Multi-core network packet steering: Difference between revisions

Revision as of 08:28, 11 July 2025

Latest revision as of 20:05, 8 August 2025

(15 intermediate revisions by 8 users not shown)

Line 1:

{{Short description|Network packet distribution with multiple cores}}

[[Network packet]] steering of transmitting and receiving traffic for [[Multi-core_processor|multi-core architectures]] is needed in modern network computing environment, especially in [[Data_center|data centers]], where the high bandwidth and heavy loads would easily congestion a single core's [[Queueing theory|queue]].<ref name="RSS++">{{Cite journal |last=Barbette |first=Tom |last2=Katsikas |first2=Georgios P. |last3=Maguire |first3=Gerald Q. |last4=Kostić |first4=Dejan |date=2019-12-03 |title=RSS++: load and state-aware receive side scaling |url=https://dl.acm.org/doi/10.1145/3359989.3365412 |journal=Proceedings of the 15th International Conference on Emerging Networking Experiments And Technologies |series=CoNEXT '19 |___location=New York, NY, USA |publisher=Association for Computing Machinery |doi=10.1145/3359989.3365412 |isbn=978-1-4503-6998-5}}</ref>

{{copyedit|reason=an encylopedic tone in the lead section|date=July 2025}}

[[Network packet]] steering of transmittingtransmitted and receivingreceived traffic for [[Multi-core_processor|multi-core architectures]] is needed in modern network computing environment, especially in [[Data_center|data centers]], where the high bandwidth and heavy loads would easily congestion a single core's [[Queueing theory|queue]].<ref name="RSS++">{{Cite journalbook |lastlast1=Barbette |firstfirst1=Tom |last2=Katsikas |first2=Georgios P. |last3=Maguire |first3=Gerald Q. |last4=Kostić |first4=Dejan |date=2019-12-03 |titlechapter=RSS++: loadLoad and state-aware receive side scaling |urldate=https://dl.acm.org/doi/10.1145/3359989.33654122019-12-03 |journaltitle=Proceedings of the 15th International Conference on Emerging Networking Experiments Andand Technologies |serieschapter-url=CoNEXThttps://dl.acm.org/doi/10.1145/3359989.3365412 '19|pages=318–333 |___location=New York, NY, USA |publisher=Association for Computing Machinery |doi=10.1145/3359989.3365412 |hdl=2078.1/262641 |isbn=978-1-4503-6998-5 }}</ref>

[[File:Simple NIC and cores architecture.png|thumb|upright=1.7|Simple graph showing the path receiving packets need to travel to reach the cores' queues]]

For this reason many techniques, both in hardware and in software, are leveraged in order to distribute the incoming load of packets across the cores of the [[Central processing unit|processor]].

ForOn receivingthe traffic-receiving side, the most notable techniques seenpresented in this article are: RSS, aRFS, RPS and RFS.

While forFor transmission, XPSwe will befocus explainedon XPS.<ref name="General intro">{{Citation |last=Madden |first=Michael M. |title=Challenges Using the Linux Network Stack for Real-Time Communication |date=2019-01-06 |work=AIAA Scitech 2019 Forum |url=https://arc.aiaa.org/doi/10.2514/6.2019-0503 |access-date=2025-07-10 |series=AIAA SciTech Forum |publisher=American Institute of Aeronautics and Astronautics |doi=10.2514/6.2019-0503 |pages=99–11 |isbn=978-111-62410-578-4 |url-access=subscription }}</ref><ref>{{Cite web |last=Herbert |first=Tom |date=2025-02-24 |title=The alphabet soup of receive packet steering: RSS, RPS, RFS, and aRFS |url=https://medium.com/@tom_84912/the-alphabet-soup-of-receive-packet-steering-rss-rps-rfs-and-arfs-c84347156d68 |access-date=2025-07-10 |website=Medium |language=en}}</ref><br>

As shown by the figure beside, packets coming into the [[Network_interface_controller|network interface card (NIC)]] are processed and loaded to the receiving queues managed by the cores (which are usually implemented as [[Circular buffer|ring buffers]] within the [[User space and kernel space|kernel space]]).

The main objective is being able to leverage all the cores available within the [[Central processing unit|CPU]] to process incoming packets, while also improving performances like [[Latency (engineering)|latency]] and [[Network throughput|throughput]].<ref name="RSS kernel linux docs">{{Cite web|title=RSS kernel linux docs|url=https://www.kernel.org/doc/html/v5.1/networking/scaling.html#rss-receive-side-scaling|access-date=2025-07-08|website=kernel.org|publisher=The Linux Kernel documentation|language=en-US}}</ref><ref name="RSS overview by microsoft">{{Cite web|title=RSS overview by microsoft|url=https://learn.microsoft.com/en-us/windows-hardware/drivers/network/introduction-to-receive-side-scaling|access-date=2025-07-08|website=learn.microsoft.com|language=en-US}}</ref><ref>{{Cite journal |lastlast1=Wu |firstfirst1=Wenji |last2=DeMar |first2=Phil |last3=Crawford |first3=Matt |date=2011-02-01 |title=Why Can Some Advanced Ethernet NICs Cause Packet Reordering? |url=https://ieeexplore.ieee.org/document/5673999/ |journal=IEEE Communications Letters |volume=15 |issue=2 |pages=253–255 |doi=10.1109/LCOMM.2011.122010.102022 |arxiv=1106.0443 |bibcode=2011IComL..15..253W |issn=1558-2558}}</ref>

== Hardware techniques ==

Hardware accelerated techniques like RSS and aRFS are used to route and load balance incoming [[Network_packet|packets]] across the multiple cores' queues of a processor.<ref name="RSS++" /><br>

Those hardware supported methods achieve extremely low latencies and reduce the load on the CPU, as compared to the software based ones. However they require a specialized hardware integrated within the [[Network_interface_controller|network interface controller]] (which, for example, is usually available on more advanced cards, like the [[Data_processing_unit|SmartNIC]]).<ref name="aRFS by redhat">{{Cite web|title=aRFS by redhat|url=https://docs.redhat.com/en/documentation/red_hat_enterprise_linux/6/html/performance_tuning_guide/network-acc-rfs|access-date=2025-07-08|website=docs.redhat.com|publisher=Red Hat Documentation|language=en-US}}</ref><ref name="aRFS by nvidea">{{Cite web|title=aRFS by nvidea|url=https://docs.nvidia.com/networking/display/mlnxofedv23070512/flow+steering#src-2396583156_safe-id-Rmxvd1N0ZWVyaW5nLUFjY2VsZXJhdGVkUmVjZWl2ZUZsb3dTdGVlcmluZyhhUkZTKQ|access-date=2025-07-08|website=docs.nvidia.com|publisher=NVIDIA Documentation Hub|language=en-US}}</ref>

=== RSS ===

Line 22 ⟶ 25:

[[File:ARFS architecture.png|upright=1.7|thumb|Simple view of the accelerated receive flow steering architecture]]

Accelerated Receive Flow Steering (aRFS) is another hardware supported technique, born with the idea of leveraging [[Locality of reference|cache locality]] to improve performances by routing incoming packet flows to specific cores.

Differently from RSS which is a fully hardware independent hardware implementation, aRFS needs to interface with the software (the [[Kernel (operating system)|kernel]]) to properly function.<ref>{{Cite web|title=aRFS kernel linux docs|url=https://www.kernel.org/doc/html/v5.1/networking/scaling.html#accelerated-rfs|access-date=2025-07-08|website=kernel.org|publisher=The Linux Kernel documentation|language=en-US}}</ref><br>

RSS simply load balance incoming traffic across the cores; however if a packet flow is directed to the ''core i'' (as a result of the hash function) while the application needing the received packet is running on ''core j'', many cache misses could be avoided by simply forcing ''i=j'', so that packets are received exactly where they are needed and consumed.<ref name="aRFS by nvidea" /><br>

To do this aRFS doesn't forward packets directly from the result of the hash function, but using a configurable routing table (which can be filled and updated for instance by the [[Scheduling (computing)|scheduler]] through an [[API]]) packet flows can be steered to the specific consuming core.<ref name="aRFS by nvidea" /><ref name="aRFS by redhat" />

Line 28 ⟶ 31:

== Software techniques ==

Software techniques like RPS and RFS employ one of the CPU cores to steer incoming packets across the other cores of the processor. This comes at the cost of introducing additional [[Inter-processor interrupt|inter-processor interrupts (IPIs)]]; however the number of hardware interrupts will not increase and potentially, by employing an [[Interrupt coalescing|interrupt aggregation]] technique, it could even be reduced.<ref name="RPS kernel linux docs">{{Cite web|title=RPS kernel linux docs|url=https://www.kernel.org/doc/html/v5.1/networking/scaling.html#rps-receive-packet-steering|access-date=2025-07-08|website=kernel.org|publisher=The Linux Kernel documentation|language=en-US}}</ref><br>

The benefits of a software solutions is the ease in implementation, without having to change any component (like the [[Network_interface_controller|NIC]]) of the currently used architecture, but by simply deploying the proper [[Loadable kernel module|kernel module]]. This benefit can be crucial especially in cases where the server machine can't be customized or accessed (like in [[Cloud computing#Infrastructure as a service (IaaS)|cloud computing]] environment), even if the network performances could be reduced as compared the hardware supported ones.<ref name="RPS linux news (LWM)">{{Cite web|last1=Corbet |first1=Jonathan |title=RPS linux news (LWM)|url=https://lwn.net/Articles/362339/|access-date=2025-07-08|website=lwn.net|date=17 November 2009 |publisher=Linux Weekly News|language=en-US}}</ref><ref name="RPS by redhat">{{Cite web|title=RPS by redhat|url=https://docs.redhat.com/en/documentation/red_hat_enterprise_linux/6/html/performance_tuning_guide/network-rps|access-date=2025-07-08|website=docs.redhat.com|publisher=Red Hat Documentation|language=en-US}}</ref><ref name="RFS by nvidea" />

=== RPS ===

Line 46 ⟶ 49:

=== XPS (in transmission) ===

Transmit Packet Steering (XPS) differentlyis froma alltransmission protocol, as opposed to the prevoiusothers protocolsthat exposed,have isbeen usedmentioned inso transmissionfar. When packets need to be loaded on one of the transmission queues exposed by the NIC, there are again many possible optimization that could be done.<ref>{{Cite web|title=XPS linux news (LWM)|url=https://lwn.net/Articles/412062/|access-date=2025-07-08|website=lwn.net|publisher=Linux Weekly News|language=en-US}}</ref><br>

For instance if multiple transmission queues are assigned to a single core, an hash function could be used to load balance outgoing packets across the queues (similarly to how RPS does in reception).

Moreover in order to improve cache locality and hit-rate (similarly to how RFS does), XPS ensures that applications producing the outgoing traffic and running in ''core i'' will favor the transmitting queues associated with the same ''core i''. This reduces the inter-core communication and cache coherency protocols overheads, resulting in better performances in heavy load environments.<ref>{{Cite web|title=XPS intel overview|url=https://www.intel.com/content/www/us/en/docs/programmable/683517/21-4/transmit-packet-steering-xps.html|access-date=2025-07-08|website=intel.com|publisher=Intel corp|language=en-US}}</ref><ref>{{Cite web|title=XPS kernel linux docs|url=https://www.kernel.org/doc/html/v5.1/networking/scaling.html#xps-transmit-packet-steering|access-date=2025-07-08|website=kernel.org|publisher=The Linux Kernel documentation|language=en-US}}</ref><ref name="General intro" />

Line 65 ⟶ 68:

== Further readings ==

* {{Cite journalbook |lastlast1=Enberg |firstfirst1=Pekka |last2=Rao |first2=Ashwin |last3=Tarkoma |first3=Sasu |date=2019-12-09 |titlechapter=Partition-Aware Packet Steering Using XDP and eBPF for Improving Application-Level Parallelism |urldate=https://dl.acm.org/doi/10.1145/3359993.33667662019-12-09 |journaltitle=Proceedings of the 1st ACM CoNEXT Workshop on Emerging in-Network Computing Paradigms |serieschapter-url=ENCPhttps://dl.acm.org/doi/10.1145/3359993.3366766 '19|pages=27–33 |___location=New York, NY, USA |publisher=Association for Computing Machinery |doi=10.1145/3359993.3366766 |hdl=10138/326309 |isbn=978-1-4503-7000-4}}

* {{Cite journalbook |lastlast1=Helbig |firstfirst1=Maike |last2=Kim |first2=Younghoon |date=2025-01-01 |titlechapter=IAPS: Decreasing Software-Based Packet Steering Overhead Through Interrupt Reduction |urldate=https://ieeexplore.ieee.org/document/10993154/2025-01-01 |journalpages=127–130 |title=2025 International Conference on Information Networking (ICOIN) |doi=10.1109/ICOIN63865.2025.10993154 |isbn=979-8-3315-0694-0 }}

* {{Cite journalbook |lastlast1=Kumar |firstfirst1=Ashwin |last2=Katkam |first2=Rajneesh |last3=Chaudhary |first3=Pranav |last4=Naik |first4=Priyanka |last5=Vutukuru |first5=Mythili |date=2024-05-01 |titlechapter=AppSteer: Framework for Improving Multicore Scalability of Network Functions via Application-aware Packet Steering |urldate=https://ieeexplore.ieee.org/document/10701416/2024-05-01 |journalpages=18–27 |title=2024 IEEE 24th International Symposium on Cluster, Cloud and Internet Computing (CCGrid) |doi=10.1109/CCGrid59990.2024.00012 |isbn=979-8-3503-9566-2 }}

* {{Cite journal |lastlast1=Tyunyayev |firstfirst1=Nikita |last2=Delzotti |first2=Clément |last3=Eran |first3=Haggai |last4=Barbette |first4=Tom |date=2025-06-09 |title=ASNI: Redefining the Interface Between SmartNICs and Applications |url=https://dl.acm.org/doi/10.1145/3730966 |journal=Proc. Proceedings of the ACM Netw.on Networking|volume=3 |issue=CoNEXT2 |pages=1–22 |doi=10.1145/3730966|url-access=subscription }}

== External links ==

Line 75 ⟶ 78:

* {{YouTube|id=dANekxZZems|title=Offloading Network Traffic Classification to Hardware}}

* [https://fast.dpdk.org/events/slides/DPDK-2017-04-VNF.pdf Packet Steering for Multicore Virtual Network Applications over DPDK]

{{Parallel computing|state=collapsed}}

{{Operating system|state=collapsed}}

{{Basic computer components|state=collapsed}}

[[Category:Networking hardware]]

[[Category:Network flow problem]]

[[Category:Manycore processors]]

[[Category:Load balancing (computing)]]

[[Category:Cache (computing)]]