Implementing Lightweight Remote Procedure Calls in the Mach 3 Operating System
نویسندگان
چکیده
The Mach 3 operating system makes extensive use of remote procedure calls (RPCs) to provide services to client applications. Although the existing Mach 3 RPC facility is highly optimized, the incorporation of a Lightweight Remote Procedure Call (LRPC) facility further reduces this critical cost. This paper describes the implementation of LRPC in the Mach 3 operating system, reviewing the original LRPC concept and implementation in the TAOS operating system, the issues involved with the Mach 3 microkernel operating system, and the resulting design of LRPCMach3. Performance measurements indicate that the resulting implementation provides a 31% reduction in latency for a minimal RPC, with even more significant benefits for more complicated RPCs.
منابع مشابه
FLEX: A Tool for Building E cient and Flexible Systems
Modern operating systems must support a wide variety of services for a diverse set of users. Designers of these systems face a tradeoo between functionality and performance. Systems like Mach provide a set of general abstractions and attempt to handle every situation, which can lead to poor performance for common cases. Other systems, such as Unix, provide a small set of abstractions that can b...
متن کاملFLEX: A Tool for Building Efficient and Flexible Systems
Modern operating systems must support a wide variety of services for a diverse set of users. Designers of these systems face a tradeoo between functionality and performance. Systems like Mach provide a set of general abstractions and attempt to handle every situation, which can lead to poor performance for common cases. Other systems, such as Unix, provide a small set of abstractions that can b...
متن کاملIn-Kernel Servers on Mach 3.0: Implementation and Performance
The advantages in modularity and power of microkernel-based operating systems such as Mach 3.0 are well known. The existing performance problems of these systems, however, are signi cant. Much of the performance degradation is due to the cost of maintaining separate protection domains, traversing software layers, and using a semantically rich inter-process communication mechanism. An approach t...
متن کاملMessage Passing, Remote Procedure Calls and Distributed Shared Memory as Communication Paradigms for Distributed Systems
Message passing and remote procedure calls are the most commonly used communication paradigms for interprocess communication in distributed systems. Distributed shared memory is an equally valuable but less often used paradigm. The advantage offered by distributed shared memory is that it abstracts away from the fact that the memory is distributed and allows the programmer to use the familiar s...
متن کاملEfficient Treatment of Failures in RPC Systems
This paper addresses extensions to be made to a basic remote procedure call system for the integration of primitive fault tolerance measures. Our main design goal is to not introduce performance penalty for remote procedure calls executing in the absence of failures, and to not impose signiicant overhead by the treatment of failures. Basically, extensions include a simple algorithm that nds and...
متن کامل