| | |
Summary: Harnessing Virtual Machine Resource Control for Job Management
Laura Grit, David Irwin, Varun Marupadi, Piyush Shivam
Aydan Yumerefendi, Jeff Chase, and Jeannie Albrecht
Duke University University of California, San Diego
{grit,irwin,varun,shivam,aydan,chase}@cs.duke.edu,jalbrecht@cs.ucsd.edu
Abstract
Virtual machine technology promises important ben-
efits for grid computing and cluster batch job systems,
including improved isolation, customizable workspaces,
and support for checkpointing and migration. One way
to gain these benefits is to "drill holes" in existing batch
computing systems; however, we believe these new capa-
bilities warrant a rethinking of the architectures of exist-
ing systems. We propose separating resource control for
VMs into a new foundational layer that focuses narrowly
on resource management.
We present JAWS, a new batch computing service that
is built as a thin-layer above a resource control plane
that enables it to share a common pool of networked
cluster resources with other cluster services. JAWS ex-
|
