Adaptive Sender-based Message Logging and Checkpointing Protocol for Large-Scale Distributed Systems

Ahn, Jin Ho

doi:10.14801/jkiit.2022.20.1.41

Cited by 1 publication

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The deadlock problem has been extensively studied in distributed operating systems [1][2][3][4][5]. Many algorithms for centralized and distributed deadlock detection, prevention, and avoidance have been proposed in the literature [6,7,9,[12][13][14].…”

Section: Related Workmentioning

confidence: 99%

“…Before granting the requested resource, the sender process is blocked and said to be dependent on the process that holds the desired resource. The distributed computing system offers many advantages over a single-site system, such as data and program sharing, higher system throughput, higher system availability, load sharing, and incremental expandability [5][6][7]. Distributed computing systems are vital to many real-time applications that require guaranteed response time and continued operation in the face of system crashes.…”

Section: Introductionmentioning

confidence: 99%

“…Extensive research has been carried out on distributed computing systems. Research issues include scheduling algorithms, deadlock detection, deadlock prevention, concurrency control protocols, and resource scheduling algorithms [5][6][7][8][9][10][11]. This paper is concerned with deadlock detection and resolution in distributed computing systems.…”

Section: Introductionmentioning

confidence: 99%

“…This constraint is not compatible with distributed computing systems. Also, deadlock avoidance is not practical in distributed computing systems because any attempt to avoid deadlock is inefficient [5,7,12]. Many researchers have tried to deal with the simpler problem of just detecting deadlocks.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An Improved Deadlock Detection and Resolution Algorithm for Distributed Computing Systems

Helmy

2024

Preprint

View full text Add to dashboard Cite

Deadlock is a real problem that can cause expensive, time-dependent hang-ups or failures in distributed computing systems. Some studies have been conducted with deadlock detection and resolution in generalized request computing models, most of these studies are based on the diffusing computation scheme, where forward and backward propagated probe and reply messages respectively are diffused between dependent processes. The replies carry the dependency information between processes for the initiator. Using this dependency information initiator can detect and resolve the deadlock cycle. It has been proven in the literature that a deadlock cycle length distribution is skewed with a large majority of cycles (90%) having length two. Based on this fact an improved algorithm is proposed for handling deadlock detection in distributed computing systems under the distributed request model where each process has several requests at a time. The improved algorithm depends mainly on message propagation and timeout policy. Probe and reply messages are propagated between the initiator and its successors only to detect deadlock cycles between them. Global timeout policy is used to detect potential deadlock cycles with large length distribution. The proposed algorithm can handle concurrent executions. Simulation experiments are performed to see the effectiveness of the improved algorithm. It is found that the improved algorithm compares favorably with other existing algorithms and it shows better results for several performance metrics especially in reducing deadlock latency and execution time.

show abstract