MJSA: Markov job scheduler based on availability in desktop grid computing environment

Probabilistic Approach to Scheduling Divisible Load on Network of Processors

“…The results are compared with the deterministic systems discussed in all previous work [7,[10][11][12][13][14]. The total load in the system is found in N load sources.…”

“…Queuing theory is a very famous tool participated to find analytical solution on such system [7,8]. Divisible Load Theory (DLT), deterministic in nature, was also used and proved that it is very much the same as Markov Chain Modeling [9].…”

“…Divisible Load Theory (DLT), deterministic in nature, was also used and proved that it is very much the same as Markov Chain Modeling [9]. However, DLT has shown that it is an excellent tool to schedule independent jobs on a Grid originated from multiple resources [7,[10][11][12][13][14].…”

“…However, communication time is rarely considered [11]. In [7], communication time is studied but not in dividing the load, so the transfer input time of the load was not part of the model. Though all parameters of the system were considered in [10], the paper did not provide a closed form analytical solution for the finish time.…”

Scheduling Tightly-Coupled Applications on Heterogeneous Desktop Grids

“…In this work we consider volatile compute resources, such as those found in desktop grids, whose volatility has been studied in [18], [19], [20], [21]. Several authors have studied the "bag-of-tasks" scheduling problem on these platforms, either at an Internet-wide scale or within an Enterprise [22], [23], [24], [25], [26], [27], [28], [29]. Most of these works propose simple greedy scheduling algorithms that rely on mechanisms to select processors based on static criteria (e.g., processor clock-rates, benchmark results, time zone), on simple statistics of past availability [22], [24], [27], [23], and on predictive statistical models of availability [28], [29], [25], [26].…”