Abstract

When multiple jobs compete for processing resources on a parallel computer, the operating system kernel's processor allocation policy determines how many and which processors to allocate to each. This dissertation investigates the issues involved in constructing a processor allocation policy for large scale, message-passing parallel computers supporting a scientific workload. First, the issues that affect the performance of scheduling policies for message-passing parallel systems are examined. We argue that reasonable policies must provide nearly equal resource allocation to all runnable jobs and allocate, to a single job, processors that are in close proximity to one another. Second, the concept of efficiency preservation is defined as a characteristic of processor allocation policie...

Citations

8882	Computers and Intractability: A Guide to the Theory of NP-completeness - Garey, Johnson - 1979
911	Active messages: a mechanism for integrated communication and computation - Eicken, Culler, et al. - 1992
420	Scheduler activations: Effective kernel support for the user-level management of threads - Anderson, Bershad, et al. - 1992
261	Scheduling Techniques for Concurrent Systems - Ousterhout - 1982
242	Lightweight remote procedure call - Bershad, Anderson, et al. - 1990
191	Process control and scheduling issues for multiprogrammed shared-memory multiprocessors - Tucker, Gupta - 1989
147	The performance of multiprogrammed multiprocessor scheduling policies - Leutenegger, Vernon - 1990
137	A dynamic processor allocation policy for multiprogrammed shared-memory multiprocessors - McCann, Vaswani, et al. - 1993
129	Speedup versus efficiency in parallel systems - Eager, Zahorjan, et al. - 1986
127	The impact of operating system scheduling policies and synchronization methods on the performance of parallel applications - Gupta, Tucker, et al. - 1991
119	Data-Parallel Programming on MIMD Computers - Hatcher, Quinn - 1991
108	The Implications of Cache Affinity on Processor Scheduling for Multiprogrammed Shared Memory Multiprocessors - Vaswani, Zahorjan - 1991
99	Characterizations of Parallelism in Applications and their Use in Scheduling - Sevcik - 1989
99	Supporting shared data structures on distributed memory machine s - Koebel, Mehrotra, et al. - 1990
95	Limits to Low-Latency Communication on High-Speed Networks.” ACM Transactions on Computer Systems,11(2):179–203, May 1993. Wolman is a graduate student at the University of Washington, currently on leave from Digital Equipment Corporation’s Cambridge Rese - Thekkath, Levy - 1992
90	Processor Scheduling in Shared Memory Multiprocessors - Zahorjan, McCann - 1990
84	Using processor-cache affinity information in shared-memory multiprocessor scheduling - Squillante, Lazowska - 1993
84	R.L.: Orthogonal packings in two dimensions - Baker, Coffman, et al. - 1980
83	Architectural requirements of parallel scientific applications with explicit communication - Cypher, Ho, et al. - 1993
83	Use of Application Characteristics and Limited Preemption for Run-to-Completion Parallel Processor Scheduling Policies - Chiang, Mansharamani, et al. - 1994
73	Scheduling in multiprogrammed parallel systems - Majumdar, Eager, et al. - 1988
70	Distributed hierarchical control for parallel processing - Feitelson, Rudolph - 1990
70	The DINO parallel programming language - Rosing, Schnabel, et al. - 1991
68	Sharing and Protection in a Single Address Space Operating System - CHASE, LEVY, et al. - 1994
62	R.E.: Performance bounds for level-oriented two-dimensional packing algorithms - Coffman, Garey, et al. - 1980
60	Application Scheduling and Processor Allocation in Multiprogrammed Parallel Processing Systems - Sevcik - 1993
58	On the Partitioning of Multiprocessor Systems - Dowdy - 1988
54	The effect of scheduling discipline on spin overhead in shared memory parallel systems - Zahorjan, Lazowska, et al. - 1991
48	Processor allocation in an n-cube multiprocessor using gray codes - Chen, Shin - 1987
45	Performance analysis of job scheduling policies in parallel supercomputing environments - Naik, Setia, et al. - 1993
44	Exploiting heterogeneous parallelism on a multithreaded multiprocessor - Alverson, Alverson, et al. - 1992
43	Spinning versus blocking in parallel systems with uncertainty - Zahorjan, Lazowska, et al. - 1988
40	Multiprogramming on Multiprocessors - Crovella, Das, et al. - 1991
38	Robust Partitioning Policies for Multiprocessor Systems - Rosti, Smirni, et al. - 1994
32	The Chare Kernel parallel programming language and system - Kale - 1990
29	Processor Pool-Based Scheduling for Large-Scale NUMA Multiprocessors - Zhou, Brecht - 1991
27	Analysis of the Impact of Memory in Distributed Parallel Processing Systems - Peris, Squillante, et al. - 1994
22	Processor scheduling on multiprogrammed, distributed memory parallel computers - Setia, Squillante, et al. - 1993
22	Subcube Allocation and Task Migration in Hypercube Multiprocessor - Chen, Shin - 1990
21	Dynamic Partitioning in a Transputer Environment - Dussa, Carlson, et al. - 1990
21	Job scheduling in a partitionable mesh using a two-dimensional buddy system partitioning scheme - Li, Cheng - 1991
19	Scheduling Parallelizable Tasks: Putting it All on the Shelf - Turek, Wolf, et al. - 1992
13	Scheduling of Large Scientific applications on distributed Memory Multiprocessor Systems - Naik, Setia, et al. - 1993
6	Scheduling independent jobs on partitionable hypercubes - Chen, Lai - 1991
5	Accurate Modeling of Parallel Scientific Computations - Nicol, Townsend - 1989
4	Scheduling multiple queries on a parallel machine - Wolf, Turek, et al. - 1994
3	Multiprogramming a Distributed Memory Multiprocessor, Concurrency: Practice and Experience - Leuze, Dowdy, et al. - 1989
1	Adhara: A Run-Time Support System for Space-Based Applications - Ashok
1	Support of Gang Scheduling - In - 1991
1	Scheduling on Multiprogrammed, Distributed Mmoery Parallel Computers - Setia - 1993