Abstract: "Interprocess communication (IPC), in particular IPC oriented towards local communication (between address spaces on the same machine), has become central to the design of contemporary operating systems. IPC has traditionally been the responsibility of the kernel, but kernel-based IPC...

Ausführliche Beschreibung

Bibliographische Detailangaben

Format:	Buch
Sprache:	English
Veröffentlicht:	Seattle, Wash. 1990
Schriftenreihe:	University of Washington <Seattle, Wash.> / Department of Computer Science: Technical report 90,5,7
Schlagworte:	Operating systems (Computers) Parallel programming (Electronic computers)
Zusammenfassung:	Abstract: "Interprocess communication (IPC), in particular IPC oriented towards local communication (between address spaces on the same machine), has become central to the design of contemporary operating systems. IPC has traditionally been the responsibility of the kernel, but kernel-based IPC has two inherent problems. First, its performance is architecturally limited by the cost of invoking the kernel and reallocating a processor from one address space to another. Second, applications that need inexpensive threads and must provide their own thread management encounter functional and performance problems stemming from the interaction between kernel-level communication and user-level thread management On a shared memory multiprocessor, these problems can be solved by moving the communication facilities out of the kernel and supporting them at the user level within each address space. Communication performance is improved since kernel invocation and processor reallocation can be avoided when communicating between address spaces on the same machine. Further, the relationship between communication and thread management can be efficiently maintained, since the facilities that provide both are implemented together at the user level. These observations motivate User-Level Remote Procedure Call (URPC), the system described in this paper URPC decouples processor reallocation from data transfer and thread management by combining a fast cross-address space communication protocol using shared memory with ultra-lightweight threads managed entirely at the user level. By decoupling, the kernel can be bypassed during cross-address space communication. The programmer sees threads and RPC through a conventional interface, though with unconventional performance. The latency of a synchronous cross-address space call is 93 [mu]secs using URPC on the Firefly, a C-VAX-based multiprocessor workstation. In a pipelined mode, two processors can complete one call every 53 [mu]secs
Beschreibung:	32 S.