Beyond the Limits: Flexible and Congestion-Aware Cluster Scheduling for the Cloud
2026-08-10 • Distributed, Parallel, and Cluster Computing
Distributed, Parallel, and Cluster Computing
AI summaryⓘ
The authors highlight problems with how cloud workloads are scheduled, noting that rigid rules for performance goals and ignoring hardware resource conflicts lead to wasted resources and poor performance. They propose two improvements: allowing some flexibility in performance targets (soft SLOs) and being aware of real-time hardware congestion when scheduling tasks. Their approach reduces unnecessary rescheduling and eases shared resource bottlenecks without hurting overall performance. This shows that considering both application needs and hardware state can make cloud scheduling more efficient.
workload schedulingcloud computingservice level objectives (SLOs)resource overcommitmentlast-level cache (LLC)memory bandwidthresource contentionreschedulingcluster efficiency
Authors
Oliver Larsson, Thijs Metsch, Cristian Klein, Erik Elmroth
Abstract
Workload scheduling in cloud environments often relies on simplistic assumptions about application resource needs and hardware utilization. Overlooking application-level performance objectives and hardware resource contention that leads to inefficient resource usage and degraded performance. This paper addresses two key limitations of current approaches. First, unnecessarily strict enforcement of service level objectives (SLOs) often leads to resource underutilization and poor energy efficiency. Second, lack of congestion awareness in shared resources such as last-level cache (LLC) and memory bandwidth. In this paper, we propose two complementary strategies to address these limitations: (i) integrating soft SLO limits that allow controlled overcommitment and tolerate minor, transient violations to improve cluster efficiency, and (ii) introducing resource-aware scheduling and rescheduling based on real-time congestion insights for shared resources such as last-level cache (LLC) and memory bandwidth. Our results show that soft SLO limits reduce corrective rescheduling actions by 49% compared to hard-limit approaches while maintaining acceptable performance guarantees. Additionally, resource-aware scheduling decreases node-level congestion by 8% and further mitigates SLO violations, demonstrating the effectiveness of incorporating application-level flexibility and hardware-level insights into scheduling and rescheduling decisions.