Beruflich Dokumente
Kultur Dokumente
I. I NTRODUCTION
The Maximum Segment Size (MSS) is a fundamental attribute of a TCP connection that defines how large blocks
of data are divided into segments for transmission over a
network. Despite this, there have been no recent studies that
have examined the MSS values that are announced and used
by TCP senders in any detail. Rather, there are several wellknown common MSS values that are often assumed to be
prevalent on the Internet; in particular, 1460 byte MSS values
are typically utilised by TCP traffic models. However, this
is done without any reference to recent measurements that
confirm these values as being representative of contemporary
Internet traffic.
In this paper, we present the results of using passive network
packet traces to investigate the MSS values that are announced
and utilised by TCP senders. Traces from several different
data sets were analysed, including captures of residential DSL
traffic, to ensure that the results encompass a broad sample
of users, devices and applications. We have examined the
distribution of MSS values that were announced in each trace
set and have identified occasions where the announced MSS
did not correspond to the MSS that the sender was using.
The primary contribution of this work is that it is a dedicated
and in-depth study of the MSS as utilised by modern TCP
hosts. Given the rate and nature of evolution of the Internet,
it is important to periodically re-evaluate the conventional
wisdom regarding properties like the MSS to ensure that
existing models of TCP accurately reflect the traffic that is
observed in reality. For instance, the increased prevalence of
protocols and technologies which reduce the effective MTU
for links, such as the Point-to-Point Protocol over Ethernet
TABLE I
L IST OF ANALYSED DATA SETS .
Name
ISP B
Waikato
ISP C-I
Auckland
ISP C-II
Date
Feb 2007
Feb 2008
Jan 2009
Oct 2009
Jan 2010
Duration
5 days
6.5 days
10 days
9 days
9 days
TCP Flows
508 million
20 million
130 million
230 million
197 million
IV. R ESULTS
1e+07
1e+06
100000
Frequency
10000
1000
10
1
1
10
100
1000
10000
Announced MSS (bytes)
100000
(a) ISP B
1e+06
100000
Frequency
10000
1000
100
10
1
10
100
1000
10000
Announced MSS (bytes)
100000
(b) Waikato
1e+07
1e+06
100000
Frequency
100
10000
1000
100
10
1
1
10
100
1000
10000
Announced MSS (bytes)
100000
TABLE II
R ANGES OF ANNOUNCED MSS VALUES
MSS Range
1 - 535
536 - 999
1000 - 1299
1300 - 1439
1440 - 1460
1461 - 8960
8961 - 66535
ISP B
0.063%
0.269%
1.215%
17.980%
80.423%
0.046%
0.003%
Auckland
0.017%
0.275%
1.272%
21.075%
77.327%
0.030%
0.004%
Waikato
0.271%
21.103%
0.779%
15.834%
61.977%
0.031%
0.005%
ISP C-I
0.195%
0.274%
1.544%
16.792%
81.195%
0.001%
0.000%
ISP C-II
0.057%
0.213%
0.809%
20.65%
78.27%
0.001%
0.001%
TABLE III
M OST FREQUENTLY ANNOUNCED MSS VALUES
ISP B
1460 (44.8%)
1452 (19.3%)
1440 (15.6%)
1360 (3.40%)
1414 (2.83%)
1412 (2.03%)
1420 (1.95%)
1380 (1.28%)
1260 (1.07%)
1432 (1.05%)
Auckland
1460 (39.5%)
1452 (19.1%)
1440 (15.7%)
1360 (5.33%)
1380 (2.92%)
1400 (2.47%)
1420 (2.44%)
1442 (2.09%)
1412 (1.41%)
1414 (1.38%)
Waikato
1460 (30.6%)
536 (21.1%)
1452 (17.5%)
1440 (12.5%)
1360 (3.28%)
1380 (2.31%)
1420 (1.92%)
1412 (1.81%)
1414 (1.33%)
1400 (0.95%)
ISP C-I
1460 (46.4%)
1440 (17.6%)
1452 (15.2%)
1360 (4.12%)
1380 (1.95%)
1414 (1.79%)
1420 (1.50%)
1412 (1.45%)
1400 (1.12%)
1456 (0.97%)
ISP C-II
1460 (40.5%)
1440 (22.7%)
1452 (13.5%)
1360 (5.70%)
1420 (2.87%)
1380 (2.41%)
1414 (2.20%)
1400 (1.56%)
1412 (1.03%)
1408 (0.77%)
1600
1400
Observed MSS (bytes)
Rank
1
2
3
4
5
6
7
8
9
10
1200
1000
800
600
400
200
0
0
200
Fig. 2. Comparing the announced MSS against the observed MSS in the
ISP B traces.
Middlebox
1600
1400
MSS=1460
MSS=536
Host B
Host A
1200
MSS=536
1000
MSS=1460
800
600
Monitor
400
200
0
0
200
Fig. 3. Comparing the announced MSS against the observed MSS in the
ISP C-II traces.
Fig. 4. An illustration of how the location of the passive monitor can affect
an analysis of MSS announcements. If a device in the middle of the path is
adjusting the announced MSS, the change is only seen in one direction at the
passive monitor.
TABLE IV
R ELATIONSHIP BETWEEN THE OBSERVED MSS AND THE ADVERTISED VALUES FOR THE CONNECTION .
MSS Matched
Receiver
Sender
Sender
Neither
Neither
Valid
Yes
Yes
No
Yes
No
ISP B
68.5%
13.3%
0.2%
17.9%
<0.1%
Auckland
77.8%
11.4%
< 0.1%
10.8%
< 0.1%
Waikato
53.0%
37.4%
0.2%
9.4%
0.1%
ISP C-I
69.7%
13.4%
0.1%
16.8%
< 0.1%
ISP C-II
69.0%
13.3%
0.1%
17.7%
< 0.1%
from the passive monitor, thus the MSS value observed in the
packet trace may not match the value seen by the destination
endpoint. We found that it is not uncommon for TCP senders
utilise a maximum segment size smaller than that announced
to them. This may be because the announced MSS exceeds
the senders MTU or because the application has limited the
size of network writes. As a result, passive analysis techniques
that depend on an accurate MSS cannot just naively rely on
the announced MSS value.
Finally, we found that less than 0.3% of all TCP halfconnections sent segments larger than those specified by the
corresponding MSS announcement. While the overall proportion was small, it is still disconcerting that we were able to
observe senders that violated the MSS in each of the trace sets
that we examined. One possible avenue of future work would
be to investigate senders that violate the MSS in greater depth
to determine why and how this occurs.
R EFERENCES
[1] W. John and S. Tafvelin, Analysis of Internet Backbone Traffic and
Header Anomalies Observed, in IMC 07: Proceedings of the 7th ACM
SIGCOMM conference on Internet measurement, 2007, pp. 111116.
[2] S. Alcock, D. Lawson, and R. Nelson, Extracting Application Objects
from TCP Packet Traces, in Proceedings of Australasian Telecommunication Networks and Applications Conference (ATNAC 2007), 2007.
[3] S. Jaiswal, G. Iannaccone, C. Diot, J. Kurose, and D. Towsley, Inferring
TCP Connection Characteristics through Passive Measurements, in
Proceedings of IEEE Infocom, 2004, pp. 15821592.
[4] S. Floyd, T. Henderson, and A. Gurtov, RFC 3782 - The NewReno
Modification to TCPs Fast Recovery Algorithm, 2004.
[5] R. Braden, RFC 1122 - Requirements for Internet Hosts - Communication Layers, 1989.
[6] J. Postel, RFC 879 - TCP Maximum Segment Size and Related Topics,
1983.
[7] WITS: Waikato Internet Trace Storage, http://www.wand.net.nz/wits/.
[8] WITS: Local ISP B-III, http://www.wand.net.nz/wits/localisp/b/3/.
[9] WITS: Local ISP C-I, http://www.wand.net.nz/wits/localisp/c/1/.
[10] WITS: Local ISP C-II, http://www.wand.net.nz/wits/localisp/c/2/.
[11] WITS: Waikato VI, http://www.wand.net.nz/wits/waikato/6/.
[12] WITS: Auckland X, http://www.wand.net.nz/wits/auckland/10/.
[13] Microsoft Help and Support, The Default MTU sizes for Different
Network Topologies, http://support.microsoft.com/kb/314496/.
[14] M. Allman, A Web Servers View of the Transport Layer, SIGCOMM
Computer Communication Review, vol. 30, no. 5, 2000.
[15] M. Arlitt, B. Krishnamurthy, and J. C. Mogul, Predicting Short-Transfer
Latency from TCP arcana: A Trace-based Validation, in In Proceedings
of Internet Measurement Conference, 2005, pp. 119124.