PhD Student at the University of Victoria
warning: Creating default object from empty value in /home/chr10000/public_html/modules/taxonomy/ on line 34.


Overcast: Eclipsing High Pro le Open Source Cloud Initiatives @ OOPSLA09 Cloud Computing Workshop

Can Cloud Computing be used without the traditional clustered, high-availability and highly complicated software stacks from big vendors or high profile open source initiatives? This paper presents the position that by leveraging the virtualization that is inherent in the cloud, we can recompose cloud systems out of more simple building blocks, breaking the dependancy on complicated software stacks and creating more secure and reliable systems than at present.

Xen PV on CentOS5.3

I had a hell of a time getting CentOS 5.3 to run images from stacklet.  Turns out the problem was that centos does not correctly detect the block devices.

The output would look like this:

Pygrub Error

Trying to setup a new Xen image from stacklet, I came across an interesting error on a CentOS 5 machine.  After I launch the domain with the pygrub configuration I get this error:

Bare metal OSGI Equinox on Xen

Just a pointer to one of my summer projects. I am working for Google Summer of Code, sponsored by the Eclipse foundation to work on:  Bare metal OSGI Equinox on Xen

Virtualized Recomposition: Cloudy or Clear? Workshop on Software Engineering Challenges in Cloud Computing @ ICSE 2009

Virtualization provides a coarse-grained isolation mechanism that results in large systems, with full operating systems and a complete software stack as their foundation. Though much of this foundation is not strictly necessary, the programmatic burden of building systems at a finer-granularity, on a smaller foundation, has previously been shown to be prohibitive.

Quantifying Artifacts of Virtualization: A Framework for Mirco-Benchmarks QuEST09 @ AINA

One of the novel benefits of virtualization is the ability to emulate many hosts with a single physical machine.  This approach is often used to support at-scale testing for large-scale distributed systems.  In order to better understand the precise ways in which virtual machines differ from their physical counterparts, we have started to quantify some of the timing artifacts that appear to be common to two modern approaches to virtualization. Here we present several systematic experiments that highlight four timing artifacts, and begin to decipher their origins within vi