ﻻ يوجد ملخص باللغة العربية
The current Cloud infrastructure services (IaaS) market employs a resource-based selling model: customers rent nodes from the provider and pay per-node per-unit-time. This selling model places the burden upon customers to predict their job resource requirements and durations. Inaccurate prediction by customers can result in over-provisioning of resources, or under-provisioning and poor job performance. Thanks to improved resource virtualization and multi-tenant performance isolation, as well as common frameworks for batch jobs, such as MapReduce, Cloud providers can predict job completion times more accurately. We offer a new definition of QoS-levels in terms of job completion times and we present a new QoS-based selling mechanism for batch jobs in a multi-tenant OpenStack cluster. Our experiments show that the QoS-based solution yields up to 40% improvement over the revenue of more standard selling mechanisms based on a fixed per-node price across various demand and supply conditions in a 240-VCPU OpenStack cluster.
A fundamental goal in the design of IaaS service is to enable both user-friendly and cost-effective service access, while attaining high resource efficiency for revenue maximization. QoS differentiation is an important lens to achieve this design goa
Efficient GPU resource scheduling is essential to maximize resource utilization and save training costs for the increasing amount of deep learning workloads in shared GPU clusters. Existing GPU schedulers largely rely on static policies to leverage t
In this paper, we study the market-oriented online bi-objective service scheduling problem for pleasingly parallel jobs with variable resources in cloud environments, from the perspective of SaaS (Software-as-as-Service) providers who provide job-exe
We describe some of the key aspects of the SAMGrid system, used by the D0 and CDF experiments at Fermilab. Having sustained success of the data handling part of SAMGrid, we have developed new services for job and information services. Our job managem
Job submissions of parallel applications to production supercomputer systems will have to be carefully tuned in terms of the job submission parameters to obtain minimum response times. In this work, we have developed an end-to-end resource management