darrell@cs.ucsd.edu (Darrell Long) (01/25/88)
[ Once again, if you are an active OS researcher, I would like to hear from ] [ you. I am compiling a list of OS research projects and contacts. --DL ] Kurt Zeilenga (zeilenga@hc.dspo.gov) Hyper UNIX Parallel Processing Research Group Deptartment of Electrical and Computer Engineering University of New Mexico Albuquerque, NM 87131 Maurice Herlihy (HERLIHY@C.CS.CMU.EDU) Avalon Carnegie-Mellon University Computer Science Department Schenley Park Pittsburgh, PA 15213
darrell@cs.ucsd.edu (Darrell Long) (02/17/88)
[ This is the latest and greatest version of the OS contact list. There are ]
[ some notable changes and well as additions. There are also some people who ]
[ are very obviously missing (you know who you are, and I won't add you till ]
[ you send your permission). --DL ]
Kurt Zeilenga (zeilenga@hc.dspo.gov) Hyper UNIX
Parallel Processing Research Group
Department of Electrical and Computer Engineering
University of New Mexico
Albuquerque, NM 87131
Availability: internal only.
Fred Douglis (douglis@ginger.Berkeley.EDU) Sprite
(spriters@ginger.Berkeley.EDU)
Computer Science Division
571 Evans Hall
University of California
Berkeley, CA 94720
Availability: not ready to estimate.
Ken Birman (ken@gvax.cs.cornell.edu) ISIS
Department of Computer Science
4105 Upson Hall
Cornell University
Ithaca, New York 14853
Availability: summer 1988.
Tony Mason (mason@pescadero.stanford.edu) V
Distributed Systems Group
Stanford University
Availability: A version is available now (version 6.0) and a new release is
tentatively scheduled for this summer (version 7.0.)
E. Douglas Jensen (edj@cs.cmu.edu) Alpha
(ksr!edj@harvard.harvard.edu)
Kendall Square Research
Cambridge, MA
(617) 494-1146
Bob Bruce (rab@mimsy.umd.edu) Parallel OS
University of Maryland
Laboratory for Parallel Computation
Department of Computer Science
College Park, MD 20742
Calton Pu (calton@cs.columbia.edu) Synthesis
Department of Computer Science
Columbia University
New York, NY 10027
(212) 280-8110
Availability: internal only -- so far.
Andy Tanenbaum (ast@cs.vu.nl) Amoeba
Department of Mathematics and Computer Science
Vrije Universiteit
Postbus 7161
1007 MC Amsterdam Holland
Jan Edler (edler@nyu.edu) Ultra
New York University
251 Mercer Street
New York, NY 10012
(212) 998-3353
Richard D. Schlichting (rick@arizona.edu) Saguaro
Department of Computer Science
The University of Arizona
Tucson, AZ 85721
Michael L. Scott (scott@cs.rochester.edu) Psyche
(716) 275-7745
Thomas J. LeBlanc (leblanc@cs.rochester.edu)
(716) 275-5426
Department of Computer Science
University of Rochester
Rochester, NY 14627
John Nicol (cosmos@comp.lancs.ac.uk) Cosmos
The COSMOS Research Group
Department of Computing
University of Lancaster
Bailrigg
Lancaster, LA1 4YR,
UNITED KINGDOM
+44 (0) 524 65201 Ext 4145, 4146
Ami Litman (ami@bellcore.com) DUNIX
Bell Communications Research
435 South street
Morristown, N.J. 07960
(201) 829-4377
Availability: DUNIX on VAX's is in use as of September, 1986.
Porting to Suns and MicroVAX's is currently under way.
Bellcore distributes DUNIX free to universities and
research institutions.
Greg Burns (gdburns@tcgould.tn.cornell.edu) Trillium
Cornell Theory Center
265 Olin Hall
Ithaca, NY 14853-5201
Kevin Murray (murray@minster.york.ac.uk) Wisdom
Department of Computer Science
University of York
York, UK, YO1 5DD
Rick Rashid (rashid@cs.cmu.edu) MACH
Department of Computer Science
Carnegie Mellon University
Pittsburgh, PA 15213
(412) 268-2617
Project: Mach
Availability: Since January 1987, current release number: 2
Machine types: VAX, SUN 3, IBM RT
Cost: None (no distribution fee, tape fee, license fee or royalty)
Licenses: Berkeley 4.3bsd (VAX & RT), SunOS binary (SUN)
Contact: Mach Project
c/o Debbie Lynn
Department of Computer Science
Carnegie Mellon University
Pittsburgh, PA 15213
(412) 268-7665
mach@cs.cmu.edu
Pamela Reyner Scott (REYNER@CS.CMU.EDU) Avalon
Carnegie Mellon University
Computer Science Department
Schenley Park
Pittsburgh, PA 15213
Availability: about one year from now.darrell@cs.ucsd.edu (Darrell Long) (03/09/88)
[ This is the last version of the OS contact list. I haven't gotten ]
[ any submissions for a couple of weeks so I think that it is stable. ]
[ My thanks to everyone who contributed! --DL ]
Kurt Zeilenga (zeilenga@hc.dspo.gov) Hyper UNIX
Parallel Processing Research Group
Department of Electrical and Computer Engineering
University of New Mexico
Albuquerque, NM 87131
Availability: internal only.
Fred Douglis (douglis@ginger.Berkeley.EDU) Sprite
(spriters@ginger.Berkeley.EDU)
Computer Science Division
571 Evans Hall
University of California
Berkeley, CA 94720
Availability: not ready to estimate.
Ken Birman (ken@gvax.cs.cornell.edu) ISIS
Department of Computer Science
4105 Upson Hall
Cornell University
Ithaca, New York 14853
Availability: summer 1988.
Tony Mason (mason@pescadero.stanford.edu) V
Distributed Systems Group
Stanford University
Availability: A version is available now (version 6.0) and a new release is
tentatively scheduled for this summer (version 7.0.)
E. Douglas Jensen (edj@cs.cmu.edu) Alpha
(ksr!edj@harvard.harvard.edu)
Kendall Square Research
Cambridge, MA
(617) 494-1146
Bob Bruce (rab@mimsy.umd.edu) Parallel OS
University of Maryland
Laboratory for Parallel Computation
Department of Computer Science
College Park, MD 20742
Calton Pu (calton@cs.columbia.edu) Synthesis
Department of Computer Science
Columbia University
New York, NY 10027
(212) 280-8110
Availability: internal only -- so far.
Andy Tanenbaum (ast@cs.vu.nl) Amoeba
Department of Mathematics and Computer Science
Vrije Universiteit
Postbus 7161
1007 MC Amsterdam Holland
Jan Edler (edler@nyu.edu) Ultra
New York University
251 Mercer Street
New York, NY 10012
(212) 998-3353
Richard D. Schlichting (rick@arizona.edu) Saguaro
Department of Computer Science
The University of Arizona
Tucson, AZ 85721
Michael L. Scott (scott@cs.rochester.edu) Psyche
(716) 275-7745
Thomas J. LeBlanc (leblanc@cs.rochester.edu)
(716) 275-5426
Department of Computer Science
University of Rochester
Rochester, NY 14627
John Nicol (cosmos@comp.lancs.ac.uk) Cosmos
The COSMOS Research Group
Department of Computing
University of Lancaster
Bailrigg
Lancaster, LA1 4YR,
UNITED KINGDOM
+44 (0) 524 65201 Ext 4145, 4146
Ami Litman (ami@bellcore.com) DUNIX
Bell Communications Research
435 South street
Morristown, N.J. 07960
(201) 829-4377
Availability: DUNIX on VAX's is in use as of September, 1986.
Porting to Suns and MicroVAX's is currently under way.
Bellcore distributes DUNIX free to universities and
research institutions.
Greg Burns (gdburns@tcgould.tn.cornell.edu) Trillium
Cornell Theory Center
265 Olin Hall
Ithaca, NY 14853-5201
Kevin Murray (murray@minster.york.ac.uk) Wisdom
Department of Computer Science
University of York
York, UK, YO1 5DD
Rick Rashid (rashid@cs.cmu.edu) MACH
Department of Computer Science
Carnegie Mellon University
Pittsburgh, PA 15213
(412) 268-2617
Project: Mach
Availability: Since January 1987, current release number: 2
Machine types: VAX, SUN 3, IBM RT
Cost: None (no distribution fee, tape fee, license fee or royalty)
Licenses: Berkeley 4.3bsd (VAX & RT), SunOS binary (SUN)
Contact: Mach Project
c/o Debbie Lynn
Department of Computer Science
Carnegie Mellon University
Pittsburgh, PA 15213
(412) 268-7665
mach@cs.cmu.edu
Pamela Reyner Scott (REYNER@CS.CMU.EDU) Avalon
Carnegie Mellon University
Computer Science Department
Schenley Park
Pittsburgh, PA 15213
Availability: about one year from now.
Partha Dasgupta (partha@gatech.edu) Clouds
School of Infomation and Computer Science
Georgia Institute of Technology
Atlanta GA 30332
(404) 894-2572
Availability: end of 1988, internally.
Dr. M. Sloman (mss@doc.ic.ac.uk) Conic
Dr. J. Kramer
Dr. J. Magee
Department of Computing
Imperial College
180 Queensgate
London, UK
SW7 2BZ
(+44-1) 589 5111 extention (5041, 5058, 5040, 5043)
Raphael A. Finkel (raphael@ms.uky.edu) Yackos, DIG
POT 959
Computer Science Department
University of Kentucky
Lexington, KY 40506-0027
James C. Berets (jberets@bbn.com) Cronus
BBN Laboratories
10 Moulton Street
Cambridge, MA 02238
(617) 873-2593
Graham Parrington (graham@cheviot.newcastle.ac.uk) Arjuna
Computing Laboratory
University of Newcastle upon Tyne
Claremont Tower
Claremont Road
Newcastle upon Tyne
NE1 7RU
ENGLAND
Darrell Long
Department of Computer Science & Engineering, UC San Diego, La Jolla CA 92093
ARPA: Darrell@Beowulf.UCSD.EDU UUCP: darrell@sdcsvax.uucp
Operating Systems submissions to: comp-os-research@sdcsvax.uucpguy@cs.ucla.edu (Richard Guy) (09/21/89)
| Date: Sat, 19 Aug 89 10:40:07 EDT | From: siegel@cs.cornell.edu (Alexander Siegel) | Subject: Deceit File System project Title: Deceit Distributed File System Contacts: Alex Siegel (siegel@cs.cornell.edu) Ken Birman (ken@cs.cornell.edu) Kieth Marzullo (marzullo@cs.cornell.edu) Deceit is a distributed file system which is being developed at Cornell, and it focuses on flexible file semantics in relation to efficiency, scalability, and reliability. Deceit servers are functionally interchangable and collectively provide the illusion of a single, large server machine to any clients which mount Deceit. Stable copies of each file are stored on a subset of the file servers. The user is able to set parameters on a file to achieve different levels of availability, performance, and one-copy behavior. Deceit behaves as a plain NFS server and can be mounted by any NFS client without modifying any client software. The current Deceit prototype uses the ISIS Distributed Programming Environment for all communication and processor group management. Availability: early prototypes available ================================================================================ | Date: Mon, 21 Aug 89 15:47:09 EDT | From: heddaya@CS.BU.EDU (Abdelsalam Heddaya) | Subject: BURDS: BU Replicated Data System Here's an entry that refers to my current project to experiment with replication methods for typed data. This project is related to operating systems the same way file systems are. If this passes your test for relevance, I'd appreciate it if you include it in the list you're compiling. Thanks. Abdelsalam A. Heddaya (heddaya@cs.bu.edu) BURDS: BU Replicated Data System Abdelsalam A. Heddaya Computer Science Department Boston University 111 Cummington St. Boston, MA 02215 (617) 353-8922 Availability: in development. ================================================================================ | Date: Tue, 22 Aug 89 14:49:37 CDT | From: roy@roy.cs.uiuc.edu (Roy Campbell) | Subject: Choices Roy Campbell (roy@cs.uiuc.edu) Choices (217) 333-0215 Vince Russo (russo@cs.uiuc.edu) (217) 333-7937 Department of Computer Science University of Illinois 1304 W. Springfield Av. Urbana, IL 61801 Availability: Stable.7.25.1989, release number: 0.0.2. Machine types: Encore Multimax NS 32332. (Future releases: MC68030, Intel 386). Cost: None (no distribution fee, license fee or royalty). License: From University of Illinois: Choices Software Distribution. Contact: Tapestry Project c/o Anda Harney Department of Computer Science 1304 W. Springfield Av. University of Illinois Urbana, IL 61801 (217) 333-3328 harney@cs.uiuc.edu Comments: Work in progress. The system, as distributed, is incomplete. ================================================================================ | Date: Wed, 23 Aug 89 16:11:35 -0400 | From: ogud@cs.UMD.EDU (Olafur Gudmundsson) | Subject: Maruti Operating system procject MARUTI, A Distributed, Fault-Tolerant, Hard Real-Time Operating System Contacts: Ashok K. Agrawala Olafur Gudmundsson Department of Computer Science Department of Computer Science University of Maryland University of Maryland College Park, MD 20742 College Park, MD 20742 agrawala@brillig.umd.edu ogud@mimsy.umd.edu (301) 454 4968 (301)-454-6497 Keywords - Hard Real-Time, Distributed, Object Oriented, Fault Tolerant, Operating system. In order to address the computational needs of the realtime applications of tomorrow it is essential that the operating system support the fault- tolerant, distributed operation while assuring the meeting of the hard real-time requirements of processing. MARUTI is an operating system environment which includes the kernel and a set of support tools aimed at addressing the issues of design, implementation and maintenance of real-time applications. MARUTI operating system has been designed as an object oriented system with suitable extensions to the standard concepts of objects to provide efficient real-time implementations. The scheduling approach includes a verification step which assures the meeting of the deadline once the processing request has been accepted by the system. The resource allocation addresses the application specific fault tolerance needs and guarantees the hard real-time performance within the constraints of the requested fault tolerance levels. This system uses a uniform mechanism for fault monitoring and reporting as well as recovery and permits the use of a variety of techniques for handling faults. It also provides a security model for the applications. The approach taken in this effort has been to implement the complete system and use it for developing applications as well as studying the design and implementation issues for hard real-time systems. Availability: Prototype will be distributable next year ================================================================================ | Date: Thu, 24 Aug 89 09:46:08 -0200 | From: deswarte@laas.laas.fr (Yves Deswarte) | Subject: Saturne SATURNE is a research project aiming at exploiting as much as possible the distribution of workstations on LANs in order to increase fault-tolerance, as well for accidental faults (e.g. harware faults) as for deliberate faults (e.g. intrusions). Two main techniques are currently developed in the scope of the Saturne project : - To tolerate accidental faults, the SATURATION technique consists in using idle resources in order to increase the redundancy of active tasks rather than decrease their response time. - To tolerate deliberate faults, the Fragmentation-and-Scattering technique consists in cutting information in small fragments such that isolated fragments cannot deliver significant information, and in disseminating those fragments throughout the distributed system. This technique has been first applied to the design of a secure file archiving service, and is currently developped for implementation of an "intrusion-tolerant" network security service. Contact : Yves Deswarte LAAS-CNRS and INRIA 7, avenue du Colonel Roche 31077 TOULOUSE FRANCE tel.: +33/ 61 33 62 88 E-mail: deswarte@laas.laas.fr or: y_deswarte@eurokom.ie ================================================================================ | From: Mark Little <M.C.Little%newcastle.ac.uk@NSFNET-RELAY.AC.UK> | Date: Thu, 24 Aug 89 14:00:48 +0100 | Subject: Arjuna Project Name: Arjuna Project Members (August 1989): Santosh K. Shrivastava (principle investigator and coordinator) Graham D. Parrington Stuart M. Wheater Fariba Hedayati Mark C. Little Shangjie Jin Contacts: Stuart M. Wheater Mark C. Little Stuart.Wheater@uk.ac.newcastle M.C.Little@uk.ac.newcastle Computing Laboratory, University of Newcastle upon Tyne, Newcastle upon Tyne, NE1 7RU, England. Environment: Sun-3 workstations Description: Arjuna is an object-oriented programming system that provides a set of tools for the construction of fault-tolerant distributed applications. A prototype version written in C++ has been designed and implemented to run on a collection of Unix workstations connected by a local area network.Arjuna provides nested atomic actions (nested atomic transactions) for structuring application programs. Atomic actions operate on objects, which are instances of abstract data types (C++ classes), by making use of remote procedure calls (RPCs). The design and implementation goal of Arjuna was to provide a state of the art programming system for constructing fault-tolerant distributed applications. In meeting this goal, three system properties were considered highly important: (i) Integration of mechanisms: a fault-tolerant distributed system requires a variety of system functions for naming, locating and invoking operations upon local and remote objects and also for concurrency control, error detection and recovery from failures etc. These mechanisms must be provided in an integrated manner such that their use is easy and natural. (ii) Flexibility: these mechanisms should also be flexible, permitting application specific enhancements, such as type-specific concurrency and recovery control, to be easily produced from existing default ones. (iii) Portability: the system should be easy to install and run on a variety of hardware configurations. The computational model of atomic actions controlling operations upon objects provides a natural framework for incorporating integrated mechanisms for fault- tolerance and distribution. In Arjuna, these mechanisms have been provided through a number of C++ classes; these classes have been organised into a class/ type hierarchy in a manner which will be familiar to the developers of 'traditional' (single node) centralised object-oriented systems. Arjuna is novel with respect to other fault-tolerant distributed systems in taking the approach that every major entity in the system is an object. Thus, Arjuna not only supports an object-oriented model of computation, but its internal structure is also object-oriented. This approach permits the use of the type inheritance mechanism of object-oriented systems for incorporating the properties of fault- tolerance and distribution in a very flexible way, permitting the implementation of concurrency control and recovery for objects in a type specific manner. In this aspect, Arjuna bears some resemblence to the Avalon/C++ system. Also, Arjuna has been implemented without any changes to the underlying operating system (Sun Unix), making it quite portable. Publications: S. K. Shrivastava, G. N. Dixon, G. D. Parrington. Objects and Actions in reliable distributed systems. IEE Software Eng. Journal, September 1987. F. Panzieri, S. K. Shrivastava. Rajdoot: a remot procedure call mechanism supporting orphan detection and killing. IEEE Trans. on Softwrae Eng. January 1988. G. N. Dixon. Object management for persistence and recoverability PhD Thesis, Technical Report 276, December 1988. G. D. Parrington. Management of concurrency in a reliable object-oriented system. PhD Thesis, Technical Report 277, December 1988. G. N. Dixon, S. K. Shrivastava. Exploiting type inheritance facilities to implement recoverability in object based systems. Proc. of 6th Symp. on Reliability in Distributed Software and Database Systems, Williamsburg, march 1987. G. N. Dixon, S. K. Shrivastava, G. D. Parrington. Managing persistent objects in Arjuna: a system for reliable distributed computing. Proc. of Workshop on persistent object systems, St. Andrews, Aug 1987. S. K. Shrivastava, L. Mancini, B. Randell. On the duality of fault-tolerant system structures. Workshop on experiences with dist. systems, Kaiserslautern, Lecture Notes in Computer Science, Vol 309, Sept. 1987 G. D. Parrington, S. K. Shrivastava. Implementing concurrency control in reliable distributed object-oriented systems. ECOOP88, Lecture Notes in Computer Science, Vol. 322. S.K. Shrivastava, G.N. Dixon, G.D. Parrington, F. Hedayati, S.M. Wheater and M. Little, The Design and Implementation of Arjuna. Technical Report, 1989. G. N. Dixon, G. D. Parrington, S. K. Shrivastava, S. M. Wheater. The treatment of persistent objects in Arjuna. ECOOP89, July 1989 (also, The Computer Journal, Vol. 32, Aug 1989). ================================================================================ | Date: Mon, 28 Aug 89 08:26:57 EDT | From: king@grasp.cis.upenn.edu | Subject: Timix Name: Timix Where: University of Pennsylvania Contact: Mr. Robert King Department of Computer and Information Science University of Pennsylvania Philadelphia, PA 19104-6389 king@grasp.cis.upenn.edu Primary Investigator: Dr. Insup Lee Department of Computer and Information Science University of Pennsylvania Philadelphia, PA 19104-6389 lee@central.cis.upenn.edu (215) 898-3532 Environment: MicroVAX processors connected via Ethernet and/or ProNET-10 Description: Timix is a real-time kernel being developed to support distributed applications, such as those found in the robotics domain. It supports processes with independent address spaces that execute, communicate and handle devices within timing constraints. The two basic communication paradigms supported are signals and asynchronous port-based message passing. New devices, which are directly controlled by application processes, can be integrated into the system without changing the kernel. Dynamic timing constraints are used for scheduling processes and interprcess communications. References: I. Lee, R. King, and R. Paul. A Predictable Real-Time Kernel for Distributed Multi-Sensor Systems. IEEE Computer (June 1989), 22(6):78 - 83. I. Lee, R. King, and R. Paul. RK: A Real-Time Kernel for Distributed System with Predictable Response. Technical Report MS-CIS-88-78, Department of Computer and Information Science, University of Pennsylvania (October 1988). I. Lee, R. King, and X. Yun. A Real-Time Kernel for Distributed Multi-Robot Systems. Proceedings of the American Control Conference (June 1988), 1083-1088. I. Lee and R. King. Timix: A Distributed Real-Time Kernel for Multi-Sensor Robots. Proceedings of the IEEE International Conference on Robotics and Automation (April 1988), 1587-1589. I. Lee, R. King, and G. Holder. Timix: A Distributed Kernel for Real-Time Applications. Proceedings of the IEEE Workshop on Design Principles for Experimental Distributed Systems (October 1986). ================================================================================ | Date: Tue, 29 Aug 89 18:34:05 +0200 | From: mcvax!imag.fr!krakowia@uunet.UU.NET (Sacha Krakowiak) | Subject: Guide Sacha Krakowiak (krakowiak@imag.imag.fr) Guide : Object-Oriented Distributed System Sacha Krakowiak Bull-IMAG 2 rue de Vignate 38610 GIERES FRANCE [This is a joint research unit involving Bull and University of Grenoble] +33 76 51 78 79 Availability: in development (prototype version should be available mid-90) ================================================================================ | From: banatre@irisa.fr | Date: 5 Sep 89 13:47:26 GMT | Subject: GOTHIC contact GOTHIC is a researh project aiming at providing an advanced programming system for developping fault-tolerant distributed applications. Two main issues in this project: -The design and the realization of fault-tolerant multi-processor workstations based on the active stable storage mechanism which incorporates built-in mechanisms for the implementation of atomicity. -The design and the implementation of languages features which reconciled object-oriented programming and parallelism. This is achieved with the introduction of the concept of multiprocedure which allows the expression of fine grain parallelism and its control within a generalized procedural framework. Multiprocedures operate on fragmented objects which are instances of abstract data types (classes), the concrete representation of such objects can be located on a set of virtual nodes. These language features have been added to Modula-2. A first prototype version of the GOTHIC system has been designed and implememted to run on a collection of fault-tolerant multiprocessor workstations connected by a local area network. Contact: Michel BANATRE INRIA IRISA, Campus de Beaulieu, 35042- RENNES cedex, FRANCE. tel:+33/ 99 36 20 00 E-mail: banatre@irisa.fr References. BANATRE J.P., BANATRE M., PLOYETTE F. The Concept of Multi-function: a General Structuring Tool for Distributing Operating Systems. Proc of 6th DCS, Cambridge, Mass, May 1986.pp.478-485. BANATRE M., MULLER G., BANATRE J.P. Ensuring Data Security with a Fast Stable Storage. Proc. of 4th Int Conf on Data Eng. L.A., Feb. 88. BANATRE J.P., BANATRE M., MULLER G. Main Aspects of the GOTHIC Distributed System. in R. Speth (ed), Research into Networks and Distributed Applications -EUTECO'88- Vienna, Austria, April 88.(North-Holland). BANATRE J.P., BANATRE M., MORIN Ch. Implementing Atomic Rendezvous within a Transactional Framework. Proc of 8th Symp on Reliable Distributed Systems, Seatle, Oct 10-12 1989 (to appear). ================================================================================ | From: hxt@cs.cmu.edu | Date: 8 Sep 89 03:34:38 GMT | Subject: RE: Real-Time Mach Our group is working on a real-time version of Mach here in CMU. We are currently implementing a real-time thread model and a better scheduler on Mach. If you need further information, please contact Hide Tokuda School of Computer Science Carnegie Mellon Univ. Pittsburgh, PA 15213 Internet: hxt@cs.cmu.edu Phone: (412)268-7672 FAX: (412)268-5016 ================================================================================ | Date: Wed, 13 Sep 89 11:43:35 K | From: Christopher J S Vance <munnari!cs.adfa.oz.au!cjsv@uunet.UU.NET> | Subject: RODOS - A Research Oriented Distributed Operating System ----- Project Name: RODOS - A Research Oriented Distributed Operating System Personnel: Dr Andrzej Goscinski ang@csadfa.cs.adfa.oz.au Dr George Gerrity gwg@csadfa.cs.adfa.oz.au Mr Christopher Vance cjsv@csadfa.cs.adfa.oz.au Dr Chris Lokan cjl@csadfa.cs.adfa.oz.au + a few research students Postal Address: Department of Computer Science University College University of New South Wales Australian Defence Force Academy Canberra ACT 2601 AUSTRALIA Please direct enquiries (including employment and enrolment applications) to Dr Goscinski. The abstract of one of our Technical Reports should give some idea of the flavour of our work: The Design of RODOS: A Research Oriented Distributed Operating System G. Gerrity, A. Goscinski, C. Vance, and B. Williams Technical Report CS 88/17, September 1988, 13 pages Abstract: We know how to design an operating system for a centralized computer system. On the other hand, the study of distributed operating systems is still in its infancy; their design and construction is still an open problem. Indeed, only the critical problem areas have been identified, and there is little agreement among researchers about appropriate solutions. This project we are carrying out is an attempt at a uniform attack on this problem. The main goal of this report is the presentation of the design process for a Research Oriented Distributed Operating System (a test bed) called RODOS, and for investigating and comparing alternative structures and methodologies for implementing the components of a distributed operating system. Other RODOS Technical Reports: The Design of the Kernel, Processes, and Communications for a Research Oriented Distributed Operating System C.J.S. Vance, CS 88/13, August 1988, 26 pages Interprocess Communication Primitives in RODOS C.J.S. Vance and A. Goscinski, CS 89/3, February 1989, 12 pages The Logical Design of a Naming Facility for RODOS C.J.S. Vance and A. Goscinski, CS 89/15, August 1989, 25 pages ================================================================================ | Date: Mon, 14 Aug 89 10:20:16 EDT | From: scott@cs.rochester.edu | Subject: Psyche Contacts: Michael L. Scott Thomas J. LeBlanc scott@cs.rochester.edu leblanc@cs.rochester.edu (716) 275-7745 (716) 275-5426 Department of Computer Science University of Rochester Rochester, NY 14627 The Psyche project at the University of Rochester is an attempt to support truly general-purpose parallel computing on large shared-memory multiprocessors. We define "general-purpose" to mean that the applications programmer must be able to do anything for which the underlying hardware is physically well-suited. Our current work focuses on the development of an operating system that will support the full range of parallel programming models in a single programming environment. Through five years of hands-on experience with a 128-node multiprocessor, we have become increasingly convinced that no single model of process state or style of communication can be appropriate for all applications. Traditional approaches ranging all the way from the most tightly-coupled shared-memory model to the most loosely-coupled form of message passing have applications for which they are conceptually attractive. Our goal is to allow each application, and in fact each *part* of an application, to be written under the model most appropriate for its own particular needs. The Psyche user interface is based on passive data abstractions called "realms." Each realm includes data and code. The code constitutes a protocol for manipulating the data and for scheduling processes running in the realm. The intent is that the data should not be accessed except by obeying the protocol. To facilitate data sharing, Psyche uses uniform addressing for realms -- each realm has the same virtual address from the point of view of every process that uses it. Which realms are actually accessible to a process depends on the protection domain in which that process is executing. Each protection domain is associated with a particular "root" realm, and includes any other realms for which access rights have been demonstrated to the kernel. Depending on the degree of protection desired, an invocation of a realm operation can be as fast as an ordinary procedure call or as safe as a remote procedure call between protection domains. Unless the *caller* insists on protection, the protected and optimized varieties of invocation both look exactly like local subroutine calls. The kernel implements protected invocations by catching and interpreting page faults. Protected invocations cause the calling process to move temporarily to the protection domain of the target realm. Multiple models of process management are supported by moving most of the responsibility for scheduling out of the kernel and into user code. The user can ask that a certain number of virtual processors be assigned to a protection domain. The kernel implements these virtual processors (which we call "activations") via multiprogramming, but otherwise stays out of process management. It provides each activation with signals (software interrupts) when scheduling decisions might be needed, including when (1) a new process has moved into the activation's protection domain by performing a protected invocation, (2) the activation's current process has left the protection domain by performing a protected invocation, (3) an invocation has completed and the calling process has returned, (4) a user-specified timeout has expired, or (5) a program fault has occurred (arithmetic, protection, etc.). We are interested in very-large scale parallelism, which implies that memory access costs will be non-uniform. Much of our work to date has focussed on the design of a virtual memory system that can balance the needs of demand paging, automatic management of locality (the so-called "NUMA problem") and Psyche-style realms and protection domains. As of summer 1989 have been writing code for about a year. Our prototype implementation runs on a BBN Butterfly Plus multiprocessor (the hardware base for the GP1000 product line). Personnel include two faculty members, two professional staff members, and eight students. We are collaborating with members of the department's computer vision and planning groups on a major project in real-time active vision and robotics, sponsored in part by a recently-announced NSF institutional infrastructure grant. Psyche forms the systems foundation for high-level vision and planning functions in the robot lab. We expect the resulting applications experience to provide valuable feedback on our design. Our first robotics application (a balloon-bouncing program) is now in the final stages of implementation. References: %A T. J. LeBlanc %A M. L. Scott %A C. M. Brown %T Large-Scale Parallel Programming: Experience with the BBN Butterfly Parallel Processor %J Proceedings of the ACM SIGPLAN PPEALS 1988 \(em Parallel Programming: Experience with Applications, Languages, and Systems %C New Haven, CT %D 19-21 July 1988 %P 161-172 %X Retrospective on early work with the Butterfly; good background for understanding the motivation for Psyche %A M. L. Scott %A T. J. LeBlanc %A B. D. Marsh %T Design Rationale for Psyche, a General-Purpose Multiprocessor Operating System %J Proceedings of the 1988 International Conference on Parallel Processing %C St. Charles, IL %D 15-19 August 1988 %P 255-262, vol. II \(mi Software %X Why we need a new kind of operating system to use shared-memory multiprocessors well %A M. L. Scott %A T. J. LeBlanc %A B. D. Marsh %T A Multi-User, Multi-Language Open Operating System %J Second Workshop on Workstation Operating Systems %C Pacific Grove, CA %D to appear, 27-29 September 1989 %X How Psyche combines the flexibility and efficiency of an open operating system with the protection of a traditional O.S. %A M. L. Scott %A T. J. LeBlanc %A B. D. Marsh %T Implementation Issues for the Psyche Multiprocessor Operating System %J Workshop on Experiences with Building Distributed and Multiprocessor Systems %C Ft. Lauderdale, FL %D to appear, 5-6 October 1989 %X Issues that arise in structuring a large shared-memory kernel %A T. J. LeBlanc %A B. D. Marsh %A M. L. Scott %T Memory Management for Large-Scale NUMA Multiprocessors %R Technical Report %I Computer Science Department, University of Rochester %D 1989 %X The design of a VM system to support demand paging, locality management, and Psyche abstractions %A M. L. Scott %A T. J. LeBlanc %A B. D. Marsh %T Evolution of an Operating System for Large-Scale Shared-Memory Multiprocessors %R Technical Report %I Computer Science Department, University of Rochester %D 1989 %X The development of Psyche from first principles to concrete mechanisms ================================================================================ | Date: Mon, 14 Aug 89 07:55:34 PDT | From: Peter Reiher <reiher@amethyst.Jpl.Nasa.Gov> Parallel Discrete Event Simulation Peter Reiher Jet Propulsion Laboratory Mail Stop 510-211 4800 Oak Grove Drive Pasadena, CA 91109 (818) 397-9213 Availability: Soon to be released to Cosmic, NASA's software distribution system ================================================================================ | Date: Mon, 14 Aug 89 11:17:29 -0400 | From: edler@jan.ultra.nyu.edu (Jan Edler) | Subject: NYU Ultracomputer Jan Edler NYU Ultracomputer Research Lab 715 Broadway, 10th floor New York, NY 10003 (212) 998-3353 edler@nyu.edu ================================================================================ | Date: Mon, 14 Aug 89 14:04:10 +0200 | From: Sape Mullender <sape@cwi.nl> | Subject: Amoeba Project: Amoeba Sape J. Mullender Centre for Mathematics and Computer Science Kruislaan 413 1098 SJ Amsterdam Netherlands sape@cwi.nl, office phone: +31 20 592 4139, fax: +31 20 592 4199 Andrew S. Tanenbaum Faculty of Mathematics and Computer Science Vrije Universiteit De Boelelaan 1081 1081 HV Amsterdam Netherlands ast@cs.vu.nl ================================================================================ | Date: Mon, 14 Aug 89 13:06:13 PDT | From: brent%sprite.Berkeley.EDU@ginger.Berkeley.EDU (Brent Welch) | Subject: Sprite Sprite is a network operating system being developed and used at UC Berkeley. It currently runs on Sun3, Sun4, and DS3100 architectures, as well as the SPUR multiprocessor. The interesting features of Sprite include its shared network file system, multiprocessor support, and a network process migration facility. Sprite is basically 4.3BSD UNIX compatible, with various extensions. Network distribution is handled entirely within the kernel. A kernel-to-kernel RPC protocol is used for high-performance network communication. The file system provides a uniformly shared, location-transparent name space. High performance file access (30% faster than NFS in long running benchmarks) is achieved by using large main-memory caches on both client and server machines. Diskless workstations are first class Sprite citizens. Files, devices, and pseudo-devices (user-level service applications) have names in the file system. Devices and pseudo-devices can be located anywhere in the network; they do not have to live on the file server that implements their name. Pseudo-devices are used to implement at user level various system services, including a TCP/UDP protocol server and a X11 window system server. Pseudo-file-systems are used to implement NFS access via a user-level service application. Process migration lets running processes move between hosts of identical CPU architecture. A parallel make facility is used to exploit this capability. Multiprocessor support means that the kernel itself is multi-threaded, and more than one user process can execute concurrently in the kernel. Sprite also allows multiple execution threads in a user process, and it provides monitor-style synchronization primatives. These features are all in day-to-day use by a small network of 3 servers and about 25 clients. All Sprite development is done on Sprite, and the Sprite system sources have been on Sprite disks for over two years now. Sprite is/will be in the public domain, although we haven't released it yet. Sprite is also being used as the OS platform for the RAID disk array and XPRS data base projects. These projects focus on high performance I/O subsystems and their use by a database system. Currently there is a prototype disk array server (RAID == Redundant Array of Inexpensive Disks) that runs Sprite, and the Postgress data base server will be ported to Sprite this fall. Members of the Sprite project can be reached via email at: spriters@ginger.Berkeley.EDU ================================================================================ | Date: Mon, 14 Aug 89 20:17:46 EDT | From: beers@tcgould.TN.CORNELL.EDU (Jim Beers) | Subject: Trollius James R. Beers, Jr. (beers@tcgould.tn.cornell.edu) Trollius -- MIMD OS esp. for Unix hosted transputers. James R. Beers, Jr. Advanced Computing Facility Cornell Theory Center 265 Olin Hall Ithaca, NY 14851 (607) 255-9393 Availability: 2.0 available soon. ================================================================================ | Date: Tue, 15 Aug 89 13:46:08 +0200 | From: Peter Schlenk <ucbvax!decwrl!fauern!immd4.informatik.uni-erlangen.de!schlenk@ucscc.UCSC.EDU> | Subject: Object-Oriented Distributed Operating System Peter Schlenk (schlenk@immd4.informatik.uni-erlangen.de) Object-Oriented Distributed Operating System Peter Schlenk Universitaet Erlangen, IMMD IV Martensstr. 1 8520 Erlangen West-Germany (0049) 9131/857269 Availability: in development. ================================================================================ | Date: Tue, 15 Aug 89 11:49:01 EDT | From: snm%horus@gatech.edu (Sathis Menon) | Subject: Clouds The Clouds Project at Georgia Institute of Technology (Distributed, object based Operating System project) internet snm@gatech.edu uucp {ihnp4,decvax,ulysses,akgua}!gatech!boa!snm Contacts: Sathis Menon Research Scientist Distributed Systems Group School of ICS Georgia Institute of Technology Atlanta, GA 30332 Partha Dasgupta Assistant Professor School of ICS Georgia Institute of Technology Atlanta, GA 30332 ================================================================================ | Date: Tue, 15 Aug 89 16:16:48 MST | From: "Larry Peterson" <llp@arizona.edu> | Subject: x-Kernel Name: The x-Kernel Project Where: University of Arizona Contact: Dr. Larry Peterson Department of Computer Science University of Arizona Tucson, AZ 85721 email: llp@arizona.edu phone: (602) 621-4231 Environment: Sun-3 workstations Description: The x-kernel is a configurable operating system kernel in which communication protocols define the fundamental building block. The x-kernel supports multiple address spaces, light-weight processes, and an architecture for implementing and composing network protocols. The primary objective of the x-kernel is to facilitate the implementation of efficient protocols. In particular, the x-kernel supports the construction of new protocols from existing protocol pieces, it serves as a workbench for designing and evaluating new protocols, and it provides a platform for accessing large, heterogeneous collections of network services. The basic research problem addressed by the x-kernel is the level to which kernel abstractions facilitate the implementation of protocols. The key is that such abstractions must be rich enough to accommodate a wide variety of protocols, yet implementable in a way that does not impose a significant performance penalty on any of the protocols. Our ultimate goal in this effort is to develop operating system techniques that make protocol construction an every day part of distributed applications programming. References: N. Hutchinson, and L. Peterson. Design of the x-Kernel. Proceedings of ACM SIGCOMM `88 (Aug. 1988), 65-75. Hutchinson, N., Mishra, S., Peterson, L., and Thomas, V. Tools for Implementing Network Protocols. Software---Practice & Experience, to appear. N. Hutchinson, L. Peterson, M. Abbott, and S. O'Malley. RPC in the x-Kerenl: Evaluating New Desgin Techniques. Proceedings of the Twelfth Symposium on Operating System Principles, (December 1989), to appear. N. Hutchinson, L. Peterson, H. Rao. The x-Kernel: An Open Operating System Design. Proceedings of the Second Workshop on Workstation Operating Systems (September 1989), to appear. ================================================================================ | Date: Wed, 16 Aug 89 11:12:50 PDT | From: bcn@june.cs.washington.edu (Clifford Neuman) | Subject: Prospero B. Clifford Neuman (bcn@cs.washington.edu) Prospero B. Clifford Neuman Department of Computer Science, FR-35 University of Washington Seattle, Washington 98195 (206) 543-7798 Prospero is a distributed operating system based on the virtual system model: a new approach to organizing large distributed systems. A user centered view of the system is supported. Users build their own virtual systems from the resources available over the network. Tools are provided to help the user organize and customize their virtual system. Among the tools are the filter and the union link. To make it clear which namespace is to be used when resolving names, closure is supported. A namespace is associated with each object, and that namespace is used to resolve names specified by that object. A prototype is running. ================================================================================ | From: anderson%charming.Berkeley.EDU@berkeley.edu (David Anderson) | Date: Wed, 16 Aug 89 13:30:37 PDT | Subject: DASH David P. Anderson 541 Evans Hall UC Berkeley Berkeley, CA 94720 (415) 642-4979 anderson@snow.Berkeley.EDU THE DASH OPERATING SYSTEM David P. Anderson Computer Science Division, EECS Department University of California, Berkeley Berkeley, CA 94720 August 16, 1989 The DASH project is doing research in system support for applications that 1) use ``multimedia'' (digital audio and video); 2) are distributed, and 3) are interactive. As a research testbed, we have developed a distributed operat- ing system kernel. The DASH kernel supports the storage, communication, and processing of data by processes in pro- tected user-level address spaces. It provides the abstrac- tion of data streams with guaranteed real-time performance (throughput and delay). As an example, consider an applica- tion that reads compressed full-motion video from a disk, transmits the data across a network (and perhaps through gateways), then decompresses and displays it in a window. Under DASH, if sufficient system resources are available at the time when the application is started, then it will per- form correctly regardless of any subsequent concurrent activities. To meet the performance requirements of multimedia I/O, the DASH system uses an abstraction of ``resources'' (CPU, network access, video processors, etc.) that are used in processing data streams. Resources can be accessed in ``sessions'' having parameters for the throughput, delay, burstiness, and reliability of the stream. A session is, in effect, a reservation of part of the resource. These ses- sions then can be combined to form ``end-to-end'' sessions. This architecture allows the real-time capabilities of net- works such as FDDI and BISDN to be exploited by user-level processes. The DASH network architecture is backwards- compatible with TCP/IP, allowing interoperation with exist- ing systems. The DASH kernel is designed for high-throughput real- time communication. The kernel uses preemptive deadline- based process scheduling, and is written using object- oriented structuring principles that make it easily modifi- able and extensible. It has a novel virtual memory design that allows data to be securely passed between virtual address spaces faster than in existing systems. ================================================================================ | Date: Thu, 17 Aug 89 13:18:40 EST | From: munnari!bruce.cs.monash.OZ.AU!rdp@uunet.UU.NET (Ronald Pose) | Subject: Monash capability kernel In the Department of Computer Science at Monash University we have developed a shared memory multiprocessor with a rather unusual address translation mechanism in which all processes share a single global virtual address space. A capability-based operating system kernel controls access to the global virtual memory which is designed to extend world-wide. Particular research interests are: Multiprocessor architectures Capability-based Operating System Unusual high-speed (40 MHZ) backplane bus User interfaces to the system Languages which can exploit the properties of the capability-based virtual memory and the multiprocessor architecture. Coupling the multiprocessor systems together across local and wide-area networks. Contact Person: Ronald Pose ACSnet: rdp@bruce.cs.monash.oz Dept. Computer Science UUCP: ..uunet!munnari!bruce.cs.monash.oz!rdp Monash University ARPA: rdp%bruce.cs.monash.oz.au@uunet.uu.net AUSTRALIA 3168. CSNET: rdp@bruce.cs.monash.oz.au Telephone: +61 3 565 3903 Fax: +61 3 565 4746 ================================================================================ | Date: Thu, 17 Aug 1989 09:24-EDT | From: Doug.Jensen@K.GP.CS.CMU.EDU | Subject: Alpha E. Douglas Jensen Concurrent Computer Corp. One Technology Way Westford, MA 01886 508-392-2999 edj@cs.cmu.edu. edj@westford.ccur.com The Alpha Real-Time Decentralized Operating System Alpha is an operating system for the mission-critical integration and operation of large, complex, distributed, real-time systems. Only recently have such systems become more common in industrial factory and plant automation (e.g., automobile manufacturing), aerospace (e.g.,space stations), and military (e.g., C3I) contexts. They differ substantially from the more widely known timesharing systems, numerically oriented supercomputers, and networks of personal workstations. More surprisingly, they also depart significantly from traditional real-time systems, which are for low-level sampled data monitoring and control. The most challenging technical requirements dictated by this application domain are in the areas of: satisfying real-time constraints despite the system's inherently stochastic and nondeterministic nature; distributed programming and system-wide (inter-node) resource management; robustness in the face of failures and even attacks; and adaptability to a wide range of ever-changing requirements over decades of use. Satisfying these entails unconventional design and implementation tradeoffs. In Alpha's distributed programming model, activities correspond to threads, which execute concurrently in otherwise passive objects, and cross object (and, transparently and reliably, node) boundaries by means of operation invocation; they carry with them attributes such as urgency, importance, and relibility specified by the application. Alpha instances cooperate to manage the global resources of the entire system based on these attributes, using best-effort resource management algorithms to ensure that as many as possible of the most important aperiodic as well as periodic time constraints are met, permitting graceful degradation in response to the inevitable overloads. To facilitate maintaining integrity of system and application distributed data and programs despite physical dispersal, asynchronous concurrency of execution, and hardware failures, Alpha includes exception handling facilities, thread repair, and kernel-level mechanisms for real-time atomic transactions and object replication. Alpha uses policy/mechanism separation to exploit application specificity in support of adaptability. Departing from common practice, Alpha's performance is optimized for the important high-stress exception cases, such as failure or attack, rather than for the normal, most frequent cases. Alpha embodies results from nine years of research performed by the Archons Project at Carnegie Mellon University, where a prototype was built from 1984 to 1987; another copy has been successfully demonstrated with application software written at General Dynamics Corp. Alpha research is ongoing at CMU and other academic and industrial institutions, but is now led by Concurrent Computer Corp., where it continues to be sponsored in part by DoD. A series of next-generation designs and implementations will be delivered to various Government and industry labs for experimental applications beginning in early 1990. ================================================================================ | Date: Fri, 18 Aug 89 16:05:28 +0200 | From: shapiro@corto.inria.fr | Subject: SOS SOS is an experimental distributed object-oriented operating system. SOS is based on a concept of "distributed object", implemented as a "group" of elementary objects distributed among different address spaces; members of a group have mutual communication privileges, which are denied to non-members. Access to a service may occur only via a local "proxy", which is a member of the group implementing the service. Typically, a client gains access to some new service by importing (migrating) a proxy for that service. A prototype of SOS has been implemented in C++, on top of Unix. It supports object migration, persistent object, dynamic linking, and arbitrarily complex user-defined objects (written in C++). The system services are accessed via a small set of pre-defined proxies. Existing system services are: a distributed object manager, a name service, a storage service, a communication service (allowing groups to choose from a library of protocol types: datagrams, RPC, multicast, atomic multicast, etc.). Applications built using SOS include a multimedia document manager and a UIMS. SOS is thouroughly documented with a reference manual (similar to Unix man) and an introductory programmer's manual. Most of the code is in the public domain, except for a few components derived from ATT code, for which an ATT licence (Unix and C++) is necessary. Contact: Marc Shapiro INRIA, B.P. 105, 78153 Le Chesnay Cedex, France. Tel.: +33 (1) 39-63-53-25 e-mail: shapiro@sor.inria.fr (internet) ...!inria!shapiro (uucp) inria!shapiro@uunet.uu.net (non-standard) Here is a bibliography of some recent papers: @InProceedings (ProxyPrinciple, Author = "Marc Shapiro", Title = "Structure and Encapsulation in Distributed Systems: the {P}roxy {P}rinciple", Booktitle = "Proc.\ 6th Intl.\ Conf.\ on Distributed Computing Systems", organization = "{IEEE}", pages = "198--204", Address = "Cambridge, Mass. ({USA})", Year = 1986, Month = May) @InProceedings (sos:sigops86, author = "Shapiro, Marc", title = "{SOS}: a distributed Object-Oriented Operating System", booktitle = "2nd {ACM SIGOPS} European Workshop, on ``Making Distributed Systems Work{''}", address = "Amsterdam (the Netherlands)", year = 1986, month = sep, note = "(Position paper)" ) @techreport(sos:v1-recueil, author = "Shapiro, Marc and Abrossimov, Vadim and Gautron, Philippe and Habert, Sabine and Makpangou, Mesaac Mounchili", title = "Un recueil de papiers sur le syst\`{e}me d'exploitation r\'{e}parti \`{a} objets {SOS}", institution = {Institut National de la Recherche en Informatique et Automatique}, address = {Rocquencourt (France)}, year = 1987, month = may, number = 84, type = "Rapport Technique" ) @InProceedings{loo:C++:286, author = "Philippe Gautron and Marc Shapiro", title = "Two extensions to {C++}: A Dynamic Link Editor and Inner data", booktitle = "Proceeding and additional papers, {C++} Workshop", year = 1987, page = "23--34", organization = "USENIX", address = "Berkeley, CA ({USA})", month = nov } @InProceedings{pro:sos:314, author = "Mesaac Makpangou and Marc Shapiro", title = "The {SOS} Object-Oriented Communication Service", booktitle = "Proc.\ 9th Int.\ Conf.\ on Computer Communication", year = 1988, address = "Tel Aviv (Israel)", month = "October--November" } @InProceedings{sos:315, author = "Marc Shapiro", title = "The Design of a Distributed Object-Oriented Operating System for Office Applications", booktitle = "Proc.\ Esprit Technical Week 1988", year = 1988, address = "Brussels (Belgium)", month = nov } @InProceedings{pro:sos:321, author = "Makpangou, Mesaac Mounchili", title = "Invocations d'objets distants dans {SOS}", booktitle = "De Nouvelles Architectures pour les Communications", year = 1988, editor = "Guy Pujolle", pages = "195--201", publisher = "Eyrolles", address = "Paris (France)", month = oct } @InProceedings{sos:prs:371, author = "Marc Shapiro and Laurence Mosseri", title = "A simple object storage system", booktitle = "Proc.\ Workshop on persistent object systems", year = 1988, pages = "320--327", editor = "J. Rosenberg", address = "Newcastle NSW (Australia)", month = jan } @TechReport{sos:388, author = "The {SOR} group", title = "{SOS} Reference Manual for Prototype {V4}", institution = {Institut National de la Recherche en Informatique et Automatique}, year = 1989, type = "Rapport Technique", number = 103, address = {Rocquencourt (France)}, month = feb } @PhdThesis{makThesis, author = "Makpangou, Mesaac Mounchili", title = "Protocoles de communication et programmation par objets~: l'exemple de {SOS}", school = "Universit\'{e} Paris {VI}", year = 1989, address = "Paris (France)", month = feb } @InProceedings{nom:sos:391, author = "J.P. Le Narzul and M. Shapiro", title = "Un Service de Nommage pour un Syst\`{e}me \`{a} Objets R\'{e}partis", booktitle = "Actes Convention Unix 89", year = 1989, pages = "73--82", organization = "{AFUU}", address = "Paris", month = mar } @InProceedings{sos:prs:c++:397, author = "Marc Shapiro and Philippe Gautron and Laurence Mosseri", title = "Persistence and Migration for {C}++ Objects", booktitle = "ECOOP'89", year = 1989, address = "Nottingham ({GB})", month = jul } @TechReport{shapiro:experiences89:sor60, author = "Marc Shapiro", title = "{P}rototyping a distributed object-oriented {OS} on {U}nix", institution = sor, year = 1989, type = "Note technique", number = "SOR--60", address = rocquencourt, month = may, note = "To appear, Workshop on Experiences with Building Distributed (and Multiprocessor) Systems, Ft.\ Lauderdale FL (USA), Oct. 1989." } @InProceedings{chorus:mv:411, author = "V. Abrossimov and M. Rozier and M. Shapiro", title = "Generic Virtual Memory Management for Operating System Kernels", booktitle = "Proc.\ 12th ACM Symp.\ on Operating Systems Principles", year = 1989, organization = "ACM SIGOPS", address = "Litchfield Park AZ (USA)", month = dec } ================================================================================ | Date: Fri, 18 Aug 89 14:09:55 EDT | From: dibble@cs.rochester.edu | Subject: Bridge Contacts: Michael L. Scott scott@cs.rochester.edu Peter C. Dibble dibble@cs.rochester.edu Parallel computers with non-parallel file systems find themselves limited by the performance of the processor running the file system. We have designed and implemented a parallel file system called Bridge that eliminates this problem by spreading both data and file system computation over a large number of processors and disks. Our design will adapt easily to a wide variety of multiprocessors and multicomputers; our current implementation runs on the BBN Butterfly. To assess the effectiveness of Bridge we have used it as the basis for several standard file-handling applications, including copying, sorting, searching, and image transposition. Analysis and empirical measurements suggest that for applications such as these Bridge can provide nearly linear speedup on over 100 nodes. ================================================================================ | Date: Mon, 18 Sep 89 18:29:46 PDT | From: Richard Guy <guy@cs.ucla.edu> | Subject: FICUS project Project: FICUS distributed file system Abstract: FICUS is a research effort at UCLA to demonstrate the feasibility and desirability of using a single, large, transparent file system structure for the entire DARPA Internet community. The sheer scale involved (60,000+ nodes in 1988) challenges many of the assumptions underlying existing transparent file systems (eg, LOCUS, NFS, Andrew). A closely related goal is to use general-purpose data replication techniques to provide high availability and reliability for file system contents. Contact: Richard Guy 3804-F Boelter Hall UCLA Computer Science Westwood, CA 90024 213/825-2756 guy@cs.ucla.edu -or- ficus@cs.ucla.edu Tom Page 3804-D Boelter Hall 213/206-8696 page@cs.ucla.edu Gerald J. Popek 3731H Boelter Hall 213/825-7879 popek@cs.ucla.edu Availability: in design/prototype stage.