Within the fast-paced world of community infrastructure, few applied sciences have confirmed as transformative as Section Routing over IPv6 (SRv6). What began as a way to simplify service supplier networks and help 5G rollouts has now develop into essential for dealing with right now’s most difficult synthetic intelligence (AI) workloads. This thrilling evolution—from overcoming conventional networking challenges to driving cutting-edge AI networks—showcases not solely the outstanding flexibility of SRv6 but in addition its pivotal position in redefining the way forward for community structure. As we embrace this new frontier, SRv6 stands on the forefront, enabling improvements that may form the best way we design AI infrastructures.
The genesis of SRv6: A quest for community simplification
Since 2012, Cisco has been on the forefront of pioneering Section Routing, serving to pave the best way for SRv6, which started to take form round 2016. This period marked a pivotal second within the business because it acknowledged the pressing want for a extra agile and programmable community infrastructure able to accommodating the calls for of rising applied sciences akin to 5G, Web of Issues (IoT), and cloud companies. The SRv6 community programming mannequin was first launched on the Web Engineering Job Drive (IETF) in March 2017, heralding the onset of an ecosystem that has since expanded quickly throughout numerous industries.
A key driver behind SRv6 was the aspiration to simplify community operations by harnessing the inherent capabilities of IPv6. In distinction to its predecessor, Section Routing Multiprotocol Label Switching (SR-MPLS), which nonetheless relied on the MPLS information airplane, SRv6 sought to function completely inside the IPv6 framework, thereby eliminating the complexities related to multiprotocol environments.
Cisco performed a key position within the early growth of SRv6 by selling its standardization on the IETF. This effort resulted in essential requirements akin to RFC 8402 (Section Routing Structure), RFC 8754 (Section Routing Header), and RFC 8986 (SRv6 Community Programming), which established the inspiration for the expertise. In 2019, Cisco launched the idea of SRv6 uSID (microsegment), enabling large-scale deployments whereas making certain compatibility with older gear.
SRv6 and the 5G revolution
The preliminary driver for SRv6 adoption was clear: The telecommunications business wanted an answer that might meet the stringent necessities of 5G networks. Conventional mobility administration executed by means of GPRS Tunneling Protocol (GTP) created complicated overlay tunneling architectures that didn’t scale to 5G necessities—elevated numbers of related units, ultra-low latency calls for, community slicing capabilities, and cellular edge computing. The third Era Partnership Venture (3GPP) formally initiated a research merchandise titled “Examine on Consumer Airplane Protocol in 5GC” to hunt attainable candidates for the following user-plane protocol, with SRv6 rising as a compelling various.
What made SRv6 significantly enticing for 5G was its means to simplify the community stack whereas enhancing capabilities. By leveraging IPv6’s deal with house to supply community programmability, SRv6 enabled operators to compose information paths within the end-to-end IPv6 layer, integrating site visitors engineering, VPNs, and repair chaining options with out the complexity of sustaining per-session tunnel states. Community assets—even wavelengths in dense wavelength division multiplexing (DWDM) programs—might be represented as IPv6 addresses, permitting management planes to program information paths that met particular utility necessities.
Speedy adoption throughout service supplier networks
Main communications service suppliers (CSPs) have embraced SRv6 and plenty of extra are contemplating doing so.
Determine 1: Throughout the globe, lots of of SRv6 initiatives have been deployed or are within the testing or planning phases
These deployments show the pliability of SRv6 throughout numerous purposes:
- Simplified VPN companies: SRv6 makes it simpler to deploy and handle community companies like L3VPNs, even throughout completely different networks. Solely the entry and exit routers have to help SRv6, whereas the principle routers can simply ahead normal IPv6 site visitors. This streamlines community operations and lowers overhead.
- Service perform chaining (SFC): SRv6 permits community capabilities, like firewalls and cargo balancers, to be included instantly in routing paths. This implies you possibly can handle site visitors with out difficult further protocols.
- Visitors engineering (TE) and quick reroute (FRR): SRv6 provides community operators advantageous management over site visitors routes, serving to to satisfy efficiency targets like low latency or bandwidth ensures.
- Operational simplicity and price discount: Through the use of solely the IPv6 framework, SRv6 minimizes the reliance on numerous overlay protocols, leading to an easier community. This results in simpler troubleshooting and decrease operational prices.
- Enhanced scalability and aggregation: SRv6 makes use of the scalability of IPv6, making it attainable to handle massive networks with fewer prefixes, which simplifies routing and boosts effectivity.
The AI infrastructure problem: A brand new frontier
As SRv6 expertise superior in service supplier networks, a major transformation was additionally happening in information facilities. The speedy progress of AI—and particularly the rise of large-scale mannequin coaching—created networking calls for which are basically completely different from conventional workloads. AI coaching workloads scale to unbelievable ranges, involving 1000’s and even tens of 1000’s of graphics processing models (GPUs) working concurrently. In contrast to conventional information heart site visitors patterns, which encompass numerous and unbiased transactions, AI coaching workloads intensify the long-standing “elephant stream” problem. Whereas elephant flows have existed in massive information shuffles, IP storage, and high-performance computing (HPC), AI coaching creates demanding patterns: 1000’s of tightly synchronized GPUs executing collective communication operations (all-reduce, all-gather) at each coaching step, producing huge, simultaneous information transfers the place any straggler delays the whole cluster.
This synchronized habits creates essential challenges that conventional networking approaches battle to deal with:
- Bursty site visitors and congestion spikes: When 1000’s of GPUs concurrently push information alongside the identical paths, sudden, intense congestion spikes can happen. Whereas Express Congestion Notification (ECN) stays essential for managing congestion reactively, with out proactive site visitors placement these mechanisms might be overwhelmed, doubtlessly inflicting head-of-line blocking that spreads congestion throughout the community.
- The “slowest packet” downside: AI community efficiency is dictated by the slowest packet, not averages. When 1000’s of GPUs anticipate a single straggler packet, even slight latency will increase can considerably influence job completion time (JCT). Each microsecond and each dropped packet issues.
- Scale-across complexity: As AI infrastructure extends past particular person information facilities, organizations face community area fragmentation, state scalability challenges at geographic scale, dynamic WAN situations, and operational complexity spanning a number of protocol domains.
SRv6 in AI: The pure evolution
The networking group acknowledged that the identical rules that made SRv6 profitable in 5G networks—stateless operation, source-driven path management, and unified IPv6-based structure—may deal with AI infrastructure challenges.
Backend GPU material optimization employs numerous congestion administration methods. Adaptive routing and flowlet load balancing are actively deployed at hyperscalers and neoclouds, offering dynamic site visitors distribution primarily based on real-time community situations. SRv6’s uSID gives an alternate strategy by means of deterministic path placement for distant direct reminiscence entry (RDMA) site visitors. Through the use of a deep integration between AI workloads and SRv6, community interface controllers (NICs) can leverage supply routing to carry out stateless, predictable path placement—explicitly distributing site visitors from completely different sources throughout out there paths. This deterministic strategy enhances reactive strategies akin to ECN by enabling proactive site visitors placement that may cut back the frequency and severity of congestion occasions. Moreover, SRv6’s specific path encoding simplifies failure restoration: When congestion or failures come up, new paths might be encoded on the supply with out counting on distributed routing convergence, permitting for speedy site visitors stream changes.
Moreover, within the realm of frontend community unification, AI frontend networks should deal with quite a lot of site visitors sorts, together with massive checkpoint writes to distributed storage, telemetry streams, management airplane messages, and consumer entry. Every of those site visitors sorts has distinctive efficiency necessities. SRv6 gives a unified framework for implementing high quality of service (QoS), safety insurance policies, and site visitors steering throughout each backend and frontend domains. This streamlining eliminates the complexity related to managing completely different coverage frameworks, permitting for larger effectivity in community administration.
Moreover, SRv6 facilitates scale-across structure enablement by eradicating the normal fragmentation between information heart and WAN domains, which results in the creation of unified IPv6-based information planes. Organizations can apply constant insurance policies for managing AI site visitors, whether or not it traverses native materials, frontend networks, or spans huge distances between information facilities. With SRv6, a single phase listing can encode paths from supply GPUs by means of the whole infrastructure to vacation spot GPUs positioned in distant information facilities. In contrast to Useful resource Reservation Protocol Visitors Engineering (RSVP-TE) or Multiprotocol Label Switching Visitors Engineering (MPLS-TE), which rely upon sustaining per-flow state on community units, SRv6 incorporates all routing directions instantly inside packet headers. This strategy eliminates state explosion, making it significantly helpful for scale-across situations.
Various hyperscalers started innovatively utilizing SRv6 of their AI backend networks to supply fine-grained community path management, maximize community utilization, and ship wonderful material resiliency. At Open Supply Summit Europe 2025, Cisco and Microsoft showcased how SRv6 in SONiC allows a variety of information heart use instances together with AI backend.
The trail ahead
The journey of SRv6, from its origins in service supplier networks to its promising position in AI infrastructure, illustrates a basic reality: Sturdy architectural rules transcend particular use instances. The stateless operations, source-driven management, and unified IPv6 framework that simplified 5G networks are the identical rules that allow deterministic efficiency in AI materials and seamless connectivity throughout geographic boundaries.
As AI continues to develop—from single-cluster deployments to large-scale architectures spanning continents—the networking challenges will solely develop. Coaching periods that contain lots of of 1000’s of GPUs distributed throughout a number of information facilities will demand community infrastructure able to sustaining microsecond-level precision on a world scale.
SRv6’s inherent flexibility and extensibility enable it to adapt to those altering wants. Its programmability allows the introduction of latest community capabilities and site visitors engineering capabilities with out requiring basic architectural modifications. As new AI communication patterns emerge, SRv6 supplies a sturdy networking basis to help them.
The expertise that simplified 5G cellular networks, enabled community slicing, and streamlined service supplier operations is now the identical expertise making certain that AI infrastructure can scale with out limits. Since its first demonstrations in 2017, SRv6 has confirmed itself not simply as a networking protocol however as a basic constructing block for the way forward for digital infrastructure. As organizations develop the following technology of AI programs, SRv6 will function a robust but unobtrusive engine, serving to be certain that the community stays an enabler of innovation slightly than a bottleneck. The journey from 5G to AI is just the start; the structure is nicely positioned for no matter comes subsequent.
