The use of virtualization technologies in high performance computing (HPC) environments has traditionally been avoided due to their inherent performance overhead. However, with the rise of container-based virtualization implementations, such as Linux VServer, OpenVZ and Linux Containers (LXC), it is possible to obtain a very low overhead leading to near-native performance. In this work, we conducted a number of experiments in order to perform an in-depth performance evaluation of container-based virtualization for HPC. We also evaluated the trade-off between performance and isolation in container-based virtualization systems and compared them with Xen, which is a representative of the traditional hypervisor-based virtualization systems used today.
1 October 2011 in Future Generation Computer Systems
Elasticity is undoubtedly one of the most striking characteristics of cloud computing. Especially in the area of high performance computing (HPC), elasticity can be used to execute irregular and CPU-intensive applications. However, the on- the-fly increase/decrease in resources is more widespread in Web systems, which have their own IaaS-level load balancer. Considering the HPC area, current approaches usually focus on batch jobs or assumptions such as previous knowledge of application phases, source code rewriting or the stop-reconfigure-and-go approach for elasticity. In this context, this article presents AutoElastic, a PaaS-level elasticity model for HPC in the cloud. Its differential approach consists of providing elasticity for high performance applications without user intervention or source code modification. The scientific contributions of AutoElastic are twofold: (i) an Aging-based approach to resource allocation and deallocation actions to avoid unnecessary virtual machine (VM) reconfigurations (thrashing) and (ii) asynchronism in creating and terminating VMs in such a way that the application does not need to wait for completing these procedures. The prototype evaluation using OpenNebula middleware showed performance gains of up to 26 percent in the execution time of an application with the AutoElastic manager. Moreover, we obtained low intrusiveness for AutoElastic when reconfigurations do not occur.
Unikernels are a promising alternative for application deployment in cloud platforms. They comprise a very small footprint, providing better deployment agility and portability among virtualization platforms. Similar to Linux containers, they are a lightweight alternative for deploying distributed applications based on microservices. However, the comparison of unikernels with other virtualization options regarding the concurrent provisioning of instances, as in the case of microservices-based applications, is still lacking. This paper provides an evaluation of KVM (Virtual Machines), Docker (Containers), and OSv (Unikernel), when provisioning multiple instances concurrently in an OpenStack cloud platform. We confirmed that OSv outperforms the other options and also identified opportunities for optimization.
Cloud resources and services are offered based on Service Level Agreements (SLAs) that state usage terms and penalties in case of violations. Although, there is a large body of work in the area of SLA provisioning and monitoring at infrastructure and platform layers, SLAs are usually assumed to be guaranteed at the application layer. However, application monitoring is a challenging task due to monitored metrics of the platform or infrastructure layer that cannot be easily mapped to the required metrics at the application layer. Sophisticated SLA monitoring among those layers to avoid costly SLA penalties and maximize the provider profit is still an open research challenge. This paper proposes an application monitoring architecture named CASViD, which stands for Cloud Application SLA Violation Detection architecture. CASViD architecture monitors and detects SLA violations at the application layer, and includes tools for resource allocation, scheduling, and deployment. Different from most of the existing monitoring architectures, CASViD focuses on application level monitoring, which is relevant when multiple customers share the same resources in a Cloud environment. We evaluate our architecture in a real Cloud testbed using applications that exhibit heterogeneous behaviors in order to investigate the effective measurement intervals for efficient monitoring of different application types. The achieved results show that our architecture, with low intrusion level, is able to monitor, detect SLA violations, and suggest effective measurement intervals for various workloads.