Efficient garbage collection is a key goal in engineering high-performance runtime systems. To reduce pause times, many collector designs traverse the object graph concurrently with the application, an optimization known as concurrent marking. Traditional concurrent marking imposes strict invariants on the object shapes: 1) static type layout of objects, 2) static object memory locations, 3) static object sizes. High performance virtual machines for dynamic languages, for example, the V8 JavaScript virtual machine used in the Google Chrome web browser, generally violate these constraints in pursuit of high throughput for a single thread. Taking V8 as an example, we show that some object shape changes are safe and can be handled by traditional concurrent marking algorithms. For unsafe shape changes, we introduce novel wait-free object snapshotting and lock-based concurrent marking algorithms and prove that they preserve key invariants. We implemented both algorithms in V8 and achieved performance improvements on various JavaScript benchmark suites and real-world web workloads. Concurrent marking of shape-changing objects using the wait-free object snapshotting algorithm is enabled by default in Chrome since version 64.

Embedding a modern language runtime as a component in a larger software system is popular these days. Communication between these systems often requires keeping references to each others' objects. In this paper we present and discuss the problem of cross-component memory management where reference cycles across component boundaries may lead to memory leaks and premature reclamation of objects may lead to dangling cross-component references. We provide a generic algorithm for effective, efficient, and safe garbage collection over component boundaries, which we call cross-component tracing. We designed and implemented cross-component tracing in the Chrome web browser where the JavaScript virtual machine V8 is embedded into the rendering engine Blink. Cross-component tracing from V8's JavaScript heap to Blink's C++ heap improves garbage collection latency and eliminates long-standing memory leaks for real websites in Chrome. We show how cross-component tracing can help web developers to reason about reachability and retainment of objects spanning both V8 and Blink components based on Chrome's heap snapshot memory tool. Cross-component tracing was enabled by default for all websites in Chrome version 57 and is also deployed in other widely used software systems such as Opera, Cobalt, and Electron.

Priority queues with parallel access are an attractive data structure for applications like prioritized online scheduling, discrete event simulation, or greedy algorithms. However, a classical priority queue constitutes a severe bottleneck in this context, leading to very small throughput. Hence, there has been significant interest in concurrent priority queues with relaxed semantics. We investigate the complementary quality criteria rank error (how close are deleted elements to the global minimum) and delay (for each element x, how many elements with lower priority are deleted before x). In this paper, we introduce MultiQueues as a natural approach to relaxed priority queues based on multiple sequential priority queues. Their naturally high theoretical scalability is further enhanced by using three orthogonal ways of batching operations on the sequential queues. Experiments indicate that MultiQueues present a very good performance-quality tradeoff and considerably outperform competing approaches in at least one of these aspects. We employ a seemingly paradoxical technique of "wait-free locking" that might be of more general interest to convert sequential data structures to relaxed concurrent data structures.

We demonstrate that general-purpose memory allocation involving many threads on many cores can be done with high performance, multicore scalability, and low memory consumption. For this purpose, we have designed and implemented scalloc, a concurrent allocator that generally performs and scales in our experiments better than other allocators while using less memory, and is still competitive otherwise. The main ideas behind the design of scalloc are: uniform treatment of small and big objects through so-called virtual spans, efficiently and effectively reclaiming free memory through fast and scalable global data structures, and constant-time (modulo synchronization) allocation and deallocation operations that trade off memory reuse and spatial locality without being subject to false sharing.

We take the paradigm of cloud computing developed in the cyber-world and put it into the physical world to create a cyber-physical computing cloud. A server in this cloud moves in space making it a vehicle with physical constraints. Such vehicles also have sensors and actuators elevating mobile sensor networks from a deployment to a service. Possible hosts include cars, planes, people with smartphones, and emerging robots like unmanned aerial vehicles or drifters. We extend the notion of a virtual machine with a virtual speed and call it a virtual vehicle, which travels through space by being bound to real vehicles and by migrating from one real vehicle to another in a manner called cyber-mobility. We discuss some of the challenges and envisioned solutions, and describe our prototype implementation.

We propose a new memory model called short-term memory for managing objects on the heap. In contrast to the traditional persistent memory model for heap management, objects in short-term memory expire after a finite amount of time, which makes deallocation unnecessary. Instead, expiration of objects may be extended, if necessary, by refreshing. We have developed a concurrent, incremental, and non-moving implementation of short-term memory for explicit refreshing called self-collecting mutators that is based on programmer-controlled time and integrated into state-of-the-art runtimes of three programming languages: C, Java, and Go. All memory management operations run in constant time without acquiring any locks modulo the underlying allocators. Our implementation does not require any additional heap management threads, hence the name. Expired objects may be collected anywhere between one at a time for maximal incrementality and all at once for maximal throughput and minimal memory consumption. The integrated systems are heap management hybrids with persistent memory as default and short-term memory as option. Our approach is fully backwards compatible. Legacy code runs without any modifications with negligible runtime overhead and constant per-object space overhead. Legacy code can be modified to take advantage of short-term memory by having some but not all objects allocated in short-term memory and managed by explicit refreshing. We study single- and multi-threaded use cases in all three languages macro-benchmarking C and Java and micro-benchmarking Go. Our results show that using short-term memory (1) simplifies heap management in a state-of-the-art H.264 encoder written in C without additional time and minor space overhead, and (2) improves, at the expense of safety, memory management throughput, latency, and space consumption by reducing the number of garbage collection runs, often even to zero, for a number of Java and Go programs.