Refine
Document Type
- Conference proceeding (12)
- Journal article (5)
- Book chapter (1)
- Doctoral Thesis (1)
Language
- English (19)
Is part of the Bibliography
- yes (19)
Institute
- Informatik (19)
Publisher
Serverless computing is an emerging cloud computing paradigm with the goal of freeing developers from resource management issues. As of today, serverless computing platforms are mainly used to process computations triggered by events or user requests that can be executed independently of each other. These workloads benefit from on-demand and elastic compute resources as well as per-function billing. However, it is still an open research question to which extent parallel applications, which comprise most often complex coordination and communication patterns, can benefit from serverless computing.
In this paper, we introduce serverless skeletons for parallel cloud programming to free developers from both parallelism and resource management issues. In particular, we investigate on the well known and widely used farm skeleton, which supports the implementation of a wide range of applications. To evaluate our concepts, we present a prototypical development and runtime framework and implement two applications based on our framework: Numerical integration and hyperparameter optimization - a commonly applied technique in machine learning. We report on performance measurements for both applications and discuss
the usefulness of our approach.
Container virtualization evolved into a key technology for deployment automation in line with the DevOps paradigm. Whereas container management systems facilitate the deployment of cloud applications by employing container based artifacts, parts of the deployment logic have been applied before to build these artifacts. Current approaches do not integrate these two deployment phases in a comprehensive manner. Limited knowledge on application software and middleware encapsulated in container-based artifacts leads to maintainability and configuration issues. Besides, the deployment of cloud applications is based on custom orchestration solutions leading to lock in problems. In this paper, we propose a two-phase deployment method based on the TOSCA standard. We present integration concepts for TOSCA-based orchestration and deployment automation using container-based artifacts. Our two-phase deployment method enables capturing and aligning all the deployment logic related to a software release leading to better maintainability. Furthermore, we build a container management system, which is composed of a TOSCA-based orchestrator on Apache Mesos, to deploy container-based cloud applications automatically.
The state of the art proposes the microservices architectural style to build applications. Additionally, container virtualization and container management systems evolved into the perfect fit for developing, deploying, and operating microservices in line with the DevOps paradigm. Container virtualization facilitates deployment by ensuring independence from the runtime environment. However, microservices store their configuration in the environment. Therefore, software developers have to wire their microservice implementation with technologies provided by the target runtime environment such as configuration stores and service registries. These technological dependencies counteract the portability benefit of using container virtualization. In this paper, we present AUTOGENIC - a model-based approach to assist software developers in building microservices as self configuring containers without being bound to operational technologies. We provide developers with a simple configuration model to specify configuration operations of containers and automatically generate a self-configuring microservice tailored for the targeted runtime environment. Our approach is supported by a method, which describes the steps to automate the generation of self-configuring microservices. Additionally, we present and evaluate a prototype, which leverages the emerging TOSCA standard.
The cloud evolved into an attractive execution environment for parallel applications, which make use of compute resources to speed up the computation of large problems in science and industry. Whereas Infrastructure as a Service (IaaS) offerings have been commonly employed, more recently, serverless computing emerged as a novel cloud computing paradigm with the goal of freeing developers from resource management issues. However, as of today, serverless computing platforms are mainly used to process computations triggered by events or user requests that can be executed independently of each other and benefit from on-demand and elastic compute resources as well as per-function billing. In this work, we discuss how to employ serverless computing platforms to operate parallel applications. We specifically focus on the class of parallel task farming applications and introduce a novel approach to free developers from both parallelism and resource management issues. Our approach includes a proactive elasticity controller that adapts the physical parallelism per application run according to user-defined goals. Specifically, we show how to consider a user-defined execution time limit after which the result of the computation needs to be present while minimizing the associated monetary costs. To evaluate our concepts, we present a prototypical elastic parallel system architecture for self-tuning serverless task farming and implement two applications based on our framework. Moreover, we report on performance measurements for both applications as well as the prediction accuracy of the proposed proactive elasticity control mechanism and discuss our key findings.
Due to frequently changing requirements, the internal structure of cloud services is highly dynamic. To ensure flexibility, adaptability, and maintainability for dynamically evolving services, modular software development has become the dominating paradigm. By following this approach, services can be rapidly constructed by composing existing, newly developed and publicly available third-party modules. However, newly added modules might be unstable, resource-intensive, or untrustworthy. Thus, satisfying non-functional requirements such as reliability, efficiency, and security while ensuring rapid release cycles is a challenging task. In this paper, we discuss how to tackle these issues by employing container virtualization to isolate modules from each other according to a specification of isolation constraints. We satisfy non-functional requirements for cloud services by automatically transforming the modules comprised into a container-based system. To deal with the increased overhead that is caused by isolating modules from each other, we calculate the minimum set of containers required to satisfy the isolation constraints specified. Moreover, we present and report on a prototypical transformation pipeline that automatically transforms cloud services developed based on the Java Platform Module System into container-based systems.
With on-demand access to compute resources, pay-per-use, and elasticity, the cloud evolved into an attractive execution environment for High Performance Computing (HPC). Whereas elasticity, which is often referred to as the most beneficial cloud-specific property, has been heavily used in the context of interactive (multi-tier) applications, elasticity-related research in the HPC domain is still in its infancy. Existing parallel computing theory as well as traditional metrics to analytically evaluate parallel systems do not comprehensively consider elasticity, i.e., the ability to control the number of processing units at runtime. To address these issues, we introduce a conceptual framework to understand elasticity in the context of parallel systems, define the term elastic parallel system, and discuss novel metrics for both elasticity control at runtime as well as the ex post performance evaluation of elastic parallel systems. Based on the conceptual framework, we provide an in depth analysis of existing research in the field to describe the state-of-the art and compile our findings into a research agenda for future research on elastic parallel systems.
With the capability of employing virtually unlimited compute resources, the cloud evolved into an attractive execution environment for applications from the High Performance Computing (HPC) domain. By means of elastic scaling, compute resources can be provisioned and decommissioned at runtime. This gives rise to a new concept in HPC: Elasticity of parallel computations. However, it is still an open research question to which extent HPC applications can benefit from elastic scaling and how to leverage elasticity of parallel computations. In this paper, we discuss how to address these challenges for HPC applications with dynamic task parallelism and present TASKWORK, a cloud-aware runtime system based on our findings. TASKWORK enables the implementation of elastic HPC applications by means of higher level development frameworks and solves corresponding coordination problems based on Apache ZooKeeper. For evaluation purposes, we discuss a development framework for parallel branch-and-bound based on TASKWORK, show how to implement an elastic HPC application, and report on measurements with respect to parallel efficiency and elastic scaling.
An important shift in software delivery is the definition of a cloud service as an independently deployable unit by following the microservices architectural style. Container virtualization facilitates development and deployment by ensuring independence from the runtime environment. Thus, cloud services are built as container based systems - a set of containers that control the lifecycle of software and middleware components. However, using containers leads to a new paradigm for service development and operation: Self service environments enable software developers to deploy and operate container based systems on their own - you build it, you run it. Following this approach, more and more operational aspects are transferred towards the responsibility of software developers. In this work, we propose a concept for self-adaptive cloud services based on container virtualization in line with the microservices architectural style and present a model-based approach that assists software developers in building these services. Based on operational models specified by developers, the mechanisms required for self-adaptation are automatically generated. As a result, each container automatically adapts itself in a reactive, decentralized manner. We evaluate a prototype which leverages the emerging TOSCA standard to specify operational behavior in a portable manner.
Parallel applications are the computational backbone of major industry trends and grand challenges in science. Whereas these applications are typically constructed for dedicated High Performance Computing clusters and supercomputers, the cloud emerges as attractive execution environment, which provides on-demand resource provisioning and a pay-per-use model. However, cloud environments require specific application properties that may restrict parallel application design. As a result, design trade-offs are required to simultaneously maximize parallel performance and benefit from cloud-specific characteristics.
In this paper, we present a novel approach to assess the cloud readiness of parallel applications based on the design decisions made. By discovering and understanding the implications of these parallel design decisions on an application’s cloud readiness, our approach supports the migration of parallel applications to the cloud.We introduce an assessment procedure, its underlying meta model, and a corresponding instantiation to structure this multi-dimensional design space. For evaluation purposes, we present an extensive case study comprising three parallel applications and discuss their cloud readiness based on our approach.
The cloud evolved into an attractive execution environment for parallel applications from the High Performance Computing (HPC) domain. Existing research recognized that parallel applications require architectural refactoring to benefit from cloud-specific properties (most importantly elasticity). However, architectural refactoring comes with many challenges and cannot be applied to all applications due to fundamental performance issues. Thus, during the last years, different cloud migration strategies have been considered for different classes of parallel applications. In this paper, we provide a survey on HPC cloud migration research. We investigate on the approaches applied and the parallel applications considered. Based on our findings, we identify and describe three cloud migration strategies.
