Writing concurrent programs is notoriously difficult, and is of increasing practical importance. A particular source of concern is that even correctly-implemented concurrency abstractions cannot be composed together to form larger abstractions. In this paper we present a new concurrency model, based on transactional memory, that offers far richer composition. All the usual benefits of transactional memory are present (e.g. freedom from deadlock), but in addition we describe new modular forms of blocking and choice that have been inaccessible in earlier work.

/pdf/composable-memory-transactions-2yr3k785o4.pdf

Composable memory transactions

We describe applications of a virtually synchronous environment for distributed programming, which underlies a collection of distributed programming tools in the ISIS2 system. A virtually synchronous environment allows processes to be structured into process groups, and makes events like broadcasts to the group as an entity, group membership changes, and even migration of an activity from one place to another appear to occur instantaneously — in other words, synchronously. A major advantage to this approach is that many aspects of a distributed application can be treated independently without compromising correctness. Moreover, user code that is designed as if the system were synchronous can often be executed concurrently. We argue that this approach to building distributed and fault-tolerant software is more straightforward, more flexible, and more likely to yield correct solutions than alternative approaches.

/pdf/exploiting-virtual-synchrony-in-distributed-systems-489dpprmq1.pdf

Exploiting virtual synchrony in distributed systems

Transactional memory (TM) simplifies parallel programming by guaranteeing that transactions appear to execute atomically and in isolation. Implementing these properties includes providing data version management for the simultaneous storage of both new (visible if the transaction commits) and old (retained if the transaction aborts) values. Most (hardware) TM systems leave old values "in place" (the target memory address) and buffer new values elsewhere until commit. This makes aborts fast, but penalizes (the much more frequent) commits. In this paper, we present a new implementation of transactional memory, log-based transactional memory (LogTM), that makes commits fast by storing old values to a per-thread log in cacheable virtual memory and storing new values in place. LogTM makes two additional contributions. First, LogTM extends a MOESI directory protocol to enable both fast conflict detection on evicted blocks and fast commit (using lazy cleanup). Second, LogTM handles aborts in (library) software with little performance penalty. Evaluations running micro- and SPLASH-2 benchmarks on a 32-way multiprocessor support our decision to optimize for commit by showing that only 1-2% of transactions abort.

/pdf/logtm-log-based-transactional-memory-diej8z7g8v.pdf

LogTM: log-based transactional memory

An approach to the coordinated sharing and interchange of computerized information is described emphasizing partial, controlled sharing among autonomous databases. Office information systems provide a particularly appropriate context for this type of information sharing and exchange. A federated database architecture is described in which a collection of independent database systems are united into a loosely coupled federation in order to share and exchange information. A federation consists of components (of which there may be any number) and a single federal dictionary. The components represent individual users, applications, workstations, or other components in an office information system. The federal dictionary is a specialized component that maintains the topology of the federation and oversees the entry of new components. Each component in the federation controls its interactions with other components by means of an export schema and an import schema. The export schema specifies the information that a component will share with other components, while the import schema specifies the nonlocal information that a component wishes to manipulate. The federated architecture provides mechanisms for sharing data, for sharing transactions (via message types) for combining information from several components, and for coordinating activities among autonomous components (via negotiation). A prototype implementation of the federated database mechanism is currently operational on an experimental basis.

A federated architecture for information management

This paper presents an overview of an integrated programming language and system designed to support the construction and maintenance of distributed programs: programs in which modules reside and execute at communicating, but geographically distinct, nodes. The language is intended to support a class of applications in which the manipulation and preservation of long-lived, on-line, distributed data is important. The language addresses the writing of robust programs that survive hardware failures without loss of distributed information and that provide highly concurrent access to that information while preserving its consistency. Several new linguistic constructs are provided; among them are atomic actions, and modules called guardians that survive node failures.

Guardians and Actions: Linguistic Support for Robust, Distributed Programs

This report addresses the issue of providing software for reliable distributed systems. In particular, we examine how to program a system so that the software continues to work in the face of a variety of failures of parts of the system. The design presented uses the concept of transactions: collections of primitive actions that are indivisible. The indivisibility of transactions insures that consistent results are obtained even when requests are processed concurrently or failures occur during a request. Our design permits transactions to be nested. Nested transactions provide nested universes of synchronization and recovery from failures. The advantages of nested transactions over single-level transactions are that they provide concurrency control within transactions by serializing subtransactions appropriately, and that they permit parts of a transaction to fail without necessarily aborting the entire transaction. The method for implementing nested transactions described in this report is novel in that it uses locking for concurrency control. We present the necessary algorithms for locking, recovery, distributed commitment, and distributed deadlock detection for a nested transaction system. While the design has not been implemented, it has been simulated.

Nested Transactions: An Approach to Reliable Distributed Computing

Garbage collectors provide memory safety, an important step toward program correctness. However, correctness of the collector itself can be challenging to establish, given both the style in which such systems are written and the weakly-ordered memory accesses of modern hardware. One way to maximize benefits is to use a framework in which effort can be focused on the correctness of small, modular critical components from which various collectors may be composed. Full proof of correctness is likely impractical, so we propose to gain a degree of confidence in collector correctness by applying model checking to critical kernels within a garbage collection framework. We further envisage a model framework, paralleling the framework nature of the collector, in hope that it will be easy to create new models for new collectors. We describe here a prototype model structure, and present results of model checking both stop-the-world and snapshot-at-the-beginning concurrent marking. We found useful regularities of model structure, and that models could be checked within possible time and space budgets on capable servers. This suggests that collectors built in a modular style might be model checked, and further that it may be worthwhile to develop a model checking framework with a domain-specific language from which to generate those models.

https://dl.acm.org/doi/pdf/10.1145/3546918.3546923

E. B. Moss

Papers

Nested Transactions: An Approach to Reliable Distributed Computing

Towards a Model Checking Framework for a New Collector Framework

The Garbage Collection Handbook