netdev - Re: [Intel-wired-lan] [PATCH iwl-next v4 4/5] ice: Add tx_scheduling

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date: Thu, 22 Feb 2024 14:25:21 +0100
From: Mateusz Polchlopek <mateusz.polchlopek@...el.com>
To: Jakub Kicinski <kuba@...nel.org>, Jiri Pirko <jiri@...nulli.us>
CC: <intel-wired-lan@...ts.osuosl.org>, <netdev@...r.kernel.org>,
	<horms@...nel.org>, <przemyslaw.kitszel@...el.com>, Lukasz Czapnik
	<lukasz.czapnik@...el.com>
Subject: Re: [Intel-wired-lan] [PATCH iwl-next v4 4/5] ice: Add
 tx_scheduling_layers devlink param



On 2/22/2024 12:38 AM, Jakub Kicinski wrote:
> On Mon, 19 Feb 2024 13:37:36 +0100 Jiri Pirko wrote:
>>> devlink dev param show pci/0000:4b:00.0 name tx_scheduling_layers
>>> pci/0000:4b:00.0:
>>>   name tx_scheduling_layers type driver-specific
>>>     values:
>>>       cmode permanent value 9
>>>
>>> Set:
>>> devlink dev param set pci/0000:4b:00.0 name tx_scheduling_layers value 5
>>> cmode permanent
> 
> It's been almost a year since v1 was posted, could you iterate quicker? :(
> 

Yes... Sorry for iterating so slowly, I promise to do it quicker in the 
future. That issue was kind of problematic for us, so it took quite a 
long time.

>> This is kind of proprietary param similar to number of which were shot
>> down for mlx5 in past. Jakub?
> 
> I remain somewhat confused about what this does.
> Specifically IIUC the problem is that the radix of each node is
> limited, so we need to start creating multi-layer hierarchies
> if we want a higher radix. Or in the "5-layer mode" the radix
> is automatically higher?

Basically, switching from 9 to 5 layers topology allows us to have 512 
leaves instead of 8 leaves which improves performance. I will add this 
information to the commit message and Documentation too, when we get an 
ACK for devlink parameter.

In the future we plan to extend this feature to support other layer 
counts too.