[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20250505232151.2698893-64-sashal@kernel.org>
Date: Mon, 5 May 2025 19:21:36 -0400
From: Sasha Levin <sashal@...nel.org>
To: linux-kernel@...r.kernel.org,
stable@...r.kernel.org
Cc: William Tu <witu@...dia.com>,
Bodong Wang <bodong@...dia.com>,
Saeed Mahameed <saeedm@...dia.com>,
Tariq Toukan <tariqt@...dia.com>,
Michal Swiatkowski <michal.swiatkowski@...ux.intel.com>,
Jakub Kicinski <kuba@...nel.org>,
Sasha Levin <sashal@...nel.org>,
andrew+netdev@...n.ch,
davem@...emloft.net,
edumazet@...gle.com,
pabeni@...hat.com,
netdev@...r.kernel.org,
linux-rdma@...r.kernel.org
Subject: [PATCH AUTOSEL 5.4 64/79] net/mlx5e: reduce rep rxq depth to 256 for ECPF
From: William Tu <witu@...dia.com>
[ Upstream commit b9cc8f9d700867aaa77aedddfea85e53d5e5d584 ]
By experiments, a single queue representor netdev consumes kernel
memory around 2.8MB, and 1.8MB out of the 2.8MB is due to page
pool for the RXQ. Scaling to a thousand representors consumes 2.8GB,
which becomes a memory pressure issue for embedded devices such as
BlueField-2 16GB / BlueField-3 32GB memory.
Since representor netdevs mostly handles miss traffic, and ideally,
most of the traffic will be offloaded, reduce the default non-uplink
rep netdev's RXQ default depth from 1024 to 256 if mdev is ecpf eswitch
manager. This saves around 1MB of memory per regular RQ,
(1024 - 256) * 2KB, allocated from page pool.
With rxq depth of 256, the netlink page pool tool reports
$./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
--dump page-pool-get
{'id': 277,
'ifindex': 9,
'inflight': 128,
'inflight-mem': 786432,
'napi-id': 775}]
This is due to mtu 1500 + headroom consumes half pages, so 256 rxq
entries consumes around 128 pages (thus create a page pool with
size 128), shown above at inflight.
Note that each netdev has multiple types of RQs, including
Regular RQ, XSK, PTP, Drop, Trap RQ. Since non-uplink representor
only supports regular rq, this patch only changes the regular RQ's
default depth.
Signed-off-by: William Tu <witu@...dia.com>
Reviewed-by: Bodong Wang <bodong@...dia.com>
Reviewed-by: Saeed Mahameed <saeedm@...dia.com>
Signed-off-by: Tariq Toukan <tariqt@...dia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@...ux.intel.com>
Link: https://patch.msgid.link/20250209101716.112774-8-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@...nel.org>
Signed-off-by: Sasha Levin <sashal@...nel.org>
---
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 26a9d38d1e2a7..479304afdada2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -53,6 +53,7 @@
#define MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE \
max(0x7, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)
#define MLX5E_REP_PARAMS_DEF_NUM_CHANNELS 1
+#define MLX5E_REP_PARAMS_DEF_LOG_RQ_SIZE 0x8
static const char mlx5e_rep_driver_name[] = "mlx5e_rep";
@@ -1430,6 +1431,8 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
/* RQ */
mlx5e_build_rq_params(mdev, params);
+ if (!mlx5e_is_uplink_rep(priv) && mlx5_core_is_ecpf(mdev))
+ params->log_rq_mtu_frames = MLX5E_REP_PARAMS_DEF_LOG_RQ_SIZE;
/* CQ moderation params */
params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
--
2.39.5
Powered by blists - more mailing lists