turning off TCP_NOPUSH

From: Igor Sysoev (is_at_rambler-co.ru)
Date: 05/28/03

  • Next message: Don Bowman: "RE: Spontan reboot of FreeBSD 4,x box" 
    Date: Wed, 28 May 2003 17:05:59 +0400 (MSD)
To: freebsd-net@freebsd.org

    The 1.53 fix

    http://www.freebsd.org/cgi/cvsweb.cgi/src/sys/netinet/tcp_usrreq.c.diff?r1=1.52&r2=1.53

    always calls tcp_output() when TCP_NOPUSH is turned off. I think
    tcp_output() should be called only if data in the send buffer is less
    than MSS:

            tp->t_flags &= ~TF_NOPUSH;
    - error = tcp_output(tp);
    + if (so->so_snd.sb_cc < tp->t_maxseg) {
    + error = tcp_output(tp);
    + }

    If the pending data is bigger than MSS then it will be sent without
    significant delay.

    Igor Sysoev
    http://sysoev.ru/en/

    _______________________________________________
    freebsd-net@freebsd.org mailing list
    http://lists.freebsd.org/mailman/listinfo/freebsd-net
    To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org"

  • Next message: Don Bowman: "RE: Spontan reboot of FreeBSD 4,x box"

    Relevant Pages

    • turning off TCP_NOPUSH
      ... > tcp_outputshould be called only if data in the send buffer is less ... > than MSS: ... we interpret that as meaning that the application wants to send a PSH ... To unsubscribe, ...
      (freebsd-net)
    • RE: [Full-disclosure] How many vendors knowingly ship GA product with security vulnerabilities?
      ... It would seem that if a few days buffer were built into the system, ... How many vendors knowingly ship GA ... But it can *still* take a while to actually integrate and test the fix, ... Find a 'struct' in that .h, ...
      (Full-Disclosure)
    • [git pull] drm-intel updates for 2.6.32.
      ... Add buffer to inactive list immediately during fault ... Register a shrinker to free inactive lists under memory pressure ... Fix the pre-9xx chipset flush. ... ACPI button: provide lid status functions ...
      (Linux-Kernel)
    • Re: [PATCH] ppc64: Fix g5-only build
      ... the bug than to commit a giant comment pointing out a small bug, ... attached an alternate fix. ... /* Creates TCEs for a user provided buffer. ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: [Bug #14015] pty regressed again, breaking expect and gccs testsuite
      ... good to fix pty_space, not leaving as wrong. ... don't get strange behavior in the near of buffer limit. ... you can see how many characters you were able to write. ...
      (Linux-Kernel)