No abstract

Achieving cloud security is not a trivial problem and developing and enforcing good cloud security controls is a fundamental requirement if this is to succeed. The very nature of cloud computing can add additional problem layers for cloud security to an already complex problem area. We discuss why this is such an issue, consider what desirable characteristics should be aimed for and propose a novel means of effectively and efficiently achieving these goals through the use of unikernel based systems. The main thrust of this paper is to discuss the key issues which need to be addressed, noting which of those might be covered by our proposed approach. We discuss how our proposed approach may help better address the key security issues we have identified.

No abstract

Achieving cloud security is not a trivial problem to address. Developing and enforcing good cloud security controls are fundamental requirements if this is to succeed. The very nature of cloud computing can add additional problem layers for cloud security to an already complex problem area. We discuss why this is such an issue, consider what desirable characteristics should be aimed for and propose a novel means of effectively and efficiently achieving these goals through the use of well-designed unikernel-based systems. We have identified a range of issues, which need to be dealt with properly to ensure a robust level of security and privacy can be achieved. We have addressed these issues in both the context of conventional cloud-based systems, as well as in regard to addressing some of the many weaknesses inherent in the Internet of things. We discuss how our proposed approach may help better address these key security issues which we have identified.

The smallest instance offered by Amazon EC2 comes with 615MB memory and a 7.9GB disk image. While small by today's standards, embedded web servers 1 with memory footprints well under 100kB, indicate that there is much to be saved. In this work we investigate how large VMpopulations the openStack hypervisor can be made to sustain, by tuning it for scalability and minimizing virtual machine images. Request-driven Qemu images of 512 byte are written in assembly, and more than 110 000 such instances are successfully booted on a 48 core host, before memory is exhausted. Other factors are shown to dramatically improve scalability, to the point where 10 000 virtual machines consume no more than 2.06% of the hypervisor CPU.