EFS: Energy-Friendly Scheduler for memory bandwidth constrained systems

Morad, Tomer Y.; Shalev, Noam; Keidar, Idit; Kolodny, Avinoam; Weiser, Uri

doi:10.1016/j.jpdc.2016.03.007

Cited by 3 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notably, leaving the decision to the end user on where to place threads constitutes a significant burden. Making effective educated mapping decisions requires the gathering of substantial information about each application, including a detailed performance profile for different LLC-way counts [27], and some notions on its sensitivity to different levels of bandwidth contention [33]. Obtaining this information offline is unrealistic in many general-purpose settings due to the time required to conduct the associated experiments, and becomes unfeasible when the cloud provider has no direct access to the applications [1].…”

Section: Llc-partitioning and Mapping In Numa Platformsmentioning

confidence: 99%

Divide&Content: A Fair OS-Level Resource Manager for Contention Balancing on NUMA Multicores

Bilbao,

Saez,

Prieto-Matias

2023

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

Chip multicore processors (CMPs) constitute the cherry-picked architecture for high-performance servers employed in supercomputers and cloud datacenters. In the last few years, Non-Uniform Memory Access (NUMA) multicore systems have become the dominant choice in these domains. Regardless of the technology advances enabling to pack an increasing number of cores and bigger caches on the same chip, contention for shared resources still represents an important challenge for the system software. Cores in CMPs typically share multiple resources, such as the last-level cache (LLC) or a DRAM controller. The competition for the usage of these resources leads to uneven performance degradation across co-running applications. Previous research has demonstrated that contention effects on CMPs can be mitigated via smart partitioning of the LLC or by distributing threads across groups of cores so as to even out the degree of competition on multiple LLCs or memory nodes. However, most existing resource-management strategies fail to effectively combine both contention-mitigating techniques, thus providing suboptimal results on NUMA multicores. In this paper, we analyze how to best combine these techniques to improve system-wide fairness, and, based on the conclusions of our analysis, propose a fair OS-level NUMA-aware resource manager that leverages dynamic contention-aware thread-to-socket mappings and cache-partitioning. We implemented our resource manager in the Linux kernel and assessed its effectiveness on a real dual-socket system featuring Intel Skylake processors. Our results show that it reduces unfairness by more than 17% on average compared to Linux and a state-of-the-art NUMA-aware resource manager.

show abstract

Section: Llc-partitioning and Mapping In Numa Platformsmentioning

confidence: 99%

Divide&Content: A Fair OS-Level Resource Manager for Contention Balancing on NUMA Multicores

Bilbao,

Saez,

Prieto-Matias

2023

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

show abstract

“…throughput or fairness) using a parallel branch-and-bound algorithm. In approximating the application slowdown, which is necessary to determine the degree of fairness, PBBCache accounts for the performance degradation due to both cache sharing and memory-bandwidth contention (to this end it uses a variant of the probabilistic model proposed in [15]).…”

Section: Analysis Of the Optimal Cache-clustering Solutionmentioning

confidence: 99%

Lfoc

Garcia-Garcia

Sáez

Castro

et al. 2019

Proceedings of the 48th International Conference on Parallel Processing

View full text Add to dashboard Cite

Multicore processors constitute the main architecture choice for modern computing systems in different market segments. Despite their benefits, the contention that naturally appears when multiple applications compete for the use of shared resources among cores, such as the last-level cache (LLC), may lead to substantial performance degradation. This may have a negative impact on key system aspects such as throughput and fairness. Assigning the various applications in the workload to separate LLC partitions with possibly different sizes, has been proven effective to mitigate shared-resource contention effects.In this article we propose LFOC, a clustering-based cache partitioning scheme that strives to deliver fairness while providing acceptable system throughput. LFOC leverages the Intel Cache Allocation Technology (CAT), which enables the system software to divide the LLC into different partitions. To accomplish its goals, LFOC tries to mimic the behavior of the optimal cache-clustering solution, which we could approximate by means of a simulator in different scenarios. To this end, LFOC effectively separates streaming aggressor programs from cache sensitive applications, which are then assigned to separate cache partitions.We implemented LFOC in the Linux kernel and evaluated it on a real system featuring an Intel Skylake processor, where we compare its effectiveness to that of two state-of-the-art policies that optimize fairness and throughput, respectively. Our experimental analysis reveals that LFOC is able to bring a higher reduction in unfairness by leveraging a lightweight algorithm suitable for adoption in a real OS.

show abstract