EXTENSION OF AN OPEN SOURCE RESOURCE MANAGEMENT TOOL FOR HETEROGENEOUS CLOUD DATA CENTERS: IMPLEMENTATION AND EVALUATION

Download

Taha_Dogan_Thesis_Submitted.pdf

Date

2022-2-11

Author

Doğan, Taha

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

349
views

97
downloads

Cloud Computing is enabled by the virtualization of computing resources to realize users' requests of virtual machines (VMs) and data processing in the scope of Infrastructure as a Service (IaaS) and Software as a Service (SaaS) respectively. The current heterogeneous cloud data centers incorporate hardware accelerators in addition to the conventional servers to offer these services more efficiently. It is an important research problem to allocate heterogeneous physical computing resources to a mixture of IaaS and SaaS requests. On the one hand, the requirements of the requests should be satisfied. On the other hand, resource use and power consumption should be efficient. OpenStack is a popular cloud management platform that focuses on IaaS. It collects the user requests and accordingly instantiates VMs in the cloud data center. The default resource allocation of OpenStack only aims for fulfilling the user request without any further optimizations regarding efficient resource use. This thesis develops, implements and evaluates an extension of OpenStack to address the resource management and allocation of heterogeneous cloud data centers to address the requirements that we list above. The default filter-based resource allocation method of OpenStack only targets fulfilling the request requirements without any optimization concern. To this end, we integrate an ILP-based cloud resource allocation method with power minimization objectives in the most recent version of OpenStack that was available at the time of writing this thesis. We develop a software architecture that interfaces the ILP solver which provides all the required messaging according to the defined APIs of OpenStack. The entire extended implementation is realized in a laboratory set-up that features cloud servers, a 40 Gbps network and FPGA cards with hardware accelerators that represent a heterogeneous cloud data center.

Subject Keywords

Cloud computing, Hardware accelerator, Resource management, OpenStack, Nova

URI

https://hdl.handle.net/11511/96353

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Optimal dynamic resource allocation for heterogenous cloud data centers Ekici, Nazım Umut; Güran Schmidt, Şenan.; Department of Electrical and Electronics Engineering (2019) Today's data centers are mostly cloud-based with virtualized servers to provide on-demand scalability and flexibility of the available resources such as CPU, memory, data storage and network bandwidth. Heterogeneous cloud data centers (CDCs) offer hardware accelerators in addition to these standard cloud server resources. A cloud data center provider may provide Infrastructure as a Service and Platform as a Service (IPaaS), where the user gets a virtual machine (VM) with processing, memory, storage and netw...
A generalization of openstack for managing heterogeneous cloud resources Heterojen bulut kaynaklarinin yonetimi için openstack genelleştirimi Erol, Ahmet; Yazar, Alper; Schmidt, Şenan Ece (2019-04-01) This paper describes the generalization of OpenStack cloud resource management software to manage hardware resources other than the standard resources on the servers. To this end, OpenStack resource data structure is updated and the Nova project, which runs on the compute node, is rewritten so that it can run on different hardware platforms without depending on the operating system.
Generalized resource management for heterogeneous cloud data centers Erol, Ahmet; Güran Schmidt, Şenan Ece.; Department of Electrical and Electronics Engineering (2019) OpenStack is a widely used management tool for cloud computing which is designed to work on servers and allocate standard computing resources such as CPU, memory or disk. The current trend for integrating different hardware accelerators such as FPGAs and GPUs in the cloud requires managing these heterogeneous resources. In this thesis, we propose a generalization for OpenStack Nova project which extends the relevant data structures to include these new resources. More importantly, we present a new lightweig...
Hardware Accelerators for Cloud Computing: Features and Implementation Tirlioglu, Anil; Demir, Omer Bayram; Yazar, Alper; Schmidt, Şenan Ece (2021-01-01) In this paper, hardware accelerator (FHA) applications realized on FPGA that can be offered as a service in cloud computing systems are discussed. It is necessary to know the hardware resources used by FHA applications and the performance they provide for the efficient meeting of the user requests and effective resource planning. To this end, the first contribution of this paper is to provide a compilation of the literature on the features of frequently used hardware accelerators (matrix multiplication, fac...
OpenStack Generalization for Hardware Accelerated Clouds Erol, Ahmet; Yazar, Alper; Schmidt, Şenan Ece (2019-01-01) OpenStack is a widely used management tool for cloud computing which is designed to work on servers and allocate standard computing resources such as CPU, memory or disk. The current trend for integrating different hardware accelerators such as FPGAs and GPUs in the cloud requires managing these heterogeneous resources. In this paper, we propose a generalization for OpenStack Nova project which extends the relevant data structures to include these new resources. More importantly, we present a new lightweigh...

Citation Formats

T. Doğan, “EXTENSION OF AN OPEN SOURCE RESOURCE MANAGEMENT TOOL FOR HETEROGENEOUS CLOUD DATA CENTERS: IMPLEMENTATION AND EVALUATION,” M.S. - Master of Science, Middle East Technical University, 2022.