Date: Sat, 4 Jan 2014 12:41:00 -0800 From: Peter Wemm <peter@wemm.org> To: "freebsd-net@freebsd.org" <freebsd-net@freebsd.org> Cc: Gavin Atkinson <gavin@freebsd.org>, Andre Oppermann <andre@freebsd.org>, Peter Wemm <peter@freebsd.org> Subject: Re: Long-haul problems - connections stuck in slow start Message-ID: <CAGE5yCpK7N1BwzGCXmx=8M4Q4cu9iUKo4Za-92gRwnkR=HvAiA@mail.gmail.com> In-Reply-To: <52C85EED.801@wemm.org> References: <52C85537.7080307@wemm.org> <52C85EED.801@wemm.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sat, Jan 4, 2014 at 11:20 AM, Peter Wemm <peter@wemm.org> wrote: > On 1/4/14, 10:38 AM, Peter Wemm wrote: >> We're seeing some unfortunate misbehavior with tcp over an intercontinental >> link. > > I forgot to mention, the socket buffers have been generously tuned for these > endpoints. They don't seem to be being used while the sender is in some sort > of limited transmit mode. > > When reading the tcpdumps, keep in mind the window scaling factor is 11 and > that's wasn't captured in the session. You'll have to manually compensate > when reading the mid-session dumps. > > XXX footnote: It seems turning SACK off makes a huge difference for this > connection. The server must have been running with sack disabled when it > was working and hadn't been saved in sysctl.conf. Turning sack off on the > server again has raised the throughput from 8K/sec to 32MB/sec. That's a > nice 400x speedup. > > I'm investigating. > It's still not solved. We just had a lucky break and the session ran fast for a while. SACK doesn't seem to be the variable. I'm looking at the duplicate acks in this trace from each end.. any clues where they're coming from? http://people.freebsd.org/~peter/acks.txt -- Peter Wemm - peter@wemm.org; peter@FreeBSD.org; peter@yahoo-inc.com; KI6FJV Yes, I know, gmail sucks now. If you see this then I forgot. Habits are hard to break.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAGE5yCpK7N1BwzGCXmx=8M4Q4cu9iUKo4Za-92gRwnkR=HvAiA>