Leveraging Reinforcement Learning for Task Resource Allocation in Scientific Workflows

Bader, Jonathan; Zunker, Nicolas; Becker, Sören; Kao, Odej

doi:10.1109/bigdata55660.2022.10020688

Cited by 7 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are methods available for predicting a task's memory requirements without the need for scientists to provide manual estimates. State-of-the-art methods approach this problem by predicting a task's peak memory with analytic methods [15], regression models [11], [16], or reinforcement learning [17]. However, they neglect the fact that a task's resource consumption varies over time.…”

Section: Introductionmentioning

confidence: 99%

Lotaru: Locally Estimating Runtimes of Scientific Workflow Tasks in Heterogeneous Clusters

Bader

Lehmann

Thamsen

et al. 2022

34th International Conference on Scientific and Statistical Database Management

View full text Add to dashboard Cite

Many scientific workflow scheduling algorithms need to be informed about task runtimes a-priori to conduct efficient scheduling. In heterogeneous cluster infrastructures, this problem becomes aggravated because these runtimes are required for each task-node pair. Using historical data is often not feasible as logs are typically not retained indefinitely and workloads as well as infrastructure changes. In contrast, online methods, which predict task runtimes on specific nodes while the workflow is running, have to cope with the lack of example runs, especially during the start-up.In this paper, we present Lotaru, a novel online method for locally estimating task runtimes in scientific workflows on heterogeneous clusters. Lotaru first profiles all nodes of a cluster with a set of shortrunning and uniform microbenchmarks. Next, it runs the workflow to be scheduled on the user's local machine with drastically reduced data to determine important task characteristics. Based on these measurements, Lotaru learns a Bayesian linear regression model to predict a task's runtime given the input size and finally adjusts the predicted runtime specifically for each task-node pair in the cluster based on the micro-benchmark results. Due to its Bayesian approach, Lotaru can also compute robust uncertainty estimates and provides them as an input for advanced scheduling methods.Our evaluation with five real-world scientific workflows and different datasets shows that Lotaru significantly outperforms the baselines in terms of prediction errors for homogeneous and heterogeneous clusters. CCS CONCEPTS• Information systems → Information systems applications; • Computer systems organization → Distributed architectures; • Software and its engineering → Software architectures.

show abstract

Section: Introductionmentioning

confidence: 99%

Lotaru: Locally Estimating Runtimes of Scientific Workflow Tasks in Heterogeneous Clusters

Bader

Lehmann

Thamsen

et al. 2022

34th International Conference on Scientific and Statistical Database Management

View full text Add to dashboard Cite

show abstract

“…In our own related work [17], we proposed two different reinforcement learning approaches based on gradient bandits and Q-learning. Both methods have the objective of minimizing resource wastage.…”

Section: A Workflow Task Memory Predictionmentioning

confidence: 99%

Predicting Dynamic Memory Requirements for Scientific Workflow Tasks

Bader,

Diedrich,

Thamsen

et al. 2023

2023 IEEE International Conference on Big Data (BigData)

Self Cite

View full text Add to dashboard Cite

With the increasing amount of data available to scientists in disciplines as diverse as bioinformatics, physics, and remote sensing, scientific workflow systems are becoming increasingly important for composing and executing scalable data analysis pipelines. When writing such workflows, users need to specify the resources to be reserved for tasks so that sufficient resources are allocated on the target cluster infrastructure. Crucially, underestimating a task's memory requirements can result in task failures. Therefore, users often resort to overprovisioning, resulting in significant resource wastage and decreased throughput.In this paper, we propose a novel online method that uses monitoring time series data to predict task memory usage in order to reduce the memory wastage of scientific workflow tasks. Our method predicts a task's runtime, divides it into k equallysized segments, and learns the peak memory value for each segment depending on the total file input size. We evaluate the prototype implementation of our method using workflows from the publicly available nf-core repository, showing an average memory wastage reduction of 29.48% compared to the best stateof-the-art approach.

show abstract

“…Bader et al [35] proposed two reinforcement learning methods based on gradient bandits and Q-learning. The object of their reinforcement learning methods is the minimization between allocated and used memory while avoiding task failure.…”

Section: A Workflow Task Memory Predictionmentioning

confidence: 99%

Reshi: Recommending Resources for Scientific Workflow Tasks on Heterogeneous Infrastructures

Bader

Lehmann

Groth

et al. 2022

2022 IEEE International Performance, Computing, and Communications Conference (IPCCC)

View full text Add to dashboard Cite

Scientific workflows typically comprise a multitude of different processing steps which often are executed in parallel on different partitions of the input data. These executions, in turn, must be scheduled on the compute nodes of the computational infrastructure at hand. This assignment is complicated by the facts that (a) tasks typically have highly heterogeneous resource requirements and (b) in many infrastructures, compute nodes offer highly heterogeneous resources. In consequence, predictions of the runtime of a given task on a given node, as required by many scheduling algorithms, are often rather imprecise, which can lead to sub-optimal scheduling decisions.We propose Reshi, a method for recommending task-node assignments during workflow execution that can cope with heterogeneous tasks and heterogeneous nodes. Reshi approaches the problem as a regression task, where task-node pairs are modeled as feature vectors over the results of dedicated micro benchmarks and past task executions. Based on these features, Reshi trains a regression tree model to rank and recommend nodes for each ready-to-run task, which can be used as input to a scheduler. For our evaluation, we benchmarked 27 AWS machine types using three representative workflows. We compare Reshi's recommendations with three state-of-the-art schedulers. Our evaluation shows that Reshi outperforms HEFT by a mean makespan reduction of 7.18% and 18.01% assuming a mean task runtime prediction error of 15%.

show abstract

Leveraging Reinforcement Learning for Task Resource Allocation in Scientific Workflows

Cited by 7 publications

References 21 publications

Lotaru: Locally Estimating Runtimes of Scientific Workflow Tasks in Heterogeneous Clusters

Lotaru: Locally Estimating Runtimes of Scientific Workflow Tasks in Heterogeneous Clusters

Predicting Dynamic Memory Requirements for Scientific Workflow Tasks

Reshi: Recommending Resources for Scientific Workflow Tasks on Heterogeneous Infrastructures

Contact Info

Product

Resources

About