[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20200515124059.33c43d03@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com>
Date: Fri, 15 May 2020 12:40:59 -0700
From: Jakub Kicinski <kuba@...nel.org>
To: Ioana Ciornei <ioana.ciornei@....com>
Cc: "davem@...emloft.net" <davem@...emloft.net>,
"netdev@...r.kernel.org" <netdev@...r.kernel.org>
Subject: Re: [PATCH v2 net-next 0/7] dpaa2-eth: add support for Rx traffic
classes
On Fri, 15 May 2020 19:31:18 +0000 Ioana Ciornei wrote:
> > Subject: Re: [PATCH v2 net-next 0/7] dpaa2-eth: add support for Rx traffic
> > classes
> >
> > On Fri, 15 May 2020 21:47:46 +0300 Ioana Ciornei wrote:
> > > This patch set adds support for Rx traffic classes on DPAA2 Ethernet
> > > devices.
> > >
> > > The first two patches make the necessary changes so that multiple
> > > traffic classes are configured and their statistics are displayed in
> > > the debugfs. The third patch adds a static distribution to said
> > > traffic classes based on the VLAN PCP field.
> > >
> > > The last patches add support for the congestion group taildrop
> > > mechanism that allows us to control the number of frames that can
> > > accumulate on a group of Rx frame queues belonging to the same traffic class.
> >
> > Ah, I miseed you already sent a v2. Same question applies:
> >
> > > How is this configured from the user perspective? I looked through the
> > > patches and I see no information on how the input is taken from the
> > > user.
>
> There is no input taken from the user at the moment. The traffic
> class id is statically selected based on the VLAN PCP field. The
> configuration for this is added in patch 3/7.
Having some defaults for RX queue per TC is understandable. But patch 1
changes how many RX queues are used in the first place. Why if user
does not need RX queues per TC?
Powered by blists - more mailing lists