1 /*! \page publis Publications
3 \section pub_reference Reference publication about SimGrid
5 When citing SimGrid, the prefered reference paper is <i>Scheduling
6 Distributed Applications: the SimGrid Simulation Framework</i>, even if it's
7 a bit old now. We are actively working on improving this.
9 \li <b>Scheduling Distributed Applications: the
10 SimGrid Simulation Framework</b>\n
11 by <em>Henri Casanova and Arnaud Legrand and Loris Marchal</em>\n
12 Proceedings of the third IEEE International Symposium
13 on Cluster Computing and the Grid (CCGrid'03)\n
14 Since the advent of distributed computer systems an active field
15 of research has been the investigation of scheduling strategies
16 for parallel applications. The common approach is to employ
17 scheduling heuristics that approximate an optimal
18 schedule. Unfortunately, it is often impossible to obtain
19 analytical results to compare the efficacy of these heuristics.
20 One possibility is to conducts large numbers of back-to-back
21 experiments on real platforms. While this is possible on
22 tightly-coupled platforms, it is infeasible on modern distributed
23 platforms (i.e. Grids) as it is labor-intensive and does not
24 enable repeatable results. The solution is to resort to
25 simulations. Simulations not only enables repeatable results but
26 also make it possible to explore wide ranges of platform and
27 application scenarios.\n
28 In this paper we present the SimGrid framework which enables the
29 simulation of distributed applications in distributed computing
30 environments for the specific purpose of developing and evaluating
31 scheduling algorithms. This paper focuses on SimGrid v2, which
32 greatly improves on the first version of the software with more
33 realistic network models and topologies. SimGrid v2 also enables
34 the simulation of distributed scheduling agents, which has become
35 critical for current scheduling research in large-scale platforms.
36 After describing and validating these features, we present a case
37 study by which we demonstrate the usefulness of SimGrid for
38 conducting scheduling research.
40 \section pub_simulation Other publications about the SimGrid framework
42 \li <b>The SimGrid Project - Simulation and Deployment of Distributed Applications</b>\n
43 by <em>A. Legrand, M. Quinson, K. Fujiwara, H. Casanova</em>\n
44 <b>POSTER</b> in Proceedings of the IEEE International Symposium on High Performance Distributed Computing (HPDC-15), Paris, France, May 2006.\n
46 <a href="http://navet.ics.hawaii.edu/~casanova/homepage/papers/simgrid_hpdc06.pdf"><img src="poster_thumbnail.png" /></a>
48 http://navet.ics.hawaii.edu/~casanova/homepage/papers/simgrid_hpdc06.pdf
50 \li <b>A Network Model for Simulation of Grid Application</b>\n
51 by <em>Henri Casanova and Loris Marchal</em>\n
53 In this work we investigate network models that can be
54 potentially employed in the simulation of scheduling algorithms for
55 distributed computing applications. We seek to develop a model of TCP
56 communication which is both high-level and realistic. Previous research
57 works show that accurate and global modeling of wide-area networks, such
58 as the Internet, faces a number of challenging issues. However, some
59 global models of fairness and bandwidth-sharing exist, and can be link
60 withthe behavior of TCP. Using both previous results and simulation (with
61 NS), we attempt to understand the macroscopic behavior of
62 TCP communications. We then propose a global model of the network for the
63 Grid platform. We perform partial validation of this model in
64 simulation. The model leads to an algorithm for computing
65 bandwidth-sharing. This algorithm can then be implemented as part of Grid
66 application simulations. We provide such an implementation for the
67 SimGrid simulation toolkit.\n
68 ftp://ftp.ens-lyon.fr/pub/LIP/Rapports/RR/RR2002/RR2002-40.ps.gz
71 \li <b>MetaSimGrid : Towards realistic scheduling simulation of
72 distributed applications</b>\n
73 by <em>Arnaud Legrand and Julien Lerouge</em>\n
74 Most scheduling problems are already hard on homogeneous
75 platforms, they become quite intractable in an heterogeneous
76 framework such as a metacomputing grid. In the best cases, a
77 guaranteed heuristic can be found, but most of the time, it is
78 not possible. Real experiments or simulations are often
79 involved to test or to compare heuristics. However, on a
80 distributed heterogeneous platform, such experiments are
81 technically difficult to drive, because of the genuine
82 instability of the platform. It is almost impossible to
83 guarantee that a platform which is not dedicated to the
84 experiment, will remain exactly the same between two tests,
85 thereby forbidding any meaningful comparison. Simulations are
86 then used to replace real experiments, so as to ensure the
87 reproducibility of measured data. A key issue is the
88 possibility to run the simulations against a realistic
89 environment. The main idea of trace-based simulation is to
90 record the platform parameters today, and to simulate the
91 algorithms tomorrow, against the recorded data: even though it
92 is not the current load of the platform, it is realistic,
93 because it represents a fair summary of what happened
94 previously. A good example of a trace-based simulation tool is
95 SimGrid, a toolkit providing a set of core abstractions and
96 functionalities that can be used to easily build simulators for
97 specific application domains and/or computing environment
98 topologies. Nevertheless, SimGrid lacks a number of convenient
99 features to craft simulations of a distributed application
100 where scheduling decisions are not taken by a single
101 process. Furthermore, modeling a complex platform by hand is
102 fastidious for a few hosts and is almost impossible for a real
103 grid. This report is a survey on simulation for scheduling
104 evaluation purposes and present MetaSimGrid, a simulator built
106 ftp://ftp.ens-lyon.fr/pub/LIP/Rapports/RR/RR2002/RR2002-28.ps.gz
108 \li <b>SimGrid: A Toolkit for the Simulation of Application
110 by <em>Henri Casanova</em>\n
111 Advances in hardware and software technologies have made it
112 possible to deploy parallel applications over increasingly large
113 sets of distributed resources. Consequently, the study of
114 scheduling algorithms for such applications has been an active area
115 of research. Given the nature of most scheduling problems one must
116 resort to simulation to effectively evaluate and compare their
117 efficacy over a wide range of scenarios. It has thus become
118 necessary to simulate those algorithms for increasingly complex
119 distributed, dynamic, heterogeneous environments. In this paper we
120 present SimGrid, a simulation toolkit for the study of scheduling
121 algorithms for distributed application. This paper gives the main
122 concepts and models behind SimGrid, describes its API and
123 highlights current implementation issues. We also give some
124 experimental results and describe work that builds on SimGrid's
126 http://grail.sdsc.edu/papers/simgrid_ccgrid01.ps.gz
128 \section pub_ext Papers that use SimGrid-generated results (not counting our owns)
130 This list is a selection of articles. We list only papers written by people
131 external to the development group, but we also use our tool ourselves (see
135 - <b>Hierarchical Scheduling of Independent Tasks with Shared Files</b>\n
136 by <em>H. Senger, F. Silva, W. Nascimento</em>.\n
137 Proceedings of the Sixth IEEE International Symposium on Cluster Computing and the Grid Workshop (CCGRIDW'06), 2006.\n
138 http://www.unisantos.br/mestrado/informatica/hermes/File/senger-HierarchicalScheduling-Workshop-TB120.pdf
139 - <b>Critical Path and Area Based Scheduling of Parallel Task Graphs on Heterogeneous Platforms</b>\n
140 by <em>Tchimou N'Takpé and Frédéric Suter</em>\n
141 Proceedings of the Twelfth International Conference on Parallel and Distributed Systems (ICPADS), 2006.
142 - <b>Evaluation of Knapsack-based Scheduling using the NPACI JOBLOG</b>\n
143 by <em>D. Vanderster, N. Dimopoulos, R. Parra-Hernandez and R. Sobie</em>.\n
144 20th International Symposium on High-Performance Computing in an
145 Advanced Collaborative Environment (HPCS'06)\n
146 http://doi.ieeecomputersociety.org/10.1109/HPCS.2006.23
147 - <b>Metascheduling Multiple Resource Types using the MMKP</b>\n
148 by <em>D. Vanderster, N. Dimopoulos, R. Sobie</em>\n
149 To Appear: 7th IEEE/ACM International Conference on Grid Computing,
150 Barcelona, September 28th-29th 2006
152 - <b>On Dynamic Resource Management Mechanism using Control
153 Theoretic Approach for Wide-Area Grid Computing</b>\n
154 by <em>Hiroyuki Ohsaki, Soushi Watanabe, and Makoto Imase</em>\n
155 in Proceedings of IEEE Conference on Control Applications (CCA 2005), Aug. 2005.\n
156 http://www.ispl.jp/~oosaki/papers/Ohsaki05_CCA.pdf
157 - <b>Evaluation of Meta-scheduler Architectures and Task Assignment Policies for
158 high Throughput Computing</b>\n
159 by <em>Eddy Caron, Vincent Garonne and Andrei Tsaregorodtsev</em>\n
160 Proceedings of 4th Internationnal Symposium on Parallel and
161 Distributed Computing Job Scheduling Strategies for Parallel
162 Processing (ISPDC'05), July 2005.\n
163 http://www.ens-lyon.fr/LIP/Pub/Rapports/RR/RR2005/RR2005-27.pdf
165 - <b>Deadline Scheduling with Priority for Client-Server Systems on the Grid</b>\n
166 by <em>E Caron, PK Chouhan, F Desprez</em>\n
167 in IEEE International Conference On Grid Computing. Super Computing 2004, oct 2004.
168 - <b>Efficient Scheduling Heuristics for GridRPC Systems</b>\n
169 by <em>Y. Caniou and E. Jeannot.</em>\n
170 in IEEE QoS and Dynamic System workshop (QDS) of International Conference
171 on Parallel and Distributed Systems (ICPADS), New-Port Beach California, USA,
172 pages 621-630, July 2004\n
173 http://graal.ens-lyon.fr/~ycaniou/QDS04.ps
174 - <b>Exploiting Replication and Data Reuse to Efficiently Schedule
175 Data-intensive Applications on Grids</b>\n
176 by <em> E. Santos-Neto, W. Cirne, F. Brasileiro, A. Lima.</em>\n
177 Proceedings of 10th Job Scheduling Strategies for Parallel Processing, June 2004.\n
178 http://www.lsd.ufcg.edu.br/~elizeu/articles/jsspp.v6.pdf
179 - <b>Resource Management and Knapsack Formulations on the Grid</b>\n
180 by <em>R. Parra-Hernandez, D. Vanderster and N. J. Dimopoulos</em>\n
181 Fifth IEEE/ACM International Workshop on Grid Computing (GRID'04)\n
182 http://doi.ieeecomputersociety.org/10.1109/GRID.2004.54
183 - <b>Scheduling BoT Applications in Grids using a Slave Oriented Adaptive
185 by <em>T. Ferreto, C. A. F. De Rose and C. Northfleet.</em>\n
186 Second International Symposium on Parallel and Distributed Processing
187 and Applications (ISPA), 2004, Hong Kong. Published in Lecture Notes in
188 Computer Science (LNCS), Volume 3358, by Springer-Verlag. p. 392-398.
190 - <b>Link-Contention-Aware Genetic Scheduling Using Task Duplication in Grid Environments</b>\n
191 by <em>Wensheng Yao, Xiao Xie and Jinyuan You</em>\n
192 in Grid and Cooperative Computing: Second International Workshop, GCC 2003, Shanghai, China, December 7-10, 2003 (LNCS)\n
193 http://www.chinagrid.edu.cn/chinagrid/download/GCC2003/pdf/266.pdf
194 - <b>New Dynamic Heuristics in the Client-Agent-Server Model</b>\n
195 by <em>Y. Caniou and E. Jeannot</em>\n
196 in IEEE 13th Heteregeneous Computing Workshop - HCW'03, Nice, France, April 2003.\n
197 http://graal.ens-lyon.fr/~ycaniou/HCW03.ps
198 - <b>A Hierarchical Resource Reservation Algorithm for Network Enabled Servers</b>\n
199 by <em>E. Caron, F. Desprez, F. Petit, V. Villain</em>\n
200 in the 17th International Parallel and Distributed Processing Symposium -- IPDPS'03, Nice - France, April 2003.
202 \section pub_self Our own papers that use SimGrid-generated results
204 This list is a selection of the articles we have written that used results
205 generated by SimGrid.
208 - <b>On the Harmfulness of Redundant Batch Requests</b>\n
209 by <em>H. Casanova</em>\n
210 Proceedings of the IEEE International Symposium on High Performance Distributed Computing (HPDC-15), Paris, France, May 2006.\n
211 http://navet.ics.hawaii.edu/~casanova/homepage/papers/hpdc_2006.pdf
212 - <b>An evaluation of Job Scheduling Strategies for Divisible Loads on Grid Platforms</b>\n
213 by <em>Y. Cardinale, H. Casanova</em>\n
214 in Proceedings of the High Performance Computing & Simulation Conference (HPC&S'06), Bonn, Germany, May 2006.\n
215 http://navet.ics.hawaii.edu/~casanova/homepage/papers/cardinale_2006.pdf
216 - <b>Interference-Aware Scheduling</b>\n
217 by <em>B. Kreaseck, L. Carter, H. Casanova, J. Ferrante, S. Nandy</em>\n
218 International Journal of High Performance Computing Applications (IJHPCA), to appear.\n
219 http://navet.ics.hawaii.edu/~casanova/homepage/papers/kreaseck_ijhpca_2005.pdf
221 - <b>From Heterogeneous Task Scheduling to Heterogeneous Mixed Data and Task Parallel Scheduling</b>\n
222 by <em>F. Suter, V. Boudet, F. Desprez, H. Casanova<em>\n
223 Proceedings of Europar, 230--237, (LCNS volume 3149), Pisa, Italy, August 2004.
224 - <b>On the Interference of Communication on Computation</b>\n
225 by <em>B. Kreaseck, L. Carter, H. Casanova, J. Ferrante</em>\n
226 Proceedings of the workshop on Performance Modeling, Evaluation, and Optimization of Parallel and Distributed Systems, Santa Fe, April 2004.\n
227 http://navet.ics.hawaii.edu/~casanova/homepage/papers/k_pmeo2004.pdf
229 - <b>RUMR: Robust Scheduling for Divisible Workloads</b>\n
230 by <em>Y. Yang, H. Casanova</em>\n
231 Proceedings of the 12th IEEE Symposium on High Performance and Distributed Computing (HPDC-12), Seattle, June 2003.\n
232 http://navet.ics.hawaii.edu/~casanova/homepage/papers/yang_hpdc2003.pdf
233 - <b>Resource Allocation Strategies for Guided Parameter Space Searches</b>\n
234 by <em>M. Faerman, A. Birnbaum, F. Berman, H. Casanova</em>\n
235 International Journal of High Performance Computing Applications (IJHPCA), 17(4), 383--402, 2003.\n
236 http://grail.sdsc.edu/papers/faerman_ijhpca04.pdf
238 - <b>Resource Allocation for Steerable Parallel Parameter Searches</b>\n
239 by <em>M. Faerman, A. Birnbaum, H. Casanova, F. Berman</em>\n
240 Proceedings of the Grid Computing Workshop, Baltimore, 157--169, November 2002.\n
241 http://grail.sdsc.edu/projects/vi_itr/grid02.pdf
243 - <b>Applying Scheduling and Tuning to On-line Parallel Tomography </b>\n
244 by <em>Shava Smallen, Henri Casanova, Francine Berman</em>\n
245 in Proceedings of Supercomputing 2001\n
246 http://grail.sdsc.edu/papers/tomo_journal.ps.gz
248 - <b>Heuristics for Scheduling Parameter Sweep applications in Grid environments</b>\n
249 by <em>Henri Casanova, Arnaud Legrand, Dmitrii Zagorodnov and Francine Berman</em>\n
250 in Proceedings of the 9th Heterogeneous Computing workshop (HCW'2000), pp349-363.\n
251 http://navet.ics.hawaii.edu/~casanova/homepage/papers/hcw00_pst.pdf
256 \li <b>Optimal algorithms for scheduling divisible workloads on
257 heterogeneous systems</b>\n
258 by <em>Olivier Beaumont and Arnaud Legrand and Yves Robert</em>\n
259 in Proceedings of the 17th International Parallel and Distributed Processing Symposium (IPDPS'03).\n
260 Preliminary version on ftp://ftp.ens-lyon.fr/pub/LIP/Rapports/RR/RR2002/RR2002-36.ps.gz
263 \li <b>On-line Parallel Tomography</b>\n
264 by <em>Shava Smallen</em>\n
265 Masters Thesis, UCSD, May 2001