An Enhanced Distributed Deadlock Detection and Recovery in Process Networks

Abstract

Abstract-The Process Network (PN) model consists of multiple concurrent processes communicating over a unidirectional First-In-First-Out (FIFO) queue. Process networks are widely used for functional parallelism in digital signal processing and streaming data applications such as MPEG encoding and decoding. However, the bounded-memory scheduling policy of process networks can lead to process deadlock. The current deadlock detection and recovery algorithms in process networks can be enhanced by incorporating the role of a coordinator.In this paper we propose an enhanced distributed deadlock detection and recovery algorithm using blocked-lists and a coordinator to detect and recover from deadlocks. The distributed blocked-list algorithms detect the blocked processes and merge them with the existing blocked-lists. When a cycle is detected in the blocked-list, the coordinator is invoked to recover the system from the deadlock by either increasing the size of the channel for artificial deadlocks or by terminating the lowest priority processes from the blocked-lists. Our evaluation of the algorithm shows that the proposed blocked-list algorithm out performs other algorithms by requiring fewer messages to detect and recover from deadlock.Index Terms-Deadlock detection, deadlock recovery, distributed systems, kahn process networks (KPN).

An Optimal Goal Programming Model to Recovery from Deadlocks

“…The author in [26] proposes the use of heuristics for choosing the right process such as the last process that has been loaded, or the process with the least remaining processing time. Many other criteria are used to guide process selection for termination such as process code size [27], number of deadlock cycles that the process involved [15,28], number of submitted operations [29,30], number of holding resources [9,28], number of terminated processes [31][32], process age [32][33] and process priority [8][9]20,[34][35].…”