@intel.com>
Signed-off-by: Kevin Traynor <kevin.traynor@intel.com>
Acked-by: Bhanuprakash Bodireddy <bhanuprakash.bodireddy@intel.com>
Acked-by: Ilya Maximets <i.maximets@samsung.com>
Acked-by: Daniele Di Proietto <diproiettod@vmware.com>

diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c
index 19d355f..582569c 100644 (file)
--- a/lib/netdev-dpdk.c
+++ b/lib/netdev-dpdk.c
@@ -141,10 +141,7 @@ static char *cuse_dev_name = NULL;    /* Character device cuse_dev_name. */
 #endif
 static char *vhost_sock_dir = NULL;   /* Location of vhost-user sockets */
 
-/*
- * Maximum amount of time in micro seconds to try and enqueue to vhost.
- */
-#define VHOST_ENQ_RETRY_USECS 100
+#define VHOST_ENQ_RETRY_NUM 8
 
 static const struct rte_eth_conf port_conf = {
     .rxmode = {
@@ -1377,7 +1374,7 @@ __netdev_dpdk_vhost_send(struct netdev *netdev, int qid,
     struct rte_mbuf **cur_pkts = (struct rte_mbuf **) pkts;
     unsigned int total_pkts = cnt;
     unsigned int qos_pkts = cnt;
-    uint64_t start = 0;
+    int retries = 0;
 
     qid = dev->tx_q[qid % dev->real_n_txq].map;
 
@@ -1404,32 +1401,13 @@ __netdev_dpdk_vhost_send(struct netdev *netdev, int qid,
         if (OVS_LIKELY(tx_pkts)) {
             /* Packets have been sent.*/
             cnt -= tx_pkts;
-            /* Prepare for possible next iteration.*/
+            /* Prepare for possible retry.*/
             cur_pkts = &cur_pkts[tx_pkts];
         } else {
-            uint64_t timeout = VHOST_ENQ_RETRY_USECS * rte_get_timer_hz() / 1E6;
-            unsigned int expired = 0;
-
-            if (!start) {
-                start = rte_get_timer_cycles();
-            }
-
-            /*
-             * Unable to enqueue packets to vhost interface.
-             * Check available entries before retrying.
-             */
-            while (!rte_vring_available_entries(virtio_dev, vhost_qid)) {
-                if (OVS_UNLIKELY((rte_get_timer_cycles() - start) > timeout)) {
-                    expired = 1;
-                    break;
-                }
-            }
-            if (expired) {
-                /* break out of main loop. */
-                break;
-            }
+            /* No packets sent - do not retry.*/
+            break;
         }
-    } while (cnt);
+    } while (cnt && (retries++ < VHOST_ENQ_RETRY_NUM));
 
     rte_spinlock_unlock(&dev->tx_q[qid].tx_lock);