[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <de59c019-8a7d-6747-ddc1-9a21f40d3e04@mojatatu.com>
Date: Sat, 14 Jan 2017 10:03:17 -0500
From: Jamal Hadi Salim <jhs@...atatu.com>
To: Jiri Pirko <jiri@...nulli.us>
Cc: John Fastabend <john.fastabend@...il.com>,
Paul Blakey <paulb@...lanox.com>,
"David S. Miller" <davem@...emloft.net>, netdev@...r.kernel.org,
Jiri Pirko <jiri@...lanox.com>,
Hadar Hen Zion <hadarh@...lanox.com>,
Or Gerlitz <ogerlitz@...lanox.com>,
Roi Dayan <roid@...lanox.com>, Roman Mashak <mrv@...atatu.com>,
Simon Horman <simon.horman@...ronome.com>
Subject: Re: [PATCH net-next] net/sched: cls_flower: Add user specified data
On 17-01-14 09:48 AM, Jiri Pirko wrote:
> Sat, Jan 14, 2017 at 01:56:35PM CET, jhs@...atatu.com wrote:
>> I think the feature makes a lot of sense (as is the action variant).
>> But can we make it:
>> a) fixed size
>
> Can you elaborate on why is this needed?
>
My experience with the action bits its easier to debug
and enforces some discipline to not abuse the amount of RAM used.
If you have 1M rules, one extra 128M is easier on the system than
a few Gigs.
>
>> b) apply to all classifiers
>> c) please post a usage example via iproute2/tc
>>
>> I am going to post the action variant in the next while - will do some more
>> testing first.
>
> I believe we have to make the cls and ats cookies exactly the same.
>
Probably - they are both needed. See the patch I just posted.
cheers,
jamal
Powered by blists - more mailing lists