[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20200305.140345.1414440008084098711.davem@davemloft.net>
Date: Thu, 05 Mar 2020 14:03:45 -0800 (PST)
From: David Miller <davem@...emloft.net>
To: idosch@...sch.org
Cc: netdev@...r.kernel.org, kuba@...nel.org, jiri@...lanox.com,
petrm@...lanox.com, jhs@...atatu.com, xiyou.wangcong@...il.com,
mlxsw@...lanox.com, idosch@...lanox.com
Subject: Re: [PATCH net-next 0/5] mlxsw: Offload FIFO
From: Ido Schimmel <idosch@...sch.org>
Date: Thu, 5 Mar 2020 09:16:39 +0200
> From: Ido Schimmel <idosch@...lanox.com>
>
> Petr says:
>
> If an ETS or PRIO band contains an offloaded qdisc, it is possible to
> obtain offloaded counters for that band. However, some of the bands will
> likely simply contain the default invisible FIFO qdisc, which does not
> present the counters.
>
> To remedy this situation, make FIFO offloadable, and offload it by mlxsw
> when below PRIO and ETS for the sole purpose of providing counters for the
> bands that do not include other qdiscs.
>
> - In patch #1, FIFO is extended to support offloading.
> - Patches #2 and #3 restructure bits of mlxsw to facilitate
> the offload logic.
> - Patch #4 then implements the offload itself.
> - Patch #5 changes the ETS selftest to use the new counters.
Series applied, thanks.
Powered by blists - more mailing lists