From: tlaronde@polynum.com
To: Fans of the OS Plan 9 from Bell Labs <9fans@9fans.net>
Subject: Re: [9fans] rtl8169 gbe slow
Date: Sat, 20 Feb 2016 18:45:48 +0100 [thread overview]
Message-ID: <20160220174548.GA1630@polynum.com> (raw)
In-Reply-To: <36a7a43105da0ea05fcec8fe089d37ac@mule>
On Sat, Feb 20, 2016 at 09:20:52AM -0800, erik quanstrom wrote:
> On Sat Feb 20 06:04:02 PST 2016, tlaronde@polynum.com wrote:
> > On Sat, Feb 20, 2016 at 02:31:54PM +0100, hiro wrote:
> > > what is the latency on WAN?
> >
> > When using traceroute, I have 42.6ms for a roundtrip
> > (cf. with LAN: 0.23ms).
> >
> > But the very same machine, under NetBSD, with the very same ip address,
> > downloads the very same file from the very same external server
> > (downloads.kergis.com) in 17s, while hget(1) spends 6 minutes doing
> > it.
> >
> > I wondered if the unsupported same chip integrated network card would
> > be a problem. But disabling it via the BIOS doesn't change anything.
> >
> > Is there a way to trace what hget is doing/calling so that I can have a
> > clue about the bottleneck? There is no transmission errors on the
> > interface, so the problem is in the upper levels of TCP/IP.
>
> yes. i believe this was suggested before. from the evidence, the best
> guess is that you are using an old kernel with an old tcp.
Does it explain the difference between LAN and WAN? ftp is TCP; and on
LAN there is no visible problem (connecting to a host running NetBSD)---
well, since the latency on LAN is the 1/300 of the latency of WAN, the
problem could be masked...
>
> the old tcp had abysmal performance starting at a latency of ~10ms. this
> was due to a flawed implementation of tcp reno. plan 9 used to commit
> the cardinal sin of tcp, and move the left edge of the window.
>
> anyway, please update your tcp. the debugging tools that are most
> helpful with tcp are
> /net/tcp/stats
> /net/tcp/*/status
> echo tcp>/net/log && tail -f /net/log
To update I need to update the sources. Where are now the "updated"
sources? since Bell Labs site seems to be definitively down... Is there
somewhere the "latest" sources, at least with the TCP corrections?
--
Thierry Laronde <tlaronde +AT+ polynum +dot+ com>
http://www.kergis.com/
http://www.arts-po.fr/
Key fingerprint = 0FF7 E906 FBAF FE95 FD89 250D 52B1 AE95 6006 F40C
next prev parent reply other threads:[~2016-02-20 17:45 UTC|newest]
Thread overview: 83+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-02-18 11:30 tlaronde
2016-02-18 13:22 ` erik quanstrom
2016-02-18 23:41 ` arisawa
2016-02-19 1:56 ` erik quanstrom
2016-02-19 15:17 ` erik quanstrom
2016-02-19 12:52 ` tlaronde
2016-02-19 15:13 ` erik quanstrom
2016-02-19 17:11 ` tlaronde
2016-02-20 10:32 ` tlaronde
2016-02-20 11:23 ` Kenny Lasse Hoff Levinsen
2016-02-20 12:11 ` tlaronde
2016-02-20 13:31 ` hiro
2016-02-20 14:01 ` tlaronde
2016-02-20 14:06 ` lucio
2016-02-20 14:22 ` tlaronde
2016-02-20 17:20 ` erik quanstrom
2016-02-20 17:45 ` tlaronde [this message]
2016-02-20 19:26 ` erik quanstrom
2016-02-20 19:41 ` Mark van Atten
2016-02-20 20:18 ` tlaronde
2016-02-20 20:18 ` tlaronde
2016-02-22 9:14 ` tlaronde
2016-02-22 9:40 ` Mark van Atten
2016-02-22 10:10 ` tlaronde
2016-02-22 10:15 ` lucio
2016-02-22 11:05 ` tlaronde
2016-02-22 11:06 ` Richard Miller
2016-02-22 11:40 ` tlaronde
2016-02-22 12:00 ` lucio
2016-02-22 12:16 ` tlaronde
2016-02-22 12:17 ` Richard Miller
2016-02-22 12:29 ` Mark van Atten
2016-02-22 12:47 ` tlaronde
2016-02-22 12:52 ` Mark van Atten
2016-02-22 13:02 ` tlaronde
2016-02-22 13:20 ` erik quanstrom
2016-02-22 15:05 ` tlaronde
2016-02-22 15:19 ` lucio
2016-02-22 15:34 ` tlaronde
2016-02-22 15:43 ` lucio
2016-02-22 13:13 ` tlaronde
2016-02-22 13:29 ` lucio
2016-02-22 13:39 ` David du Colombier
2016-02-22 14:39 ` rod
2016-02-22 15:12 ` tlaronde
2016-02-22 15:21 ` stanley lieber
2016-02-22 15:27 ` tlaronde
2016-02-22 15:45 ` erik quanstrom
2016-02-22 15:46 ` David du Colombier
2016-02-22 16:28 ` Kenny Lasse Hoff Levinsen
2016-02-22 16:40 ` lucio
2016-02-22 16:57 ` Kenny Lasse Hoff Levinsen
2016-02-22 17:03 ` [9fans] FP instructions in note handlers (Was: rtl8169 gbe slow) lucio
2016-02-23 10:36 ` hiro
2016-02-22 16:45 ` [9fans] rtl8169 gbe slow rod
2016-02-22 16:57 ` tlaronde
2016-02-22 17:13 ` David du Colombier
2016-02-22 17:57 ` Skip Tavakkolian
2016-02-23 10:34 ` hiro
2016-02-23 12:24 ` erik quanstrom
2016-02-23 12:30 ` hiro
2016-02-23 12:37 ` hiro
2016-02-23 12:40 ` hiro
2016-02-23 12:48 ` hiro
2016-02-23 15:16 ` erik quanstrom
2016-02-23 17:27 ` hiro
2016-02-23 15:17 ` erik quanstrom
2016-02-23 17:24 ` hiro
2016-02-23 17:38 ` erik quanstrom
2016-02-23 17:50 ` hiro
2016-02-23 18:16 ` erik quanstrom
2016-02-23 18:38 ` hiro
2016-02-23 19:19 ` erik quanstrom
2016-02-23 19:35 ` hiro
2016-02-23 20:21 ` tlaronde
2016-02-23 17:54 ` Kenny Lasse Hoff Levinsen
2016-02-23 18:08 ` erik quanstrom
2016-02-23 17:48 ` lucio
2016-02-23 17:52 ` hiro
2016-02-23 15:18 ` erik quanstrom
2016-02-22 15:44 ` erik quanstrom
2016-02-20 19:07 ` tlaronde
2016-02-20 19:21 ` erik quanstrom
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=20160220174548.GA1630@polynum.com \
--to=tlaronde@polynum.com \
--cc=9fans@9fans.net \
/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;
as well as URLs for NNTP newsgroup(s).