diff options
author | Tariq Toukan <tariqt@mellanox.com> | 2016-09-15 16:08:36 +0300 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2016-09-17 16:51:40 +0300 |
commit | 7e426671704d2266757dff9c4254b788561aa11e (patch) | |
tree | 0fe0c74ea07692bc6d1c72e8483b1fdaf0fec7a8 /drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | |
parent | d19127473a575c629c70974cee0bb8acb6374f08 (diff) | |
download | linux-7e426671704d2266757dff9c4254b788561aa11e.tar.xz |
net/mlx5e: Single flow order-0 pages for Striding RQ
To improve the memory consumption scheme, we omit the flow that
demands and splits high-order pages in Striding RQ, and stay
with a single Striding RQ flow that uses order-0 pages.
Moving to fragmented memory allows the use of larger MPWQEs,
which reduces the number of UMR posts and filler CQEs.
Moving to a single flow allows several optimizations that improve
performance, especially in production servers where we would
anyway fallback to order-0 allocations:
- inline functions that were called via function pointers.
- improve the UMR post process.
This patch alone is expected to give a slight performance reduction.
However, the new memory scheme gives the possibility to use a page-cache
of a fair size, that doesn't inflate the memory footprint, which will
dramatically fix the reduction and even give a performance gain.
Performance tests:
The following results were measured on a freshly booted system,
giving optimal baseline performance, as high-order pages are yet to
be fragmented and depleted.
We ran pktgen single-stream benchmarks, with iptables-raw-drop:
Single stride, 64 bytes:
* 4,739,057 - baseline
* 4,749,550 - this patch
no reduction
Larger packets, no page cross, 1024 bytes:
* 3,982,361 - baseline
* 3,845,682 - this patch
3.5% reduction
Larger packets, every 3rd packet crosses a page, 1500 bytes:
* 3,731,189 - baseline
* 3,579,414 - this patch
4% reduction
Fixes: 461017cb006a ("net/mlx5e: Support RX multi-packet WQE (Striding RQ)")
Fixes: bc77b240b3c5 ("net/mlx5e: Add fragmented memory support for RX multi packet WQE")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5/core/en_stats.h')
-rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 4 |
1 files changed, 0 insertions, 4 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 499487ce3b53..1f56543feb63 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -73,7 +73,6 @@ struct mlx5e_sw_stats { u64 tx_xmit_more; u64 rx_wqe_err; u64 rx_mpwqe_filler; - u64 rx_mpwqe_frag; u64 rx_buff_alloc_err; u64 rx_cqe_compress_blks; u64 rx_cqe_compress_pkts; @@ -105,7 +104,6 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_frag) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) }, @@ -274,7 +272,6 @@ struct mlx5e_rq_stats { u64 lro_bytes; u64 wqe_err; u64 mpwqe_filler; - u64 mpwqe_frag; u64 buff_alloc_err; u64 cqe_compress_blks; u64 cqe_compress_pkts; @@ -290,7 +287,6 @@ static const struct counter_desc rq_stats_desc[] = { { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler) }, - { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_frag) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) }, |