Towards Practical Default-On Multi-Core Record/Replay

Mashtizadeh, Ali José; Garfinkel, Tal; Terei, David; Mazières, David; Rosenblum, Mendel

doi:10.1145/3093336.3037751

Cited by 13 publications

(27 citation statements)

References 30 publications

(5 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We categorize this previous work into record-and-replay systems, and deterministic execution systems. Many record and replay (RnR) systems have been proposed both from academia [40][41][42][43][44][45][46] and industry [47][48][49]. These systems record a trace of one nondeterministic execution to enable subsequent replay of that execution, typically for debugging purposes.…”

Section: Related Workmentioning

confidence: 99%

Reproducible Containers

Leija

Shiptoski

Scott

et al. 2020

Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Syste

View full text Add to dashboard Cite

We describe the design and implementation of DetTrace, a reproducible container abstraction for Linux implemented in user space. All computation that occurs inside a DetTrace container is a pure function of the initial filesystem state of the container. Reproducible containers can be used for a variety of purposes, including replication for fault-tolerance, reproducible software builds and reproducible data analytics. We use DetTrace to achieve, in an automatic fashion, reproducibility for 12,130 Debian package builds, containing over 800 million lines of code, as well as bioinformatics and machine learning workflows. We show that, while software in each of these domains is initially irreproducible, DetTrace brings reproducibility without requiring any hardware, OS or application changes. DetTrace's performance is dictated by the frequency of system calls: IO-intensive software builds have an average overhead of 3.49×, while a compute-bound bioinformatics workflow is under 2%. CCS Concepts. Software and its engineeringMultiprocessing / multiprogramming / multitasking.

show abstract

Section: Related Workmentioning

confidence: 99%

Reproducible Containers

Leija

Shiptoski

Scott

et al. 2020

Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Syste

View full text Add to dashboard Cite

show abstract

“…A problem for migrating virtual machine storage also has been designed. Authors in [18][19] proposed the algorithms and found the solution to migrate the virtual machines. There are some other approaches which have been proposed for improving the VM migration.…”

Section: Related Workmentioning

confidence: 99%

Dynamic Load Balancing Ant Colony Optimization (DLBACO) Algorithm for Task Scheduling in Cloud Environment

Kushwaha*¹,

Amjad²,

Kumar³

2019

IJITEE

View full text Add to dashboard Cite

Cloud computing is a framework which provides on-demand services to the user for scalability, security, and reliability based on pay as used service anytime & anywhere. For load balancing, task scheduling is the most critical issues in the cloud environment. There are so many meta-heuristic algorithms used to solve the load balancing problem. A good task scheduling algorithm should be used for optimum load balancing in cloud environment. Such scheduling algorithm must have some vital characteristic like minimum makespan, maximum throughput, and maximum resource utilization, etc. In this paper, a dynamic load balancing and task scheduling algorithm based on ant colony optimization (DLBACO) has been proposed. This algorithm assigns the task the VM which has highest probability of availability in minimum time. The proposed algorithm balances the whole system by minimizing the makespan of the task and maximizing the throughput. CloudSim simulator is used to simulate the proposed scheduling algorithm and results show that the proposed (DLBACO) algorithm is better than the existing algorithms such as FCFS, LBACO (Load balancing ACO), and primary ACO

show abstract

“…Carving & Replay와 관련된 몇 가지의 연구들이 이 미 존재한다 [9][10][11][12][13][14]. 이 중 일부는 디버깅을 돕거나 오류 상황을 재현하기 위해 개발되었고 [9][10][11], 일부는 스레드 스케쥴링 같은 동시성의 재현을 위해 개발되었다 [12][13][14]. ADDA [9]…”

Section: 관련 연구unclassified

Automated Capturing and Replaying Unit Inputs of C Programs from System Executions through Static and Dynamic Analysis

Lim¹,

Kim²,

Kim³

2018

JOK

View full text Add to dashboard Cite

Despite the high testing power of unit testing, it has an infeasible input problem, which is an impossible input for a unit in a real system. There is a technique known as Carving and Replay (CR) that serializes the state of the program when a target function is called in system execution and uses it as unit test case by deserializing it, to solve this infeasible input problem. However, unlike programming languages like Java, the C programming language does not provide a serialization method. Also, because of the C programming language's features such as structure, union, and pointer, it has its own challenges for applying the CR technique. In this paper, we examine the challenges and suggest a CR tool for C programs by solving such problems with tracking the memory usage of the program, using run-time information from dynamic analysis, and inserting a probe code by static analysis.

show abstract

Towards Practical Default-On Multi-Core Record/Replay

Cited by 13 publications

References 30 publications

Reproducible Containers

Reproducible Containers

Dynamic Load Balancing Ant Colony Optimization (DLBACO) Algorithm for Task Scheduling in Cloud Environment

Automated Capturing and Replaying Unit Inputs of C Programs from System Executions through Static and Dynamic Analysis

Contact Info

Product

Resources

About