Aug 2026· Proceedings of the ACM SIGCOMM 2026 Conference· 0 citations· 54 references
TL;DR
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.
Abstract
Modern datacenter networks host diverse services and workloads with varying quality-of-service (QoS) requirements, yet are constrained by hardware limitations. Most notably, the small number of physical priority queues available in commodity switches. Existing scheduling mechanisms, whether end-host or in-network based, struggle to scale under these constraints due to their reliance on global priority information or complex queue management. This paper presents P2CS (Priority-based Probabilistic Congestion Signaling), a lightweight and scalable approach that enables fine-grained traffic prioritization using only a single FIFO queue. P2CS combines priority-aware probabilistic congestion signaling, priority-aware packet dropping, and simple switch-side arbitration to enforce prioritization across flows. P2CS supports a range of scheduling objectives, and requires minimal software changes making it readily deployable in today's datacenter infrastructure. Evaluation on representative workloads, including multi-tenant ML training, HPC, and mixed spray/ECMP traffic, demonstrates that P2CS achieves performance comparable to in-network mechanisms while significantly reducing complexity and cost.
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.
Alessandro Cornacchia, Andrea Bianco, Paolo Giaccone et al.· 0 citations
Compute and memory resources in cloud environments are strictly managed and isolated by the control plane; in contrast, network resources lack equivalent management and isolation mechanisms. This best-effort treatment of networking leads to significant challenges for modern AI workloads, which have diverse and bandwidth-intensive communication patterns. Without fine-grained network resource control, these workloads suffer from interference, unpredictable throughput, and suboptimal cluster utilization. To address these issues, this paper demonstrates how network bandwidth can be elevated to a first-class, schedulable, and enforceable resource within Kubernetes, the de facto standard for cloud-native orchestration. We introduce a new scheduling capability that models network interfaces as allocatable resources and regulates bandwidth sharing through the Dynamic Resource Allocation (DRA) framework, with enforcement implemented using the Hierarchical Token Bucket (HTB) mechanism. We evaluate the system using multitenant AI workloads derived from real-world communication characteristics with a simulation-based approach and validate the proposed enforcement strategy in a real cluster. Results show that the proposed two-level bandwidth allocation improves tenant performance predictability and satisfaction while maintaining packed cluster utilization.
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
STORM is presented, a NIC-level scheduler for all types of RDMA workloads using NIC-only information: the known RDMA request size, and per-queue-pair backlog, and converts these signals into a small number of extra priority levels on the wire and prioritizes requests that are either near completion or blocking queued dependent work.
Jichun Wu, Ran Shu, Gianni Antichi et al.· 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.
To achieve high-throughput and low-latency Remote Direct Memory Access (RDMA) communication in data center networks, load balancing is critical for preventing congestion and ensuring that traffic is efficiently distributed across available network paths. However, existing schemes may not effectively detect rerouting opportunities in continuous RDMA packet streams and may degrade in-order delivery, limiting their applicability to RDMA traffic. To address these limitations, we propose ProLet, a load balancing scheme that enables proactive probing and reroutes elephant flows at flowlet granularity in lossless RDMA networks. ProLet dynamically fine-tunes per-destination top-of-rack timeouts and enables effective in-network flowlet identification based on real-time network conditions. Meanwhile, it leverages lightweight mice flows as proactive probes to maintain network-wide congestion awareness. This allows ProLet to reroute elephant flows before congestion accumulates, mitigating the persistent queue buildup inherent in subflow-based schemes. Extensive numerical evaluations demonstrate that ProLet reduces average and tail flow completion time slowdowns by 69% and 79%, respectively, compared to state-of-the-art load balancing schemes.
Hong Wang, Jinhao Luo, J. Tan et al.· Asia-Pacific Workshop on Net...· 0 citations