Reactive Resource Provisioning Heuristics for Dynamic Dataflows on Cloud Infrastructure

Abstract

The need for low latency analysis over high-velocity data streams motivates the need for distributed continuous dataflow systems. Contemporary stream processing systems use simple techniques to scale on elastic cloud resources to handle variable data rates. However, application QoS is also impacted by variability in resource performance exhibited by clouds and hence necessitates autonomic methods of provisioning elastic resources to support such applications on cloud infrastructure. We develop the concept of "dynamic dataflows" which utilize alternate tasks as additional control over the dataflow's cost and QoS. Further, we formalize an optimization problem to represent deployment and runtime resource provisioning that allows us to balance the application's QoS, value, and the resource cost. We propose two greedy heuristics, centralized and sharded, based on the variable-sized bin packing algorithm and compare against a Genetic Algorithm (GA) based heuristic that gives a near-optimal solution. A large-scale simulation study, using the Linear Road Benchmark and VM performance traces from the AWS public cloud, shows that while GA-based heuristic provides a better quality schedule, the greedy heuristics are more practical, and can intelligently utilize cloud elasticity to mitigate the effect of variability, both in input data rates and cloud resource performance, to meet the QoS of fast data applications.

Stream Data Load Prediction for Resource Scaling Using Online Support Vector Regression

“…Mayer et al [12] used time series analysis to predict the input data of the operation and calculates the parallelism of operation based on queuing theory. Kumbhare et al [13] considered the volatility of resource performance and used a heuristic resource adjustment method to maintain the throughput of the application at the minimum resource cost. Kumbhare et al [14] proposed a method to predict the stream data load and performance, which adaptively plans resource distribution to limit throughput while satisfying resource adjustment costs.…”

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

“…It is suitable for the rapidly increasing workloads, especially in a homogeneous resource environment. A genetic algorithm based on the heuristic approach was successfully implemented for dynamic dataflow scheduling. Q‐aware is a QoS metric–oriented workload classification and scheduling mechanism.…”

Formally modeling and analyzing cost‐aware job scheduling for cloud data center

“…Under a cloud computing environment, the data center consists of a large amount of computers, usually up to millions, and stores petabyte even exabyte of data . When the workload of the cloud data center increases rapidly, more hosts will be started on, and more virtual machines will be deployed to provide more available resources . How to lower the cost of those geographically distributed data centers has become a challenging issue.…”