xref: /freebsd/share/man/man4/cc_chd.4 (revision 5370c80e0e6aa7aaaf53e62ec4010cee92440a8f)
1.\"
2.\" Copyright (c) 2010-2011 The FreeBSD Foundation
3.\" All rights reserved.
4.\"
5.\" This documentation was written at the Centre for Advanced Internet
6.\" Architectures, Swinburne University of Technology, Melbourne, Australia by
7.\" David Hayes under sponsorship from the FreeBSD Foundation.
8.\"
9.\" Redistribution and use in source and binary forms, with or without
10.\" modification, are permitted provided that the following conditions
11.\" are met:
12.\" 1. Redistributions of source code must retain the above copyright
13.\"    notice, this list of conditions and the following disclaimer.
14.\" 2. Redistributions in binary form must reproduce the above copyright
15.\"    notice, this list of conditions and the following disclaimer in the
16.\"    documentation and/or other materials provided with the distribution.
17.\"
18.\" THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
19.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
20.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
21.\" ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE FOR
22.\" ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
23.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
24.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
25.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
26.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
27.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
28.\" SUCH DAMAGE.
29.\"
30.\" $FreeBSD$
31.\"
32.Dd September 15, 2011
33.Dt CC_CHD 4
34.Os
35.Sh NAME
36.Nm cc_chd
37.Nd CHD Congestion Control Algorithm
38.Sh DESCRIPTION
39CHD enhances the HD algorithm implemented in
40.Xr cc_hd 4 .
41It provides tolerance to non-congestion related packet loss and improvements to
42coexistence with traditional loss-based TCP flows, especially when the
43bottleneck link is lightly multiplexed.
44.Pp
45Like HD, the algorithm aims to keep network queuing delays below a particular
46threshold (queue_threshold) and decides to reduce the congestion window (cwnd)
47probabilistically based on its estimate of the network queuing delay.
48.Pp
49It differs from HD in three key aspects:
50.Bl -bullet
51.It
52The probability of cwnd reduction due to congestion is calculated once per round
53trip time instead of each time an acknowledgement is received as done by
54.Xr cc_hd 4 .
55.It
56Packet losses that occur while the queuing delay is less than queue_threshold
57do not cause cwnd to be reduced.
58.It
59CHD uses a shadow window to help regain lost transmission opportunities when
60competing with loss-based TCP flows.
61.El
62.Sh MIB Variables
63The algorithm exposes the following tunable variables in the
64.Va net.inet.tcp.cc.chd
65branch of the
66.Xr sysctl 3
67MIB:
68.Bl -tag -width ".Va queue_threshold"
69.It Va queue_threshold
70Queueing congestion threshold (qth) in ticks.
71Default is 20.
72.It Va pmax
73Per RTT maximum backoff probability as a percentage.
74Default is 50.
75.It Va qmin
76Minimum queuing delay threshold (qmin) in ticks.
77Default is 5.
78.It Va loss_fair
79If 1, cwnd is adjusted using the shadow window when a congestion
80related loss is detected.
81Default is 1.
82.It Va use_max
83If 1, the maximum RTT seen within the measurement period is used as the basic
84delay measurement for the algorithm, otherwise a sampled RTT measurement
85is used.
86Default is 1.
87.El
88.Sh SEE ALSO
89.Xr cc_cubic 4 ,
90.Xr cc_hd 4 ,
91.Xr cc_htcp 4 ,
92.Xr cc_newreno 4 ,
93.Xr cc_vegas 4 ,
94.Xr h_ertt 4 ,
95.Xr mod_cc 4 ,
96.Xr tcp 4 ,
97.Xr khelp 9 ,
98.Xr mod_cc 9
99.Rs
100.%A "D. A. Hayes"
101.%A "G. Armitage"
102.%T "Improved coexistence and loss tolerance for delay based TCP congestion control"
103.%J "in 35th Annual IEEE Conference on Local Computer Networks"
104.%D "October 2010"
105.%P "24-31"
106.Re
107.Sh ACKNOWLEDGEMENTS
108Development and testing of this software were made possible in part by grants
109from the FreeBSD Foundation and Cisco University Research Program Fund at
110Community Foundation Silicon Valley.
111.Sh HISTORY
112The
113.Nm
114congestion control module first appeared in
115.Fx 9.0 .
116.Pp
117The module was first released in 2010 by David Hayes whilst working on the
118NewTCP research project at Swinburne University of Technology's Centre for
119Advanced Internet Architectures, Melbourne, Australia.
120More details are available at:
121.Pp
122http://caia.swin.edu.au/urp/newtcp/
123.Sh AUTHORS
124.An -nosplit
125The
126.Nm
127congestion control module and this manual page were written by
128.An David Hayes Aq Mt david.hayes@ieee.org .
129