[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZbtLgcBcd5B2ZkPC@nanopsycho>
Date: Thu, 1 Feb 2024 08:42:57 +0100
From: Jiri Pirko <jiri@...nulli.us>
To: Yinjun Zhang <yinjun.zhang@...igine.com>
Cc: Louis Peens <louis.peens@...igine.com>,
David Miller <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>, Paolo Abeni <pabeni@...hat.com>,
Fei Qin <fei.qin@...hogine.com>,
"netdev@...r.kernel.org" <netdev@...r.kernel.org>,
oss-drivers <oss-drivers@...igine.com>
Subject: Re: [PATCH net-next 2/2] nfp: customize the dim profiles
Thu, Feb 01, 2024 at 03:16:50AM CET, yinjun.zhang@...igine.com wrote:
>On Wednesday, January 31, 2024 5:39 PM, Jiri Pirko wrote:
><...>
>> It looks incorrect to hardcode it like this. There is a reason this is
>> abstracted out in lib/dim/net_dim.c to avoid exactly this. Can't you
>> perhaps introduce your modified profile there and keep using
>> net_dim_get_[tr]x_moderation() helpers?
>>
>
>We don't know if this introduced profile is adaptable to other NICs/vendors,
>it's generated based on NFP's performance. Do you really think it's
>appropriate to move it to the net_dim.c as a new common profile like:
>enum dim_cq_period_mode {
> DIM_CQ_PERIOD_MODE_START_FROM_EQE = 0x0,
> DIM_CQ_PERIOD_MODE_START_FROM_CQE = 0x1,
>+ DIM_CQ_PERIOD_MODE_SPECIFIC_0 = 0x2,
Maybe. Can't think of anything better atm. Maybe others would have some
ideas.
> DIM_CQ_PERIOD_NUM_MODES
> };
>
>
Powered by blists - more mailing lists