QoS-Constrained,Reliable and Energy-Efficient Task Deployment in Cloud Computing

Reliability,QoS and energy consumption are three important concerns of cloud service providers.Most of the current research on reliable task deployment in cloud computing focuses on only one or two of the three concerns.However,these three factors have intrinsic trade-off relationships.The existing studies show that load concentration can reduce the number of servers and hence save energy.In this paper,we deal with the problem of reliable task deployment in data centers,with the goal of minimizing the number of servers used in cloud data centers under the constraint that the job execution deadline can be met upon single server failure.We propose a QoS-Constrained,Reliable and Energy-efficient task replica deployment(QSRE)algorithm for the problem by combining task replication and re-execution.For each task in a job that cannot finish executing by re-execution within deadline,we initiate two replicas for the task:main task and task replica.Each main task runs on an individual server.The associated task replica is deployed on a backup server and completes part of the whole task load before the main task failure.Different from the main tasks,multiple task replicas can be allocated to the same backup server to reduce the energy consumption of cloud data centers by minimizing the number of servers required for running the task replicas.Specifically,QSRE assigns the task replicas with the longest and the shortest execution time to the backup servers in turn,such that the task replicas can meet the QoS-specified job execution deadline under the main task failure.We conduct experiments through simulations.The experimental results show that QSRE can effectively reduce the number of servers used,while ensuring the reliability and QoS of job execution.

Overbooking-Enabled Task Scheduling and Resource Allocation in Mobile Edge Computing Environments

Mobile Edge Computing(MEC)is proposed to solve the needs of Inter-net of Things(IoT)users for high resource utilization,high reliability and low latency of service requests.However,the backup virtual machine is idle when its primary virtual machine is running normally,which will waste resources.Overbooking the backup virtual machine under the above circumstances can effectively improve resource utilization.First,these virtual machines are deployed into slots randomly,and then some tasks with cooperative relationship are off-loaded to virtual machines for processing.Different deployment locations have different resource utilization and average service response time.We want tofind a balanced solution that minimizes the average service response time of the IoT application while maximizing resource utilization.In this paper,we propose a task scheduler and exploit a Task Deployment Algorithm(TDA)to obtain an optimal virtual machine deployment scheme.Finally,the simulation results show that the TDA can significantly increase the resource utilization of the system,while redu-cing the average service response time of the application by comparing TDA with the other two classical methods.The experimental results confirm that the perfor-mance of TDA is better than that of other two methods.

Online Nonstop Task Management for Storm-Based Distributed Stream Processing Engines

Most distributed stream processing engines(DSPEs)do not support online task management and cannot adapt to time-varying data flows.Recently,some studies have proposed online task deployment algorithms to solve this problem.However,these approaches do not guarantee the Quality of Service(QoS)when the task deployment changes at runtime,because the task migrations caused by the change of task deployments will impose an exorbitant cost.We study one of the most popular DSPEs,Apache Storm,and find out that when a task needs to be migrated,Storm has to stop the resource(implemented as a process of Worker in Storm)where the task is deployed.This will lead to the stop and restart of all tasks in the resource,resulting in the poor performance of task migrations.Aiming to solve this problem,in this pa-per,we propose N-Storm(Nonstop Storm),which is a task-resource decoupling DSPE.N-Storm allows tasks allocated to resources to be changed at runtime,which is implemented by a thread-level scheme for task migrations.Particularly,we add a local shared key/value store on each node to make resources aware of the changes in the allocation plan.Thus,each resource can manage its tasks at runtime.Based on N-Storm,we further propose Online Task Deployment(OTD).Differ-ing from traditional task deployment algorithms that deploy all tasks at once without considering the cost of task migra-tions caused by a task re-deployment,OTD can gradually adjust the current task deployment to an optimized one based on the communication cost and the runtime states of resources.We demonstrate that OTD can adapt to different kinds of applications including computation-and communication-intensive applications.The experimental results on a real DSPE cluster show that N-Storm can avoid the system stop and save up to 87%of the performance degradation time,compared with Apache Storm and other state-of-the-art approaches.In addition,OTD can increase the average CPU usage by 51%for computation-intensive applications and reduce network communication costs by 88%for communication-intensive ap-plications.