From: John Fastabend <john.r.fastabend@intel.com>
To: "Yu, Fenghua" <fenghua.yu@intel.com>
Cc: "David S. Miller" <davem@davemloft.net>,
Eric Dumazet <eric.dumazet@gmail.com>,
"Tang, Xinan" <xinan.tang@intel.com>,
Junchang Wang <junchangwang@gmail.com>,
netdev <netdev@vger.kernel.org>,
linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 3/3] drivers/net/ixgbe/ixgbe_main.c: get tx queue mapping specified in socket
Date: Wed, 15 Dec 2010 12:54:17 -0800 [thread overview]
Message-ID: <4D092AF9.9050802@intel.com> (raw)
In-Reply-To: <e37daf1b95d0e61008c69298db5520d6b97acdba.1292405004.git.fenghua.yu@intel.com>
On 12/15/2010 12:02 PM, Yu, Fenghua wrote:
> From: Fenghua Yu <fenghua.yu@intel.com>
>
> Instead of using calculated tx queue mapping, this patch selects tx queue mapping
> which is specified in socket.
>
> By doing this, tx queue mapping can be bigger than the number of cores and
> stressfully use multiqueue TSS. Or application can specify some of cores/queues
> to send packets and implement flexible load balance policies.
>
> Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
> Signed-off-by: Junchang Wang <junchangwang@gmail.com>
> Signed-off-by: Xinan Tang <xinan.tang@intel.com>
> ---
> drivers/net/ixgbe/ixgbe_main.c | 9 ++++++++-
> 1 files changed, 8 insertions(+), 1 deletions(-)
>
> diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
> index eee0b29..4d98928 100644
> --- a/drivers/net/ixgbe/ixgbe_main.c
> +++ b/drivers/net/ixgbe/ixgbe_main.c
> @@ -6255,7 +6255,14 @@ static int ixgbe_maybe_stop_tx(struct net_device *netdev,
> static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb)
> {
> struct ixgbe_adapter *adapter = netdev_priv(dev);
> - int txq = smp_processor_id();
> + int txq;
> +
> + txq = sk_tx_queue_get(skb->sk);
> +
> + if (txq >= 0 && txq < dev->real_num_tx_queues)
> + return txq;
> +
> + txq = smp_processor_id();
> #ifdef IXGBE_FCOE
> __be16 protocol;
>
We are trying to remove stuff from select_queue not add it. I believe however you solve this problem should be generic and not specific to ixgbe.
Thanks,
John.
prev parent reply other threads:[~2010-12-15 20:54 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-12-15 20:02 [PATCH 0/3] Kernel interfaces for multiqueue aware socket Fenghua Yu
2010-12-15 20:02 ` [PATCH 1/3] " Fenghua Yu
2010-12-15 20:48 ` Eric Dumazet
2010-12-15 20:56 ` Eric Dumazet
2010-12-16 1:14 ` Fenghua Yu
2010-12-16 1:23 ` Stephen Hemminger
2010-12-16 1:28 ` Changli Gao
2010-12-16 2:43 ` Dimitris Michailidis
2010-12-17 6:22 ` Junchang Wang
2010-12-17 6:50 ` Eric Dumazet
2010-12-16 4:44 ` Eric Dumazet
2010-12-17 6:12 ` Junchang Wang
2010-12-16 1:52 ` Junchang Wang
2010-12-16 5:00 ` Eric Dumazet
2010-12-17 6:15 ` Junchang Wang
2010-12-15 20:52 ` John Fastabend
2010-12-15 20:02 ` [PATCH 2/3] net/packet/af_packet.c: implement multiqueue aware socket in af_apcket Fenghua Yu
2010-12-15 20:02 ` [PATCH 3/3] drivers/net/ixgbe/ixgbe_main.c: get tx queue mapping specified in socket Fenghua Yu
2010-12-15 20:54 ` John Fastabend [this message]
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=4D092AF9.9050802@intel.com \
--to=john.r.fastabend@intel.com \
--cc=davem@davemloft.net \
--cc=eric.dumazet@gmail.com \
--cc=fenghua.yu@intel.com \
--cc=junchangwang@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=xinan.tang@intel.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).