All of lore.kernel.org
 help / color / mirror / Atom feed
From: Changli Gao <xiaosuo@gmail.com>
To: Tom Herbert <therbert@google.com>
Cc: davem@davemloft.net, netdev@vger.kernel.org
Subject: Re: [PATCH] rfs: Receive Flow Steering
Date: Fri, 2 Apr 2010 13:04:58 +0800	[thread overview]
Message-ID: <j2u412e6f7f1004012204r76dd8ccbg2e6e78d46541b85@mail.gmail.com> (raw)
In-Reply-To: <alpine.DEB.1.00.1004012045560.4252@pokey.mtv.corp.google.com>

On Fri, Apr 2, 2010 at 11:59 AM, Tom Herbert <therbert@google.com> wrote:
> @@ -714,6 +716,8 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
>  {
>        struct sock *sk = sock->sk;
>
> +       inet_rps_record_flow(sk);
> +
>        /* We may need to bind the socket. */
>        if (!inet_sk(sk)->inet_num && inet_autobind(sk))
>                return -EAGAIN;
> @@ -722,12 +726,13 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
>  }
>  EXPORT_SYMBOL(inet_sendmsg);
>
> -
>  static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
>                             size_t size, int flags)
>  {
>        struct sock *sk = sock->sk;
>
> +       inet_rps_record_flow(sk);
> +
>        /* We may need to bind the socket. */
>        if (!inet_sk(sk)->inet_num && inet_autobind(sk))
>                return -EAGAIN;
> @@ -737,6 +742,22 @@ static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
>        return sock_no_sendpage(sock, page, offset, size, flags);
>  }
>

for sending packets, how about letting sender compute the rxhash of
the packets from the other side if the rxhash of socket hasn't been
set yet. I is better for client applications.

For router and bridge, the current RPS can work well, but not for
server or client applications. So I propose a new socket option to get
the rps cpu of the packets received on a socket. It may be like this:

int cpu;
getsockopt(sock, SOL_SOCKET, SO_RPSCPU, &cpu, sizeof(cpu));

As Tom's patch did, rxhash is recorded in socket. When the call above
is made, rps_map is looked up to find the RPSCPU for that hash. Once
we get the cpu of the current connection, for a TCP server, it can
dispatch the new connection to the processes which run on that CPU.
the server code will be like this:

fd = accpet(fd, NULL, NULL);
getsockopt(fd, SOL_SOCKET, SO_RPSCPU, &cpu, sizeof(cpu));
asyncq_enqueue(work_queue[cpu], fd);

For a client program, the rxhash can be got after the first packet of
the connection is sent. So the client code will be:

fd = connect(fd, &addr, addr_len);
getsockopt(fd, SOL_SOCKET, SO_RPSCPU, &cpu, sizeof(cpu));
asyncq_enqueue(work_queue[cpu], fd);

I do think this idea is easier to understood. I'll cook a patch later
if it is welcomed.

-- 
Regards,
Changli Gao(xiaosuo@gmail.com)

  reply	other threads:[~2010-04-02  5:05 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-04-02  3:59 [PATCH] rfs: Receive Flow Steering Tom Herbert
2010-04-02  5:04 ` Changli Gao [this message]
2010-04-02  7:29   ` Eric Dumazet
2010-04-02 10:58     ` Changli Gao
2010-04-02 12:01       ` Eric Dumazet
2010-04-02 13:45         ` Changli Gao
2010-04-02 17:01     ` Rick Jones
     [not found]       ` <g2i65634d661004021045uff7c0e25ge7dfd17929bc9ee9@mail.gmail.com>
2010-04-02 18:25         ` Rick Jones
2010-04-08  1:37           ` Changli Gao
2010-04-02  7:58 ` Eric Dumazet
2010-04-02  8:35 ` Eric Dumazet
2010-04-02 12:37   ` Eric Dumazet
2010-04-02 16:28     ` Eric Dumazet
2010-04-02 19:43       ` 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=j2u412e6f7f1004012204r76dd8ccbg2e6e78d46541b85@mail.gmail.com \
    --to=xiaosuo@gmail.com \
    --cc=davem@davemloft.net \
    --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 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.