diff options
| author |   William Tu <witu@nvidia.com> | 2025-02-09 12:17:09 +0200 |
|---|---|---|
| committer |   Jakub Kicinski <kuba@kernel.org> | 2025-02-12 10:46:17 -0800 |
| commit | a38cc5706fb9f7dc4ee3a443f61de13ce1e410ed (patch) | |
| tree | 15012f56f45a13950d29d2fcaf46ecf84b5ac2f7 /net/ipv4/tcp_fastopen.c | |
| parent | net/mlx5e: reduce rep rxq depth to 256 for ECPF (diff) | |
| download | wireguard-linux-a38cc5706fb9f7dc4ee3a443f61de13ce1e410ed.tar.xz wireguard-linux-a38cc5706fb9f7dc4ee3a443f61de13ce1e410ed.zip | |
net/mlx5e: set the tx_queue_len for pfifo_fast
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>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250209101716.112774-9-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net/ipv4/tcp_fastopen.c')
0 files changed, 0 insertions, 0 deletions