[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <9a16f24d-90a4-4a3e-3848-0513958631c3@gmail.com>
Date: Wed, 18 May 2022 18:07:11 +0100
From: Edward Cree <ecree.xilinx@...il.com>
To: Xin Long <lucien.xin@...il.com>,
network dev <netdev@...r.kernel.org>
Cc: davem@...emloft.net, kuba@...nel.org
Subject: Re: [PATCHv3 net] Documentation: add description for
net.core.gro_normal_batch
On 18/05/2022 17:09, Xin Long wrote:
> Describe it in admin-guide/sysctl/net.rst like other Network core options.
> Users need to know gro_normal_batch for performance tuning.
>
> Fixes: 323ebb61e32b ("net: use listified RX for handling GRO_NORMAL skbs")
> Reported-by: Prijesh Patel <prpatel@...hat.com>
> Signed-off-by: Xin Long <lucien.xin@...il.com>
Reviewed-by: Edward Cree <ecree.xilinx@...il.com>
> ---
> v1->v2:
> - improve the description according to the suggestion from Edward
> and Jakub.
> v2->v3:
> - improve more for the description, and drop the default for
> gro_normal_batch, suggested by Jakub.
>
> Documentation/admin-guide/sysctl/net.rst | 9 +++++++++
> 1 file changed, 9 insertions(+)
>
> diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst
> index f86b5e1623c6..46b44fa82fa2 100644
> --- a/Documentation/admin-guide/sysctl/net.rst
> +++ b/Documentation/admin-guide/sysctl/net.rst
> @@ -374,6 +374,15 @@ option is set to SOCK_TXREHASH_DEFAULT (i. e. not overridden by setsockopt).
> If set to 1 (default), hash rethink is performed on listening socket.
> If set to 0, hash rethink is not performed.
>
> +gro_normal_batch
> +----------------
> +
> +Maximum number of the segments to batch up on output of GRO. When a packet
> +exits GRO, either as a coalesced superframe or as an original packet which
> +GRO has decided not to coalesce, it is placed on a per-NAPI list. This
> +list is then passed to the stack when the number of segments reaches the
> +gro_normal_batch limit.
> +
> 2. /proc/sys/net/unix - Parameters for Unix domain sockets
> ----------------------------------------------------------
>
>
Powered by blists - more mailing lists