From f84411be9e307d2723052a8ae8ee80a1fd9f559b Mon Sep 17 00:00:00 2001 From: Yongseok Koh Date: Mon, 12 Mar 2018 10:05:45 -0700 Subject: [PATCH] net/mlx5: remove excessive data prefetch In Enhanced Multi-Packet Send (eMPW), entire packet data is prefetched to LLC if it isn't inlined. Even though this helps reducing jitter when HW fetches data by DMA, this can thresh the LLC with evicting precious data. And if the size of queue is large and there are many queues, this might not be effective. Also, if application runs on a remote node from the PCIe link, it may not be helpful and can even cause bad results. Signed-off-by: Yongseok Koh Acked-by: Adrien Mazarguil --- drivers/net/mlx5/mlx5_rxtx.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx5_rxtx.c index a44530381a..05fe109184 100644 --- a/drivers/net/mlx5/mlx5_rxtx.c +++ b/drivers/net/mlx5/mlx5_rxtx.c @@ -1360,7 +1360,6 @@ txq_burst_empw(struct mlx5_txq_data *txq, struct rte_mbuf **pkts, do { struct rte_mbuf *buf = *(pkts++); uintptr_t addr; - unsigned int n; unsigned int do_inline = 0; /* Whether inline is possible. */ uint32_t length; uint8_t cs_flags; @@ -1480,11 +1479,8 @@ txq_burst_empw(struct mlx5_txq_data *txq, struct rte_mbuf **pkts, ((uintptr_t)mpw.data.raw + inl_pad); (*txq->elts)[elts_head++ & elts_m] = buf; - addr = rte_pktmbuf_mtod(buf, uintptr_t); - for (n = 0; n * RTE_CACHE_LINE_SIZE < length; n++) - rte_prefetch2((void *)(addr + - n * RTE_CACHE_LINE_SIZE)); - addr = rte_cpu_to_be_64(addr); + addr = rte_cpu_to_be_64(rte_pktmbuf_mtod(buf, + uintptr_t)); *dseg = (rte_v128u32_t) { rte_cpu_to_be_32(length), mlx5_tx_mb2mr(txq, buf), -- 2.20.1