On testing persistent-memory-based software

Oukid, Ismail; Booss, Daniel; Lespinasse, Adrien; Lehner, Wolfgang

doi:10.1145/2933349.2933354

Cited by 10 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) Huge testing space. Exhaustive testing approach [32,42,55] attempts to permute all possible persistent states on a crash. Then, for each crashed state, they rely on a userprovided consistency checker to validate whether NVM data is consistent.…”

Section: Limitations Of Existing Solutionsmentioning

confidence: 99%

“…Recently, several solutions for detecting crash consistency bugs have been proposed, but they are not satisfactory. One line of tools [32,42,55] attempts to test all possible inconsistent states exhaustively, leading to a scalability issue. For instance, Yat [42] reports that a program execution with 14K cache line flushes leads to 789 million combinations to test, which will take roughly 5.2 years.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

WITCHER : Detecting Crash Consistency Bugs in Non-volatile Memory Programs

Fu¹,

Kim²,

Shreepathi³

et al. 2020

Preprint

View full text Add to dashboard Cite

The advent of non-volatile main memory (NVM) enables the development of crash-consistent software without paying storage stack overhead. However, building a correct crashconsistent program remains very challenging in the presence of a volatile cache. This paper presents WITCHER, a crash consistency bug detector for NVM software, that is (1) scalable -does not suffer from test space explosion, (2) automatic -does not require manual source code annotations, and (3) precise -does not produce false positives. WITCHER first infers a set of "likely invariants" that are believed to be true to be crash-consistent by analyzing source codes and NVM access traces. WITCHER automatically composes NVM images that simulate those potentially inconsistent (crashing) states violating the likely invariants. Then WITCHER performs "output equivalence checking" by comparing the output of program executions with and without a simulated crash. It validates if a likely invariant violation under test is a true crash consistency bug. Evaluation with ten persistent data structures, two real-world servers, and five example codes in Intel's PMDK library shows that WITCHER outperforms state-of-the-art tools. WITCHER discovers 37 (32 new) crash consistency bugs, which were all confirmed.

show abstract

Section: Limitations Of Existing Solutionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

WITCHER : Detecting Crash Consistency Bugs in Non-volatile Memory Programs

Fu¹,

Kim²,

Shreepathi³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The last few years have seen a surge in research efforts that investigate how database systems can leverage SCM as persistent main memory. These research efforts can be categorized into: SCM memory management [19,44,45,31], SCM-based persistent data structures [53,6,43,28], optimizing database algorithms for SCM [7,51], new testing frameworks for SCM-based software [26,42], improving the database logging infrastructure [11,52,16], and finally exploring novel, SCMenabled database storage architectures [41,2,22].…”

Section: Scm Drammentioning

confidence: 99%

“…software [26,42], improving the database logging infrastructure [11,52,16], and finally exploring novel, SCMenabled database storage architectures [41,2,22].…”

Section: Application Application Address Spacementioning

confidence: 99%

On the Diversity of Memory and Storage Technologies

Oukid

Lersch

2018

Datenbank Spektrum

Self Cite

View full text Add to dashboard Cite

The last decade has seen tremendous developments in memory and storage technologies, starting with Flash Memory and continuing with the upcoming Storage-Class Memories. Combined with an explosion of data processing, data analytics, and machine learning, this led to a segmentation of the memory and storage market. Consequently, the traditional storage hierarchy, as we know it today, might be replaced by a multitude of storage hierarchies, with potentially different depths, each tailored for specific workloads. In this context, we explore in this "Kurz Erklärt" the state of memory technologies and reflect on their future use with a focus on data management systems.

show abstract

Non-Volatile Memory Database Management Systems

Arulraj

Pavlo

2019

Synthesis Lectures on Data Management

View full text Add to dashboard Cite

On testing persistent-memory-based software

Cited by 10 publications

References 9 publications

WITCHER : Detecting Crash Consistency Bugs in Non-volatile Memory Programs

WITCHER : Detecting Crash Consistency Bugs in Non-volatile Memory Programs

On the Diversity of Memory and Storage Technologies

Non-Volatile Memory Database Management Systems

Contact Info

Product

Resources

About