Adaptive Workflow Scheduling on Cloud Computing Platforms with IterativeOrdinal Optimization

Abstract

The scheduling of multitask jobs on clouds is an NP-hard problem. The problem becomes even worse when complex workflows are executed on elastic clouds, such as Amazon EC2 or IBM RC2. The main difficulty lies in the large search space and high overhead of generating optimal schedules, especially for real-time applications with dynamic workloads. In this work, a new iterative ordinal optimization (IOO) method is proposed. The ordinal optimization method is applied in each iteration to achieve suboptimal schedules. IOO aims at generating more efficient schedules from a global perspective over a long period. We prove through overhead analysis the advantages in time and space efficiency in using the IOO method. The IOO method is designed to adapt to system dynamism to yield suboptimal performance.In cloud experiments on IBM RC2 cloud, we execute 20,000 tasks in LIGO (Laser Interferometer Gravitational-wave Observatory) verification workflow on 128 virtual machines. The IOO schedule is generated in less than 1,000 seconds, while using the Monte Carlo simulation takes 27.6 hours, 100 times longer to yield an optimal schedule. The IOO-optimized schedule results in a throughput of 1,100 tasks/sec with 7 GB memory demand, compared with 60% decrease in throughput and 70% increase in memory demand in using the Monte Carlo method. Our LIGO experimental results clearly demonstrate the advantage of using the IOO-based workflow scheduling over the traditional blind-pick, ordinal optimization, or Monte Carlo methods. These numerical results are also validated by the theoretical complexity and overhead analysis provided.

ProMo: A Probabilistic Model for Dynamic Load-Balanced Scheduling of Data Flows in Cloud Systems

“…Then, the mean arrival rates at the network's layers are found from the system of Equation (8), and they are λ 1 = 78.6 jobs/s, λ 2 = 86.3 jobs/s, λ 3 = 77.7 jobs/s, λ 4 = 70 jobs/s (these values have been rounded to one decimal place). The utilization values for each layer are found from Equation (12). (10) and 11: This value means that the probability of changing the state with time is a very small one, 0.001044, which virtually means that the system's state does not change with time.…”

“…This is due to the fact that while new data flows keep arriving at different (or even similar) rates between data servers, some links may collapse and become unavailable for some time [11], meaning that some data flows may need to be re-transmitted to a different server or servers, thus changing the amount of load being stored and processed by each machine. Thus, the workload distributed fluctuates, and this necessitates a time-or period-based scheduling [12]. In this regard, the static flow scheduling approaches become rather unsuitable for big data flows.…”

Service‐level agreement–aware scheduling and load balancing of tasks in cloud

“…In the dynamic cloud environment, the task assignment problem can be considered an NP-hard problem. 10 Finding an optimal task assignment and load balancing in the dynamic cloud environment is a cumbersome task. The optimal task deployment increases the customer satisfaction and provider's revenue.…”

Fuzzy Resource Pre-processing and Compress and Join Gang Polling Evaluation Scheduling in Cloud Computing

“…Fan Zhang et al [21] proposed a technique which was producing more effective arrangements from a worldwide point of view over quite a while. They demonstrated through overhead investigation and the points of interest in time and space proficiency for utilizing the technique.…”