Enabling fair pricing on HPC systems with node sharing

Breslow, Alex D.; Tiwari, Ananta; Schulz, Martin; Carrington, Laura; Tang, Lingjia; Mars, Jason

doi:10.1145/2503210.2503256

Cited by 21 publications

(12 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We rely on the presence of an admission control system that chooses VM placement across the data center [Chen et al 2012;Schwarzkopf et al 2013], and we assume that the hypervisor supports live migration [Jo et al 2013] in case a node becomes overloaded. While both VM placement and migration present open questions for research, AutoPro focuses on a different challenging and interesting problem: automating allocation of a contended resource within a single node, based on application-level performance SLOs.…”

Section: Automated Fine-grained Provisioningmentioning

confidence: 99%

See 1 more Smart Citation

Automated Fine-Grained CPU Provisioning for Virtual Machines

Bartolini

Sironi

Sciuto

et al. 2014

ACM Trans. Archit. Code Optim.

View full text Add to dashboard Cite

Ideally, the pay-as-you-go model of Infrastructure as a Service (IaaS) clouds should enable users to rent just enough resources (e.g., CPU or memory bandwidth) to fulfill their service level objectives (SLOs). Achieving this goal is hard on current IaaS offers, which require users to explicitly specify the amount of resources to reserve; this requirement is nontrivial for users, because estimating the amount of resources needed to attain application-level SLOs is often complex, especially when resources are virtualized and the service provider colocates virtual machines (VMs) on host nodes. For this reason, users who deploy VMs subject to SLOs are usually prone to overprovisioning resources, thus resulting in inflated business costs.This article tackles this issue with AutoPro: a runtime system that enhances IaaS clouds with automated and fine-grained resource provisioning based on performance SLOs. Our main contribution with AutoPro is filling the gap between application-level performance SLOs and allocation of a contended resource, without requiring explicit reservations from users. In this article, we focus on CPU bandwidth allocation to throughput-driven, compute-intensive multithreaded applications colocated on a multicore processor; we show that a theoretically sound, yet simple, control strategy can enable automated fine-grained allocation of this contended resource, without the need for offline profiling. Additionally, AutoPro helps service providers optimize infrastructure utilization by provisioning idle resources to best-effort workloads, so as to maximize node-level utilization.Our extensive experimental evaluation confirms that AutoPro is able to automatically determine and enforce allocations to meet performance SLOs while maximizing node-level utilization by supporting batch workloads on a best-effort basis.

show abstract

Section: Automated Fine-grained Provisioningmentioning

confidence: 99%

“…To deal with the second issue, the provider could employ techniques to limit performance degradation [Mars et al 2011;Govindan et al 2011] and, when this is not enough, to estimate the extent of the performance degradation [Breslow et al 2013;Dwyer et al 2012] and scale the bill accordingly.…”

Section: Billing Schemementioning

confidence: 99%

Automated Fine-Grained CPU Provisioning for Virtual Machines

Bartolini

Sironi

Sciuto

et al. 2014

ACM Trans. Archit. Code Optim.

View full text Add to dashboard Cite

show abstract

“…ing the low use of a node's memory and underutilization of a node's CPU resource [1]- [3]. Consequently, various cluster scheduling algorithms (such as POPPA [4], DFRS [5]) and backfilling algorithms [6]- [8] have been developed to allow multiple jobs to coexist on the same node to improve overall turn-around times and fairness, which leads to improving the utilization of HPC systems. Trends for HPC workload point toward diversity.…”

Section: Introductionmentioning

confidence: 99%

Improving Per-Node Computing Efficiency by an Adaptive Lock-Free Scheduling Model

Zheng

Zhou

et al. 2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Job scheduling on many-core computers with tens or even hundreds of processing cores is one of the key technologies in High Performance Computing (HPC) systems. Despite many scheduling algorithms have been proposed, scheduling remains a challenge for executing highly effective jobs that are assigned in a single computing node with diverse scheduling objectives. On the other hand, the increasing scale and the need for rapid response to changing requirements are hard to meet with existing scheduling models in an HPC node. To address these issues, we propose a novel adaptive scheduling model that is applied to a single node with a many-core processor; this model solves the problems of scheduling efficiency and scalability through an adaptive optimistic control mechanism. This mechanism exposes information such that all the cores are provided with jobs and the tools necessary to take advantage of that information and thus compete for resources in an uncoordinated manner. At the same time, the mechanism is equipped with adaptive control, allowing it to adjust the number of running tools dynamically when frequent conflict happens. We justify this scheduling model and present the simulation results for synthetic and real-world HPC workloads, in which we compare our proposed model with two widely used scheduling models, i.e. multi-path monolithic and two-level scheduling. The proposed approach outperforms the other models in scheduling efficiency and scalability. Our results demonstrate that the adaptive optimistic control affords significant improvements for HPC workloads in the parallelism of the node-level scheduling model and performance.

show abstract

“…While this approach prevents jobs from different users from clobbering one another, it leads to a missed performance opportunity. In fact, recent work has shown that colocation, where a set of jobs from different users runs 1 This paper received a nomination for the Best Paper Award at the SC2013 conference and is published here with permission of ACM, see [12]. Also, the paper was nominated for the Best Student Paper Award.…”

Section: Introductionmentioning

confidence: 99%

Enabling Fair Pricing on High Performance Computer Systems with Node Sharing

Breslow

Tiwari

Schulz

et al. 2014

Scientific Programming

Self Cite

View full text Add to dashboard Cite

Abstract. Co-location, where multiple jobs share compute nodes in large-scale HPC systems, has been shown to increase aggregate throughput and energy efficiency by 10-20%. However, system operators disallow co-location due to fair-pricing concerns, i.e., a pricing mechanism that considers performance interference from co-running jobs. In the current pricing model, application execution time determines the price, which results in unfair prices paid by the minority of users whose jobs suffer from co-location. This paper presents POPPA, a runtime system that enables fair pricing by delivering precise online interference detection and facilitates the adoption of supercomputers with co-locations. POPPA leverages a novel shutter mechanism -a cyclic, fine-grained interference sampling mechanism to accurately deduce the interference between co-runners -to provide unbiased pricing of jobs that share nodes. POPPA is able to quantify inter-application interference within 4% mean absolute error on a variety of co-located benchmark and real scientific workloads.

show abstract

Enabling fair pricing on HPC systems with node sharing

Cited by 21 publications

References 53 publications

Automated Fine-Grained CPU Provisioning for Virtual Machines

Automated Fine-Grained CPU Provisioning for Virtual Machines

Improving Per-Node Computing Efficiency by an Adaptive Lock-Free Scheduling Model

Enabling Fair Pricing on High Performance Computer Systems with Node Sharing

Contact Info

Product

Resources

About