Network Working Group J. Dong, Ed. Internet-Draft Huawei Technologies Intended status: Informational M. McBride, Ed. Expires: 23 April 2026 Futurewei F. Clad, Ed. Cisco Systems Z. Zhang Juniper Networks Y. Zhu China Telecom X. Xu China Mobile R. Pang China Unicom H. Lu Y. Liu Tencent L. Contreras Telefonica M. Durmus Turkcell 20 October 2025 Fast Notification Problem Statement draft-dong-fantel-problem-statement-00 Abstract Modern networks require adaptive traffic manipulation including Traffic Engineering (TE), load balancing, flow control and protection etc. to support applications like AI training and real-time services. A good and timely understanding of network operational status, such as congestion and failures, can help improve utilization, reduce latency, and enable faster response to critical events. This document describes the existing problems and why the IETF may need a new set of fast notification related solutions to support any high- throughput, low-latency and lossless application. Status of This Memo This Internet-Draft is submitted in full conformance with the provisions of BCP 78 and BCP 79. Internet-Drafts are working documents of the Internet Engineering Task Force (IETF). Note that other groups may also distribute working documents as Internet-Drafts. The list of current Internet- Drafts is at https://datatracker.ietf.org/drafts/current/. Dong, Ed., et al. Expires 23 April 2026 [Page 1] Internet-Draft FaNTEL Problem Statement October 2025 Internet-Drafts are draft documents valid for a maximum of six months and may be updated, replaced, or obsoleted by other documents at any time. It is inappropriate to use Internet-Drafts as reference material or to cite them other than as "work in progress." This Internet-Draft will expire on 23 April 2026. Copyright Notice Copyright (c) 2025 IETF Trust and the persons identified as the document authors. All rights reserved. This document is subject to BCP 78 and the IETF Trust's Legal Provisions Relating to IETF Documents (https://trustee.ietf.org/ license-info) in effect on the date of publication of this document. Please review these documents carefully, as they describe your rights and restrictions with respect to this document. Code Components extracted from this document must include Revised BSD License text as described in Section 4.e of the Trust Legal Provisions and are provided without warranty as described in the Revised BSD License. Table of Contents 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 3 1.1. Requirements Language . . . . . . . . . . . . . . . . . . 3 2. Glossary . . . . . . . . . . . . . . . . . . . . . . . . . . 3 3. The Problem . . . . . . . . . . . . . . . . . . . . . . . . . 4 4. Example: AI Training Cluster with Fiber Link Failure . . . . 5 4.1. Limitations of Existing Mechanisms . . . . . . . . . . . 5 4.2. How Fast Notification Helps . . . . . . . . . . . . . . . 6 5. Fast Notification Problem Statement . . . . . . . . . . . . . 7 5.1. Information of Fast Notifications . . . . . . . . . . . . 8 5.2. Recipients of Fast Notifications . . . . . . . . . . . . 8 5.3. Delivery of Fast Notifications . . . . . . . . . . . . . 11 6. Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 7. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 12 8. Security Considerations . . . . . . . . . . . . . . . . . . . 12 9. Acknowledgement . . . . . . . . . . . . . . . . . . . . . . . 13 10. Contributors . . . . . . . . . . . . . . . . . . . . . . . . 13 11. References . . . . . . . . . . . . . . . . . . . . . . . . . 13 11.1. Normative References . . . . . . . . . . . . . . . . . . 13 11.2. Informative References . . . . . . . . . . . . . . . . . 13 Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 14 Dong, Ed., et al. Expires 23 April 2026 [Page 2] Internet-Draft FaNTEL Problem Statement October 2025 1. Introduction Modern network applications, ranging from AI training to large-scale cloud services, require lossless and adaptive networks to ensure reliable, congestion-free data transfer within a single data center or across multiple sites. These workloads demand high throughput, low latency, and minimal packet loss across dynamically shifting traffic patterns. To meet these requirements, networks employ mechanisms such as traffic engineering (TE), load balancing, flow control, and protection. However, existing solutions often face limitations in responsiveness, coverage, and operational complexity, particularly in high-speed, large-scale environments. This document summarizes the limitations of existing mechanisms that prevent rapid notification and action to critical network events, including link or node failures and congestion. This document describes why the IETF may need a new set of fast notification related solutions to support these use cases. [I-D.geng-fantel-fantel-gap-analysis] provides a gap analysis of existing solutions and where they are deficient in supporting high demand services. This document primarily focuses on describing the problem space. 1.1. Requirements Language The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in RFC 2119 [RFC2119]. 2. Glossary FaNTEL: Fast Notification for Traffic Engineering and Load Balancing FRR: Fast Re-Route ECN: Explicit Congestion Notification BFD: Bidirectional Forwarding Detection IOAM: In-situ Operations, Administration, and Maintenance Dong, Ed., et al. Expires 23 April 2026 [Page 3] Internet-Draft FaNTEL Problem Statement October 2025 3. The Problem Current network traffic manipulation mechanisms such as TE, load balancing, flow control, and protection, has deficiencies in providing the low-latency, high-granularity responsiveness needed in modern, dynamic networks, at least in part due to the lack of dynamic network state information. This results in suboptimal performance, low reliability and delayed recovery. FaNTEL is proposed as a set of solutions to address this by enabling fast, real-time, lightweight notifications that enhance the responsiveness for traffic engineering, congestion mitigation, and rapid failure protection. There is a demonstrable need for a standardized framework in IETF to define these fast notification mechanisms, requirements and integration strategies. The following describes a summary of limitations of existing notification solutions: * Slow Reaction: Existing control protocols (e.g., routing protocol, etc.) may be used for dissemination of dynamic network state information, while they usually rely on control plane based hop- by-hop distribution, which causes delay when the recipient is multiple hops away. With modern high-throughput environments (AI/ ML clusters, multi-DC WANs), this delay is often prohibitive. Explicit Congestion Notification (ECN) [RFC3168] needs congestion signals to be sent back to the sender, which can be slow if the source node is far away, and it relies on the source node to react in the transport layer. What is needed is a lightweight signaling method that can provide real-time alerts (e.g., at the level of sub-10 ms) on failures, congestion, or threshold breaches, enabling immediate actions (e.g., in ms to 10s ms ranges) in the network layer. * Coarse-Grained Signals: ECN and similar mechanisms only provide binary or threshold-based feedback, without granularity for rapid, fine-tuned adjustments. This leads to either overreaction or underutilization of available capacity. What would be useful is a set of notifications that aren't just "on-off" state reports but can also convey information like congestion level/utilization information, latency spikes, queue buildup or flow characteristics, so that it can trigger immediate and precise responses like rerouting, rate adjustment, or protection switching for specific flows. * Overhead and Churn: IOAM [RFC9197] and similar tools provide detailed telemetry information, but the collection and feedback loops are controller-centric. They cannot be used to deliver lightweight, real-time alerts for immediate action on specific Dong, Ed., et al. Expires 23 April 2026 [Page 4] Internet-Draft FaNTEL Problem Statement October 2025 network nodes. And carrying dynamic network state information in control protocols (e.g. routing protocols) also increases the overhead and churn of the control plane, which may have negative impact to the core functionality of the protocol. It would be useful to have solutions designed to avoid the overhead and churn introduced by telemetry flooding or route distribution, so it can adapt to large-scale networks and dynamic traffic patterns (e.g. AI workloads, cloud WAN bursts). * Local-Only Decision Making: Current load-balancing, flow-control and fast reroute (FRR) techniques often act on local information and fail to capture downstream or cross- domain network conditions, limiting their effectiveness. The Point of Local Repair (PLR) makes its decision based on its local view of the topology and network status. It does not know about the state of the entire path of the backup route (e.g., if the backup path itself is congested). It would be helpful to send fast notifications to upstream nodes which can perform the action based on the view of regional or global network conditions. * Scalability Challenges: High-volume information or frequent signaling introduces bandwidth and processing overhead. At scale, this becomes a bottleneck rather than a solution. 4. Example: AI Training Cluster with Fiber Link Failure Consider a large-scale AI/ML training job distributed across multiple data centers. These clusters exchange terabits per second of data between GPU nodes, requiring ultra-low latency and high throughput to maintain synchronization. In such environments, a single fiber link failure or severe congestion event can disrupt the entire training run, leading to: * Delays in job completion (hours to days for large models) * Massive energy and compute cost waste due to resynchronization * Degraded convergence accuracy if synchronization windows are missed 4.1. Limitations of Existing Mechanisms Today's mechanisms provide partial solutions but are not fast or precise enough for these scenarios: Dong, Ed., et al. Expires 23 April 2026 [Page 5] Internet-Draft FaNTEL Problem Statement October 2025 * BFD [RFC5880]: Provides fast forwarding path failure detection. It can be used for both link and path failure detection, while it cannot be used to detect link or path congestion, nor can it notify the failure or congestion to other nodes in the network. BFD is preconfigured with periodic message exchange, while fast notifications needs to be event-driven. When the transmit interval is set to a small value (e.g., at the level of ms), frequent BFD message exchange may become a burden to some systems. * FRR [RFC4090][RFC5714]/Route convergence: Without fast notification, the failure detection can take tens of milliseconds, followed by either local repair (FRR) or route convergence. The former lacks of global network situation thus may cause congestion on the backup paths, while the latter may breach strict synchronization deadlines. * ECN: Provides binary congestion feedback to the endpoints, which is insufficient for granular congestion spikes on high-speed links, and the action can be slow. * Telemetry (e.g., IOAM): Offers detailed information, but relies on collection and RTT-based feedback, which delays action. * Receiver/Sender Flow Control: Tied to RTT or packet loss, unsuitable for the bursty nature of AI traffic patterns. In practice, this means that by the time a fiber link failure is detected and recovery mechanisms are invoked, critical GPU synchronization barriers may already be missed, forcing rollbacks or restarts of the training process. 4.2. How Fast Notification Helps Fast notification mechanisms could improve the response to fiber link failures and congestion in AI/ML clusters: * Real-Time Alerts: Nodes adjacent to the failure or congestion could immediately (e.g., at 10 ms level) send lightweight notifications to nodes whose fowarding paths can be affected. * Action-Oriented Response: Upon receiving the notification, routing and load balancing mechanisms could instantly shift traffic to backup paths or alternative DC interconnects. * Granularity: Notifications could carry more detailed information than "link failure/congestion," e.g., indicating specific link utilization, queue buildup or microburst congestion, allowing differentiated responses to different traffic flows. Dong, Ed., et al. Expires 23 April 2026 [Page 6] Internet-Draft FaNTEL Problem Statement October 2025 * Complementary: The fast notification solutions are complementary to BFD or IOAM, it would bridge the time gap between event onset and slower control plane or telemetry-driven responses, and enable network-wide optimization. By deploying fast notifications, large AI/ML workloads can maintain synchronization across data centers even during transient failures or congestion, protecting job completion time and resource utilization. +-------------------------+ +-------------------------+ | Data Center A (GPU) |-------| Data Center B (GPU) | +-------------------------+ +-------------------------+ | | | High-speed Fiber Link | +-----------X (Failure) ------+ | (Failure Event) Figure 1: AI Training Cluster with Fiber Link Failure Existing Approach: * BFD detects failure after tens of ms * FRR causes congestion on backup paths * Reroute/convergence delays impact GPU sync * Result: Training stalls, job wastes compute Fast Notifications Approach: * BFD detects failure after tens of ms * Fast notification alerts upstream nodes of failure or congestion in real time * Regional or global TE steers traffic quickly to link without causing new congestion * Result: Training continues with minimal disruption 5. Fast Notification Problem Statement Dong, Ed., et al. Expires 23 April 2026 [Page 7] Internet-Draft FaNTEL Problem Statement October 2025 5.1. Information of Fast Notifications The information carried in the fast notifications, by the originating node, can be one or multiple of the following: * Failure information: This can include the location of failure, and the type of failure. * Fine-grained Congestion information: This can include link utilization, queue length, or the level of congestion, together with the location where the congestion happens. * Fine-grained Performance information: This can include link or node delay, jitter, packet loss information etc., together with the location where the performance degradation happens. * Path identification information: This can be used to indicate the path along which one service flow is being forwarded. * Flow identification information: This can include either the identification or the 5-tuple of a flow. Other information related to the network status and need to be timely actioned may also be carried in the fast notifications. Thus there is a need to work on the information model of Fast Notifications to better understand what needs to be carried in the notifications. 5.2. Recipients of Fast Notifications Fast notifications may be consumed by two broad forms of recipients: (1) recipient nodes that participate directly in forwarding or signaling, and (2) functions and applications that consume notifications in order to optimize, monitor, or adapt behaviors. Separating these categories clarifies which entities are physical/ logical nodes versus which are higher-level functional consumers. Dong, Ed., et al. Expires 23 April 2026 [Page 8] Internet-Draft FaNTEL Problem Statement October 2025 +==================+======================+=======================+ | Node Type | Role | Example Benefit | +==================+======================+=======================+ | Adjacent Routers | Data-plane neighbors | Enable local repair | | / Switches | that forward packets | (e.g., FRR, ECMP | | | | adjustments) | +------------------+----------------------+-----------------------+ | Non-Adjacent | Remote upstream | Accelerated awareness | | Routers / | forwarding elements | of failure/congestions| | Switches | | on specific nodes | +------------------+----------------------+-----------------------+ | Ingress Routers | Traffic entry points | Re-map affected flows | | | of a network | before forwarding | | | domain | into failed regions | +------------------+----------------------+-----------------------+ | End Hosts / Edge | Optional | Adapt sending rate, | | Nodes | subscribers, policy- | select alternate | | | driven | uplinks | +------------------+----------------------+-----------------------+ | Network Controler| Optional | Accelerated awareness | | / PCE | subscribers, policy- | of failure/congestion | | | driven | for global TE/LB | +------------------+----------------------+-----------------------+ Table 1: Recipient Nodes Dong, Ed., et al. Expires 23 April 2026 [Page 9] Internet-Draft FaNTEL Problem Statement October 2025 +=======================+===============+===========================+ | Function / | Role | Example Benefit | | Application | | | +=======================+===============+===========================+ | Routing Protocols | Control-plane | Accelerated path re- | | (OSPF, IS-IS, BGP) | convergence | computation after failure | +-----------------------+---------------+---------------------------+ | Traffic Engineering | Centralized | Pre-compute new paths | | Controllers (PCE/ | optimization | before congestion | | SDN) | | propagates | +-----------------------+---------------+---------------------------+ | Network Operators | Operational | Faster troubleshooting, | | (NMS/OSS) | visibility | earlier alerting | +-----------------------+---------------+---------------------------+ | Telemetry / | Monitoring | Predictive analytics, ML- | | Analytics Systems | and | based congestion | | | prediction | forecasting | +-----------------------+---------------+---------------------------+ | Applications / | Critical app | AI workloads, financial | | Services | consumers | apps adapt to degraded | | | | links | +-----------------------+---------------+---------------------------+ Table 2: Recipient Functions and Applications Dong, Ed., et al. Expires 23 April 2026 [Page 10] Internet-Draft FaNTEL Problem Statement October 2025 +-----------------------------+ | Application Plane | | - Applications / Services | | - End Hosts / Edge Nodes | +-------------^---------------+ | +-------------|---------------+ | Management Plane | | - Operators (NMS/OSS) | | - Telemetry / Analytics | +-------------^---------------+ | +-------------|---------------+ | Control Plane | | - Routing Protocols | | - TE Controllers (PCE/SDN) | +-------------^---------------+ | +-------------|----------------+ | Data Plane | | - Adjacent Routers/Switches | | - Non-Adjacent Routers | | - Ingress Routers | +------------------------------+ Figure 2: Notification Recipients Across Network Planes As illustrated above, the latency sensitivity of recipients decreases as one moves from the data plane to the application plane. Recipient nodes (e.g., adjacent forwarding elements, ingress routers,etc.) often require near-instantaneous notification, while functions and applications (e.g., routing protocols, analytics, NMS, etc.) may tolerate slightly longer timescales but still benefit from rapid awareness compared to existing mechanisms. The range of recipients of the notification depends on the type of recipients, it also depends on what type of action is required. The mechanism to determine the type and range of the recipients is something needs further consideration. 5.3. Delivery of Fast Notifications Depending on the position and number of the recipient nodes, fast notifications may be sent via one of the following delivery modes: * Unicast directly to the recipient node * Multicast to a group of recipient nodes Dong, Ed., et al. Expires 23 April 2026 [Page 11] Internet-Draft FaNTEL Problem Statement October 2025 * Hop-by-hop to a series of receipt nodes along a specified path * Flooding in a specified range of the network Additionally, recipient nodes or functions may subscribe to specific types of notifications based on their roles or interests. A subscription-based approach enables selective delivery, reduces unnecessary signaling overhead, and ensures that each recipient receives only the information relevant to its function. Mechanisms supporting both delivery and subscription must guarantee timely, reliable, and secure propagation of notifications. Examples: * Adjacent routers subscribing to all local failure notifications * Centralized controllers subscribing only to congestion alerts exceeding defined thresholds * Applications or analytics systems subscribing to performance degradation events affecting specific flows or services The mechanisms to support the above delivery mode needs to make sure the notification is always sent to the targeted recipient noded in a timely manner. It could be based on existing messaging and transport mechanisms, or a new protocol may be introduced. 6. Summary Current network mechanisms were not designed for the responsiveness and scale required by todays' dynamic environments. Techniques such as load balancing, protection switching, and flow control rely on telemetry and feedback loops that are often too slow, too coarse, or too resource-intensive. This results in performance bottlenecks, delayed recovery, and inefficiencies in large-scale AI, cloud, and WAN deployments. A fast notification mechanism could help to address these gaps by providing lightweight, real-time, actionable alerts that complement existing tools and enable faster, more accurate network management decisions. 7. IANA Considerations This document has no IANA actions. 8. Security Considerations Fast notifications, Dong, Ed., et al. Expires 23 April 2026 [Page 12] Internet-Draft FaNTEL Problem Statement October 2025 if not properly authenticated and rate-limited, could be exploited as a vector for Denial-of-Service (DoS) attacks. An attacker able to inject or flood spurious notifications may trigger unnecessary re- convergence, path changes or repeated state updates, overwhelming both recipient nodes and higher-level applications. Implementations must therefore ensure integrity protection, origin authentication, and appropriate rate controls on notification messages. 9. Acknowledgement The authors would like to thank XXX for the valuable comments and discussion. 10. Contributors The following people contributed substantially to the content of this document. Zafar Ali Cisco zali@cisco.com Tianran Zhou Huawei zhoutianran@huawei.com Xuesong Geng Huawei gengxuesong@huawei.com 11. References 11.1. Normative References [RFC2119] Bradner, S., "Key words for use in RFCs to Indicate Requirement Levels", BCP 14, RFC 2119, DOI 10.17487/RFC2119, March 1997, . 11.2. Informative References [I-D.geng-fantel-fantel-gap-analysis] Geng, X., Huo, P., Cheng, W., Li, D., Zhu, Y., and H. Zhengxin, "Gap Analysis of Fast Notification for Traffic Engineering and Load Balancing", Work in Progress, Internet-Draft, draft-geng-fantel-fantel-gap-analysis-01, 7 July 2025, . Dong, Ed., et al. Expires 23 April 2026 [Page 13] Internet-Draft FaNTEL Problem Statement October 2025 [RFC3168] Ramakrishnan, K., Floyd, S., and D. Black, "The Addition of Explicit Congestion Notification (ECN) to IP", RFC 3168, DOI 10.17487/RFC3168, September 2001, . [RFC4090] Pan, P., Ed., Swallow, G., Ed., and A. Atlas, Ed., "Fast Reroute Extensions to RSVP-TE for LSP Tunnels", RFC 4090, DOI 10.17487/RFC4090, May 2005, . [RFC5714] Shand, M. and S. Bryant, "IP Fast Reroute Framework", RFC 5714, DOI 10.17487/RFC5714, January 2010, . [RFC5880] Katz, D. and D. Ward, "Bidirectional Forwarding Detection (BFD)", RFC 5880, DOI 10.17487/RFC5880, June 2010, . [RFC9197] Brockners, F., Ed., Bhandari, S., Ed., and T. Mizrahi, Ed., "Data Fields for In Situ Operations, Administration, and Maintenance (IOAM)", RFC 9197, DOI 10.17487/RFC9197, May 2022, . Authors' Addresses Jie Dong (editor) Huawei Technologies Email: jie.dong@huawei.com Mike McBride (editor) Futurewei Email: mmcbride7@gmail.com Francois Clad (editor) Cisco Systems Email: fclad@cisco.com Jeffrey Zhang Juniper Networks Email: zzhang@juniper.net Yongqing Zhu China Telecom Email: zhuyq8@chinatelecom.cn Dong, Ed., et al. Expires 23 April 2026 [Page 14] Internet-Draft FaNTEL Problem Statement October 2025 Xiaohu Xu China Mobile Email: xuxiaohu_ietf@hotmail.com Ran Pang China Unicom Email: pangran@chinaunicom.cn Hao Lu Tencent Email: vickkylu@tencent.com Yadong Liu Tencent Email: zeepliu@tencent.com Luis M. Contreras Telefonica Email: luismiguel.contrerasmurillo@telefonica.com Mehmet Durmus Turkcell Email: mehmet.durmus@turkcell.com.tr Dong, Ed., et al. Expires 23 April 2026 [Page 15]