Most computer architectures are moving to 64-bit virtual address spaces. We first discuss how this change impacts conventional linear, forwardmapped, and hashed page tables. We then introduce a new page table data structure—clustered page table—that can be viewed as a hashed page table aug-mented with subblocking. Specifically, it associates mapping information for several pages (e.g., sixteen) with a single virtual tag and next pointer. Simulation results with several workloads show that clustered page tables use less memory than alternatives with-out adversely affecting page table access time. Since physical address space use is also increas-ing, computer architects are using new techniques— such as superpages, complete-subblocking, and partial-subblocking—to increase the memory mapped by a translation lookaside buffer (TLB). Since these tech-niques are completely ineffective without page table support, we next look at extending conventional and clustered page tables to support them. Simulation re-sults show clustered page tables support medium-sized superpage and subblock TLBs especially well.

In this paper we describe an architecture for extensible file systems. The architecture enables the extension of file system functionality by composing (or stacking) new file systems on top of existing file systems. A file system that is stacked on top of an existing file system can access the existing file system's files via a well-defined naming interface and can share the same underlying file data in a coherent manner. We describe extending file systems in the context of the Spring operating system. Composing file systems in Spring is facilitated by basic Spring features such as its virtual memory architecture, its strongly-typed well-defined interfaces, its location-independent object invocation mechanism, and its flexible naming architecture. File systems in Spring can reside in the kernel, in user-mode, or on remote machines, and composing them can be done in a very flexible manner.

Abstract Shared memory is a simple yet powerful paradigm for structuring systems. Recently, there has been an interest in extending this paradigm to non‐shared memory architectures as well. For example, the virtual address spaces for all objects in a distributed object‐based system could be viewed as constituting a globaldistributed shared memory. We propose a set of primitives for managing distributed shared memory. We present an implementation of these primitives in the context of an object‐based operating system as well as on top of Unix.

In a distributed system, remote services may be provided either by a remote procedure call (RPC) mechanism or by paging in the required memory segments and performing the services locally. The latter approach, termed distributed shared memory (DSM) has several benefits given the current trend of structuring computing systems using diskless computational servers (workstations) and data servers (file servers). A set of distributed shared memory mechanisms that handle networkwide memory management for an object-based system is proposed. The implementation of these mechanisms is discussed and examples of their use in implementing the programming language Linda, process migration, two-phase commit and a distributed game are provided.>

Object-based operating systems have the desirable property of separating policies from mechanisms while providing a protected procedure call interface for accessing system services. However, the kernel mechanisms in such systems rely very heavily on efficient memory management. A set of criteria for supporting the kernel mechanisms in object-based systems is presented. The design of a simple MMU (memory management unit) tailored for object-based systems is presented. The proposed design is an engineering solution combining the features available in commercial MMUs.>

The authors present a resource (e.g. file, process) location scheme which utilizes the multicast communication capability of local area networks (LANs). In the scheme, the universe of resource names is partitioned into a relatively small number of groups and each group is assigned a unique address. Nodes storing the locations of resources belonging to a particular group instruct their network interfaces to receive all location messages sent to the group address. To locate a resource, a node first determines the address of the group to which the resource belongs, and a multicast message is then sent to the address. The algorithm performance is studied by simulation, and approximate closed-form solutions are derived for systems operating at heavy and low loads. The scheme's performance is compared with that of broadcast, and it is shown that the proposed scheme performs much better than broadcast alone.>