Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 19 Mar 2002 17:06:51 -0700
From:      Colin Harford <colin.harford@mail.su.ualberta.ca>
To:        Doug White <dwhite@resnet.uoregon.edu>, <freebsd-stable@freebsd.org>, <abaugher@esc.pike.il.us>
Subject:   Re: Network stalls with 4.5
Message-ID:  <B8BD20AB.8516%colin.harford@mail.su.ualberta.ca>
In-Reply-To: <20020319154511.L80289-100000@resnet.uoregon.edu>

next in thread | previous in thread | raw e-mail | index | archive | help
On 19/3/02 4:48 PM, "Doug White" <dwhite@resnet.uoregon.edu> wrote:

> On 19 Mar 2002, Aaron Baugher wrote:
>=20
>> To add to the previous info, here's a chunk of a tcpdump.  I logged in
>> through ssh, and ran 'top' to generate some traffic.  My home machine
>> (Mandrake Linux, connected with a modem) is 11.22.33.44, and the
>> FreeBSD machine having the problem is 55.66.77.88.  (I should stress
>> that the problem occurs from several different client machines and
>> OS's, so it's definitely caused at the server end.)
>=20
> This looks like simple packet loss on the network. Can you set up a
> monitor port on the Cisco switch and confirm the packet that is retried i=
s
> actually making it onto the wire? Also set up other monitors downstream
> and see if you can isolate where the packet disappears.
>=20
>> 09:41:22.371874 55.66.77.88.22 > 11.22.33.44.4257: P 33324:33472(148) ac=
k 161
>> win 65535 [tos 0x10]
>> 09:41:23.371716 55.66.77.88.22 > 11.22.33.44.4257: P 33324:33472(148) ac=
k 161
>> win 65535 [tos 0x10]
>>=20
>> That's the same packet sent twice, right?
>>=20
>> 09:41:24.381831 55.66.77.88.22 > 11.22.33.44.4257: P 33472:33628(156) ac=
k 161
>> win 65535 [tos 0x10]
>> 09:41:24.629822 11.22.33.44.4257 > 55.66.77.88.22: . ack 33324 win 51360=
 (DF)
>> [tos 0x10]
>> 09:41:25.371763 55.66.77.88.22 > 11.22.33.44.4257: P 33324:33628(304) ac=
k 161
>> win 65535 [tos 0x10]
>>=20
>> Now here's the same number (33324) as the doubled packet above, but
>> with a different second number and size.
>=20
> The change in size is the system gluing the payloads of the two packets
> together since the remote sent an ACK up to 33324.
>=20
>> 09:41:34.666565 11.22.33.44.4257 > 55.66.77.88.22: . ack 33324 win 51360=
 (DF)
>> [tos 0x10]
>> 09:41:34.666621 55.66.77.88.22 > 11.22.33.44.4257: P 33324:34336(1012) a=
ck
>> 161 win 65535 [tos 0x10]
>> 09:41:35.147334 11.22.33.44.4257 > 55.66.77.88.22: . ack 34336 win 51360=
 (DF)
>> [tos 0x10]
>=20
> Look like your network keeled over for 10 seconds. Bandwidth problems
> downstream?
>=20
> Also make sure something downstream isn't, say, loosing the ARP entry for
> it's default gateway.
>=20
> Doug White                    |  FreeBSD: The Power to Serve
> dwhite@resnet.uoregon.edu     |  www.FreeBSD.org
>=20
>=20
> To Unsubscribe: send mail to majordomo@FreeBSD.org
> with "unsubscribe freebsd-stable" in the body of the message


I was having a similar situation as Aaron at home on both my FreeBSD
machines

=80 K6-3-450, 512 RAM, rl interface
=80 K7-1.2Ghz, 1GB RAM, xl interface

Both started happening in FreeBSD 4.5, both are connected to an internal
10/100 switch at 100T and are about 10 inches from each other...

The k7 is a dual boot machine, and when I am in winblowdoze I do not have
the same problem, so I have mostly ruled out hardware problems...(that and
hardware has been tested in other situations without problems)

I updated both machines this past weekened, to RELENG_4_5 and no longer do =
I
have this problem.=20

HTH


Colin Harford =A0=A0=A0

=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 =A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0
Systems and Network Administrator =A0=A0=A0=A0    Apple Product Professional
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =A0=A0=A0=A0
Computer and Network Support =A0=A0=A0=A0=A0=A0=A0=A0
University of Alberta Students' Union =A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0
Phone: (780) 492-4241 =A0=A0Fax: =A0(780) 492-4643
http://www.su.ualberta.ca


"I sense much NT in you, NT leads to Blue Screen.
Blue Screen leads to downtime, downtime leads to suffering.
NT is the path to the darkside."
         - Unknown Unix Jedi




To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-stable" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?B8BD20AB.8516%colin.harford>