[95969] in North American Network Operators' Group
Re: Thoughts on increasing MTUs on the internet
daemon@ATHENA.MIT.EDU (Warren Kumari)
Thu Apr 12 12:12:45 2007
In-Reply-To: <96C7E3A8-0E0C-4030-9971-C9D886F12E67@corp.earthlink.net>
Cc: NANOG list <nanog@merit.edu>
From: Warren Kumari <warren@kumari.net>
Date: Thu, 12 Apr 2007 11:56:54 -0400
To: Gian Constantine <constantinegi@corp.earthlink.net>
Errors-To: owner-nanog@merit.edu
--Apple-Mail-18-517719425
Content-Transfer-Encoding: 7bit
Content-Type: text/plain;
charset=US-ASCII;
delsp=yes;
format=flowed
On Apr 12, 2007, at 10:04 AM, Gian Constantine wrote:
> I agree. The throughput gains are small. You're talking about a
> difference between a 4% header overhead versus a 1% header overhead
> (for TCP).
One of the "benefits" of larger MTU is that, during the additive
increase phase, or after recovering from congestion, you reach full
speed sooner -- it does also mean that if you do reach congestion,
you throw away more data, and, because of the length of flows, are
probably more likely to cause congestion...
>
> One could argue a decreased pps impact on intermediate systems, but
> when factoring in the existing packet size distribution on the
> Internet and the perceived adjustment seen by a migration to 4470
> MTU support, the gains remain small.t
>
> Development costs and the OpEx costs of implementation and support
> will, likely, always outweigh the gains.
>
> Gian Anthony Constantine
>
>
> On Apr 12, 2007, at 7:50 AM, Saku Ytti wrote:
>
>>
>> On (2007-04-12 11:20 +0200), Iljitsch van Beijnum wrote:
>>
>>> What do you guys think about a mechanism that allows hosts and
>>> routers on a subnet to automatically discover the MTU they can use
>>> towards other systems on the same subnet, so that:
>>> 1. It's no longer necessary to limit the subnet MTU to that of the
>>> least capable system
>>>
>>> 2. It's no longer necessary to manage 1500 byte+ MTUs manually
>>
>> To me this sounds adding complexity for rather small pay-off. And
>> then we'd have to ask IXP people, would the enable this feature
>> if it was available? If so, why don't they offer high MTU VLAN
>> today?
>> And in the end, pay-off of larger MTU is quite small, perhaps
>> some interrupts are saved but not sure how relevant that is
>> in poll() based NIC drivers. Of course bigger pay-off
>> would be that users could use tunneling and still offer 1500
>> to LAN.
>>
>> IXP peeps, why are you not offering high MTU VLAN option?
>> From my point of view, this is biggest reason why we today
>> generally don't have higher end-to-end MTU.
>> I know that some IXPs do, eg. NetNOD but generally it's
>> not offered even though many users would opt to use it.
>>
>> Thanks,
>> --
>> ++ytti
>
--
Some people are like Slinkies......Not really good for anything but
they still bring a smile to your face when you push them down the
stairs.
--Apple-Mail-18-517719425
Content-Transfer-Encoding: quoted-printable
Content-Type: text/html;
charset=ISO-8859-1
<HTML><BODY style=3D"word-wrap: break-word; -khtml-nbsp-mode: space; =
-khtml-line-break: after-white-space; "><BR><DIV><DIV>On Apr 12, 2007, =
at 10:04 AM, Gian Constantine wrote:</DIV><BR =
class=3D"Apple-interchange-newline"><BLOCKQUOTE type=3D"cite">I agree. =
The throughput gains are small. You're talking about a difference =
between a 4% header overhead versus a 1% header overhead (for =
TCP).</BLOCKQUOTE><DIV><BR =
class=3D"khtml-block-placeholder"></DIV><DIV>One of the "benefits" of =
larger MTU is that, during=A0the additive increase phase, or after =
recovering from congestion, you reach full speed sooner --=A0 it does =
also mean that if you do reach congestion, you throw away more data, =
and, because of the length of flows, are probably more likely to cause =
congestion...</DIV><DIV><BR =
class=3D"khtml-block-placeholder"></DIV><DIV><BR =
class=3D"khtml-block-placeholder"></DIV><BLOCKQUOTE type=3D"cite"><DIV><BR=
class=3D"khtml-block-placeholder"></DIV><DIV>One could argue a =
decreased pps impact on intermediate systems, but when factoring in the =
existing packet size distribution on the Internet and the perceived =
adjustment seen by a migration to 4470 MTU support, the gains remain =
small.t=A0</DIV></BLOCKQUOTE><BR><BLOCKQUOTE type=3D"cite"><DIV><BR =
class=3D"khtml-block-placeholder"></DIV><DIV>Development costs and the =
OpEx costs of implementation and support will, likely, always outweigh =
the gains.</DIV><DIV><BR><DIV> <SPAN class=3D"Apple-style-span" =
style=3D"border-collapse: separate; border-spacing: 0px 0px; color: =
rgb(0, 0, 0); font-family: Helvetica; font-size: 12px; font-style: =
normal; font-variant: normal; font-weight: normal; letter-spacing: =
normal; line-height: normal; text-align: auto; =
-khtml-text-decorations-in-effect: none; text-indent: 0px; =
-apple-text-size-adjust: auto; text-transform: none; orphans: 2; =
white-space: normal; widows: 2; word-spacing: 0px; "><SPAN =
class=3D"Apple-style-span" style=3D"border-collapse: separate; =
border-spacing: 0px 0px; color: rgb(0, 0, 0); font-family: Helvetica; =
font-size: 12px; font-style: normal; font-variant: normal; font-weight: =
normal; letter-spacing: normal; line-height: normal; text-align: auto; =
-khtml-text-decorations-in-effect: none; text-indent: 0px; =
-apple-text-size-adjust: auto; text-transform: none; orphans: 2; =
white-space: normal; widows: 2; word-spacing: 0px; "><DIV>Gian Anthony =
Constantine</DIV><BR class=3D"Apple-interchange-newline"></SPAN></SPAN> =
</DIV><BR><DIV><DIV>On Apr 12, 2007, at 7:50 AM, Saku Ytti =
wrote:</DIV><BR class=3D"Apple-interchange-newline"><BLOCKQUOTE =
type=3D"cite"><DIV style=3D"margin-top: 0px; margin-right: 0px; =
margin-bottom: 0px; margin-left: 0px; min-height: 14px; "><BR></DIV><DIV =
style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: 0px; =
margin-left: 0px; ">On (2007-04-12 11:20 +0200), Iljitsch van Beijnum =
wrote:</DIV><DIV style=3D"margin-top: 0px; margin-right: 0px; =
margin-bottom: 0px; margin-left: 0px; min-height: 14px; "><BR></DIV> =
<BLOCKQUOTE type=3D"cite"><DIV style=3D"margin-top: 0px; margin-right: =
0px; margin-bottom: 0px; margin-left: 0px; ">What do you guys think =
about a mechanism that allows hosts and <SPAN =
class=3D"Apple-converted-space">=A0</SPAN></DIV><DIV style=3D"margin-top: =
0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; ">routers =
on a subnet to automatically discover the MTU they can use <SPAN =
class=3D"Apple-converted-space">=A0</SPAN></DIV><DIV style=3D"margin-top: =
0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; ">towards =
other systems on the same subnet, so that:</DIV><DIV style=3D"margin-top: =
0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; ">1. It's =
no longer necessary to limit the subnet MTU to that of the <SPAN =
class=3D"Apple-converted-space">=A0</SPAN></DIV><DIV style=3D"margin-top: =
0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; ">least =
capable system</DIV><DIV style=3D"margin-top: 0px; margin-right: 0px; =
margin-bottom: 0px; margin-left: 0px; min-height: 14px; "><BR></DIV><DIV =
style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: 0px; =
margin-left: 0px; ">2. It's no longer necessary to manage 1500 byte+ =
MTUs manually</DIV> </BLOCKQUOTE><DIV style=3D"margin-top: 0px; =
margin-right: 0px; margin-bottom: 0px; margin-left: 0px; min-height: =
14px; "><BR></DIV><DIV style=3D"margin-top: 0px; margin-right: 0px; =
margin-bottom: 0px; margin-left: 0px; ">To me this sounds adding =
complexity for rather small pay-off. And</DIV><DIV style=3D"margin-top: =
0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; ">then =
we'd have to ask IXP people, would the enable this feature</DIV><DIV =
style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: 0px; =
margin-left: 0px; ">if it was available? If so, why don't they offer =
high MTU VLAN</DIV><DIV style=3D"margin-top: 0px; margin-right: 0px; =
margin-bottom: 0px; margin-left: 0px; ">today?</DIV><DIV =
style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: 0px; =
margin-left: 0px; ">And in the end, pay-off of larger MTU is quite =
small, perhaps</DIV><DIV style=3D"margin-top: 0px; margin-right: 0px; =
margin-bottom: 0px; margin-left: 0px; ">some interrupts are saved but =
not sure how relevant that is</DIV><DIV style=3D"margin-top: 0px; =
margin-right: 0px; margin-bottom: 0px; margin-left: 0px; ">in poll() =
based NIC drivers. Of course bigger pay-off</DIV><DIV style=3D"margin-top:=
0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; ">would =
be that users could use tunneling and still offer 1500</DIV><DIV =
style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: 0px; =
margin-left: 0px; ">to LAN.</DIV><DIV style=3D"margin-top: 0px; =
margin-right: 0px; margin-bottom: 0px; margin-left: 0px; min-height: =
14px; "><BR></DIV><DIV style=3D"margin-top: 0px; margin-right: 0px; =
margin-bottom: 0px; margin-left: 0px; ">IXP peeps, why are you not =
offering high MTU VLAN option?</DIV><DIV style=3D"margin-top: 0px; =
margin-right: 0px; margin-bottom: 0px; margin-left: 0px; ">=46rom my =
point of view, this is biggest reason why we today</DIV><DIV =
style=3D"margin-top: 0px; margin-right: 0px; margin-bottom: 0px; =
margin-left: 0px; ">generally don't have higher end-to-end =
MTU.</DIV><DIV style=3D"margin-top: 0px; margin-right: 0px; =
margin-bottom: 0px; margin-left: 0px; ">I know that some IXPs do, eg. =
NetNOD but generally it's</DIV><DIV style=3D"margin-top: 0px; =
margin-right: 0px; margin-bottom: 0px; margin-left: 0px; ">not offered =
even though many users would opt to use it.</DIV><DIV style=3D"margin-top:=
0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; =
min-height: 14px; "><BR></DIV><DIV style=3D"margin-top: 0px; =
margin-right: 0px; margin-bottom: 0px; margin-left: 0px; =
">Thanks,</DIV><DIV style=3D"margin-top: 0px; margin-right: 0px; =
margin-bottom: 0px; margin-left: 0px; ">--<SPAN =
class=3D"Apple-converted-space">=A0</SPAN></DIV><DIV style=3D"margin-top: =
0px; margin-right: 0px; margin-bottom: 0px; margin-left: 0px; "><SPAN =
class=3D"Apple-converted-space">=A0 </SPAN>++ytti</DIV> =
</BLOCKQUOTE></DIV><BR></DIV></BLOCKQUOTE></DIV><BR><DIV> <SPAN =
class=3D"Apple-style-span" style=3D"border-collapse: separate; =
border-spacing: 0px 0px; color: rgb(0, 0, 0); font-family: Helvetica; =
font-size: 12px; font-style: normal; font-variant: normal; font-weight: =
normal; letter-spacing: normal; line-height: normal; text-align: auto; =
-khtml-text-decorations-in-effect: none; text-indent: 0px; =
-apple-text-size-adjust: auto; text-transform: none; orphans: 2; =
white-space: normal; widows: 2; word-spacing: 0px; "><SPAN =
class=3D"Apple-style-span" style=3D"border-collapse: separate; =
border-spacing: 0px 0px; color: rgb(0, 0, 0); font-family: Helvetica; =
font-size: 12px; font-style: normal; font-variant: normal; font-weight: =
normal; letter-spacing: normal; line-height: normal; text-align: auto; =
-khtml-text-decorations-in-effect: none; text-indent: 0px; =
-apple-text-size-adjust: auto; text-transform: none; orphans: 2; =
white-space: normal; widows: 2; word-spacing: 0px; =
"><DIV>--</DIV><DIV>Some people are like Slinkies......Not really good =
for anything but they still bring a smile to your face when you push =
them down the stairs.</DIV><DIV><BR =
class=3D"khtml-block-placeholder"></DIV><BR =
class=3D"Apple-interchange-newline"></SPAN></SPAN> =
</DIV><BR></BODY></HTML>=
--Apple-Mail-18-517719425--
