Abstract
This paper describes Project Kittyhawk, an undertaking at IBM Research to explore the construction of a next-generation platform capable of hosting many simultaneous web-scale workloads. We hypothesize that for a large class of web-scale workloads the Blue Gene/P platform is an order of magnitude more efficient to purchase and operate than the commodity clusters in use today. Driven by scientific computing demands the Blue Gene designers pursued an aggressive system-on-a-chip methodology that led to a scalable platform composed of air-cooled racks. Each rack contains more than a thousand independent computers with highspeed interconnects inside and between racks.
We postulate that the same demands of efficiency and density apply to web-scale platforms. This project aims to develop the system software to enable Blue Gene/P as a generic platform capable of being used by heterogeneous workloads. We describe our firmware and operating system work to provide Blue Gene/P with generic system software, one of the results of which is the ability to run thousands of heterogeneous Linux instances connected by TCP/IP networks over the high-speed internal interconnects.
- Appavoo, J., Silva, D. D., Krieger, O., Auslander, M., Ostrowski, M., Rosenburg, B., Waterland, A., Wisniewski, R. W., Xenidis, J., Stumm, M., and Soares, L. Experience distributing objects in an SMMP OS. ACM Transactions on Computer Systems (TOCS) 25, 3 (2007), 6. Google ScholarDigital Library
- Carter, J. B., Khandekar, D., and Kamb, L. Distributed shared memory: Where we are and where we should be headed. In Fifth Workshop on Hot Topics in Operating Systems (HotOS-V) (1995). Google ScholarDigital Library
- Coraid. EtherDrive Storage. http://coraid.com.Google Scholar
- Daly, D., Choi, J. H., Moreira, J. E., and Waterland, A. Base operating system provisioning and bringup for a commercial supercomputer. In International Parallel and Distributed Processing Symposium (IPDPS) (2007), IEEE.Google ScholarCross Ref
- Denx Software Engineering. Das U-Boot -- the Universal Boot Loader. http://www.denx.de/wiki/UBoot.Google Scholar
- Dunkels, A. lwIP -- A Lightweight TCP/IP stack. http://www.sics.se/~adam/lwip/.Google Scholar
- Dunkels, A. Full TCP/IP for 8-bit architectures. In The International Conference on Mobile Systems, Applications, and Services (MobiSys) (San Francisco, CA, May 2003), USENIX. Google ScholarDigital Library
- Fan, X., Weber, W.-D., and Barroso, L. A. Power provisioning for a warehouse-sized computer. In Proceedings of the 34th annual international symposium on Computer architecture (ISCA '07) (New York, NY, USA, 2007), ACM Press. Google ScholarDigital Library
- Goldberg, R. P. Survey of virtual machine research. IEEE Computer Magazine 7, 6 (1974).Google ScholarDigital Library
- Grbic, A., Brown, S., Caranci, S., Grindley, G., Gusat, M., Lemieux, G., Loveless, K., Manjikian, N., Srbljic, S., Stumm, M., Vranesic, Z., and Zilic, Z. Design and implementation of the NUMAchine multiprocessor. In Proceedings of the 1998 Conference on Design Automation (DAC-98) (Los Alamitos, CA, June 15--19 1998), ACM/IEEE. Google ScholarDigital Library
- IBM. Exploiting the Dual Floating Point Units in Blue Gene/L. White Paper 7007511, IBM, http://www-1.ibm.com/support/docview.wss?uid=swg27007511, June 2006.Google Scholar
- IEEE. 1149.1-1990 IEEE Standard Test Access Port and Boundary-Scan Architecture-Description. IEEE, New York, NY, USA, 1990. Google ScholarDigital Library
- Jain, N., Amini, L., Andrade, H., King, R., Park, Y., Selo, P., and Venkatramani, C. Design, implementation, and evaluation of the linear road benchmark on the stream processing core. In Proceedings of the 2006 ACM SIGMOD international conference on Management of data (SIGMOD '06) (New York, NY, USA, 2006), ACM Press. Google ScholarDigital Library
- Li, K. IVY: A shared virtual memory system for parallel computing. Proceedings of the 1988 International Conference on Parallel Processing, Vol. II Software (Aug. 1988).Google Scholar
- Liedtke, J. On μ-kernel construction. In Proceedings of the 15th ACM Symposium on Operating System Principles (SOSP '95) (Copper Mountain Resort, CO, Dec. 1995). Google ScholarDigital Library
- Seshadri, A., Luk, M., Shi, E., Perrig, A., van Doorn, L., and Khosla, P. Pioneer: Verifying integrity and guaranteeing execution of code on legacy platforms. In Proceedings of the 20th ACM Symposium on Operating System Principles (SOSP '07) (Brighton, UK, Oct. 2005), ACM. Google ScholarDigital Library
- The Standard Performance Evaluation Corporation (SPEC). SPECjbb2005 Java Server Benchmark. http://www.spec.org/jbb2005.Google Scholar
- Vise, D., and Malseed, M. The Google Story: Inside the Hottest Business, Media, and Technology Success of Our Time. Delta, Aug. 2006. Google ScholarDigital Library
Index Terms
- Project Kittyhawk: building a global-scale computer: Blue Gene/P as a generic computing platform
Recommendations
The turtles project: design and implementation of nested virtualization
OSDI'10: Proceedings of the 9th USENIX conference on Operating systems design and implementationIn classical machine virtualization, a hypervisor runs multiple operating systems simultaneously, each on its own virtual machine. In nested virtualization, a hypervisor can run multiple other hypervisors with their associated virtual machines. As ...
Supporting USB Devices for the Global Migration
SAINT '10: Proceedings of the 2010 10th IEEE/IPSJ International Symposium on Applications and the InternetVirtualization has been also used as desktop utility and supports VM migration, which is a function to migrate a VM (Virtual Machine) from a physical host to another. However, it cannot migrate hardware configuration of peripherals. We focus on USB ...
The Kaya OS project and the μMPS hardware emulator
Ideally, the most meaningful learning experience for students in an undergraduate OS course would be to develop fully-functional OS's on their own. This can be accomplished using μmps, a hardware emulator for a pedagogically undergraduate-appropriate ...
Comments