lkml.org 
[lkml]   [2006]   [Jun]   [13]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: 2.6.17: networking bug??
    Linus Torvalds wrote:
    >
    > On Tue, 13 Jun 2006, John Heffner wrote:
    >> The best thing you can do is try to find this broken box and inform its owner
    >> that it needs to be fixed. (If you can find out what it is, I'd be interested
    >> to know.) In the meantime, disabling window scaling will work around the
    >> problem for you.
    >
    > Well, arguably, we shouldn't necessarily have defaults that use window
    > scaling, or we should have ways to recognize automatically when it
    > doesn't work (which may not be possible).
    >
    > It's not like there aren't broken boxes out there, and it might be better
    > to make the default buffer sizes just be low enough that window scaling
    > simply isn't an issue.
    >
    > I suspect that the people who really want/need window scaling know about
    > it, and could be assumed to know enough to raise their limits, no?
    >
    > Linus

    Unfortunately, there's really no way to detect this, at least not until
    it's too late. You can't un-negotiate window scale after the connection
    is initiated.

    64k buffers, the largest you can use without window scaling, are
    adequate for most home users on DSL or cable modems (good to about 10
    Mbps across the US, not quite that over trans-oceanic links).
    Unfortunately, that's about a factor of ten too small for that average
    university user, and a factor of 100-1000 too small for high end use.
    Check out the figure at
    <http://people.internet2.edu/~ghb/pmwiki/pmwiki.php/BridgingTheGap/BtGWizGap>,
    which has some data points. (The bottom line is the best "normal" users
    can get with system default buffers, the top line is what high-end users
    have gotten with tuned systems over the wide area. Note that this gap
    is increasing at an exponential rate.)

    In the last couple years, we've added code that can automatically size
    the buffers as appropriate for each connection, but it's completely
    crippled unless you use a window scale. Personally, I think it's not a
    question of *whether* we have to start using a window scale by default,
    but *when*. I don't know that we want to let a small number of
    unambiguously broken middleboxes kill our forward progress.

    Though I haven't gotten my hands on it, I believe Windows will soon have
    this capability, too. I'm sure Windows is big enough that whenever they
    turn this on, it will flush out all these boxes pretty quickly. We
    could wait for them to do it first, that that's not my favored approach.

    BTW, as one data point, I've been personally running with a large window
    scale for about 5 years, and only seen a small handful of problems, most
    of which were corrected fairly quickly after I sent email to the admin
    of the box in question. No "big" sites have been an issue.

    Thanks,
    -John
    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

    \
     
     \ /
      Last update: 2006-06-13 20:30    [W:0.023 / U:1.600 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site