Don't Persist All : Efficient Persistent Data Structures

1991

Reachability-based persistence imposes new requirements for main memory management in general, and garbage collection in particular. After a brief introduction to the characteristics and requirements of reachability-based persistence, we present the design of a run-time storage manager for Persistent Smalltalk and Persistent Modula-3, which allows the reclamation of storage from both temporary objects and buffered persistent objects.

Workshop on Persistent Object Systems, 1990

We consider how a persistent programming language might offer performance competitive with that of non-persistent languages, at least on memory resident data. We are concerned with object-oriented languages, and with implementing persistence via object faulting, where the system detects uses of non-resident objects and fetches them on demand. We present some background on object faulting and means for implementing it, and describe a specific language we are developing, namely Persistent Modula-3. Then we explore approaches to optimising persistence aspects of Persistent Modula-3, and outline techniques under consideration in our compiler development effort.

2021

Unlocking the true potential of the new persistent memories (PMEMs) requires eliminating traditional persistent I/O abstractions altogether, by introducing persistent semantics directly into main memory programming. Such a programming model elevates failure atomicity to a first-class application property in addition to in-memory data layout, concurrency-control, and fault tolerance, and therefore requires redesign of programming abstractions for both program correctness and maximum performance gains. To address these challenges, this thesis proposes a set of system software designs that integrate persistence with main memory programming, and makes the following contributions. First, this thesis proposes a PMEM-aware I/O runtime, NVStream, that supports fast durable streaming I/O. NVStream uses a memory-based I/O interface that integrates with existing I/O data movement operations of an application to accelerate persistent data writes. NVStream carefully designs its persistent data s...

2020

The recent emergence of fast, dense, nonvolatile main memory suggests that certain long-lived data might remain in its natural pointer-rich format across program runs and hardware reboots. Operations on such data must be instrumented with explicit write-back and fence instructions to ensure consistency in the wake of a crash. Techniques to minimize the cost of this instrumentation are an active topic of research. We present what we believe to be the first general-purpose approach to building buffered durably linearizable persistent data structures, and a system, Montage, to support that approach. Montage is built on top of the Ralloc nonblocking persistent allocator. It employs a slow-ticking epoch clock, and ensures that no operation appears to span an epoch boundary. It also arranges to persist only that data minimally required to reconstruct the structure after a crash. If a crash occurs in epoch $e$, all work performed in epochs $e$ and $e-1$ is lost, but work from prior epochs ...

2017

for their contributions to the implementation of JaphaVM. It was great belonging to this team. I owe a great debt to Pedro Garcez Monteiro, for his valuable contributions to JaphaVM, first at the LIS lab, and later as an HP colleague. Diego Rahn Medaglia and Marcelo S. Neves made important contributions to adapt the OO7 benchmark, create testing environments, and discuss experimental results. You guys are awesome. Haris Volos and Susan Spence, from HP Labs, and Prof. Avelino Zorzo, from PUCRS, reviewed early drafts of this text and made many valuable suggestions. Dejan S. Milojicic, also from HP Labs, provided support and guidance in many ways. I am truly grateful for all their contributions. I would also like to thank collectively all the pioneer researchers of orthogonal persistence, for seeing further into the future. None of this would have been possible without my family: my wife Ana Paula da Fonseca, my daughter Valentina Velez and my mother-in-law Ana Maria Beati. They kept me sane and fed and warm and loved. I dearly love you all. Since I was too young to remember, my mother, Neusa Marisa Elias Dreckmann, fanned the fires of my curiosity and taught me by example how to have the drive and resilience to turn visions into reality. I wouldn't be here if not for her, in many ways.

Lecture Notes in Computer Science, 1989

2015

We consider how a persistent programming language might offer performance competitive with that of non-persistent languages, at least on memory resident data. We are concerned with object-oriented languages, and with implementing persistence via object faulting, where the system detects uses of non-resident objects and fetches them on demand. We present some background on object faulting and means for implementing it, and describe a specific language we are developing, namely Persistent Modula-3. Then we explore approaches to optimising persistence aspects of Persistent Modula-3, and outline techniques under consideration in our compiler development effort.

ArXiv, 2021

MCAS (Memory Centric Active Storage) is a persistent memory tier for high-performance durable data storage. It is designed from the ground-up to provide a key-value capability with low-latency guarantees and data durability through memory persistence and replication. To reduce data movement and make further gains in performance, we provide support for user-defined “push-down” operations (known as Active Data Objects) that can execute directly and safely on the value-memory associated with one or more keys. The ADO mechanism allows complex pointer-based dynamic data structures (e.g., trees) to be stored and operated on in persistent memory. To this end, we examine a real-world use case for MCAS-ADO in the handling of enterprise storage system metadata for Continuous Data Protection (CDP). This requires continuously updated complex metadata that must be kept consistent and durable. In this paper, we i.) present the MCAS-ADO system architecture, ii.) show how the CDP use case is implem...

Pointer information, indispensable for static analysis tools, is expensive to compute and query. We provide a query-efficient persistence technique, Pestrie, to mitigate the costly computation and slow querying of precise pointer information. Leveraging equivalence and hub properties, Pestrie can compress pointer information and answers pointer related queries very efficiently. The experiment shows that Pestrie produces 10.5× and 17.5× smaller persistent files than the traditional bitmap and BDD encodings. Meanwhile, Pestrie is 2.9× to 123.6× faster than traditional demand-driven approaches for serving points-to related queries.

Computing Systems, 1992