All of lore.kernel.org
 help / color / mirror / Atom feed
From: Amir Vadai <amirv@mellanox.com>
To: John Fastabend <john.r.fastabend@intel.com>
Cc: "David S. Miller" <davem@davemloft.net>, <netdev@vger.kernel.org>,
	Roland Dreier <roland@purestorage.com>,
	Oren Duer <oren@mellanox.com>, Amir Vadai <amirv@mellanox.co.il>
Subject: Re: [PATCH 4/8] net/mlx4_en: Set max rate-limit for a TC
Date: Wed, 14 Mar 2012 12:31:15 +0200	[thread overview]
Message-ID: <4F607373.7090001@mellanox.com> (raw)
In-Reply-To: <4F5F915E.4020505@intel.com>

On 03/13/2012 08:26 PM, John Fastabend wrote:
> On 3/13/2012 10:21 AM, Amir Vadai wrote:
>> From: Amir Vadai<amirv@mellanox.co.il>
>>
>> Set max rate-limit using sysfs file /sys/class/net/<interface>/qos/ratelimit
>>
>> To set, enter a space separated list of values in units of 100Mbps.  For
>> example to set ratelimit of 5G to TC0 and 10G for the reset on eth2 issue:
>> echo 50 100 100 100 100 100 100 100 100>  /sys/class/net/eth2/qos/ratelimit
>>
>> Signed-off-by: Amir Vadai<amirv@mellanox.co.il>
>> ---
>>
>> We used sysfs since max bw isn't part of the ETS / DCBX NL support, and we're
>> open to other suggestions to add generic support for max bw, e.g add call to
>> the DCBX NL API.
>>
>
> Its not really part of DCB so adding it to DCBnl seems a bit forced. But how
> about adding it as an attribute of the mqprio which "knows" about the queue
> groupings?
See my answer below
>
> Does the rate limiter take into account the user priority to tc mapping or
> is it really just a group of queues with a rate limit? The code makes it
> look like it really is per 802.1Q traffic class.
This is true, the rate limiter is per 802.1Q traffic class, and the HW 
is using the UP to TC mapping when enforcing it.
That's why it can't be added to mqprio, which is a group of queues and 
not 802.1Q traffic class.
>
> .John

Thanks,
Amir

  reply	other threads:[~2012-03-14 10:31 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-03-13 17:21 [PATCH 0/8] net/mlx4_en: DCB QoS support Amir Vadai
2012-03-13 17:21 ` [PATCH 1/8] net/mlx4_en: Force user priority by QP attribute Amir Vadai
2012-03-13 17:21 ` [PATCH 2/8] net/mlx4_core: set port QoS attributes Amir Vadai
2012-03-13 17:21 ` [PATCH 3/8] net/mlx4_en: DCB QoS support Amir Vadai
2012-03-13 17:21 ` [PATCH 4/8] net/mlx4_en: Set max rate-limit for a TC Amir Vadai
2012-03-13 18:26   ` John Fastabend
2012-03-14 10:31     ` Amir Vadai [this message]
2012-03-13 19:16   ` Dave Taht
2012-03-14 10:42     ` Amir Vadai
2012-03-13 17:22 ` [PATCH 5/8] net/mlx4_en: sk_prio <=> UP for untagged traffic Amir Vadai
2012-03-13 17:22 ` [PATCH 6/8] IB/rdma_cm: TOS <=> UP mapping for IBoE Amir Vadai
2012-03-13 17:22 ` [PATCH 7/8] net: support tx_ring per UP in HW based QoS mechanism Amir Vadai
2012-03-13 18:23   ` John Fastabend
2012-03-14 10:09     ` Amir Vadai
2012-03-14 21:36       ` John Fastabend
2012-03-15 10:05         ` Amir Vadai
2012-03-16  7:16           ` John Fastabend
2012-03-13 17:22 ` [PATCH 8/8] net/mlx4_en: num cores tx rings for every UP Amir Vadai
2012-03-20 11:29 ` [PATCH 0/8] net/mlx4_en: DCB QoS support Amir Vadai
2012-03-20 19:58   ` David Miller

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=4F607373.7090001@mellanox.com \
    --to=amirv@mellanox.com \
    --cc=amirv@mellanox.co.il \
    --cc=davem@davemloft.net \
    --cc=john.r.fastabend@intel.com \
    --cc=netdev@vger.kernel.org \
    --cc=oren@mellanox.com \
    --cc=roland@purestorage.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.