The proposed Multi-Path Multi-Level Feedback Queueing (MP-MLFQ) leverages the spatial diversity and regularity of DCNs to realize a scheduler with numerous logical priority levels while occupying as low as 2 physical priority queues within network switches.
Evaluation on representative workloads demonstrates that P2CS achieves performance comparable to in-network mechanisms while significantly reducing complexity and cost, and requires minimal software changes making it readily deployable in today's datacenter infrastructure.
Ali Munir, Xiaolin Pang, Junyi Zhang· Proceedings of the ACM SIGCO...· 0 citations
As Data Center Networks (DCNs) continue to scale, the limitations of traditional centralized Software-Defined Networking (SDN) architectures become increasingly apparent, as they fail to meet the stringent demands for low latency and quality of service (QoS). In this paper, we propose an adaptive traffic-aware load balancing mechanism (ATL), a telemetrydriven in-switch scheme implemented on the programmable data plane (PDP) using P4 and driven by In-band Network Telemetry (INT). The current traffic regime is inferred by analyzing the remaining capacity (RC) of each link and its short-term variation (VAR), and adopts a dual-optimization strategy: (i) separating elephant flows (large flows) and mice flows (small flows) onto disjoint path sets to mitigate head-of-line blocking and packet reordering; (ii) dynamically adjusting the flowlet threshold $\left(F^{*}\right)$ to strike a balance between maximizing parallelism and ensuring in-order delivery. We prototyped and evaluated ATL in a Mininet/BMv2 environment, targeting bandwidth-constrained scenarios representative of IoT and edge deployments. The results show that, compared to existing methods such as ECMP, HULA, AWCMP, and APS, ATL consistently reduces both the average and 99th-percentile AFCT while achieving superior elephant-flow throughput, with notable improvements in traffic stability and packet-ordering preservation. Furthermore, ATL demonstrates a favorable cost-performance trade-off ratio of 1:0.99, confirming its efficiency and feasibility within the resource-constrained P4 switch environment.
Optimizing burst-heavy datacenter workloads necessitates finegrained network control and visibility. We introduce CSIG, a protocol that delivers precise, multi-bit bottleneck congestion signals via a fixed-length Ethernet header. The architecture captures μsgranularity switch metrics, such as available bandwidth, and signals them to end-hosts using in-band, line-rate operations. We propose Fast Ramp-Up, a congestion control primitive that leverages these bottleneck signals to reduce median RPC latency by 20% and unclaimed bandwidth by 60% in production. Beyond transport-level performance, CSIG enables flow-aware observability by embedding μs-scale metrics into every packet, allowing individual application transfers to pinpoint their bottleneck location, such as the topology tier limiting their performance. CSIG thus transforms network telemetry from post-hoc correlation into a real time, context-aware capability. We demonstrate CSIG's broad deployability by validating it across five generations of commodity switch hardware (up to 102.4 Tbps), four NIC generations, and five transport stacks. Our design proves that a streamlined Layer 2 approach, focusing exclusively on the principal path bottleneck, provides transport-agnostic gains without requiring forklift hardware upgrades.
Abhiram Ravi, N. Dukkipati, Weiwu Pang et al.· 0 citations
Protocols such as L4S for low latency network services have attracted growing interest from major industry stakeholders such as Comcast, Apple, T-Mobile, and NVIDIA. However, L4S requires isolation between L4S flows and classic flows in order to maintain its low latency benefits and safe coexistence. The L4S architecture uses a DualPI2 AQM mechanism to provide this isolation when the bottleneck occurs at the home access link. In practice, however, bottlenecks may also occur at other locations in the network, such as peering points, ingress to wide area networks, or occasionally congested links in the core, where deploying DualPI2 AQM is not feasible. Without a solution to this problem, L4S may struggle to gain deployment, since its benefits may remain limited without end-to-end support. To address this challenge, we propose a deployment strategy that reduces the need to upgrade expensive core routers by using existing networking mechanisms such as BGP communities, SRv6, and priority queues with rate caps. We demonstrate the feasibility of this approach through large scale experiments on the FABRIC testbed. Our results demonstrate a practical deployment strategy for extending low latency service across the Internet, even across independently administered networks.
Harkirat Singh, Fatih Berkay Sarpkaya, Hakan Gulec et al.· 0 citations
In data centers, large-scale many-to-one traffic can rapidly exhaust switch buffers and trigger priority-based flow control (PFC) pause, resulting in increased flow completion time (FCT) for uncongested flows. To address this issue, we propose an innovative switch-side fast and accurate flow control (FAFC) scheme. By differentially allocating pause time for each port during congestion, FAFC can minimize the performance loss for uncongested flows. Furthermore, FAFC is also coupled with an effective queue length prediction algorithm to enable proactive and reliable estimation of the congestion level. Extensive system-level simulations demonstrate that FAFC can flexibly allocate pause times across congested ports, which are not only compatible with existing PFC but also do not require per-flow states. We implemented FAFC in P4 programmable switches, showing it as lightweight flow control method that is portable for implementation in hardware. Remarkably, our large-scale simulations illustrate that compared to traditional PFC, FAFC improves the average FCT slowdown and 95% FCT slowdown by 10.6% and 23.3%, respectively, under Hadoop workload when performing HPCC congestion control.
Chengdi Lu, Yuang Chen, Fangyu Zhang et al.· IEEE Transactions on Network...· 0 citations
The rapid evolution of 5G and emerging 6G networks requires optical access systems to support immersive extended reality (XR) services with stringent quality-of-service (QoS) requirements, like ultra-low latency and high bandwidth. However, conventional dynamic bandwidth allocation (DBA) schemes in passive optical networks (PONs) allocate upstream bandwidth solely based on reported queue occupancy, without considering the unique characteristics of XR traffic. To address these limitations, we propose an XR-aware Predictive (XP)-DBA scheme that integrates XR traffic prediction, deadline-aware scheduling, adaptive grant control, and a cycle-controller to proactively allocate bandwidth, prioritize latency-critical packets, and limit polling-cycle growth. We also derive closed-form analytical expressions to characterize XR-specific stability and delay feasibility in PON systems. We evaluate XP-DBA under standardized and burst-enhanced XR traffic models across varying XR user densities and transmission distances of up to 100 km. The results show that XP-DBA will reduce latency, jitter, and polling-cycle time while increasing throughput and supporting higher XR user densities under heavy network loads without violating XR delay bounds. These findings establish XP-DBA as an efficient and scalable scheduling solution for next-generation immersive XR services over long-reach optical access networks.
Akhilesh Patel, Y. Singh· IEEE Transactions on Network...· 0 citations