Deadlock Detection Technique Research Articles

Handling Physical-Layer Deadlock Caused by Permanent Faults in Quasi-Delay-Insensitive Networks-on-Chip

Networks-on-Chip (NoCs) are promising fabrics to provide scalable and efficient on-chip communication for large-scale many-core systems. In place of the well-studied synchronous NoCs, the event-driven asynchronous ones have emerged as promising replacement thanks to their strong timing robustness especially when implemented in quasi-delay-insensitive (QDI) circuits. However, their fault tolerance has rarely been studied. The QDI NoCs show complicated failure scenarios and behave differently from synchronous ones. As the scaling semiconductor technology is expected with the accelerated aging process, permanent faults become more likely to happen at runtime. These faults can break the handshake, leading to physical-layer deadlocks which can spread and paralyze the whole QDI NoC. This physical-layer deadlock cannot be resolved using conventional fault-tolerant or deadlock management techniques. This paper systematically studies the impact of permanent faults on QDI NoCs, and presents novel deadlock detection and recovery techniques to handle the fault-caused physical-layer deadlock. The proposed detection technique has been implemented to protect the NoC data paths that occupy ~90% of the logic. Employing the detection and recovery techniques to protect interrouter links (~60% of the logic), a permanently faulty link is precisely located and the network function can be recovered with graceful performance degradation.

Communication and Resource Deadlock Analysis Using IMDS Formalism and Model Checking

Modern static deadlock detection techniques deal with the global properties of the verified systems, using methods that explore the state space. Local features, like partial deadlocks or individual process terminations, are not easily expressed or checked by such methods. Also the distinction between communication deadlocks and resource deadlocks, common in dynamic waits-for methods, cannot be addressed or verified by static methods. An Integrated Model of Distributed Systems (IMDS) is proposed which specifies distributed systems as sets of servers’ states, sets of messages and sets of actions. The message passing/resource sharing dualism of distributed systems is provided by projections: on servers (server view) and on agents (agent view), yet the uniform specification of a verified system is preserved. A progress of computation is defined in terms of actions which change (local) states and generate messages. Distributed actions do not depend on global states and are independent from one another. Therefore, local features of subsystems can be easily described in IMDS. Communication and resource deadlocks can be handled separately and total and partial deadlocks and terminations can be distinguished from each other. Integration of IMDS with model checking is outlined and temporal formulas for deadlock and termination checking are discussed.

Detecting Deadlocks Involving Diverse Synchronization Mechanisms Using Extended Petri Nets

Synchronization mechanisms provide flexibility for concurrent programming. However, they also increase the difficulty of deadlock detection, since detection methods have to consider deadlocks caused by different mechanisms and their attributes. Traditional deadlock detection techniques are for deadlocks that involve a few types of synchronization mechanisms, typically mutex only. This paper introduces extensions of Petri nets, called Attribute Petri nets (APNs), which focus on modelling most kinds of synchronization mechanisms and their attributes. APNs are constructed in a modular way; therefore, new synchronization mechanisms can be easily hooked to APNs, each of which is developed as an independent APNs plugin. A tool called SniperX has been developed to analyse C/C++ threaded programs that use the Pthreads (POSIX threads, a POSIX standard for threads), containing plugins for mutual exclusions, semaphores, barriers, condition variables, etc. We have applied it to some open source multithreaded systems and a large commercial system, finding several previously unknown deadlocks that involve multiple synchronization mechanisms.

Deadlock Prevention Policy with Behavioral Optimality or Suboptimality Achieved by the Redundancy Identification of Constraints and the Rearrangement of Monitors

This work develops an iterative deadlock prevention method for a special class of Petri nets that can well model a variety of flexible manufacturing systems. A deadlock detection technique, called mixed integer programming (MIP), is used to find a strict minimal siphon (SMS) in a plant model without a complete enumeration of siphons. The policy consists of two phases. At the first phase, SMSs are obtained by MIP technique iteratively and monitors are added to the complementary sets of the SMSs. For the possible existence of new siphons generated after the first phase, we add monitors with their output arcs first pointed to source transitions at the second phase to avoid new siphons generating and then rearrange the output arcs step by step on condition that liveness is preserved. In addition, an algorithm is proposed to remove the redundant constraints of the MIP problem in this paper. The policy improves the behavioral permissiveness of the resulting net and greatly enhances the structural simplicity of the supervisor. Theoretical analysis and experimental results verify the effectiveness of the proposed method.

Distributed Deadlock Detection Technique with the Finite Automata

In the distributed, system deadlocks is a fundamental problem. A process may request resources in any order, which may not be known in advance and a process can request resource while holding others. Deadlocks can occur if the sequence of the allocations of resources to the processes is not controlled. Fast and efficient deadlock detection is very challenging and difficult task in distributed systems. In this paper distributed deadlock is detected by the distributed control manager. We proposed a distributed deadlock detection algorithm based on the finite automata to detect deadlock in a distributed environment. In this proposed solution we draw the wait for graph for the distributed transaction with the help of finite automata. Our proposed algorithm avoids the transmitting massage to other nodes; it is based on the expansion of an unvisited node in the wait for graph with the help of finite automata. This finite automaton based deadlock detection technique works fast and takes less number of comparisons to detect the deadlock in the wait for graph.

Magiclock: Scalable Detection of Potential Deadlocks in Large-Scale Multithreaded Programs

We present Magiclock, a novel potential deadlock detection technique by analyzing execution traces (containing no deadlock occurrence) of large-scale multithreaded programs. Magiclock iteratively eliminates removable lock dependencies before potential deadlock localization. It divides lock dependencies into thread specific partitions, consolidates equivalent lock dependencies, and searches over the set of lock dependency chains without the need to examine any duplicated permutations of the same lock dependency chains. We validate Magiclock through a suite of real-world, large-scale multithreaded programs. The experimental results show that Magiclock is significantly more scalable and efficient than existing dynamic detectors in analyzing and detecting potential deadlocks in execution traces of large-scale multithreaded programs.

Unstructured deadlock detection technique with scalability and complexity‐efficiency in clouds

SUMMARYTo detect deadlock in distributed systems, the initiator should construct an efficient explicit or implicit global wait‐for graph. In this paper, we present an unstructured deadlock detection algorithm using a gossip protocol in cloud computing environments, where constituting nodes may join and leave at any time. Because of the inherit properties of a gossip protocol, we argue that our proposed deadlock detection algorithm is scalable, fault‐tolerant, and efficient, retaining safety and liveness properties. The correctness proof of the algorithm is also provided. The message complexity of our proposed algorithm is O(n), where n is the number of nodes. Our performance evaluation with scalable settings shows that our approach has a significant advantage over previous deadlock detection algorithms in terms of solving scalability, fault‐tolerance, and complexity–efficiency issues. Copyright © 2013 John Wiley & Sons, Ltd.

Deadlock Detection and Avoidance in Static Step Topology under Distributed Environment

During the past years, the distributed computing approach has become very popular due to various advantages over centralized approach. In the distributed approach, the execution of a process has reduced and also it requires low cost for installation. Many of the researchers are using the modeling approach for solution of the software and hardware architecture research problems. The most popular approach of modeling is known as Unified Modeling Language based on the object-oriented technology. In the present work, a method of deadlock detection is explained for the newly proposed static step topology for the distributed network. In the step topology, the processes are taken as a task, sub task, macro, subroutine, etc which are executed in reflexive and symmetric manners when the systems are interconnected to each other under distributed environment and avoidance technique is also presented for the same. The deadlock detection technique is presented through a UML class model.

A Review of Distributed Deadlock Detection Techniques based on Diffusion Computation Approach

is a system state in which every process in some group requests resources from other processes in the group, and then waits indefinitely for these requests to be satisfied. Deadlocks have a very adverse effect on the efficient working of operating system therefore they should be either prevented, avoided or if exist should be detected and resolved. Because distributed systems are more vulnerable to deadlocks, the problems of deadlock detection and resolution have long been considered important problems in such systems. This paper provides a comprehensive review of the some of the existing techniques for deadlock detection in distributed environment.

An iterative method for synthesizing non-blocking supervisors for a class of generalized Petri nets using mathematical programming

This paper presents a novel and computational deadlock prevention policy for a class of generalized Petri nets, namely G-systems, which allows multiple resource acquisitions and flexible routings with machining, assembly and disassembly operations. In this research, a mixed integer programming (MIP)-based deadlock detection technique is used to find an insufficiently marked minimal siphon from a maximal deadly marked siphon for generalized Petri nets. In addition, two-stage control method is employed for deadlock prevention in Petri net model. Such proposed method is an iterative approach consisting of two stages. The first one is called siphons control, which adds a control place to the original net for each insufficiently marked minimal siphon. The objective is to prevent minimal siphons from being insufficiently marked. The second one, called control-induced siphons control, is to add a control place to the augmented net with its output arcs connecting to source transitions, which assures that there is no new insufficiently marked siphon generated due to the addition of the monitors. Compared with the existing approaches, the proposed deadlock prevention policy can usually lead to a non-blocking supervisor with more permissive behavior and high computational efficiency for a sizeable plant model due to avoiding complete siphon enumeration. Finally, a practical flexible manufacturing system (FMS) example is utilized to illustrate the proposed method.

Design of Liveness-Enforcing Supervisors for Flexible Manufacturing Systems Using Petri Nets

This correspondence develops a methodology to synthesize supervisors for a special class of Petri nets that can well model many flexible manufacturing systems. In our previous work, siphons in a Petri net are divided into elementary and dependent ones on the condition that all emptiable minimal siphons are computed. In this research, a mixed integer programming (MlP)-based deadlock detection technique is used to find some, in general not all, minimal siphons in a plant model without complete siphon enumeration. For each siphon found, depending on its noncontrollability, a monitor is added such that it is invariant-controlled. Our siphon control method guarantees that no emptiable control-induced siphon is generated due to the addition of the monitors. The siphon control process proceeds iteratively until there is no unmarked siphon in the supervisor of a plant model. Compared with the existing approaches, the novel deadlock prevention policy can usually lead to a structurally simple liveness-enforcing supervisor by adding only a small number of monitors and arcs. More importantly, complete siphon enumeration is avoided. A practical flexible manufacturing system (FMS) example is utilized to illustrate the proposed methods.

A deadlock detection mechanism for true fully adaptive routing in regular wormhole networks

Different from traditional deadlock avoidance schemes, deadlock detection and recovery-based routing algorithms in wormhole networks have gained attention due to low hardware complexity and high routing adaptability. By its nature, current deadlock detection techniques based on time-out accompany unignorable number of false deadlock detections especially in a heavily loaded network or with long packet size and may mark more than one packet in a deadlock as deadlocked. This would saturate the resources allocated for recovery, making deadlock recovery schemes less viable. This paper proposes a simple but more accurate deadlock detection scheme which is less dependent on the time-out value. The proposed scheme uses a control packet to find a potential cyclic dependency between packets and presumes a deadlock only upon finding such dependency. The suggested scheme considerably reduces the probability of false deadlock detections over previous schemes, thus enabling more efficient deadlock recovery and higher network throughput. Simulation results are provided to demonstrate the efficiency of the proposed scheme.

Timed Petri nets and prediction to improve the Chandy–Misra conservative-distributed simulation

The main contribution of this paper shows that distributed simulation of timed Petri nets (TPN) can take advantage of their structure to obtain a significant lookahead which is usually difficult to compute with other models. In this paper, we introduce a conservative-distributed simulation with a reduced number of control messages and without deadlock resolution. This approach is based on a part of optimism computed on the prediction time each logical process can determine for its advancement. Obviously this prediction time must be computed easily according to the structure of the simulated logical process. Timed Petri nets meet these requirements and we use their structure to evaluate the depth of the prediction. In conservative-distributed simulation, it is known that the deeper the prediction, the better the efficiency of the simulation. We present a method we have devised based on channel time prediction. We compare its performance to the Chandy–Misra method and to some related Petri nets approaches (Chiola). Experiments carried out on Sun stations show that there is more parallelism and a reduced number of null messages in the cases of deadlock avoidance. Moreover, considering deadlock detection and resolution technique we observe that in many cases no deadlock occurs with less control messages.

Deadlock prevention policy based on Petri nets and siphons

This paper presents a deadlock prevention method for a class of flexible manufacturing systems where deadlocks are caused by unmarked siphons in their Petri net models. This method is an iterative approach consisting of two main stages. At each iteration, a fast deadlock detection technique developed by mixed integer programming is used to find an unmarked maximal siphon. An algorithm is formalized that can efficiently obtain an unmarked minimal siphon from the maximal siphon. The first stage, called siphons control, of the proposed method is to add, for each unmarked minimal siphons, a control place to the original net with its output arcs to the sink transitions of the minimal siphon. The objective is to prevent a minimal siphon from being unmarked. The second stage, called augmented siphons control, is to add a control place to the modified net with its output arcs to the source transitions of the resultant net if the resource places are removed. The second stage is required since adding control places in the first stage may create new unmarked siphons. In addition, the second stage assures that there are no new unmarked siphons generated. The relation of the proposed method and the liveness and reversibility of the controlled net have been obtained. Finally, manufacturing examples are presented to illustrate the method and to allow comparison with earlier methods.

An Iterative Deadlock Prevention Policy Based on Petri net

This paper presents a deadlock prevention method for a class of flexible manufacturing systems (FMS) where deadlocks are caused by unmarked siphons in their Petri net models. This method is an iterative approach consisting of two main stages. At each iteration, a fast deadlock detection technique developed by mixed integer programming (MIP) is used to fmd an unmarked maximal siphon. The fIrst stage, called siphons control, of the proposed method is to add, for each unmarked minimal siphons, a control place to the original net to prevent a minimal siphon from being unmarked. The second stage, called augmented siphons control, is to add a control place to the modified net. The second stage is required since adding control places in the fIrst stage may create new unmarked siphons. In addition, the second stage assures that there are no new unmarked siphons generated. We have obtained the relation of the proposed method and the liveness and reversibility of the controlled net. Finally, manufacturing examples are presented for illustrating the method and allow us to compare with prior methods.

Deadlock prevention in concurrent real-time systems

To meet consistency requirements found in concurrent applications, a process must be guaranteed that it will be able to use all resources in a set ofpassive resources (such as shared data structures). To provide predictable execution time required in real-time systems, a process also needs guaranteed access to at least one of a set ofactive resources (such as processors) associated with each passive resource. As such, a concurrent real-time-process has AND-OR resource requirements. If locking is used to provide exclusive access to resources, deadlock is possible since processes can request additional resources while holding other resources. Deadlock detection and recovery techniques and deadlock avoidance techniques typically involve preempting resources or terminating processes, and are therefore inappropriate for real-time systems that require the execution time of processes to be predictable. This paper describes a general resource request condition that we proveprevents deadlock in AND-OR systems. It also describes how we use this AND-OR deadlock prevention technique in a concurrent real-time system.

Deadlock detection without wait-for graphs

Deadlock detection is an important service that the run-time system of a parallel environment should provide. In parallel programs deadlock can occur when the different processes are waiting for various events, as opposed to concurrent systems, where deadlock occurs when processes wait for resources held by other processes. Therefore classical deadlock detection techniques such as checking for cycles in the wait-for graph are unapplicable. An alternative algorithm that checks whether all the processes are blocked is presented. This algorithm deals with situations in which the state transition from blocked to unblocked is indirect, as may happen when busy-waiting is used.

Deadlock detection in distributed systems

The author describes a series of deadlock detection techniques based on centralized, hierarchical, and distributed control organizations. The point of view is that of practical implications. An up-to-date and comprehensive survey of deadlock detection algorithms is presented, their merits and drawbacks are discussed, and their performances (delays as well as message complexity) are compared. Related issues such as correctness of the algorithms, performance of the algorithms, and deadlock resolution, which require further research are examined. >