[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <d67d91dd-7a6d-474d-8041-5367f3bf8d26@6wind.com>
Date: Mon, 3 Jun 2024 08:51:58 +0200
From: Nicolas Dichtel <nicolas.dichtel@...nd.com>
To: Ido Schimmel <idosch@...dia.com>, Jakub Kicinski <kuba@...nel.org>
Cc: Petr Machata <petrm@...dia.com>, "David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>, Paolo Abeni <pabeni@...hat.com>,
netdev@...r.kernel.org, David Ahern <dsahern@...nel.org>,
Jonathan Corbet <corbet@....net>, linux-doc@...r.kernel.org,
Simon Horman <horms@...nel.org>
Subject: Re: [PATCH net-next 2/4] net: ipv4: Add a sysctl to set multipath
hash seed
Le 02/06/2024 à 13:15, Ido Schimmel a écrit :
> On Thu, May 30, 2024 at 06:00:34PM -0700, Jakub Kicinski wrote:
>> On Wed, 29 May 2024 13:18:42 +0200 Petr Machata wrote:
>>> +fib_multipath_hash_seed - UNSIGNED INTEGER
>>> + The seed value used when calculating hash for multipath routes. Applies
>>
>> nits..
>>
>> For RSS we call it key rather than seed, is calling it seed well
>> established for ECMP?
It seems standard for me (we call it like this in our products).
>
> I have only seen documentation where it is called "seed". Examples:
>
> Cumulus:
> https://docs.nvidia.com/networking-ethernet-software/cumulus-linux-59/Layer-3/Routing/Equal-Cost-Multipath-Load-Sharing/#unique-hash-seed
>
> Arista:
> https://arista.my.site.com/AristaCommunity/s/article/hashing-for-l2-port-channels-and-l3-ecmp
>
> Research from Fastly around load balancing (Section 6.3):
> https://www.usenix.org/system/files/conference/nsdi18/nsdi18-araujo.pdf
>
You can add some others:
https://www.juniper.net/documentation/us/en/software/junos/interfaces-ethernet-switches/topics/topic-map/switches-interface-resilient-hashing.html
https://www.cisco.com/c/en/us/td/docs/switches/datacenter/nexus9000/sw/6-x/unicast/configuration/guide/l3_cli_nxos/l3_manage-routes.html
Powered by blists - more mailing lists