netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: David Miller <davem@davemloft.net>
To: therbert@google.com
Cc: eric.dumazet@gmail.com, netdev@vger.kernel.org,
	bhutchings@solarflare.com
Subject: Re: [PATCH net-next-2.6] sched: use xps information for qdisc NUMA affinity
Date: Tue, 30 Nov 2010 10:48:34 -0800 (PST)	[thread overview]
Message-ID: <20101130.104834.112604433.davem@davemloft.net> (raw)
In-Reply-To: <AANLkTimU+7aY0DZrnBtL=BsP_qGpCsBw0d4TCKOJSzRL@mail.gmail.com>

From: Tom Herbert <therbert@google.com>
Date: Tue, 30 Nov 2010 10:31:48 -0800

> On Mon, Nov 29, 2010 at 10:14 AM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
>> I was thinking of using XPS tx_queue->cpu mapping to eventually allocate
>> memory with correct NUMA affinities, for qdisc/class stuff for example.
>>
> 
> An interesting idea, but the real question is can this be used for all
> queue related allocations.  This includes those that drivers allocate
> which are probably done in initialization.

Most drivers do, and all drivers ought to, allocate DMA queues and
whatnot when the interface is brought up.

That solves this particular issue.

For example, drivers/net/niu.c does this by calling
niu_alloc_channels() via niu_open().

The only thing we really can't handle currently is the netdev
itself (and the associated driver private).  Jesse Brandeburg
has been reminding me about this over and over :-)

There might be some things we can even do about that part.  For
example, we can put all of the things the driver touches in the
RX and TX fast paths via indirect pointers and therefore be able
to allocate and reallocate those portions as we want long after
device registry.

Doing the core netdev struct itself is too hard because it sits
in so many tables.

  parent reply	other threads:[~2010-11-30 18:48 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-11-21 23:17 [PATCH 2/2 v7] xps: Transmit Packet Steering Tom Herbert
2010-11-22 11:42 ` Changli Gao
2010-11-22 13:33 ` Eric Dumazet
2010-11-24 19:45 ` David Miller
2010-11-26 17:13   ` Tom Herbert
2010-11-26 17:17     ` Eric Dumazet
2010-11-28 15:43       ` [PATCH net-next-2.6] xps: NUMA allocations for per cpu data Eric Dumazet
2010-11-29 17:43         ` David Miller
2010-11-25 17:12 ` [PATCH 2/2 v7] xps: Transmit Packet Steering Ben Hutchings
2010-11-29 18:14   ` [PATCH net-next-2.6] sched: use xps information for qdisc NUMA affinity Eric Dumazet
2010-11-30 18:31     ` Tom Herbert
2010-11-30 18:39       ` Eric Dumazet
2010-11-30 18:46         ` Ben Hutchings
2010-11-30 18:52           ` Eric Dumazet
2010-11-30 18:48       ` David Miller [this message]
2010-11-30 19:07         ` Eric Dumazet
2010-11-30 19:19           ` Ben Hutchings
2010-11-30 19:21           ` David Miller
2010-11-30 20:01             ` Brandeburg, Jesse
2010-12-01 20:49     ` David Miller
2010-12-01 20:55       ` Eric Dumazet

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=20101130.104834.112604433.davem@davemloft.net \
    --to=davem@davemloft.net \
    --cc=bhutchings@solarflare.com \
    --cc=eric.dumazet@gmail.com \
    --cc=netdev@vger.kernel.org \
    --cc=therbert@google.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).