[165305] in North American Network Operators' Group
Re: IP Fragmentation - Not reliable over the Internet?
daemon@ATHENA.MIT.EDU (Owen DeLong)
Wed Aug 28 22:26:45 2013
From: Owen DeLong <owen@delong.com>
In-Reply-To: <521DC232.20209@ripe.net>
Date: Wed, 28 Aug 2013 19:22:28 -0700
To: Emile Aben <emile.aben@ripe.net>
Cc: Tore Anderson <tore@fud.no>,
North American Network Operators' Group <nanog@nanog.org>
Errors-To: nanog-bounces+nanog.discuss=bloom-picayune.mit.edu@nanog.org
Has the path MTU been measured for all vantage point pairs?
Is it known to be 1500 or just the end-point MTUs?
That could affect your results very differently.
Owen
On Aug 28, 2013, at 02:26 , Emile Aben <emile.aben@ripe.net> wrote:
> On 28/08/2013 08:05, Tore Anderson wrote:
>> * Owen DeLong
>>=20
>>> On Aug 27, 2013, at 07:33 , Valdis.Kletnieks@vt.edu wrote:
>>>=20
>>>> Saku Ytti and Emile Aben have numbers that say otherwise. And =
there must
>>>> be a significantly bigger percentage of failures than "pretty close =
to 0",
>>>> or Path MTU Discovery wouldn't have a reputation of being next to =
useless.
>>>=20
>>> No, their numbers describe what happens to single packets of =
differing sizes.
>>>=20
>>> Nothing they did describes results of actually fragmented packets.
>>=20
>> Yes, it did.
>>=20
>> Hint: 1473 + 8 + 20
>=20
> For Saku: yes. For me: that was my intention, but later I discovered =
the
> Atlas ping does include the ICMP header in it's 'size' parameter so =
what
> I did in effect was 1473 + 20 =3D 1493 (and not the 1501 I intended).
>=20
> Redid the tests to a "known good" destination where I knew interface =
MTU
> (1500) and could tcpdump which confirmed that I was looking at
> fragmentation. I also took an offline recommendation to do different
> packet sizes to try to distinguish fragmentation issues from general
> corruption-based packet loss.
>=20
> Results:
> size =3D ICMP packet size, add 20 for IPv4 packet size
> fail% =3D % of vantage points where 5 packets where sent, 0 where =
received.
> #size fail% vantage points
> 100 0.88 2963
> 300 0.77 3614
> 500 0.88 1133
> 700 1.07 3258
> 900 1.13 3614
> 1000 1.04 770
> 1100 2.04 3525
> 1200 1.91 3303
> 1300 1.76 681
> 1400 2.06 3014
> 1450 2.53 3597
> 1470 3.01 2192
> 1470 3.12 3592
> 1473 4.96 3566
> 1475 4.96 3387
> 1480 6.04 679
> 1480 4.93 3492 [*]
> 1481 9.86 3489
> 1482 9.81 3567
> 1483 9.94 3118
>=20
> There is a ~5% difference going up from 1480 to 1481.
>=20
> As to interpreting this: Leo Bicknell's observations (this is to a
> "known good" host, and the RIPE Atlas vantage points may very well =
have
> a clueful-operator bias) stand, so interpret with care. Also: roughly
> 2/3 of these vantage points are behind NATs that may also have some
> firewall(ish) behaviour.
>=20
> Hope this data point helps interpreting the magnitude of IPv4
> fragmentation problems.
>=20
> Emile Aben
> RIPE NCC
>=20
> [*] redid the 'size 1480' experiment because the first time around it
> had significantly less vantage points.
