Heterogeneous MacroTasking (HeMT) for Parallel Processing in the Public Cloud

by   Yuquan Shan, et al.

Using tiny, equal-sized tasks (Homogeneous microTasking, HomT) has long been regarded an effective way of load balancing in parallel computing systems. When combined with nodes pulling in work upon becoming idle, HomT has the desirable property of automatically adapting its load distribution to the processing capacities of participating nodes - more powerful nodes finish their work sooner and, therefore, pull in additional work faster. As a result, HomT is deemed especially desirable in settings with heterogeneous (and possibly possessing dynamically changing) processing capacities. However, HomT does have additional scheduling and I/O overheads that might make this load balancing scheme costly in some scenarios. In this paper, we first analyze these advantages and disadvantages of HomT. We then propose an alternative load balancing scheme - Heterogeneous MacroTasking (HeMT) - wherein workload is intentionally partitioned according to nodes' processing capacity. Our goal is to study when HeMT is able to overcome the performance disadvantages of HomT. We implement a prototype of HeMT within the Apache Spark application framework with complementary enhancements to the Apache Mesos cluster manager. Spark's built-in scheduler, when parameterized appropriately, implements HomT. Our experimental results show that HeMT out-performs HomT when accurate workload-specific estimates of nodes' processing capacities are learned. As representative results, Spark with HeMT offers about 10 completion times for realistic data processing workloads over the default system.


Dynamic Constraint-based Influence Framework and its Application in Stochastic Modeling of Load Balancing

Components connected over a network influence each other and interact in...

A Programming Model for GPU Load Balancing

We propose a GPU fine-grained load-balancing abstraction that decouples ...

Dynamic Load Balancing Techniques for Particulate Flow Simulations

Parallel multiphysics simulations often suffer from load imbalances orig...

Load Balancer Tuning: Comparative Analysis of HAProxy Load Balancing Methods

Load balancing is prevalent in practical application (e.g., web) deploym...

Towards Co-execution on Commodity Heterogeneous Systems: Optimizations for Time-Constrained Scenarios

Heterogeneous systems are present from powerful supercomputers, to mobil...

Auto-tuning of dynamic load balancing applied to 3D reverse time migration on multicore systems

Reverse time migration (RTM) is an algorithm widely used in the oil and ...

Improving Makespan in Dynamic Task Allocation for Cloud Robotic Systems with Time Window Constraints

A scheduling method in a robotic network cloud system with minimal makes...

Please sign up or login with your details

Forgot password? Click here to reset