FFMRA: A Fully Fair Multi-Resource Allocation Algorithm in Cloud Environments

Abstract

The need for effective and fair resource allocation in cloud computing has been identified in the literature and in industrial contexts for a while. Cloud computing seen as a promising technology, offers usage-based payment, scalable and on-demand computing resources. However, during the past decade, the growing complexity of the IT world has resulted in making Quality of Service (QoS) in the cloud a challenging subject and an NP-hard problem. Specifically, the fair allocation of resources in the cloud becomes particularly interesting when many users submit several tasks which require multiple resources. Research in this area has been increasing since 2012 by introducing the Dominant Resource Fairness (DRF) algorithm as an initial attempt to solve the fair resource allocation problem in the cloud. Although DRF meets a sort of desirable fairness properties, it has been proven to be inefficient in certain conditions. Noticeably, DRF and other works in its extension are not intuitively fair after all. Those implementations have been unable to utilize all the resources in the system, leaving the system in an imbalanced situation with respect to each specific system resource. In order to address those issues, we propose in this paper a novel algorithm namely a Fully Fair Multi-Resource Allocation Algorithm in Cloud Environments (FFMRA) which allocates resources in a fully fair way considering both dominant and non-dominant shares. The results from the experiments conducted in CloudSim show that FFMRA provides approximately 100% recourse utilization, and distributing them fairly among the users while meeting desirable fairness features.

A New Approach to Calculate Resource Limits with Fairness in Kubernetes

“…Therefore, allocatable resources r of a particular no0de i can be defined as AL ri . Hence, (14) and (15) can be changed to (16) and (17):…”

“…Taking into account the above-mentioned problems, In this paper, the first attempt is to model and integrate three different fair allocation algorithms, MLF-DRS [13] and FFMRA [14] as well as DRF in Kubernetes, trying to assign resource limits fairly among different pods running in a specific node.…”

MRFS: A Multi-resource Fair Scheduling Algorithm in Heterogeneous Cloud Computing

“…The results from the experiments confirm that the allocation under MRFS policy gains an optimal utility maximization while the fairness is also achieved. Furthermore, the resource allocation under MRFS scheduling policy alongside FFMRA algorithm [17] shows that the utility is maximized by %15-20 compared to FFMRA without MRFS algorithm. FFMRA tries to equalize dominant and non-dominant resources to ensure that resources are distributed evenly among users.…”

“…Equalizing the number of dominant resources in each specific resource type may contribute to maximizing the proportion of the entire resource pool in the data-center to all dominant resources. Based on the FFMRA allocation policy(see [17]), Fig.7(a)(b) clearly states that the proportion of resource pool for dominant resources under the MRFS policy is considerably better than the VM Allocation policy in which FFMRA operates accordingly. Assume that CPU and RAM are considered as two types of resources, the total proportion for dominant CPU and RAM in MRFS scheduling policy is strictly better than FFMRA in absense of MRFS in the CloudSim.…”

H-FFMRA: A Multi Resource Fully Fair Resources Allocation Algorithm in Heterogeneous Cloud Computing

“…Taking into account all the above-mentioned issues, in this paper, we present H-FFMRA as an extension of our previous work [11] in multiple servers. H-FFMRA captures multiresource allocation, considering dominant and non-dominant resources for each server.…”