ixgbe: speed up non-vector Tx

The freeing of mbuf's in ixgbe is one of the observable hot spots
under load. Optimize it by doing bulk free of mbufs using code similar
to i40e and fm10k.

Drop the no longer needed micro-optimization for the no refcount flag.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

diff --git a/drivers/net/ixgbe/ixgbe_rxtx.c b/drivers/net/ixgbe/ixgbe_rxtx.c
index 73e7ecca5ef489ace439cf6e62263f647ab74781..ffb40701ef2b2cb2d04d26ccf82b6749fc15a9d1 100644 (file)
--- a/drivers/net/ixgbe/ixgbe_rxtx.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx.c
@@ -127,7 +127,8 @@ ixgbe_tx_free_bufs(struct ixgbe_tx_queue *txq)
 {
        struct ixgbe_tx_entry *txep;
        uint32_t status;
-       int i;
+       int i, nb_free = 0;
+       struct rte_mbuf *m, *free[RTE_IXGBE_TX_MAX_FREE_BUF_SZ];
 
        /* check DD bit on threshold descriptor */
        status = txq->tx_ring[txq->tx_next_dd].wb.status;
@@ -140,20 +141,27 @@ ixgbe_tx_free_bufs(struct ixgbe_tx_queue *txq)
         */
        txep = &(txq->sw_ring[txq->tx_next_dd - (txq->tx_rs_thresh - 1)]);
 
-       /* free buffers one at a time */
-       if ((txq->txq_flags & (uint32_t)ETH_TXQ_FLAGS_NOREFCOUNT) != 0) {
-               for (i = 0; i < txq->tx_rs_thresh; ++i, ++txep) {
-                       txep->mbuf->next = NULL;
-                       rte_mempool_put(txep->mbuf->pool, txep->mbuf);
-                       txep->mbuf = NULL;
-               }
-       } else {
-               for (i = 0; i < txq->tx_rs_thresh; ++i, ++txep) {
-                       rte_pktmbuf_free_seg(txep->mbuf);
-                       txep->mbuf = NULL;
+       for (i = 0; i < txq->tx_rs_thresh; ++i, ++txep) {
+               /* free buffers one at a time */
+               m = __rte_pktmbuf_prefree_seg(txep->mbuf);
+               txep->mbuf = NULL;
+
+               if (unlikely(m == NULL))
+                       continue;
+
+               if (nb_free >= RTE_IXGBE_TX_MAX_FREE_BUF_SZ ||
+                   (nb_free > 0 && m->pool != free[0]->pool)) {
+                       rte_mempool_put_bulk(free[0]->pool,
+                                            (void **)free, nb_free);
+                       nb_free = 0;
                }
+
+               free[nb_free++] = m;
        }
 
+       if (nb_free > 0)
+               rte_mempool_put_bulk(free[0]->pool, (void **)free, nb_free);
+
        /* buffers were freed, update counters */
        txq->nb_tx_free = (uint16_t)(txq->nb_tx_free + txq->tx_rs_thresh);
        txq->tx_next_dd = (uint16_t)(txq->tx_next_dd + txq->tx_rs_thresh);

diff --git a/drivers/net/ixgbe/ixgbe_rxtx.h b/drivers/net/ixgbe/ixgbe_rxtx.h
index f34e591f646bf7b44d48f20ac81b7037cb0f6d81..f9e708f8ce71818a95b0591968ee8ce7c9c0fe4f 100644 (file)
--- a/drivers/net/ixgbe/ixgbe_rxtx.h
+++ b/drivers/net/ixgbe/ixgbe_rxtx.h
@@ -58,13 +58,13 @@
 
 #define RTE_PMD_IXGBE_TX_MAX_BURST 32
 #define RTE_PMD_IXGBE_RX_MAX_BURST 32
+#define RTE_IXGBE_TX_MAX_FREE_BUF_SZ 64
 
 #define RTE_IXGBE_DESCS_PER_LOOP    4
 
 #ifdef RTE_IXGBE_INC_VECTOR
 #define RTE_IXGBE_RXQ_REARM_THRESH      32
 #define RTE_IXGBE_MAX_RX_BURST          RTE_IXGBE_RXQ_REARM_THRESH
-#define RTE_IXGBE_TX_MAX_FREE_BUF_SZ    64
 #endif
 
 #define RX_RING_SZ ((IXGBE_MAX_RING_DESC + RTE_IXGBE_DESCS_PER_LOOP - 1) * \