[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <ce194914-f4be-5aee-90f1-7a652c7fa8b0@intel.com>
Date: Wed, 12 Apr 2023 16:16:15 -0700
From: Jacob Keller <jacob.e.keller@...el.com>
To: Hariprasad Kelam <hkelam@...vell.com>, <netdev@...r.kernel.org>,
<linux-kernel@...r.kernel.org>
CC: <kuba@...nel.org>, <davem@...emloft.net>,
<willemdebruijn.kernel@...il.com>, <andrew@...n.ch>,
<sgoutham@...vell.com>, <lcherian@...vell.com>,
<gakula@...vell.com>, <jerinj@...vell.com>, <sbhatta@...vell.com>,
<naveenm@...vell.com>, <edumazet@...gle.com>, <pabeni@...hat.com>,
<jhs@...atatu.com>, <xiyou.wangcong@...il.com>, <jiri@...nulli.us>,
<maxtram95@...il.com>, <corbet@....net>
Subject: Re: [net-next Patch v7 6/6] docs: octeontx2: Add Documentation for
QOS
On 4/10/2023 12:29 AM, Hariprasad Kelam wrote:
> Add QOS example configuration along with tc-htb commands
>
> Signed-off-by: Hariprasad Kelam <hkelam@...vell.com>
> Reviewed-by: Simon Horman <simon.horman@...igine.com>
> ---
> .../ethernet/marvell/octeontx2.rst | 39 +++++++++++++++++++
> 1 file changed, 39 insertions(+)
>
> diff --git a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
> index 5ba9015336e2..eca4309964c8 100644
> --- a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
> +++ b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
> @@ -13,6 +13,7 @@ Contents
> - `Drivers`_
> - `Basic packet flow`_
> - `Devlink health reporters`_
> +- `Quality of service`_
>
> Overview
> ========
> @@ -287,3 +288,41 @@ For example::
> NIX_AF_ERR:
> NIX Error Interrupt Reg : 64
> Rx on unmapped PF_FUNC
> +
> +
> +Quality of service
> +==================
> +
> +octeontx2 silicon and CN10K transmit interface consists of five transmit levels starting from SMQ/MDQ, TL4 to TL1.
> +The hardware uses the below algorithms depending on the priority of scheduler queues
> +
> +1. Strict Priority
> +
> + - Once packets are submitted to MDQ, hardware picks all active MDQs having different priority
> + using strict priority.
> +
> +2. Round Robin
> +
> + - Active MDQs having the same priority level are chosen using round robin.
> +
> +3. Each packet will traverse MDQ, TL4 to TL1 levels. Each level contains an array of queues to support scheduling and
> + shaping.
> +
> +4. once the user creates tc classes with different priority
> +
> + - Driver configures schedulers allocated to the class with specified priority along with rate-limiting configuration.
> +
> +5. Enable HW TC offload on the interface::
> +
> + # ethtool -K <interface> hw-tc-offload on
> +
> +6. Crate htb root::
> +
> + # tc qdisc add dev <interface> clsact
> + # tc qdisc replace dev <interface> root handle 1: htb offload
> +
> +7. Create tc classes with different priorities::
> +
> + # tc class add dev <interface> parent 1: classid 1:1 htb rate 10Gbit prio 1
> +
> + # tc class add dev <interface> parent 1: classid 1:2 htb rate 10Gbit prio 7
This part of the doc is confusing. It starts by reading like a list of
algorithms, then transitions into a list of instructions. I think those
should be separated into two pieces, one with the explanation and one
with some example how to set it up.
Powered by blists - more mailing lists