xref: /freebsd/share/man/man4/cc_hd.4 (revision aa0a1e58)
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, Melbourne, Australia by David Hayes
7.\" 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 February 15, 2011
33.Dt CC_HD 4
34.Os
35.Sh NAME
36.Nm cc_hd
37.Nd HD Congestion Control Algorithm
38.Sh DESCRIPTION
39The HD congestion control algorithm is an implementation of the Hamilton
40Institute's delay-based congestion control which aims to keep network queuing
41delays below a particular threshold (queue_threshold).
42.Pp
43HD probabilistically reduces the congestion window (cwnd) based on its estimate
44of the network queuing delay.
45The probability of reducing cwnd is zero at hd_qmin or less, rising to a maximum
46at queue_threshold, and then back to zero at the maximum queuing delay.
47.Pp
48Loss-based congestion control algorithms such as NewReno probe for network
49capacity by filling queues until there is a packet loss.
50HD competes with loss-based congestion control algorithms by allowing its
51probability of reducing cwnd to drop from a maximum at queue_threshold to be
52zero at the maximum queuing delay.
53This has been shown to work well when the bottleneck link is highly multiplexed.
54.Sh MIB Variables
55The algorithm exposes the following tunable variables in the
56.Va net.inet.tcp.cc.hd
57branch of the
58.Xr sysctl 3
59MIB:
60.Bl -tag -width ".Va queue_threshold"
61.It Va queue_threshold
62Queueing congestion threshold (qth) in ticks.
63Default is 20.
64.It Va pmax
65Per packet maximum backoff probability as a percentage.
66Default is 5.
67.It Va qmin
68Minimum queuing delay threshold (qmin) in ticks.
69Default is 5.
70.El
71.Sh SEE ALSO
72.Xr cc 4 ,
73.Xr cc_chd 4 ,
74.Xr cc_cubic 4 ,
75.Xr cc_htcp 4 ,
76.Xr cc_newreno 4 ,
77.Xr cc_vegas 4 ,
78.Xr h_ertt 4 ,
79.Xr tcp 4 ,
80.Xr cc 9 ,
81.Xr khelp 9
82.Rs
83.%A "L. Budzisz"
84.%A "R. Stanojevic"
85.%A "R. Shorten"
86.%A "F. Baker"
87.%T "A strategy for fair coexistence of loss and delay-based congestion control algorithms"
88.%J "IEEE Commun. Lett."
89.%D "Jul 2009"
90.%V "13"
91.%N "7"
92.%P "555-557"
93.Re
94.Sh ACKNOWLEDGEMENTS
95Development and testing of this software were made possible in part by grants
96from the FreeBSD Foundation and Cisco University Research Program Fund at
97Community Foundation Silicon Valley.
98.Sh FUTURE WORK
99The Hamilton Institute have recently made some improvements to the algorithm
100implemented by this module and have called it Coexistent-TCP (C-TCP).
101The improvments should be evaluated and potentially incorporated into this
102module.
103.Sh HISTORY
104The
105.Nm
106congestion control module first appeared in
107.Fx 9.0 .
108.Pp
109The module was first released in 2010 by David Hayes whilst working on the
110NewTCP research project at Swinburne University's Centre for Advanced Internet
111Architectures, Melbourne, Australia.
112More details are available at:
113.Pp
114http://caia.swin.edu.au/urp/newtcp/
115.Sh AUTHORS
116.An -nosplit
117The
118.Nm
119congestion control module and this manual page were written by
120.An David Hayes Aq david.hayes@ieee.org .
121