Menu
Home
People
Places
Arts
History
Plants & Animals
Science
Life & Culture
Technology
Reference.org
Network scheduler
open-in-new
<h2 id="terminology-and-responsibilities">Terminology and responsibilities</h2> <p>A network scheduler may have responsibility in implementation of specific <a href="/facts/Network_traffic_control/98KPazFF">network traffic control</a> initiatives. Network traffic control is an umbrella term for all measures aimed at reducing <a href="/facts/Network_congestion/9ohkRMso">network congestion</a>, latency and packet loss. Specifically, <a href="/facts/Active_queue_management/dPk4QqtM">active queue management</a> (AQM) is the selective dropping of queued network packets to achieve the larger goal of preventing excessive network congestion. The scheduler must choose which packets to drop. <a href="/facts/Traffic_shaping/VCF0Gb3b">Traffic shaping</a> smooths the bandwidth requirements of traffic flows by delaying transmission packets when they are queued in bursts. The scheduler decides the timing for the transmitted packets. <a href="/facts/Quality_of_service/joz9VkUm">Quality of service</a> (QoS) is the prioritization of traffic based on service class (<a href="/facts/Differentiated_services/GcqpLBW3">Differentiated services</a>) or reserved connection (<a href="/facts/Integrated_services/HTxRIh7X">Integrated services</a>). </p> <h2 id="algorithms">Algorithms</h2> <p>In the course of time, many network queueing disciplines have been developed. Each of these provides specific reordering or dropping of network packets inside various transmit or receive <a href="/facts/Data_buffer/tVy4j2Dc">buffers</a>.<a class="footnote-ref" id="fnref:1" href="#fn:1"><sup>1</sup></a> Queuing disciplines are commonly used as attempts to compensate for various networking conditions, like reducing the <a href="/facts/Network_latency/JK7jmoJu">latency</a> for certain classes of network packets, and are generally used as part of QoS measures.<a class="footnote-ref" id="fnref:2" href="#fn:2"><sup>2</sup></a><a class="footnote-ref" id="fnref:3" href="#fn:3"><sup>3</sup></a><a class="footnote-ref" id="fnref:4" href="#fn:4"><sup>4</sup></a> </p><p><i>Classful</i> queueing disciplines allow the creation of classes, which work like branches on a tree. Rules can then be set to filter packets into each class. Each class can itself have assigned other classful or <i>classless</i> queueing discipline. Classless queueing disciplines do not allow adding more queueing disciplines to it.<a class="footnote-ref" id="fnref:5" href="#fn:5"><sup>5</sup></a> </p><p>Examples of algorithms suitable for managing network traffic include: </p> Queueing Algorithms<table><tbody><tr><th>Algorithm</th><th>Acronym</th><th>Type</th><th>HW Support</th></tr><tr><td><a href="/facts/Generic_cell_rate_algorithm/dFA1R8bP">Generic cell rate algorithm</a></td><td>GCRA</td><td></td><td></td></tr><tr><td>CHOose and Kill for unresponsive flows</td><td>CHOKe</td><td>Classless</td><td></td></tr><tr><td><a href="/facts/CoDel/kN2yzg4P">Controlled delay</a></td><td>CoDel</td><td>Classless</td><td></td></tr><tr><td><a href="/facts/CAKE_(queue_management_algorithm)/kN2yzg4P">Common Applications Kept Enhanced</a><a class="footnote-ref" id="fnref:6" href="#fn:6"><sup>6</sup></a></td><td>CAKE</td><td></td><td></td></tr><tr><td>Earliest TxTime First</td><td>ETF</td><td>Classless</td><td>Yes</td></tr><tr><td><a href="/facts/FIFO_(computing_and_electronics)/RctvBNgE">First in, first out</a></td><td>FIFO</td><td>Classless</td><td></td></tr><tr><td><a href="/facts/Fair_queuing/hwv3AIud">Fair queuing</a></td><td>FQ</td><td>Classless</td><td></td></tr><tr><td><a href="/facts/FQ-CoDel/kN2yzg4P">Fair Queuing Controlled Delay</a></td><td>FQ-CoDel</td><td>Classless</td><td></td></tr><tr><td>Flow Queuing with Proportional Integral controller Enhanced</td><td>FQ-PIE</td><td>Classless</td><td></td></tr><tr><td>Generalized Random Early Detection</td><td>GRED</td><td>Classless</td><td></td></tr><tr><td>Heavy-Hitter Filter<a class="footnote-ref" id="fnref:7" href="#fn:7"><sup>7</sup></a></td><td>HHF</td><td>Classless</td><td></td></tr><tr><td>Multiqueue Priority</td><td>MQ-PRIO</td><td>Classless</td><td>Yes</td></tr><tr><td>Multiqueue</td><td>MULTIQ</td><td>Classless</td><td>Yes</td></tr><tr><td><a href="/facts/Netem/MXH1hU0g">Network Emulator</a><a class="footnote-ref" id="fnref:8" href="#fn:8"><sup>8</sup></a></td><td>NETEM</td><td>Classless</td><td></td></tr><tr><td>Proportional Integral controller-Enhanced<a class="footnote-ref" id="fnref:9" href="#fn:9"><sup>9</sup></a></td><td>PIE</td><td>Classless</td><td></td></tr><tr><td><a href="/facts/Random_early_detection/h2YyDNQL">Random early detection</a></td><td>RED</td><td>Classless</td><td></td></tr><tr><td><a href="/facts/Stochastic_fair_Blue/9LJRgMYz">Stochastic fair Blue</a></td><td>SFB</td><td>Classless</td><td></td></tr><tr><td>Stochastic Fairness Queueing</td><td>SFQ</td><td>Classless</td><td></td></tr><tr><td><a href="/facts/Token_Bucket_Filter/vqSDnuIm">Token Bucket Filter</a></td><td>TBF</td><td>Classless</td><td></td></tr><tr><td><a href="/facts/Class-based_queueing/fgKb8BP9">Class-based queueing</a></td><td>CBQ</td><td>Classful</td><td></td></tr><tr><td><a href="/facts/Credit-based_fair_queuing/bmEPF0At">Credit-Based Shaper</a></td><td>CBS</td><td>Classful</td><td>Yes</td></tr><tr><td><a href="/facts/Deficit_round_robin/exc9lWIz">Deficit round robin</a><a class="footnote-ref" id="fnref:10" href="#fn:10"><sup>10</sup></a></td><td>DRR</td><td>Classful</td><td></td></tr><tr><td><a href="/facts/Enhanced_Transmission_Selection/zJTJSmS9">Enhanced Transmission Selection</a></td><td>ETS</td><td>Classful</td><td></td></tr><tr><td><a href="/facts/Hierarchical_fair-service_curve/zoUt8uN2">Hierarchical fair-service curve</a></td><td>HFSC</td><td>Classful</td><td></td></tr><tr><td><a href="/facts/Hierarchical_Token_Bucket/vqSDnuIm">Hierarchical Token Bucket</a><a class="footnote-ref" id="fnref:11" href="#fn:11"><sup>11</sup></a></td><td>HTB</td><td>Classful</td><td></td></tr><tr><td>Priority</td><td>PRIO</td><td>Classful</td><td></td></tr><tr><td>Quick Fair Queueing<a class="footnote-ref" id="fnref:12" href="#fn:12"><sup>12</sup></a></td><td>QFQ</td><td>Classful</td><td></td></tr><tr><td>Time Aware Priority Shaper</td><td>TAPRIO</td><td>Classful</td><td>Yes</td></tr></tbody></table> <p>Several of the above have been implemented as <a href="/facts/Linux_kernel_module/UXvHsj2c">Linux kernel modules</a><a class="footnote-ref" id="fnref:13" href="#fn:13"><sup>13</sup></a><a class="footnote-ref" id="fnref:14" href="#fn:14"><sup>14</sup></a> and are <a href="/facts/Free_and_open-source_software/1cHtjLCB">freely available</a>. </p> <h2 id="bufferbloat">Bufferbloat</h2> <p><a href="/facts/Bufferbloat/mbtScFvU">Bufferbloat</a> is a phenomenon in packet-switched networks in which excess <a href="/facts/Buffer_(telecommunication)/tVy4j2Dc">buffering</a> of packets causes high <a href="/facts/Network_latency/JK7jmoJu">latency</a> and <a href="/facts/Packet_delay_variation/eWTDWWYr">packet delay variation</a>. Bufferbloat can be addressed by a network scheduler that strategically discards packets to avoid an unnecessarily high buffering backlog. Examples include <a href="/facts/CoDel/kN2yzg4P">CoDel</a>, <a href="/facts/FQ-CoDel/kN2yzg4P">FQ-CoDel</a> and <a href="/facts/Random_early_detection/h2YyDNQL">random early detection</a>. </p> <h2 id="implementations">Implementations</h2> <h3>Linux kernel</h3> <p>The Linux kernel packet scheduler is an integral part of the <a href="/facts/Linux_kernel/dlkduHuA">Linux kernel</a>'s network stack and manages the transmit and receive <a href="/facts/Ring_buffer/Xu7vpzmP">ring buffers</a> of all NICs. </p><p>The packet scheduler is configured using the utility called <a href="/facts/Tc_(Linux)/MXH1hU0g">tc</a> (short for <i>traffic control</i>). As the default queuing discipline, the packet scheduler uses a FIFO implementation called <i>pfifo_fast</i>,<a class="footnote-ref" id="fnref:15" href="#fn:15"><sup>15</sup></a> although <a href="/facts/Systemd/zls5HoVh">systemd</a> since its version 217 changes the default queuing discipline to fq_codel.<a class="footnote-ref" id="fnref:16" href="#fn:16"><sup>16</sup></a> </p><p>The <a href="/facts/Ifconfig/CwBoHjpf">ifconfig</a> and <a href="/facts/Iproute2/JoyfcKU5">ip</a> utilities enable system administrators to configure the buffer sizes txqueuelen and rxqueuelen for each device separately in terms of number of Ethernet frames regardless of their size. The Linux kernel's network stack contains several other buffers, which are not managed by the network scheduler.<a class="footnote-ref" id="fnref:17" href="#fn:17"><sup>17</sup></a> </p><p><a href="/facts/Berkeley_Packet_Filter/G9AHJjCr">Berkeley Packet Filter</a> filters can be attached to the packet scheduler's classifiers. The <a href="/facts/EBPF/G9AHJjCr">eBPF</a> functionality brought by version 4.1 of the Linux kernel in 2015 extends the classic BPF programmable classifiers to eBPF.<a class="footnote-ref" id="fnref:18" href="#fn:18"><sup>18</sup></a> These can be compiled using the <a href="/facts/LLVM/nPmcspQN">LLVM</a> eBPF backend and loaded into a running kernel using the tc utility.<a class="footnote-ref" id="fnref:19" href="#fn:19"><sup>19</sup></a> </p> <h3>BSD and OpenBSD</h3> <p><a href="/facts/ALTQ/MIBxUVaW">ALTQ</a> is the implementation of a network scheduler for <a href="/facts/BSD/XQKcURrh">BSDs</a>. As of OpenBSD version 5.5 ALTQ was replaced by the HFSC scheduler. </p> <h3>Cell-Free Network Scheduling</h3> <p>Schedulers in communication networks manage resource allocation, including packet prioritization, timing, and resource distribution. Advanced implementations increasingly leverage artificial intelligence to address the complexities of modern network configurations. For instance, a supervised neural network (NN)-based scheduler has been introduced in cell-free networks to efficiently handle interactions between multiple radio units (RUs) and user equipment (UEs). This approach reduces computational complexity while optimizing latency, throughput, and resource allocation, making it a promising solution for beyond-5G networks. <a class="footnote-ref" id="fnref:20" href="#fn:20"><sup>20</sup></a> </p> <h2 id="see-also">See also</h2> <ul><li><a href="/facts/Queueing_theory/8NDl56EM">Queueing theory</a></li> <li><a href="/facts/Statistical_time-division_multiplexing/rLGcaGHV">Statistical time-division multiplexing</a></li> <li><a href="/facts/Type_of_service/vDrH66oL">Type of service</a></li></ul> <h2 id="notes">Notes</h2> <h2 id="references">References</h2> <ol> <li id="fn:1"><p>"Traffic Control HOWTO: Classless Queuing Disciplines (qdiscs)". tldp.org. Retrieved November 24, 2013. <a href="http://www.tldp.org/HOWTO/Traffic-Control-HOWTO/classless-qdiscs.html" target="_blank">http://www.tldp.org/HOWTO/Traffic-Control-HOWTO/classless-qdiscs.html</a> <a href="#fnref:1" class="footnote-back-ref">↩</a></p></li> <li id="fn:2"><p>"Traffic Control HOWTO: Components of Linux Traffic Control". tldp.org. Retrieved November 24, 2013. <a href="http://www.tldp.org/HOWTO/Traffic-Control-HOWTO/components.html" target="_blank">http://www.tldp.org/HOWTO/Traffic-Control-HOWTO/components.html</a> <a href="#fnref:2" class="footnote-back-ref">↩</a></p></li> <li id="fn:3"><p>"Traffic Control HOWTO: Traditional Elements of Traffic Control". tldp.org. Retrieved November 24, 2013. <a href="http://www.tldp.org/HOWTO/Traffic-Control-HOWTO/elements.html" target="_blank">http://www.tldp.org/HOWTO/Traffic-Control-HOWTO/elements.html</a> <a href="#fnref:3" class="footnote-back-ref">↩</a></p></li> <li id="fn:4"><p>"Queuing Disciplines: Order of Packet Transmission and Dropping" (PDF). tau.ac.il. October 25, 2006. Retrieved March 18, 2014. <a href="http://www.eng.tau.ac.il/~netlab/resources/booklet/lab9.pdf" target="_blank">http://www.eng.tau.ac.il/~netlab/resources/booklet/lab9.pdf</a> <a href="#fnref:4" class="footnote-back-ref">↩</a></p></li> <li id="fn:5"><p>"Advanced traffic control - ArchWiki". wiki.archlinux.org. Retrieved 2023-09-11. <a href="https://wiki.archlinux.org/title/advanced_traffic_control" target="_blank">https://wiki.archlinux.org/title/advanced_traffic_control</a> <a href="#fnref:5" class="footnote-back-ref">↩</a></p></li> <li id="fn:6"><p>"Let them run CAKE". LWN.net. <a href="https://lwn.net/Articles/758353/" target="_blank">https://lwn.net/Articles/758353/</a> <a href="#fnref:6" class="footnote-back-ref">↩</a></p></li> <li id="fn:7"><p>"Heavy-Hitter Filter qdisc". kernel.org. <a href="https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=10239edf86f137ce4c39b62ea9575e8053c549a0" target="_blank">https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=10239edf86f137ce4c39b62ea9575e8053c549a0</a> <a href="#fnref:7" class="footnote-back-ref">↩</a></p></li> <li id="fn:8"><p>"Network emulator Linux kernel network scheduler module". kernel.org. Retrieved 2013-09-07. <a href="https://git.kernel.org/cgit/linux/kernel/git/stable/linux-stable.git/tree/net/sched/sch_netem.c" target="_blank">https://git.kernel.org/cgit/linux/kernel/git/stable/linux-stable.git/tree/net/sched/sch_netem.c</a> <a href="#fnref:8" class="footnote-back-ref">↩</a></p></li> <li id="fn:9"><p>"Proportional Integral controller Enhanced (PIE)". kernel.org. <a href="https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=d4b36210c2e6ecef0ce52fb6c18c51144f5c2d88" target="_blank">https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=d4b36210c2e6ecef0ce52fb6c18c51144f5c2d88</a> <a href="#fnref:9" class="footnote-back-ref">↩</a></p></li> <li id="fn:10"><p>"DRR Linux kernel network scheduler module". kernel.org. Retrieved 2013-09-07. <a href="https://git.kernel.org/cgit/linux/kernel/git/stable/linux-stable.git/tree/net/sched/sch_drr.c" target="_blank">https://git.kernel.org/cgit/linux/kernel/git/stable/linux-stable.git/tree/net/sched/sch_drr.c</a> <a href="#fnref:10" class="footnote-back-ref">↩</a></p></li> <li id="fn:11"><p>"HTB Linux kernel network scheduler module". kernel.org. Retrieved 2013-09-07. <a href="https://git.kernel.org/cgit/linux/kernel/git/stable/linux-stable.git/tree/net/sched/sch_htb.c" target="_blank">https://git.kernel.org/cgit/linux/kernel/git/stable/linux-stable.git/tree/net/sched/sch_htb.c</a> <a href="#fnref:11" class="footnote-back-ref">↩</a></p></li> <li id="fn:12"><p>"QFQ Linux kernel network scheduler module". kernel.org. Retrieved 2013-09-07. <a href="https://git.kernel.org/cgit/linux/kernel/git/stable/linux-stable.git/tree/net/sched/sch_qfq.c" target="_blank">https://git.kernel.org/cgit/linux/kernel/git/stable/linux-stable.git/tree/net/sched/sch_qfq.c</a> <a href="#fnref:12" class="footnote-back-ref">↩</a></p></li> <li id="fn:13"><p>"The Linux kernel network scheduler". kernel.org. 2012-12-26. Retrieved 2013-09-07. <a href="https://git.kernel.org/cgit/linux/kernel/git/stable/linux-stable.git/tree/net/sched" target="_blank">https://git.kernel.org/cgit/linux/kernel/git/stable/linux-stable.git/tree/net/sched</a> <a href="#fnref:13" class="footnote-back-ref">↩</a></p></li> <li id="fn:14"><p>"tc(8) - Linux manual page". man7.org. Retrieved 2023-09-11. <a href="https://man7.org/linux/man-pages/man8/tc.8.html" target="_blank">https://man7.org/linux/man-pages/man8/tc.8.html</a> <a href="#fnref:14" class="footnote-back-ref">↩</a></p></li> <li id="fn:15"><p>"Linux Advanced Routing and Traffic Control HOWTO, Section 9.2.1. pfifo_fast". lartc.org. 2012-05-19. Retrieved 2014-09-19. <a href="http://www.lartc.org/howto/lartc.qdisc.classless.html" target="_blank">http://www.lartc.org/howto/lartc.qdisc.classless.html</a> <a href="#fnref:15" class="footnote-back-ref">↩</a></p></li> <li id="fn:16"><p>"systemd System and Service Manager: NEWS file". freedesktop.org. 2015-05-22. Retrieved 2015-06-09. <a href="http://cgit.freedesktop.org/systemd/systemd/tree/NEWS" target="_blank">http://cgit.freedesktop.org/systemd/systemd/tree/NEWS</a> <a href="#fnref:16" class="footnote-back-ref">↩</a></p></li> <li id="fn:17"><p>The overall size of all buffers has been the point of critique by the Bufferbloat project, which provided a partial solution with CoDel that has been primarily tested in OpenWrt. <a href="/wiki/Bufferbloat" target="_blank">/wiki/Bufferbloat</a> <a href="#fnref:17" class="footnote-back-ref">↩</a></p></li> <li id="fn:18"><p>"Linux kernel 4.1, Section 11. Networking". kernelnewbies.org. 2015-06-21. <a href="http://kernelnewbies.org/Linux_4.1#head-c64a7aa1ccb73618b4a7b5f3bef64ff435738098" target="_blank">http://kernelnewbies.org/Linux_4.1#head-c64a7aa1ccb73618b4a7b5f3bef64ff435738098</a> <a href="#fnref:18" class="footnote-back-ref">↩</a></p></li> <li id="fn:19"><p>"BPF and XDP Reference Guide". Cilium documentation web site. <a href="https://cilium.readthedocs.io/en/latest/bpf/" target="_blank">https://cilium.readthedocs.io/en/latest/bpf/</a> <a href="#fnref:19" class="footnote-back-ref">↩</a></p></li> <li id="fn:20"><p>Huleihel, Yara; Maman, Gil; Hadad, Zion; Shasha, Eli; Permuter, Haim H. (2025). "Data-driven cell-free scheduler". Ad Hoc Networks. 169. Elsevier: 103738. doi:10.1016/j.adhoc.2025.103738. <a href="/wiki/Doi_(identifier)" target="_blank">/wiki/Doi_(identifier)</a> <a href="#fnref:20" class="footnote-back-ref">↩</a></p></li> </ol>