Filters








56 Hits in 2.6 sec

Process migration in DEMOS/MP

Michael L. Powell, Barton P. Miller
1983 Proceedings of the ninth ACM symposium on Operating systems principles - SOSP '83  
Process migration has been added to the DEMOS/MP operating system. A process can be moved during its execution, and continue on another processor, with continuous access to all its resources.  ...  No centralized algorithms are necessary to move a process. A number of characteristics of DEMOS/NIP allowed process migration to be implemented efficiently and with no changes to system services.  ...  The Environment: DEMOS/MP Process migration was added to the DEMOS/MP [Powell, Miller, & Presotto 83] operating system.  ... 
doi:10.1145/800217.806619 dblp:conf/sosp/PresottoM83 fatcat:uvceu5gx55gtzmt5hfl5fxrmaq

Process migration in DEMOS/MP

Michael L. Powell, Barton P. Miller
1983 ACM SIGOPS Operating Systems Review  
Process migration has been added to the DEMOS/MP operating system. A process can be moved during its execution, and continue on another processor, with continuous access to all its resources.  ...  No centralized algorithms are necessary to move a process. A number of characteristics of DEMOS/NIP allowed process migration to be implemented efficiently and with no changes to system services.  ...  The Environment: DEMOS/MP Process migration was added to the DEMOS/MP [Powell, Miller, & Presotto 83] operating system.  ... 
doi:10.1145/773379.806619 fatcat:y3p5lcwgxrhqvk3nbv4uu7nlca

DEMOS/MP: The development of a distributed operating system

Barton P. Miller, Michael L. Powell, David L. Presotto
1987 Software, Practice & Experience  
The changes made to produce DEMOS/MP involved the internal structure of link, modification to parts of the kernel, and limited changes to the various system processes.  ...  The DEMOS/MP operating system has moved from a super computer with a simple addressing structure to a network of microcomputers.  ...  In spite of these differences, a program that runs in the DEMOS environment will run under DEMOS/MP. There are two goals of the DEMOS/MP project.  ... 
doi:10.1002/spe.4380170404 fatcat:2x2vukh5azf2hebotmiobgib5m

Lightweight process migration and memory prefetching in openMosix

Roy S.C. Ho, Cho-Li Wang, Francis C.M. Lau
2008 Proceedings, International Parallel and Distributed Processing Symposium (IPDPS)  
We propose a lightweight process migration mechanism and an adaptive memory prefetching scheme called AM-PoM (Adaptive Memory Prefetching in openMosix), whose goal is to reduce the migration freeze time  ...  These results indicate that by exploiting memory access locality and prefetching, process migration can be a lightweight operation with little software overhead in remote paging. * This research was supported  ...  Because of these advantages, there had been active research on process migration during '80s and '90s, which includes DEMOS/MP [17] , Amoeba [21] , V [22] , to name a few.  ... 
doi:10.1109/ipdps.2008.4536329 dblp:conf/ipps/HoWL08a fatcat:jgofrp2hcbdvdiuj33k6mrcmym

An Efficient Live Process Migration Approach for High Performance Cluster Computing Systems [chapter]

Ehsan Mousavi Khaneghah, Najmeh Osouli Nezhad, Seyedeh Leili Mirtaheri, Mohsen Sharifi, Ashakan Shirpour
2011 Communications in Computer and Information Science  
They however fail to migrate processes lively in the sense that moving processes are blocked (frozen) and are non-responsive to any requests sent to them while they are moving to their new destinations  ...  To achieve this, we have added a new state called the exile state to the traditional state model of processes in operating systems.  ...  Demos/MP [4] , Amoeba [5] , and Charlotte [6] are examples that use some versions of this algorithm in user level or kernel level.  ... 
doi:10.1007/978-3-642-27337-7_34 fatcat:nwo6gozmbvh7bkoxk7ufwvp7b4

Designing a process migration facility: the Charlotte experience

Y. Artsy, R. Finkel
1989 Computer  
Our goal in this paper is to discuss our experience with process migration in the Charlotte distributed operating system.  ...  Aprocess migration facility in ad istributed operating system dynamically relocates processes among the component machines.  ...  We feel that ease of implementation is a dominant motivation for separating mechanisms from each other when process migration is added to an existing operating system, such as was the case in Demos/MP,  ... 
doi:10.1109/2.35213 fatcat:42gdvdngyjalhl7mpok43uq26u

A survey of process migration mechanisms

Jonathan M. Smith
1988 ACM SIGOPS Operating Systems Review  
We define process migration as the transfer of a sufficient amount of a process's state from one machine to another for the process to execute on the target machine.  ...  The effect of operating system design upon the ease of implementation is discussed in some detail; we conclude that message-passing systems simplify designs for migration.  ...  DEMOS/MP DEMOS/MP is a distributed system developed at the University of California, Berkeley [Powell1983a] .  ... 
doi:10.1145/47671.47673 fatcat:3cjhpf2vtbhspp4fckubqkfjly

Publishing

Michael L. Powell, David L. Presotto
1983 Proceedings of the ninth ACM symposium on Operating systems principles - SOSP '83  
The prototype version implemented in DEMOS/MP demonstrates that an error recovery can be transparent to user processes and can be centralized in the network.  ...  The recovery mechanism can .be completely transparent to the failed process and all processes interacting with it.  ...  We have implemented published communications in DEMOS/MP, a message-based distributed operating system.  ... 
doi:10.1145/800217.806618 dblp:conf/sosp/PowellP83 fatcat:bc3tdxixxzejjdzpv2bszrit4e

Preemptable remote execution facilities for the V-system

Marvin M. Theimer, Keith A. Lantz, David R. Cheriton
1985 Proceedings of the tenth ACM symposium on Operating systems principles - SOSP '85  
There are many circumstances in which the user can make use of this idle processing power.  ...  In particular, we focus on network transparency of the execution environment, preemption and migration of remotely executed programs, and avoidance of residual dependencies on the original host.  ...  Related Work Demos/MP provides preemption and migration for individual processes [15] .  ... 
doi:10.1145/323647.323629 dblp:conf/sosp/TheimerLC85 fatcat:t22lfkrewnclvhjtwqvvpxcqk4

Preemptable remote execution facilities for the V-system

Marvin M. Theimer, Keith A. Lantz, David R. Cheriton
1985 ACM SIGOPS Operating Systems Review  
There are many circumstances in which the user can make use of this idle processing power.  ...  In particular, we focus on network transparency of the execution environment, preemption and migration of remotely executed programs, and avoidance of residual dependencies on the original host.  ...  Related Work Demos/MP provides preemption and migration for individual processes [15] .  ... 
doi:10.1145/323627.323629 fatcat:h7xff6y2yfdwviorvj4y4fx45e

The Mojave Compiler: Providing Language Primitives for Whole-Process Migration and Speculation for Distributed Applications

Justin D. Smith, Cristian Tapus, Jason Hickey
2007 2007 IEEE International Parallel and Distributed Processing Symposium  
We present an approach for implementing languagelevel primitives for whole-process migration and speculative execution in a compiler and associated runtime environment.  ...  We demonstrate the use of migration and speculation primitives for checkpointing in a canonical grid computation application, and analyze the results of this implementation.  ...  DEMOS/MP does not address the issue of node failure.  ... 
doi:10.1109/ipdps.2007.370411 dblp:conf/ipps/SmithTH07 fatcat:tg4lxhtfebdolfbv6rxyoiyliq

Object and native code thread mobility among heterogeneous computers (includes sources)

B. Steensgaard, E. Jul
1995 Proceedings of the fifteenth ACM symposium on Operating systems principles - SOSP '95  
The excellent intra-node performance of the original homogeneous Emerald is retained: migrated threads run at native code speed bet'ore and after migration; the same speed as on homogeneous Emeralci and  ...  Our implementation of mobility hm not been optimized: thread mobility and trans-architecture invocations take about 60% longer than in lhe homogeneous implementation.  ...  Juul at DIKU for many interesting discussions about the Emerald system Thanks are also due to the many people that have encouraged us to write up this work (Including the SOSP'93 audience at the work-in-progress  ... 
doi:10.1145/224056.224063 dblp:conf/sosp/SteensgaardJ95 fatcat:psidv2f5sjehdppne663yaxvm4

Fine-Grain Cycle Stealing for Networks of Workstations

Kyung Dong Ryu, J.K. Hollingsworth
1998 Proceedings of the IEEE/ACM SC98 Conference  
For parallel computing, we showed that the Linger-Longer policy outperforms reconfiguration strategies when the processor utilization by the local process is 20% or less in both synthetic bulk synchronous  ...  We compare two variations of our policy to two previous policies: Immediate-Eviction and Pause-and-Migrate.  ...  DEMOS/MP [12] , Accent [18] , Locus [15] , and V [14] all provided manual or semi-automated migration of processes.  ... 
doi:10.1109/sc.1998.10011 dblp:conf/sc/RyuH98 fatcat:mdilzhonvrgudgnlmijq76hz2a

Attacking the process migration bottleneck

E. Zayas
1987 ACM SIGOPS Operating Systems Review  
Moving the contents of a large virtual address space stands out as the bottleneck in process migration, dominating all other costs and growing with the size of the program.  ...  Any attempt to make process migration a more usable and attractive facility in the presence of large address spaces must focus on this basic bottleneck. One approach is to perform a  ...  RIG's ports were visibly tied with the process owning them, so it suffered from DCN's problem. The DEMOS/MP operating system [9] was among the first to offer full transparency.  ... 
doi:10.1145/37499.37503 fatcat:bzq6cylpljg4nhkkkc7uk47v7y

Attacking the process migration bottleneck

E. Zayas
1987 Proceedings of the eleventh ACM Symposium on Operating systems principles - SOSP '87  
Moving the contents of a large virtual address space stands out as the bottleneck in process migration, dominating all other costs and growing with the size of the program.  ...  Any attempt to make process migration a more usable and attractive facility in the presence of large address spaces must focus on this basic bottleneck. One approach is to perform a  ...  RIG's ports were visibly tied with the process owning them, so it suffered from DCN's problem. The DEMOS/MP operating system [9] was among the first to offer full transparency.  ... 
doi:10.1145/41457.37503 dblp:conf/sosp/Zayas87 fatcat:xemulnfjdvb3jlivqfmawbjij4
« Previous Showing results 1 — 15 out of 56 results