D.R. Cheriton, "The V Kernel: A Software Base for Distributed Systems", IEEE Software 1(2), April, 1984.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....tively slow time shared machines (VAX 11 780s in the BSD study) to today s much faster personal workstations. Second, several network oriented operating systems and file systems have been developed during the last decade, e.g. AFS [4] Amoeba [7] Echo [31, Locus [14] NFS [16] Sprite [9] and V [1]; they provide transparent network file systems and, in some cases, the ability for a single user to harness many workstations to work on a single task. Given these changes in computers and the way they are used, we hoped to learn how file system access patterns have changed, and what the ....

Cheriton, D. R., "The V Kernel: A Software Base for Distributed Systems", IEEE Software l, 2 (April 1984), 19-43.

....Unix, it was clear that the network protocol should not depend on aspects of the operating system. The name X derives from the lineage of the system. At Stanford University, Paul Asente and Brian Reid had begun work on the W window system [3] as an alternative to VGTS [12, 21] for the V system [5]. Both VGTS and W allow network transparent access to the display, using the synchronous V communication mechanism. Both systems provide text windows for ASCII terminal emulation. VGTS provides graphics windows driven by fairly high level object definitions from a structured display file; W ....

Cheriton, D. "The V Kernel: A Software Base for Distributed Systems". IEEE Software 1, 2 (April 1984).

....may be built on top of this simple facility. Since a minimal parameter block is the only context that is transferred to the invoked container, invocation is therefore inherently low cost. In this respect, the invoke primitive is very similar to the message passing system used in the V kernel [7]. A locus may invoke and return through many containers in a manner similar to conventional procedure calls. The Grasshopper kernel maintains a call chain of invocations between containers. Implicitly each locus is rooted in the container representing the kernel: when a locus returns to this ....

....operating systems restrict the mapping of memory to a single level. Both VMS [24] and variants of Unix (such as SunOS) provide the ability to share memory segments between process address spaces, and a separate ability to map from disk storage into a process address space. Several other systems [7, 8] provide the notion of a memory object, which provides an abstraction of data. In these systems, memory objects can be mapped into a process address space, however memory objects and processes are separate abstractions. It is therefore impossible to directly address a memory object, or to compose ....

Cheriton, D. R. "The V Kernel: A Software Base for Distributed Systems", Software, vol 1, 2, pp. 91-42, 1984.

....the distributed operation system for SUPttENUM and GENESIS, approaches this problem profiting by its constitution of a multitude of system servers. Modern distributed operating systems, matching in their concepts the prob lems of parallel systems too [20] are process structured like e.g. V [3], AMOEBA [11] MACH [24] and CHORUS [17] A process providing dedicated system ser vices forms a system server. Under this aspect system restructuring means the termination and creation of system server objects, concerning software scalability, and the booting and rebootlEg of single nodes, ....

D. R. Cheriton "The V Kernel: A Software Base for Distributed Systems", IEEE Software, Vol. 1, No. 2, pp. 19-43, 1984

....operating systems restrict the mapping of memory to a single level. Both VMS [23] and variants of Unix (such as SunOS) provide the ability to share memory segments between process address spaces, and a separate ability to map from disk storage into a process address space. Several other systems [8, 9] [26] provide the notion of a memory object, which provides an abstraction of data. In these systems, memory objects can be mapped into a process address space, however memory objects and processes are separate abstractions. It is therefore impossible to directly address a memory object, or to ....

....may be built on top of this simple facility. Since a minimal parameter block is the only context that is transferred to the invoked container, invocation is therefore inherently low cost. In this respect, the invoke primitive is very similar to the message passing system used in the V kernel [8]. A locus may invoke and return through many containers in a manner similar to conventional procedure call. The Grasshopper kernel maintains a call chain of invocations between containers. Implicitly each locus appears to be rooted in the container representing the kernel: when a locus returns to ....

Cheriton, D. R. "The V Kernel: A Software Base for Distributed Systems", Software, vol 1, 2, pp.91-42, 1984.

....to its previous allocation site. In the case of object migration, several solutions can be outlined. One solution leaves a proxy in the original site in charge of forwarding the successive requests to the server current location [13] another solution implies requalifying all object references [14]. A further solution less expensive for the migration support raises an exception, which is handled by clients that have to lookup the new server location. 4. Mobile Objects in a Distributed Environment We have developed a system, called MODE (Mobile Objects in a Distributed Environment) ....

Cheriton, D. R., "V Kernel: a Software Base for Distributed Systems," IEEE Software, 1(2), p. 19-42, April 1984.

....V on a multiprocessor machine, connecting it to wide area networks and implementing reliability issues such as atomic transactions and replication. 48 Contact: David R. Cheriton or Tony Mason, Computer Science Department, Stanford University, Stanford CA 94305. References: 318] 319] 320] [321], 322] 323] 324] 325] 326] 327] 328] 329] 330] 331] 332] 333] 146] 334] 29] 335] 336] 2.51 VAXcluster Main Goal The Digital Equipment Corporation has been developed the VAXcluster product as a set of closely coupled DEC VAX computers providing a highly available ....

D.R. Cheriton, "The V Kernel: A Software Base for Distributed Systems", IEEE Software, 1(2):19--42, April 1984.

....container. Grasshopper provides two facilities that allow the transfer of data between containers: mapping and invocation. Container mapping allows data in a region of one container to be viewed within a region of another container. Unlike the memory mapping mechanisms provided by other systems [1,2,22] containers may be arbitrarily (possibly recursively) composed providing considerably enhanced flexibility and performance [15] Invocation is the process whereby a locus moves between containers. During invocation, a locus may supply a parameter block which contains data to be used in the ....

Cheriton, D. R. "The V Kernel: A Software Base for Distributed Systems", IEEE Software, Vol 1, No 2, pp. 9-42, 1984.

....as threads, address spaces, and inter process communication. These abstractions can be composed to build user level servers that implement common services such as file systems, processes, and virtual memory. Examples of micro kernel architectures include Mach [3] Chorus [57] Amoeba [26, 47] V [16], Choices [11] Psyche [59] L3 L4 [37] and Arena [41] The most notable effect of the micro kernel design is to separate the implementation of the system into smaller, more manageable pieces in the form of the kernel and the user level servers. This arrangement greatly improves the modularity ....

D.R. Cheriton, "The V Kernel: A Software Base for Distributed Systems ", Software, 1(2), pp. 9-42, 1984.

....containers. This is achieved by allowing data in a region of one container to be viewed within a region of another container. Mappings may be either global, or private to a particular locus while executing in a particular container. Unlike the memory object mechanism provided by other systems [7], containers may be arbitrarily (possibly recursively) composed which provides considerably enhanced flexibility and performance [17] Since any container can have another mapped into it, it is possible to construct a hierarchy of container mappings which forms a directed acyclic graph as shown ....

Cheriton, D. R. "The V Kernel: A Software Base for Distributed Systems", Software, vol 1, 2, pp. 9-42, 1984.

....other operating system has a lower RPC delay or higher bandwidth on this class of hardware. In particular, our tests measure delay and throughput from user process to user process (not kernel to kernel) and do not involve any tricks or special cases. Noteworthy are the performance of the V system [15,16] and the Firefly RPC [17] V because it is widely thought to be the fastest distributed system currently in existence and the Firefly because it is a multiprocessor. For V [18] we find that delay for null RPCs is 2.54 msec (vs. 1.4 msec for Amoeba) and that the bandwidth for 8 Kbyte RPCs is 460 ....

Cheriton, D.R.: "The V Kernel: A Software Base for Distributed Systems," IEEE Softw. , vol. 1, no. 2, pp. 19-42, Apr. 1984.

....operating systems restrict the mapping of memory to a single level. Both VMS [24] and variants of Unix (such as SunOS) provide the ability to share memory segments between process address spaces, and a separate ability to map from disk storage into a process address space. Several other systems [7, 8, 28, 31] provide the notion of a memory object, which provides an abstraction over data. In these systems, memory objects can be mapped into a process address space, however memory objects and processes are separate abstractions. It is therefore impossible to directly address a memory object, or to ....

Cheriton, D. R."The V Kernel: A Software Base for Distributed Systems ", Software, 1(2), pp. 9-42, 1984.

....slow time shared machines (VAX 11 780s in the BSD study) to today s much faster personal workstations. Second, several network oriented operating systems and file systems have been developed during the last decade, e.g. AFS [4] Amoeba [7] Echo [3] Locus [14] NFS [16] Sprite [9] and V [1]; they provide transparent network file systems and, in some cases, the ability for a single user to harness many workstations to work on a single task. Given these changes in computers and the way they are used, we hoped to learn how file system access patterns have changed, and what the ....

Cheriton, D. R., "The V Kernel: A Software Base for Distributed Systems", IEEE Software 1, 2 (April 1984), 19-43.

....concurrently with the sender task which resumes processing after receiving the reply to the message. The rendezvous feature is used in a large number of programming languages and operating systems that support concurrency. Examples include Occam [2] the Thoth operating system [9] and the V System [10] in which send and wait and receive and wait primitives are used for intertask communication. Ada [8] and XMS [20] use procedural request accept constructs which are equivalent to the rendezvous concept from the control flow point of view. Remote Procedure Calls supported by the SUNOS and the ....

D.R. Cheriton, "The V kernel: A software base for distributed systems," IEEE Software, Vol. 1, No. 2, pp. 19--42, April 1984.

....is provided by a low level kernel and a set of additional services running, like applications, above the kernel. Although the kernel supports distributed processing, the functionality of this kernel is fundamentally richer than that of, for example, UNIX [Bach86] Mach [Jones86] Vkernel [Cheriton84] or Amoeba [Mullender85 ] in that it also provides a basis for common data management services required by many applications. Examples of the additional support provided includes atomic transactions and recovery; decomposition and reconstruction of complex data entities so as to accelerate ....

D. Cheriton, "The V-Kernel: A Software Base for Distributed Systems" IEEE Software, Vol. 1, No. 2,April 1984.

....systems to be used in the validation studies were limited to the parallel systems that were available to us. These were a 16 node Intel iPSC hypercube and the LooselyCoupled Multiprocessor (LCMP) a set of Sun workstations interconnected by an Ethernet and running the distributed V system kernel [23]. Neither system is ideal for this purpose. A major 13 problem that they have in common is the lack of a high resolution clock. The iPSC was also difficult to work with because the interprocessor communication mechanism caused some interference with (i.e. delayed) the user processes executing ....

D. R. Cheriton, "The V Kernel: A Software Base for Distributed Systems," IEEE Software, Vol. 1, No. 2, pp. 19-42, Apr. 1984.

....Message Transaction Protocol (VMTP) is a transport protocol developed by the Distributed Systems Group at Stanford University in the mid eighties. It was developed for use in a distributed systems environment to provide communication between network entities by means of message transactions [81] [89] VMTP is highly divergent from the connection oriented transport protocols. It is primarily designed to be used within a distributed system composed of a group of computers and to provide transaction oriented communication based on fast request response type of interactions such as remote ....

. D. R. Cheriton. "The V Kernel: A Software Base for Distributed Systems". IEEE Software 1, 2 (April 1984), 19-43.

....trend in the development of distributed systems is the provision of multicast communications: with multicast facilities, messages can be forwarded to multiple selected destinations in a single call. Examples of existing systems exploiting multicast include operating system kernels such as V [Cheriton,84] and Chorus [Herrmann,88] which have the notionof# port groups for multicast addressing, and ISIS [Birman,85] which enables distributed applications to be built using groups of UNIX processes. The ISIS system is particularly noteworthy as it was the first distributed system to treat multicast ....

Cheriton, D.R. "The V Kernel: A Software Base for Distributed Systems." IEEE Software Vol: 1 No. 2, April 1984, Pages 19-42.

....bulkier components of a typical UNIX configuration, such as a file system, can be built. It has proven to be an especially effective and elegant UNIX base for tightly coupled multiprocessor configurations. 2. 5 V Kernel The V Kernel is a distributed system base developed at Stanford University [7]. It is similar to Mach in that it provides a set of primitive services with which more sophisticated systems can be built. V supports two primary abstractions: processes and interprocess communication (IPC) Software systems built on top of V typically consist of multiple processes which ....

Cheriton, D. R. "The V Kernel: A Software Base for Distributed Systems", IEEE Software, April, 1984, pp. 19-42.

No context found.

D.R. Cheriton, "The V Kernel: A Software Base for Distributed Systems", IEEE Software 1(2), April, 1984.

No context found.

D. Cheriton, "The V Kernel: A software base for distributed systems," IEEE Software 1(2) pp. 19-42 (April 1984).

No context found.

Cheriton, D.R., "The V Kernel: A Software Base for Distributed Systems", IEEE Software, Vol. 1, No. 2, April 1984, pp. 19-42.

No context found.

Cheriton, D.R. "The V Kernel: A Software Base for Distributed Systems." IEEE Software Vol: 1 No.: 2, April 1984, Pages: 19-42.

No context found.

Cheriton84. D. R. Cheriton, "The V Kernel: A software base for distributed systems.", IEEE Software 1, 2 (Apr. 1984), 19-42.

No context found.

Cheriton84. D. R. Cheriton, "The V Kernel: A software base for distributed systems.", IEEE Software 1, 2 (Apr. 1984), 19-42.

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC