netdev - [PATCH net 1/1] net/mlx5e: Set EQE based as default TX interrupt moderation mode

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20180330225008.21042-1-saeedm@mellanox.com>
Date:   Fri, 30 Mar 2018 15:50:08 -0700
From:   Saeed Mahameed <saeedm@...lanox.com>
To:     "David S. Miller" <davem@...emloft.net>
Cc:     netdev@...r.kernel.org, Tal Gilboa <talgi@...lanox.com>,
        Saeed Mahameed <saeedm@...lanox.com>
Subject: [PATCH net 1/1] net/mlx5e: Set EQE based as default TX interrupt moderation mode

From: Tal Gilboa <talgi@...lanox.com>

The default TX moderation mode was mistakenly set to CQE based. The
intention was to add a control ability in order to improve some specific
use-cases. In general, we prefer to use EQE based moderation as it gives
much better numbers for the common cases.

CQE based causes a degradation in the common case since it resets the
moderation timer on CQE generation. This causes an issue when TSO is
well utilized (large TSO sessions). The timer is set to 16us so traffic
of ~64KB TSO sessions per second would mean timer reset (CQE per TSO
session -> long time between CQEs). In this case we quickly reach the
tcp_limit_output_bytes (256KB by default) and cause a halt in TX traffic.

By setting EQE based moderation we make sure timer would expire after
16us regardless of the packet rate.
This fixes an up to 40% packet rate and up to 23% bandwidth degradtions.

Fixes: 0088cbbc4b66 ("net/mlx5e: Enable CQE based moderation on TX CQ")
Signed-off-by: Tal Gilboa <talgi@...lanox.com>
Signed-off-by: Saeed Mahameed <saeedm@...lanox.com>
---

Hi Dave,

Sorry for the late net submission but this patch is very important since
it addresses a very serious TX performance degradation.

For -stable 4.15.

 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 9b4827d36e3e..1560ec0e1779 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3980,7 +3980,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 			    struct mlx5e_params *params,
 			    u16 max_channels)
 {
-	u8 cq_period_mode = 0;
+	u8 rx_cq_period_mode;
 	u32 link_speed = 0;
 	u32 pci_bw = 0;

@@ -4016,12 +4016,12 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 	params->lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);

 	/* CQ moderation params */
-	cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
+	rx_cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
 			MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
 			MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
-	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
-	mlx5e_set_tx_cq_mode_params(params, cq_period_mode);
+	mlx5e_set_rx_cq_mode_params(params, rx_cq_period_mode);
+	mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);

 	/* TX inline */
 	params->tx_max_inline = mlx5e_get_max_inline_cap(mdev);
-- 
2.14.3