All Tags AWS ai algorithm-design architecture browser cloud cloud-efficiency cloud-principles cost-reduction data-centric data-compression data-processing deployment design documentation edge-computing email-sharing energy-efficiency energy-footprint enterprise-optimization green-ai hardware libraries llm locality machine-learning maintainability management measured microservices migration mobile model-optimization model-training multi-objective network-traffic parameter-tuning performance queries rebuilding scaling services storage-optimization strategies tabs template testing workloads

Tactic: [Implement Resource-Aware Job Scheduling]

Tactic sort: Awesome Tactic

Type: Architectural Tactic

Category: resource-allocation

Tags: management

Title

[Implement Resource-Aware Job Scheduling]

Description

Integrate job scheduling techniques that account for multiple system resources—such as memory, CPU, network bandwidth, and energy—rather than relying solely on CPU-based policies. This involves extending existing job schedulers (e.g., Slurm’s backfill algorithm) to estimate job resource requirements and dynamically prioritize or migrate jobs based on estimated or real-time resource utilization. Integration with resource monitoring systems enables adaptive workload distribution that minimizes idle time and energy waste

Participant

Scientific software developers

Related software artifact

Job scheduler configuration (e.g., Slurm scripts), resource monitoring systems

Context

Scientific software or HPC platforms deployed on shared-resource clusters where workflows are executed in parallel, and resource constraints such as memory, bandwidth, and energy must be considered

Software feature

Multi-Resource Scheduling Capability; Workload Characterization; Job Prioritization

Tactic intent

To optimize system-wide energy efficiency and performance by allocating jobs based on a broader set of resource constraints and expected utilization

Target quality attribute

Energy efficiency

Other related quality attributes

< unknown >

Measured impact

Execution time

Source

Stoico, Vincenzo and Voronovs, Dmitrijs and Malavolta, Ivano and Lago, Patricia, How Does Parallelism Impact the Energy Efficiency and Performance of High-Performance Scientific Software? The Case of Haddock (February 13, 2025). (DOI: http://dx.doi.org/10.2139/ssrn.5137167)