xref: /freebsd/share/man/man4/cc_vegas.4 (revision 71f0c44a045421bed4f27fefdb3caf30e1b54fe4)
1.\"
2.\" Copyright (c) 2010-2011 The FreeBSD Foundation
3.\"
4.\" This documentation was written at the Centre for Advanced Internet
5.\" Architectures, Swinburne University of Technology, Melbourne, Australia by
6.\" David Hayes under sponsorship from the FreeBSD Foundation.
7.\"
8.\" Redistribution and use in source and binary forms, with or without
9.\" modification, are permitted provided that the following conditions
10.\" are met:
11.\" 1. Redistributions of source code must retain the above copyright
12.\"    notice, this list of conditions and the following disclaimer.
13.\" 2. Redistributions in binary form must reproduce the above copyright
14.\"    notice, this list of conditions and the following disclaimer in the
15.\"    documentation and/or other materials provided with the distribution.
16.\"
17.\" THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
18.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
19.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
20.\" ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE FOR
21.\" ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
22.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
23.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
24.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
25.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
26.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
27.\" SUCH DAMAGE.
28.\"
29.\" $FreeBSD$
30.\"
31.Dd May 13, 2021
32.Dt CC_VEGAS 4
33.Os
34.Sh NAME
35.Nm cc_vegas
36.Nd Vegas Congestion Control Algorithm
37.Sh DESCRIPTION
38The Vegas congestion control algorithm uses what the authors term the actual and
39expected transmission rates to determine whether there is congestion along the
40network path i.e.
41.Bl -item -offset indent
42.It
43actual rate = (total data sent in a RTT) / RTT
44.It
45expected rate = cwnd / RTTmin
46.It
47diff = expected - actual
48.El
49.Pp
50where RTT is the measured instantaneous round trip time and RTTmin is the
51smallest round trip time observed during the connection.
52.Pp
53The algorithm aims to keep diff between two parameters alpha and beta, such
54that:
55.Bl -item -offset indent
56.It
57alpha < diff < beta
58.El
59.Pp
60If diff > beta, congestion is inferred and cwnd is decremented by one packet (or
61the maximum TCP segment size).
62If diff < alpha, then cwnd is incremented by one packet.
63Alpha and beta govern the amount of buffering along the path.
64.Pp
65The implementation was done in a clean-room fashion, and is based on the
66paper referenced in the
67.Sx SEE ALSO
68section below.
69.Sh IMPLEMENTATION NOTES
70The time from the transmission of a marked packet until the receipt of an
71acknowledgement for that packet is measured once per RTT.
72This implementation does not implement Brakmo's and Peterson's original
73duplicate ACK policy since clock ticks in today's machines are not as coarse as
74they were (i.e. 500ms) when Vegas was originally designed.
75Note that modern TCP recovery processes such as fast retransmit and SACK are
76enabled by default in the TCP stack.
77.Sh MIB Variables
78The algorithm exposes the following tunable variables in the
79.Va net.inet.tcp.cc.vegas
80branch of the
81.Xr sysctl 3
82MIB:
83.Bl -tag -width ".Va alpha"
84.It Va alpha
85Query or set the Vegas alpha parameter as a number of buffers on the path.
86When setting alpha, the value must satisfy: 0 < alpha < beta.
87Default is 1.
88.It Va beta
89Query or set the Vegas beta parameter as a number of buffers on the path.
90When setting beta, the value must satisfy: 0 < alpha < beta.
91Default is 3.
92.El
93.Sh SEE ALSO
94.Xr cc_cdg 4 ,
95.Xr cc_chd 4 ,
96.Xr cc_cubic 4 ,
97.Xr cc_dctcp 4 ,
98.Xr cc_hd 4 ,
99.Xr cc_htcp 4 ,
100.Xr cc_newreno 4 ,
101.Xr h_ertt 4 ,
102.Xr mod_cc 4 ,
103.Xr tcp 4 ,
104.Xr khelp 9 ,
105.Xr mod_cc 9
106.Rs
107.%A "L. S. Brakmo"
108.%A "L. L. Peterson"
109.%T "TCP Vegas: end to end congestion avoidance on a global internet"
110.%J "IEEE J. Sel. Areas Commun."
111.%D "October 1995"
112.%V "13"
113.%N "8"
114.%P "1465-1480"
115.Re
116.Sh ACKNOWLEDGEMENTS
117Development and testing of this software were made possible in part by grants
118from the FreeBSD Foundation and Cisco University Research Program Fund at
119Community Foundation Silicon Valley.
120.Sh HISTORY
121The
122.Nm
123congestion control module first appeared in
124.Fx 9.0 .
125.Pp
126The module was first released in 2010 by David Hayes whilst working on the
127NewTCP research project at Swinburne University of Technology's Centre for
128Advanced Internet Architectures, Melbourne, Australia.
129More details are available at:
130.Pp
131http://caia.swin.edu.au/urp/newtcp/
132.Sh AUTHORS
133.An -nosplit
134The
135.Nm
136congestion control module and this manual page were written by
137.An David Hayes Aq Mt david.hayes@ieee.org .
138