public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Dave Dykstra <dwd@bell-labs.com>
To: linux-kernel@vger.kernel.org
Cc: davem@redhat.com, kuznet@ms2.inr.ac.ru
Subject: Linux 2.2.16 through 2.2.18preX TCP hang bug triggered by rsync
Date: Tue, 23 Jan 2001 14:42:14 -0600	[thread overview]
Message-ID: <20010123144214.A11759@lucent.com> (raw)

Ville Herva <v@iki.fi> suggested I post this bug report here and that
possibly David Miller or Alexey Kuznetsov could help out.  I found the
problem back at the end of October and narrowed it down as much as I could
but didn't know where to report it until now.  For complete details please
see the rsync mailing list archive at
    http://lists.samba.org/pipermail/rsync/2000-October/003004.html
and some of the preceding and following messages.  In particular, the next
message
    http://lists.samba.org/pipermail/rsync/2000-October/003005.html
is an interpretation of the TCP dump by my co-worker which implicates the
Linux side.  Also, in
    http://lists.samba.org/pipermail/rsync/2000-October/002985.html
Andrew Tridgell refers to a TCP patch that went into Linux kernel 2.2.17
and that "Stephen" told him about it but I don't know what Stephen he was
referring to; that fix didn't help anyway.

The first message above refers to a set of data that could possibly be used
to reproduce the problem, but unfortunately nobody else has reported to me
that they have successfully reproduced it.  I only saw the failures when
using rsync to pull to a particular Solaris 7 workstation, but it happened
when pulling from two different Linux machines and three different kernels
but no other type of machine.  Another message
    http://lists.samba.org/pipermail/rsync/2000-October/002981.html
gives a more complete rsync command for reproducing the problem.  The
original report at
    http://lists.samba.org/pipermail/rsync/2000-October/002964.html
says that I first noticed the problem on Linux kernel 2.2.16-3smp.

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

             reply	other threads:[~2001-01-23 20:42 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2001-01-23 20:42 Dave Dykstra [this message]
2001-01-23 22:51 ` Linux 2.2.16 through 2.2.18preX TCP hang bug triggered by rsync Dave Dykstra
  -- strict thread matches above, loose matches on Subject: below --
2001-01-23 22:17 Manfred Spraul
2001-01-23 22:59 ` Manfred Spraul
2001-01-24 20:03 ` kuznet
2001-01-24 20:34   ` Manfred Spraul
2001-01-24 20:42     ` kuznet
2001-01-25 18:35     ` kuznet
2001-01-24 20:56   ` Andi Kleen
2001-01-25 10:58     ` Matthias Andree
2001-01-25 12:17       ` James Sutherland
2001-01-25 12:27         ` Matthias Andree
2001-01-25 11:32     ` David S. Miller
2001-01-25 11:40       ` Andi Kleen
2001-01-25 11:44         ` David S. Miller
2001-01-25 11:56           ` Andi Kleen
2001-01-25 12:25       ` James Sutherland
2001-01-25 12:24 Studierende der Universitaet des Saarlandes
2001-01-25 12:34 ` Andi Kleen
2001-01-26 20:56 Dave Dykstra
2001-01-27 18:27 ` kuznet

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=20010123144214.A11759@lucent.com \
    --to=dwd@bell-labs.com \
    --cc=davem@redhat.com \
    --cc=kuznet@ms2.inr.ac.ru \
    --cc=linux-kernel@vger.kernel.org \
    /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