From mboxrd@z Thu Jan  1 00:00:00 1970
From: "Andrew Grover" <andy.grover@gmail.com>
Subject: Re: [PATCH 1/9] [I/OAT] DMA memcpy subsystem
Date: Fri, 31 Mar 2006 12:04:13 -0800
Message-ID: <c0a09e5c0603311204k6b64842bm741d3e7726b39e77@mail.gmail.com>
References: <20060329225505.25585.30392.stgit@gitlost.site>
	 <c0a09e5c0603301036s4e9a63e5v476d89ff8ba37760@mail.gmail.com>
	 <351C5BDA-D7E3-4257-B07E-ABDDCF254954@kernel.crashing.org>
	 <200603311026.33391.netdev@axxeo.de>
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7BIT
Cc: "Kumar Gala" <galak@kernel.crashing.org>,
	"Chris Leech" <christopher.leech@intel.com>,
	linux-kernel@vger.kernel.org, netdev@vger.kernel.org
Return-path: <linux-kernel-owner+glk-linux-kernel-3=40m.gmane.org-S932266AbWCaUER@vger.kernel.org>
To: "Ingo Oeser" <netdev@axxeo.de>
In-Reply-To: <200603311026.33391.netdev@axxeo.de>
Content-Disposition: inline
Sender: linux-kernel-owner@vger.kernel.org
List-Id: netdev.vger.kernel.org

On 3/31/06, Ingo Oeser <netdev@axxeo.de> wrote:
> Kumar Gala wrote:
> > Fair, but wouldn't it be better to have the association per client.
> >
> > Maybe leave the one as a summary and have a dir per client with
> > similar stats that are for each client and add a per channel summary
> > at the top level as well.
> Such level of detail really belongs to debugging, IMHO.
[snip]

If we implemented more stats then yes debugfs sounds like it might be
the way to go.

> BTW: What is the actual frequency, at which such counters
> will be incremented?

Currently the code updates these variables (kept per cpu) every time a
copy is queued. See include/linux/dmaengine.h.

-- Andy