Changes in Makefile

031beb4e - sys: Remove $FreeBSD$: one-line sh pattern

Wed, 16 Aug 2023 17:54:58 +0000

sys: Remove $FreeBSD$: one-line sh patternRemove /^\s*#[#!]?\s*\$FreeBSD\$.*$\n/ List of files: /freebsd-14.2/sys/modules/cc/Makefile

be78a311 - tcp: fix build issue for some cc modules

Thu, 13 Jul 2023 16:56:25 +0000

tcp: fix build issue for some cc modulesThe TCP_HHOOK option was moved from opt_inet.h to opt_global.h inhttps://cgit.FreeBSD.org/src/commit/?id=e68b3792440cac248347afe08ba5881a00ba6523The corresponding changes in two Makefiles were missed, which resultedin not building cc_cdg, cc_chd, cc_hd, and cc_vegas anymore.Reported by: void@f-m.fmReviewed by: rrs, rscheffSponsored by: Netflix, Inc.Differential Revision: https://reviews.freebsd.org/D41010 List of files: /freebsd-14.2/sys/modules/cc/Makefile

b8d60729 - tcp: Congestion control cleanup.

Thu, 11 Nov 2021 11:28:18 +0000

tcp: Congestion control cleanup.NOTE: HEADS UP read the note below if your kernel config is not including GENERIC!!This patch does a bit of cleanup on TCP congestion control modules. There were some ratherinteresting surprises that one could get i.e. where you use a socket option to changefrom one CC (say cc_cubic) to another CC (say cc_vegas) and you could in theory geta memory failure and end up on cc_newreno. This is not what one would expect. Thenew code fixes this by requiring a cc_data_sz() function so we can malloc with M_WAITOKand pass in to the init function preallocated memory. The CC init is expected in thiscase *not* to fail but if it does and a module does break the"no fail with memory given" contract we do fall back to the CC that was in place at the time.This also fixes up a set of common newreno utilities that can be shared amongst otherCC modules instead of the other CC modules reaching into newreno and executingwhat they think is a "common and understood" function. Lets put these functions incc.c and that way we have a common place that is easily findable by future developers orbug fixers. This also allows newreno to evolve and grow support for its features i.e. ABEand HYSTART++ without having to dance through hoops for other CC modules, insteadboth newreno and the other modules just call into the common functions if they desirethat behavior or roll there own if that makes more sense.Note: This commit changes the kernel configuration!! If you are not using GENERIC insome form you must add a CC module option (one of CC_NEWRENO, CC_VEGAS, CC_CUBIC,CC_CDG, CC_CHD, CC_DCTCP, CC_HTCP, CC_HD). You can have more than one definedas well if you desire. Note that if you create a kernel configuration that does notdefine a congestion control module and includes INET or INET6 the kernel compile willbreak. Also you need to define a default, generic adds 'options CC_DEFAULT=\"newreno\"but you can specify any string that represents the name of the CC module (same namesthat show up in the CC module list under net.inet.tcp.cc). If you fail to add theoptions CC_DEFAULT in your kernel configuration the kernel build will also break.Reviewed by: Michael TuexenSponsored by: Netflix Inc.RELNOTES:YESDifferential Revision: https://reviews.freebsd.org/D32693 List of files: /freebsd-14.2/sys/modules/cc/Makefile

bd79708d - In the TCP stack, the hhook(9) framework provides hooks for kernel modules

Wed, 12 Oct 2016 02:16:42 +0000

In the TCP stack, the hhook(9) framework provides hooks for kernel modulesto add actions that run when a TCP frame is sent or received on a TCPsession in the ESTABLISHED state. In the base tree, this functionality isonly used for the h_ertt module, which is used by the cc_cdg, cc_chd, cc_hd,and cc_vegas congestion control modules.Presently, we incur overhead to check for hooks each time a TCP frame issent or received on an ESTABLISHED TCP session.This change adds a new compile-time option (TCP_HHOOK) to determine whetherto include the hhook(9) framework for TCP. To retain backwardscompatibility, I added the TCP_HHOOK option to every configuration file thatalready defined "options INET". (Therefore, this patch introduces nofunctional change. In order to see a functional difference, you need tocompile a custom kernel without the TCP_HHOOK option.) This change willallow users to easily exclude this functionality from their kernel, shouldthey wish to do so.Note that any users who use a custom kernel configuration and use one of thecongestion control modules listed above will need to add the TCP_HHOOKoption to their kernel configuration.Reviewed by: rrs, lstewart, hiren (previous version), sjg (makefiles only)Sponsored by: NetflixDifferential Revision: https://reviews.freebsd.org/D8185 List of files: /freebsd-14.2/sys/modules/cc/Makefile

64807b30 - DCTCP (Data Center TCP) implementation.

Mon, 12 Jan 2015 08:33:04 +0000

DCTCP (Data Center TCP) implementation.DCTCP congestion control algorithm aims to maximise throughput and minimiselatency in data center networks by utilising the proportion of ExplicitCongestion Notification (ECN) marked packets received from capable hardware as acongestion signal.Highlights:Implemented as a mod_cc(4) module.ECN (Explicit congestion notification) processing is done differently fromRFC3168.Takes one-sided DCTCP into consideration where only one of the sides is usingDCTCP and other is using standard ECN.IETF draft: http://tools.ietf.org/html/draft-bensley-tcpm-dctcp-00Thesis report by Midori Kato: https://eggert.org/students/kato-thesis.pdfSubmitted by: Midori Kato and Lars Eggert with help and modifications from hirenDifferential Revision: https://reviews.freebsd.org/D604Reviewed by: gnn List of files: /freebsd-14.2/sys/modules/cc/Makefile

92a0637f - Import an implementation of the CAIA Delay-Gradient (CDG) congestion control

Tue, 02 Jul 2013 08:44:56 +0000

Import an implementation of the CAIA Delay-Gradient (CDG) congestion controlalgorithm, which is based on the 2011 v0.1 patch release and described in thepaper "Revisiting TCP Congestion Control using Delay Gradients" by David Hayesand Grenville Armitage. It is implemented as a kernel module compatible with themodular congestion control framework.CDG is a hybrid congestion control algorithm which reacts to both packet lossand inferred queuing delay. It attempts to operate as a delay-based algorithmwhere possible, but utilises heuristics to detect loss-based TCP cross trafficand will compete effectively as required. CDG is therefore incrementallydeployable and suitable for use on shared networks.In collaboration with: David Hayes and Grenville Armitage MFC after: 4 daysSponsored by: Cisco University Research Program and FreeBSD Foundation List of files: /freebsd-14.2/sys/modules/cc/Makefile

0927e1a1 - Import an implementation of the CAIA-Hamilton-Delay (CHD) congestion control

Tue, 01 Feb 2011 07:05:14 +0000

Import an implementation of the CAIA-Hamilton-Delay (CHD) congestion controlalgorithm described in the paper "Improved coexistence and loss tolerance fordelay based TCP congestion control" by Hayes and Armitage. It is implemented asa kernel module compatible with the recently committed modular congestioncontrol framework.CHD enhances the approach taken by the Hamilton-Delay (HD) algorithm to providetolerance to non-congestion related packet loss and improvements to coexistencewith loss-based congestion control algorithms. A key idea in improvingcoexistence with loss-based congestion control algorithms is the use of a shadowwindow, which attempts to track how NewReno's congestion window (cwnd) wouldevolve. At the next packet loss congestion event, CHD uses the shadow window tocorrect cwnd in a way that reduces the amount of unfairness CHD experiences whencompeting with loss-based algorithms.In collaboration with: David Hayes and Grenville Armitage Sponsored by: FreeBSD FoundationReviewed by: bz and others along the wayMFC after: 3 months List of files: /freebsd-14.2/sys/modules/cc/Makefile

ac230a79 - Import a clean-room implementation of the Hamilton-Delay (HD) congestion control

Tue, 01 Feb 2011 06:42:46 +0000

Import a clean-room implementation of the Hamilton-Delay (HD) congestion controlalgorithm based on the paper "A strategy for fair coexistence of loss anddelay-based congestion control algorithms" by Budzisz, Stanojevic, Shorten andBaker. It is implemented as a kernel module compatible with the recentlycommitted modular congestion control framework.HD uses a probabilistic approach to reacting to delay-based congestion. Theprobability of reducing cwnd is zero when the queuing delay is very small,increasing to a maximum at a set threshold, then back down to zero again whenthe queuing delay is high. Normal operation keeps the queuing delay below theset threshold. However, since loss-based congestion control algorithms push thequeuing delay high when probing for bandwidth, having the probability ofreducing cwnd drop back to zero for high delays allows HD to compete withloss-based algorithms.In collaboration with: David Hayes and Grenville Armitage Sponsored by: FreeBSD FoundationReviewed by: bz and others along the wayMFC after: 3 months List of files: /freebsd-14.2/sys/modules/cc/Makefile

1d4ed791 - Import a clean-room implementation of the VEGAS congestion control algorithm

Tue, 01 Feb 2011 06:17:00 +0000

Import a clean-room implementation of the VEGAS congestion control algorithmbased on the paper "TCP Vegas: end to end congestion avoidance on a globalinternet" by Brakmo and Peterson. It is implemented as a kernel modulecompatible with the recently committed modular congestion control framework.VEGAS uses network delay as a congestion indicator and unlike regular loss-basedalgorithms, attempts to keep the network operating with stable queuing delaysand no congestion losses. By keeping network buffers used along the path withina set range, queuing delays are kept low while maintaining high throughput.In collaboration with: David Hayes and Grenville Armitage Sponsored by: FreeBSD FoundationReviewed by: bz and others along the wayMFC after: 3 months List of files: /freebsd-14.2/sys/modules/cc/Makefile

5728a0ea - Import a clean-room implementation of the experimental H-TCP congestion control

Thu, 02 Dec 2010 06:40:21 +0000

Import a clean-room implementation of the experimental H-TCP congestion controlalgorithm based on the Internet-Draft "draft-leith-tcp-htcp-06.txt". It isimplemented as a kernel module compatible with the recently committed modularcongestion control framework.H-TCP was designed to provide increased throughput in fast and long-distancenetworks. It attempts to maintain fairness when competing with legacy NewRenoTCP in lower speed scenarios where NewReno is able to operate adequately. Thepaper "H-TCP: A framework for congestion control in high-speed and long-distancenetworks" provides additional detail.In collaboration with: David Hayes and Grenville Armitage Sponsored by: FreeBSD FoundationReviewed by: rpaulo (older patch from a few weeks ago)MFC after: 3 months List of files: /freebsd-14.2/sys/modules/cc/Makefile

67fef78b - Import a clean-room implementation of the experimental CUBIC congestion control

Thu, 02 Dec 2010 06:05:44 +0000

Import a clean-room implementation of the experimental CUBIC congestion controlalgorithm based on the Internet-Draft "draft-rhee-tcpm-cubic-02.txt". It isimplemented as a kernel module compatible with the recently committed modularcongestion control framework.CUBIC was designed for provide increased throughput in fast and long-distancenetworks. It attempts to maintain fairness when competing with legacy NewRenoTCP in lower speed scenarios where NewReno is able to operate adequately. Thepaper "CUBIC: A New TCP-Friendly High-Speed TCP Variant" provides additionaldetail.In collaboration with: David Hayes and Grenville Armitage Sponsored by: FreeBSD FoundationReviewed by: rpaulo (older patch from a few weeks ago)MFC after: 3 months List of files: /freebsd-14.2/sys/modules/cc/Makefile

ad4e3b96 - Add build infrastructure for the forthcoming CC algorithm modules.

Thu, 02 Dec 2010 03:10:35 +0000

Add build infrastructure for the forthcoming CC algorithm modules.Sponsored by: FreeBSD FoundationSubmitted by: David Hayes MFC after: 3 months List of files: /freebsd-14.2/sys/modules/cc/Makefile