Content-based publish/subscribe is an attractive paradigm for designing large-scale systems, as it decouples producers of information from consumers. This provides extensive flexibility for applications, which can use a modular architecture. Using this architecture, each participant expresses its interest in events by means of filters on the content of those events instead of using pre-established communication channels. However, matching events against filters has a non-negligible processing cost. Scaling the infrastructure with the number of users or events requires appropriate provisioning of resources for each of the operations involved: routing and filtering. In this paper, we propose and describe a generic, modular, and scalable infrastructure for supporting high-performance content-based publish/subscribe. We analyze its properties and show how it dynamically scales in a realistic setting. Our results provide valuable insights into the design and deployment of scalable content-based routing infrastructures.

Abstract We consider the problem of scheduling an application composed of independent tasks on a fully heterogeneous master–worker platform with communication costs. We introduce a bi‐criteria approach aiming at maximizing the throughput of the application while minimizing the energy consumed by participating resources. Assuming arbitrary super‐linear power consumption laws, we investigate different models, with energy overheads and memory constraints. Building upon closed‐form expressions for the uni‐processor case, we derive asymptotically optimal solutions for all models. Copyright © 2010 John Wiley & Sons, Ltd.

Scheduling problems are already difficult on traditional parallel machines, and they become extremely challenging on heterogeneous clusters. In this paper, we deal with the problem of scheduling multiple applications, made of collections of independent and identical tasks, on a heterogeneous master-worker platform. The applications are submitted online, which means that there is no a priori (static) knowledge of the workload distribution at the beginning of the execution. The objective is to minimize the maximum stretch, i.e., the maximum ratio between the actual time an application has spent in the system and the time this application would have spent if executed alone. On the theoretical side, we design an optimal algorithm for the offline version of the problem (when all release dates and application characteristics are known beforehand). We also introduce a heuristic for the general case of online applications. On the practical side, we have conducted extensive simulations and MPI experiments, showing that we are able to deal with very large problem instances in a few seconds. Also, the solution that we compute totally outperforms classical heuristics from the literature, thereby fully assessing the usefulness of our approach.

In this paper, we deal with the large-scale divisible load problem studied in. We show how to reduce this problem to a classical preemptive scheduling problem on a single machine, thereby establishing new complexity results, and providing new approximation algorithms and heuristics that subsume those presented in. We also give some hints on how to extend the results to a more realistic framework where communication costs are taken into account.

Scheduling problems are already difficult on traditional parallel machines. They become extremely challenging on heterogeneous clusters, even when embarrassingly parallel applications are considered. In this paper we deal with the problem of scheduling multiple applications, made of collections of independent and identical tasks, on a heterogeneous master-worker platform. The applications are submitted online, which means that there is no a priori (static) knowledge of the workload distribution at the beginning of the execution. The objective is to minimize the maximum stretch, i.e. the maximum ratio between the actual time an application has spent in the system and the time this application would have spent if executed alone. On the theoretical side, we design an optimal algorithm for the offline version of the problem (when all release dates and application characteristics are known beforehand). We also introduce several heuristics for the general case of online applications. On the practical side, we have conducted extensive simulations and MPI experiments, showing that we are able to deal with very large problem instances in a few seconds. Also, the solution that we compute totally outperforms classical heuristics from the literature, thereby fully assessing the usefulness of our approach.

This paper is focused on designing efficient parallel matrix-product algorithms for heterogeneous master-worker platforms. While matrix-product is well-understood for homogeneous 2D-arrays of processors (e.g., Cannon algorithm and ScaLAPACK outer product algorithm), there are three key hypotheses that render our work original and innovative:

This paper is aimed at designing efficient parallel matrix-product algorithms for homogeneous master-worker platforms. While matrix-product is well-understood for homogeneous 2D-arrays of processors (e.g., Cannon algorithm and ScaLAPACK outer product algorithm), there are two key hypotheses that render our work original and innovative: 1) centralized data: we assume that all matrix files originate from, and must be returned to, the master. The master distributes both data and computations to the workers (while in ScaLAPACK, input and output matrices are initially distributed among participating resources). Typically, our approach is useful in the context of speeding up MATLAB or SCILAB clients running on a server (which acts as the master and initial repository of files). 2) Limited memory: because we investigate the parallelization of large problems, we cannot assume that full matrix panels can be stored in the worker memories and re-used for subsequent updates (as in ScaLAPACK). The amount of memory available in each worker is expressed as a given number of buffers, where a buffer can store a square block of matrix elements. These square blocks are chosen so as to harness the power of level 3 BIAS routines; they are of size 80 or 100 on most platforms. We have devised efficient algorithms for resource selection (deciding which workers to enroll) and communication ordering (both for input and result messages), and we report a set of MPI experiments conducted on a platform at the University of Tennessee.

In this paper, we assess the impact of heterogeneity for scheduling independent tasks on master-slave platforms. We assume a realistic one-port model where the master can communicate with a single slave at any time-step. We target online scheduling problems, and we focus on simpler instances where all tasks have the same size. While such problems can be solved in polynomial time on homogeneous platforms, we show that there does not exist any optimal deterministic algorithm for heterogeneous platforms. Whether the source of heterogeneity comes from computation speeds, or from communication bandwidths, or from both, we establish lower bounds on the competitive ratio of any deterministic algorithm. We provide such bounds for the most important objective functions: the minimization of the makespan (or total execution time), the minimization of the maximum response time (difference between completion time and release time), and the minimization of the sum of all response times. Altogether, we obtain nine theorems which nicely assess the impact of heterogeneity on online scheduling. These theoretical contributions are complemented on the practical side by the implementation of several heuristics on a small but fully heterogeneous MPI platform. Our (preliminary) results show the superiority of those heuristics which fully take into account the relative capacity of the communication links.

In this paper, we deal with the problem of scheduling independent tasks on heterogeneous master-slave platforms. We target both off-line and on-line problems, with several objective functions (makespan, maximum response time, total completion time). On the theoretical side, our results are two-fold: (i) For offline scheduling, we prove several optimality results for problems with release dates; (ii) For on-line scheduling, we establish lower bounds on the competitive ratio of any deterministic algorithm. On the practical side, we have implemented several heuristics, some classical and some new ones derived in this paper, on a small but fully heterogeneous MPI platform. Our results show the superiority of those heuristics which fully take into account the relative capacity of the communication links.