From: Tariq Toukan <tariqt@nvidia.com>
To: "David S. Miller" <davem@davemloft.net>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
Eric Dumazet <edumazet@google.com>,
"Andrew Lunn" <andrew+netdev@lunn.ch>
Cc: <netdev@vger.kernel.org>, Saeed Mahameed <saeedm@nvidia.com>,
Gal Pressman <gal@nvidia.com>,
Leon Romanovsky <leonro@nvidia.com>,
Simon Horman <horms@kernel.org>,
Donald Hunter <donald.hunter@gmail.com>,
Jiri Pirko <jiri@resnulli.us>, Jonathan Corbet <corbet@lwn.net>,
Leon Romanovsky <leon@kernel.org>,
Tariq Toukan <tariqt@nvidia.com>,
Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
"Jesper Dangaard Brouer" <hawk@kernel.org>,
John Fastabend <john.fastabend@gmail.com>,
"Richard Cochran" <richardcochran@gmail.com>,
<linux-kernel@vger.kernel.org>, <linux-doc@vger.kernel.org>,
<linux-rdma@vger.kernel.org>, <bpf@vger.kernel.org>,
William Tu <witu@nvidia.com>, Daniel Jurgens <danielj@nvidia.com>
Subject: [PATCH net-next 08/15] net/mlx5e: set the tx_queue_len for pfifo_fast
Date: Sun, 9 Feb 2025 12:17:09 +0200 [thread overview]
Message-ID: <20250209101716.112774-9-tariqt@nvidia.com> (raw)
In-Reply-To: <20250209101716.112774-1-tariqt@nvidia.com>
From: William Tu <witu@nvidia.com>
By default, the mq netdev creates a pfifo_fast qdisc. On a
system with 16 core, the pfifo_fast with 3 bands consumes
16 * 3 * 8 (size of pointer) * 1024 (default tx queue len)
= 393KB. The patch sets the tx qlen to representor default
value, 128 (1<<MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE), which
consumes 16 * 3 * 8 * 128 = 49KB, saving 344KB for each
representor at ECPF.
Signed-off-by: William Tu <witu@nvidia.com>
Reviewed-by: Daniel Jurgens <danielj@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index da399adc8854..07f38f472a27 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -889,6 +889,8 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev,
netdev->ethtool_ops = &mlx5e_rep_ethtool_ops;
netdev->watchdog_timeo = 15 * HZ;
+ if (mlx5_core_is_ecpf(mdev))
+ netdev->tx_queue_len = 1 << MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE;
#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
netdev->hw_features |= NETIF_F_HW_TC;
--
2.45.0
next prev parent reply other threads:[~2025-02-09 10:19 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-09 10:17 [PATCH net-next 00/15] Rate management on traffic classes + misc Tariq Toukan
2025-02-09 10:17 ` [PATCH net-next 01/15] devlink: Extend devlink rate API with traffic classes bandwidth management Tariq Toukan
2025-02-09 10:17 ` [PATCH net-next 02/15] net/mlx5: Add no-op implementation for setting tc-bw on rate objects Tariq Toukan
2025-02-09 10:17 ` [PATCH net-next 03/15] net/mlx5: Add support for setting tc-bw on nodes Tariq Toukan
2025-02-09 10:17 ` [PATCH net-next 04/15] net/mlx5: Add traffic class scheduling support for vport QoS Tariq Toukan
2025-02-09 10:17 ` [PATCH net-next 05/15] net/mlx5: Manage TC arbiter nodes and implement full support for tc-bw Tariq Toukan
2025-02-09 10:17 ` [PATCH net-next 06/15] net/mlx5e: reduce the max log mpwrq sz for ECPF and reps Tariq Toukan
2025-02-10 9:47 ` Michal Swiatkowski
2025-02-09 10:17 ` [PATCH net-next 07/15] net/mlx5e: reduce rep rxq depth to 256 for ECPF Tariq Toukan
2025-02-10 9:49 ` Michal Swiatkowski
2025-02-09 10:17 ` Tariq Toukan [this message]
2025-02-10 9:51 ` [PATCH net-next 08/15] net/mlx5e: set the tx_queue_len for pfifo_fast Michal Swiatkowski
2025-02-09 10:17 ` [PATCH net-next 09/15] net/mlx5: Rename and move mlx5_esw_query_vport_vhca_id Tariq Toukan
2025-02-09 10:17 ` [PATCH net-next 10/15] net/mlx5: Expose ICM consumption per function Tariq Toukan
2025-02-09 10:17 ` [PATCH net-next 11/15] net/mlx5e: Move RQs diagnose to a dedicated function Tariq Toukan
2025-02-09 10:17 ` [PATCH net-next 12/15] net/mlx5e: Add direct TIRs to devlink rx reporter diagnose Tariq Toukan
2025-02-09 10:17 ` [PATCH net-next 13/15] net/mlx5e: Expose RSS via " Tariq Toukan
2025-02-09 10:17 ` [PATCH net-next 14/15] net/mlx5: Extend Ethtool loopback selftest to support non-linear SKB Tariq Toukan
2025-02-09 10:17 ` [PATCH net-next 15/15] net/mlx5: XDP, Enable TX side XDP multi-buffer support Tariq Toukan
2025-02-12 19:20 ` [PATCH net-next 00/15] Rate management on traffic classes + misc patchwork-bot+netdevbpf
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250209101716.112774-9-tariqt@nvidia.com \
--to=tariqt@nvidia.com \
--cc=andrew+netdev@lunn.ch \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=corbet@lwn.net \
--cc=daniel@iogearbox.net \
--cc=danielj@nvidia.com \
--cc=davem@davemloft.net \
--cc=donald.hunter@gmail.com \
--cc=edumazet@google.com \
--cc=gal@nvidia.com \
--cc=hawk@kernel.org \
--cc=horms@kernel.org \
--cc=jiri@resnulli.us \
--cc=john.fastabend@gmail.com \
--cc=kuba@kernel.org \
--cc=leon@kernel.org \
--cc=leonro@nvidia.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=richardcochran@gmail.com \
--cc=saeedm@nvidia.com \
--cc=witu@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox