Date: Thu, 13 Jan 2005 20:12:55 +0100 From: Lars Eggert <lars.eggert@netlab.nec.de> To: Julian Elischer <julian@elischer.org> Cc: net@freebsd.org Subject: Re: TCP out-of-order packets. Message-ID: <41E6C837.1020503@netlab.nec.de> In-Reply-To: <41E6C564.50005@elischer.org> References: <41E5C9D8.4090209@elischer.org> <20050113055111.GA11141@odin.ac.hmc.edu> <41E6C564.50005@elischer.org>
next in thread | previous in thread | raw e-mail | index | archive | help
[-- Attachment #1 --]
>>> I have a link which is provided by someone else that is 7 x E1s
>>> aggregated. At leat it looks that way to me when I get to see it.
>>> however I have only been able to get 60kB.sec across this,
>>> despite having a tcp window size of 131072 bytes.. After
>>> investigation it appears that the link is massively re-orderring
>>> packets. groups of upto 10 packets may appear in random order.
>>> (Maybe more, bu tI have seen 10) >>>
>>> in fact packets are rarely IN order.
>>> This plays havoc with the tcp sessions.
A gap or jump in the ACK stream looks to TCP like a loss, no matter that
it's caused by reordering. Multiple such things per window look like
multiple losses and trigger a slow start under Reno. TCP/SACK should be
more robust against reorderings (up to a degree, at least.) Does 4.x
have the SACK code yet?
What sort of link multiplexer is this? Decent ones jump through all
sorts of hoops to try and reestablish the original packet order.
Lars
--
Lars Eggert NEC Network Laboratories
[-- Attachment #2 --]
0 *H
01 0 + 0 *H
0.0 Z0
*H
0b1 0 UZA1%0#U
Thawte Consulting (Pty) Ltd.1,0*U#Thawte Personal Freemail Issuing CA0
040617072203Z
050617072203Z010
UEggert1
0 U*Lars10U Lars Eggert1(0& *H
lars.eggert@netlab.nec.de1"0 *H
lars.eggert@gmx.net0"0
*H
0
01A!ձA *)
'vAC堜 V3MN 'I_0?
6,<y n1s0זQ_QZH 뮵p:`-8[,=x=ZKڻ E>sx炮H_KgM(͡H^zclm-,AhqmgOKq@IJ|.~u pyMf
8j_2y?8~F6!N+ K0I09U 200lars.eggert@netlab.nec.delars.eggert@gmx.net0 U 0 0
*H
Ok:u-$DX,Ȱ~ PJ>Ȓu3U%ŀkrךW`x~Ӧ$/g`bƿ]p M@8,eyfӤ_("@~O<d tc64f +,0.0 Z0
*H
0b1 0 UZA1%0#U
Thawte Consulting (Pty) Ltd.1,0*U#Thawte Personal Freemail Issuing CA0
040617072203Z
050617072203Z010
UEggert1
0 U*Lars10U Lars Eggert1(0& *H
lars.eggert@netlab.nec.de1"0 *H
lars.eggert@gmx.net0"0
*H
0
01A!ձA *)
'vAC堜 V3MN 'I_0?
6,<y n1s0זQ_QZH 뮵p:`-8[,=x=ZKڻ E>sx炮H_KgM(͡H^zclm-,AhqmgOKq@IJ|.~u pyMf
8j_2y?8~F6!N+ K0I09U 200lars.eggert@netlab.nec.delars.eggert@gmx.net0 U 0 0
*H
Ok:u-$DX,Ȱ~ PJ>Ȓu3U%ŀkrךW`x~Ӧ$/g`bƿ]p M@8,eyfӤ_("@~O<d tc64f +,0?0
0
*H
01 0 UZA10U Western Cape10U Cape Town10U
Thawte Consulting1(0&U Certification Services Division1$0"UThawte Personal Freemail CA1+0) *H
personal-freemail@thawte.com0
030717000000Z
130716235959Z0b1 0 UZA1%0#U
Thawte Consulting (Pty) Ltd.1,0*U#Thawte Personal Freemail Issuing CA00
*H
0 Ħ<UsUNʙZ hup [v :aQP
0cZ,p+Z?qV˯< 6$*+w=+>@dקe*TH<a@ dr` 00U 0 0CU <0:08642http://crl.thawte.com/ThawtePersonalFreemailCA.crl0 U 0)U "0 0 10UPrivateLabel2-1380
*H
HP .
fgCL!6 -6/ P p<ab:~ t%Pb'qW%ݩ9 Oe_N4[5MwV!x!5$ F]_eO1;070i0b1 0 UZA1%0#U
Thawte Consulting (Pty) Ltd.1,0*U#Thawte Personal Freemail Issuing CA Z0 + 0 *H
1 *H
0 *H
1
050113191255Z0# *H
1LFs sp(Ӟnʻ9d!Z0R *H
1E0C0
*H
0*H
0
*H
@0+0
*H
(0x +71k0i0b1 0 UZA1%0#U
Thawte Consulting (Pty) Ltd.1,0*U#Thawte Personal Freemail Issuing CA Z0z *H
1ki0b1 0 UZA1%0#U
Thawte Consulting (Pty) Ltd.1,0*U#Thawte Personal Freemail Issuing CA Z0
*H
jCJm NAцGOt G1vI;B4 l^ߪO;OYqjƎ 82|3L#,UnHKtJ V $9H1;iVͥ*i"|c:_Uh{^
n35
˴-!h8WGA@NLJDeؑ?6+Gr]L;} .$7G) L|
YkZX<sX(À0C \
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?41E6C837.1020503>