Palacios Virtual Machine Monitor

The Prognostic Lab | Computer Science Department | University of Pittsburgh

About

Palacios is a highly configurable virtual machine monitor (VMM) designed to be embeddable into a wide range of host operating systems. Currently it fully supports both Linux and Kitten based environments. When embedded into Kitten, the combination acts as a lightweight hypervisor supporting full system virtualization. Palacios can run on generic PC hardware, in addition to specialized hardware such as Cray supercomputer systems. In combination with Kitten, Palacios has been shown to provide near native performance when deploying tightly coupled HPC applications at large scale (4096 nodes on a Cray XT3).

This page contains information on a fork of the Palacios VMM maintained by the Prognostic Lab. Information on the original version of Palacios can be found on the V3Vee project page. Both versions of Palacios are distributed under the BSD license.

The Palacios Virtual Machine Monitor is a virtualization architecture designed explicitly for HPC environments. By focusing on HPC, the Palacios VMM is able to eschew many of the features deemed necessary for commodity environments and instead focus on the requirements needed for scalable HPC performance. Palacios integrates with both Linux and Kitten via a kernel module interface and so does not require any modifications to the kernel itself. This ensures compatibility with a wide range of kernel versions and OS architectures.

The original Palacios/Kitten development team (circa 2008)

Download Palacios

Checkout the source code:
git clone https://gitlab.prognosticlab.org/jarusl/palacios.git

Browse the Git repository

Related Publications

HPDC	[2015]	(pdf)	J. Ouyang, B. Kocoloski, J. Lange and K. Pedretti, Achieving Performance Isolation with Lightweight Co-Kernels, Proceedings of the 24th International ACM Symposium on High Performance Parallel and Distributed Computing, (HPDC 2015)

HPDC	[2015]	(pdf)	B. Kocoloski and J. Lange, XEMEM: Efficient Shared Memory for Composed Applications on Multi-OS/R Exascale Systems, Proceedings of the 24th International ACM Symposium on High Performance Parallel and Distributed Computing, (HPDC 2015)

CLUSTER	[2014]	(pdf)	L. Xia, Z. Cui, J. Lange, Y. Tang, P. Dinda, P. Bridges, Fast VMM-based Overlay Networking For Bridging the Cloud and High Performance Computing, Cluster Computing, Volume 17, Issue 1, pages 39-59, March 2014

IJHPCA	[2013]	(pdf)	B. Kocoloski and J. Lange, Improving Compute Node Performance Using Virtualization, International Journal of High Performance Computing Applications, Volume 27, Number 2, pages 124-135, May 2013

SOCC	[2012]	(pdf)	B. Kocoloski, J. Ouyang, and J.Lange, A Case for Dual Stack Virtualization: Consolidating HPC and Commodity Applications in the Cloud, Proceedings of the ACM Symposium on Cloud Computing, (SOCC 2012)

VEE	[2011]	(pdf)	J. Lange and P. Dinda, SymCall: Symbiotic Virtualization Through VMM-to-Guest Upcalls, Proceedings of the 2011 ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments, (VEE 2011)

VEE	[2011]	(pdf)	J. Lange, K. Pedretti, P. Dinda, P. Bridges, C. Bae, P. Soltero, and A. Merritt, Minimal Overhead Virtualization of a Large Scale Supercomputer, Proceedings of the 2011 ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments, (VEE 2011)

IPDPS	[2010]	(pdf)	J. Lange, K. Pedretti, T. Hudson, P. Dinda, Z. Cui, L. Xia, P. Bridges, M.Levenhagen, R. Brightwell, A. Gocke, S. Jaconette, Palacios: A New Open Source Virtual Machine Monitor for Scalable High Performance Computing, Proceedings of the 24th IEEE International Parallel and Distributed Processing Symposium, (IPDPS 2010)