Profiling the scheduling decisions for handling critical paths in deadline-constrained cloud workflows

Editorial for FGCS Special issue on “Time-critical Applications on Software-defined Infrastructures”

“…Taal et al profile the behaviour of partial critical path algorithms for planning customised virtual infrastructures for time-critical applications [9]. The partial critical path algorithm initially proposed in [10] for scheduling the execution of time-critical tasks on Cloud resources has been used as the basis to plan the infrastructure of networked virtual machines for application workflows with multi deadlines [11].…”

Virtual Infrastructure Optimisation

“…Most current work focuses on guaranteeing a single deadline encompassing the entire application, e.g. the Critical Path-based Iterative (CPI) [23] and Complete Critical paths (CPIS) [24] algorithms. All these technologies have been widely investigated for applications modelled as directed acyclic graphs (DAGs) as DAG-based methods are popular for building data-flows for data-intensive applications.…”

SPIRIT: A Microservice-Based Framework for Interactive Cloud Infrastructure Planning

“…The process of designing and formally describing a customized Cloud infrastructure for an application with specific requirements can be described as Virtual Infrastructure planning [3][4][5]. Virtual infrastructure planning is also often referred to as Infrastructure as a Service planning or even simply infrastructure planning.…”

“…If infrastructure planning is used to migrate an existing on-premise application to the cloud, one can pick services in the cloud with similar specifications as the on-premise services. This is often referred to as resource mapping 4 . Nevertheless, this approach is only viable if there is already an on-premise solution available.…”

“…These tasks usually process large data sets and require a specific amount of servers with certain properties [8]. This problem requires a different IaaS planning approach, such as estimating required resources through the use of scheduling algorithms, such as the partial critical path algorithm [4]. We will be looking at existing solutions more extensively in this research.…”