Daniele Bonetta

An object storage model for the truffle language implementation framework

Truffle is a Java-based framework for developing high-performance language runtimes. Language implementers aiming at developing new runtimes have to design all the runtime mechanisms for managing dynamically typed objects from scratch. This not only leads to potential code duplication, but also impacts the actual time needed to develop a fully-fledged runtime. In this paper we address this issue by introducing a common object storage model (OSM) for Truffle that can be used by language implementers to develop new runtimes. The OSM is generic, language-agnostic, and portable, as it can be used to implement a great variety of dynamic languages. It is extensible, featuring built-in support for custom extension mechanisms. It is also high-performance, as it is designed to benefit from the optimizing compiler in the Truffle framework. Our initial evaluation indicates that the Truffle OSM can be used to implement high-performance language runtimes, with no performance overhead when compared to language-specific solutions.

An Architectural Style for Liquid Web Services

Just as liquids adapt their shape to the one of their container, liquid architectures feature a high degree of adaptability so that they can provide scalability to applications as they are executed on a wide variety of heterogeneous deployment environments. In this paper we enumerate the properties to be guaranteed by so-called liquid service-oriented architectures and define a set of design constraints that make up a novel architectural style for liquid architectures. These constraints drive the careful construction of a pattern, the Restful Actor (Reactor), which enables to deliver the required scalability by means of replication of its constituent parts. Reactors feature a Restful Web service interface and a composable architecture which is capable of delivering scalability and high performance in a way that is independent from the chosen deployment infrastructure. We discuss how the Reactor can be deployed to run on distributed (shared-nothing) execution environments typical of virtualized Cloud computing environments as well as on modern multicore processors with shared memory architectures.

Efficient and thread-safe objects for dynamically-typed languages

We are in the multi-core era. Dynamically-typed languages are in widespread use, but their support for multithreading still lags behind. One of the reasons is that the sophisticated techniques they use to efficiently represent their dynamic object models are often unsafe in multithreaded environments. This paper defines safety requirements for dynamic object models in multithreaded environments. Based on these requirements, a language-agnostic and thread-safe object model is designed that maintains the efficiency of sequential approaches. This is achieved by ensuring that field reads do not require synchronization and field updates only need to synchronize on objects shared between threads. Basing our work on JRuby+Truffle, we show that our safe object model has zero overhead on peak performance for thread-local objects and only 3% average overhead on parallel benchmarks where field updates require synchronization. Thus, it can be a foundation for safe and efficient multithreaded VMs for a wide range of dynamic languages.

S: a scripting language for high-performance RESTful web services

There is an urgent need for novel programming abstractions to leverage the parallelism in modern multicore machines. We introduce S, a new domain-specific language targeting the server-side scripting of high-performance RESTful Web services. S promotes an innovative programming model based on explicit (control-flow) and implicit (process-level) parallelism control, allowing the service developer to specify which portions of the control-flow should be executed in parallel. For each service, the choice of the best level of parallelism is left to the runtime system. We assess performance and scalability by implementing two non-trivial composite Web services in S. Experiments show that S-based Web services can handle thousands of concurrent client requests on a modern multicore machine.

TigerQuoll: parallel event-based JavaScript

JavaScript, the most popular language on the Web, is rapidly moving to the server-side, becoming even more pervasive. Still, JavaScript lacks support for shared memory parallelism, making it challenging for developers to exploit multicores present in both servers and clients. In this paper we present TigerQuoll, a novel API and runtime for parallel programming in JavaScript. TigerQuoll features an event-based API and a parallel runtime allowing applications to exploit a mutable shared memory space. The programming model of TigerQuoll features automatic consistency and concurrency management, such that developers do not have to deal with shared-data synchronization. TigerQuoll supports an innovative transaction model that allows for eventual consistency to speed up high-contention workloads. Experiments show that TigerQuoll applications scale well, allowing one to implement common parallelism patterns in JavaScript.

Overseer: low-level hardware monitoring and management for Java

The high-level and portable nature of the Java platform allows applications to be written once and executed on all the supported systems. However, such a feature comes at the cost of hardware abstraction, making it more difficult or even impossible to access several low-level functionalities. Overseer is a Java framework that makes it possible on Linux systems by simplifying access to real-time measurement of low-level data such as Hardware Performance Counters (HPCs), IPMI sensors, and Java VM internal events. Overseer supports functionalities such as HPC-management, process/thread affinity settings, hardware topology identification, as well as power-consumption and temperature monitoring. In this paper we describe Overseer and how to use it to extend Java applications with functionalities not provided by the default runtime. A public release of Overseer is available.

Exploiting multicores to optimize business process execution

While modern CPUs offer an increasing number of cores with shared caches, prevailing execution engines for business processes, workflows, or Web service compositions have not been optimized for properly exploiting the abundant processing resources of such CPUs. One factor limiting performance is the inefficient thread scheduling by the operating system, which can result in suboptimal use of shared caches. In this paper we study performance of the JOpera business process execution engine on a recent multicore machine. By analyzing the engines architecture and by binding threads that are likely to access shared data to cores with a common cache, we achieve speedups up to 13% for a variety of workloads, without modifying the engines architecture and implementation, apart from binding threads to CPUs. As the engine is implemented in Java, we provide a new Java library to manage thread bindings and hardware performance counters. We also leverage hardware performance counters to explain the observed speedup in our performance analysis.

Hardware-aware Thread Scheduling: The Case of Asymmetric Multicore Processors

Modern processor architectures are increasingly complex and heterogeneous, often requiring solutions tailored to the specific characteristics of each processor model. In this paper we address this problem by targeting the AMD Bulldozer processor as case study for specific hardware-oriented performance optimizations. The Bulldozer architecture features an asymmetric simultaneous multithreading implementation with shared floating point units (FPUs) and per-core arithmetic logic units (ALUs). Bulld Over, presented in this paper, improves thread scheduling by exploiting this hardware characteristic to increase performance of floating point-intensive workloads on Linux-based operating systems. Bulld Over is a user-space monitoring tool that automatically identifies FPU-intensive threads and schedules them in a more efficient way without requiring any patches or modifications at the kernel level. Our measurements using standard benchmark suites show that speedups of up to 10% can be achieved by simply allowing Bulld Over to monitor applications, without any modification of the workload.

A Multicore-Aware Runtime Architecture for Scalable Service Composition

Middleware for web service orchestration, such as runtime engines for executing business processes, workflows, or web service compositions, can easily become performance bottlenecks when the number of concurrent service requests increases. Many existing process execution engines have been designed to address scalability with distribution and replication techniques. However, the advent of modern multicore machines, comprising several chip multi-processors each offering multiple cores and often featuring a large shared cache, offers the opportunity to redesign the architecture of process execution engines in order to take full advantage of the underlying hardware resources. In this paper we present an innovative process execution engine architecture. Its design takes into account the specific constraints of multicore machines and scales well on different processor architectures, as shown by our extensive performance evaluation. A key feature of the design is self-configuration at startup according to the type and number of available CPUs. We show that our design makes efficient use of the available resources and can scale to run thousands of concurrent business process instances per second, highlighting the potential and the benefits for multicore-awareness in the design of scalable process execution engines.

Towards Self-Organizing Service-Oriented Architectures

Service-oriented architectures (SOAs) provide a successful model for structuring complex distributed software systems, as they reduce the cost of ownership and ease the creation of new applications by composing existing services. However, currently, the development of service-oriented applications requires many manual tasks and prevailing infrastructure is often based on centralized components that are central points of failure and easily become bottlenecks. In this paper, we promote self-organizing SOA as a new approach to overcome these limitations. Self-organizing SOA integrates research results in the areas of autonomic and service oriented computing. We consider self-organizing features for the whole life-cycle of a service-oriented application, from the creation to the execution, optimization, and monitoring.