[PATCH net-next 11/13] net/mlx5e: Prefetch next RX CQE
From: Saeed Mahameed <hidden>
Date: 2016-03-11 13:41:48
Subsystem:
mellanox ethernet driver (mlx5e), mellanox mlx5 core vpi driver, networking drivers, the rest · Maintainers:
Saeed Mahameed, Tariq Toukan, Mark Bloch, Leon Romanovsky, Andrew Lunn, "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Linus Torvalds
From: Tariq Toukan <redacted> Performance optimization that prefetches the next RX CQE while handling the current one. Performance tested on ConnectX4-Lx 50G. * Netperf single TCP stream: - bw raise of 3-10% for various representative messages sizes. Signed-off-by: Tariq Toukan <redacted> Signed-off-by: Saeed Mahameed <redacted> --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 6 +++++- 1 files changed, 5 insertions(+), 1 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index aa7f90c..b53e9bd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c@@ -664,15 +664,19 @@ mpwrq_cqe_out: int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) { struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq); + struct mlx5_cqe64 *next_cqe = mlx5e_get_cqe(cq); + struct mlx5_cqe64 *cqe; int work_done; for (work_done = 0; work_done < budget; work_done++) { - struct mlx5_cqe64 *cqe = mlx5e_get_cqe(cq); + cqe = next_cqe; if (!cqe) break; mlx5_cqwq_pop(&cq->wq); + next_cqe = mlx5e_get_cqe(cq); + prefetch(next_cqe); rq->handle_rx_cqe(rq, cqe); }
--
1.7.1