1 /*! \page publis Reference publications about SimGrid
4 When citing SimGrid, the prefered reference paper is <i>Scheduling
5 Distributed Applications: the SimGrid Simulation Framework</i>, even if it's
6 a bit old now. We are actively working on improving this.
8 \li <b>Scheduling Distributed Applications: the
9 SimGrid Simulation Framework</b>\n
10 by <em>Henri Casanova and Arnaud Legrand and Loris Marchal</em>\n
11 Proceedings of the third IEEE International Symposium
12 on Cluster Computing and the Grid (CCGrid'03)\n
13 Since the advent of distributed computer systems an active field
14 of research has been the investigation of scheduling strategies
15 for parallel applications. The common approach is to employ
16 scheduling heuristics that approximate an optimal
17 schedule. Unfortunately, it is often impossible to obtain
18 analytical results to compare the efficacy of these heuristics.
19 One possibility is to conducts large numbers of back-to-back
20 experiments on real platforms. While this is possible on
21 tightly-coupled platforms, it is infeasible on modern distributed
22 platforms (i.e. Grids) as it is labor-intensive and does not
23 enable repeatable results. The solution is to resort to
24 simulations. Simulations not only enables repeatable results but
25 also make it possible to explore wide ranges of platform and
26 application scenarios.\n
27 In this paper we present the SimGrid framework which enables the
28 simulation of distributed applications in distributed computing
29 environments for the specific purpose of developing and evaluating
30 scheduling algorithms. This paper focuses on SimGrid v2, which
31 greatly improves on the first version of the software with more
32 realistic network models and topologies. SimGrid v2 also enables
33 the simulation of distributed scheduling agents, which has become
34 critical for current scheduling research in large-scale platforms.
35 After describing and validating these features, we present a case
36 study by which we demonstrate the usefulness of SimGrid for
37 conducting scheduling research.\n
38 http://www-id.imag.fr/Laboratoire/Membres/Legrand_Arnaud/articles/simgrid2_CCgrid03.pdf
40 Previous publication do not cover the GRAS part of the framework. So, if you
41 want to cite GRAS, please use this publication instead:
43 \li <b>Gras: A Research & Development Framework for Grid and P2P
45 by <em>Martin Quinson</em>\n
46 <b>Best paper</b> of the 18th IASTED International Conference on
47 Parallel and Distributed Computing and Systems (PDCS 2006)\n
48 http://www.loria.fr/~quinson/articles/gras-iasted06.pdf
50 \section publis_others Other publications
52 A lot of other papers where published about SimGrid. The list is
53 splited in 3 pages (also accessible from the navbar on top of this page):
55 This section contains papers describing some sub-parts of SimGrid,
56 or references superseeded by the one given above.
57 - \ref publis_extern\n
58 SimGrid is used by an ever growing scientific community. This
59 section lists all the papers resulting of works in which the core
60 SimGrid team were not involved.
62 This section lists the paper co-signed by at least one of the core
63 team member, and using SimGrid as a tool (and not studying SimGrid
66 \section publis_count Amount of published papers using SimGrid results
70 <tr><td>Year</td><td>2000</td><td>2001</td><td>2002</td><td>2003</td><td>2004</td><td>2005</td><td>2006</td><td>2007</td>
72 <tr><td>Amount of papers external to the core team</td>
73 <td>-</td> <td>-</td> <td>-</td> <td>3</td> <td>6</td> <td>3</td> <td>8</td> <td>5</td>
75 <tr><td>Amount of papers co-signed by one team member</td>
76 <td>1</td> <td>1</td> <td>1</td> <td>2</td> <td>2</td> <td>-</td> <td>4</td> <td>4</td>
80 \page publis_core Other publications about the SimGrid framework
82 \li <b>Speed and Accuracy of Network Simulation in the SimGrid Framework</b>\n
83 by <em>K. Fujiwara, H. Casanova</em>\n
84 in Proceedings of the First International Workshop on Network Simulation Tools (NSTools), Nantes, France, October 2007.\n
85 http://navet.ics.hawaii.edu/~casanova/homepage/papers/fujiwara_nstool2007.pdf
87 \li <b>Cost and Accuracy of Packet-Level vs. Analytical Network Simulations: An Empirical Study</b>\n
88 by <em>K. Fujiwara</em>\n
89 <b>M.S. Thesis</b>, Dept. of Information and Computer Sciences, University of Hawai`i at Manoa, April 2007.\n
90 http://navet.ics.hawaii.edu/~casanova/homepage/theses/kayo_fujiwara_MS.pdf
92 \li <b>The SimGrid Project - Simulation and Deployment of Distributed Applications</b>\n
93 by <em>A. Legrand, M. Quinson, K. Fujiwara, H. Casanova</em>\n
94 <b>POSTER</b> in Proceedings of the IEEE International Symposium on High Performance Distributed Computing (HPDC-15), Paris, France, May 2006.\n
96 <a href="http://navet.ics.hawaii.edu/~casanova/homepage/papers/simgrid_hpdc06.pdf"><img src="poster_thumbnail.png" /></a>
98 http://navet.ics.hawaii.edu/~casanova/homepage/papers/simgrid_hpdc06.pdf
100 \li <b>A Network Model for Simulation of Grid Application</b>\n
101 by <em>Henri Casanova and Loris Marchal</em>\n
103 In this work we investigate network models that can be
104 potentially employed in the simulation of scheduling algorithms for
105 distributed computing applications. We seek to develop a model of TCP
106 communication which is both high-level and realistic. Previous research
107 works show that accurate and global modeling of wide-area networks, such
108 as the Internet, faces a number of challenging issues. However, some
109 global models of fairness and bandwidth-sharing exist, and can be link
110 withthe behavior of TCP. Using both previous results and simulation (with
111 NS), we attempt to understand the macroscopic behavior of
112 TCP communications. We then propose a global model of the network for the
113 Grid platform. We perform partial validation of this model in
114 simulation. The model leads to an algorithm for computing
115 bandwidth-sharing. This algorithm can then be implemented as part of Grid
116 application simulations. We provide such an implementation for the
117 SimGrid simulation toolkit.\n
118 ftp://ftp.ens-lyon.fr/pub/LIP/Rapports/RR/RR2002/RR2002-40.ps.gz
121 \li <b>MetaSimGrid : Towards realistic scheduling simulation of
122 distributed applications</b>\n
123 by <em>Arnaud Legrand and Julien Lerouge</em>\n
124 Most scheduling problems are already hard on homogeneous
125 platforms, they become quite intractable in an heterogeneous
126 framework such as a metacomputing grid. In the best cases, a
127 guaranteed heuristic can be found, but most of the time, it is
128 not possible. Real experiments or simulations are often
129 involved to test or to compare heuristics. However, on a
130 distributed heterogeneous platform, such experiments are
131 technically difficult to drive, because of the genuine
132 instability of the platform. It is almost impossible to
133 guarantee that a platform which is not dedicated to the
134 experiment, will remain exactly the same between two tests,
135 thereby forbidding any meaningful comparison. Simulations are
136 then used to replace real experiments, so as to ensure the
137 reproducibility of measured data. A key issue is the
138 possibility to run the simulations against a realistic
139 environment. The main idea of trace-based simulation is to
140 record the platform parameters today, and to simulate the
141 algorithms tomorrow, against the recorded data: even though it
142 is not the current load of the platform, it is realistic,
143 because it represents a fair summary of what happened
144 previously. A good example of a trace-based simulation tool is
145 SimGrid, a toolkit providing a set of core abstractions and
146 functionalities that can be used to easily build simulators for
147 specific application domains and/or computing environment
148 topologies. Nevertheless, SimGrid lacks a number of convenient
149 features to craft simulations of a distributed application
150 where scheduling decisions are not taken by a single
151 process. Furthermore, modeling a complex platform by hand is
152 fastidious for a few hosts and is almost impossible for a real
153 grid. This report is a survey on simulation for scheduling
154 evaluation purposes and present MetaSimGrid, a simulator built
156 ftp://ftp.ens-lyon.fr/pub/LIP/Rapports/RR/RR2002/RR2002-28.ps.gz
158 \li <b>SimGrid: A Toolkit for the Simulation of Application
160 by <em>Henri Casanova</em>\n
161 Advances in hardware and software technologies have made it
162 possible to deploy parallel applications over increasingly large
163 sets of distributed resources. Consequently, the study of
164 scheduling algorithms for such applications has been an active area
165 of research. Given the nature of most scheduling problems one must
166 resort to simulation to effectively evaluate and compare their
167 efficacy over a wide range of scenarios. It has thus become
168 necessary to simulate those algorithms for increasingly complex
169 distributed, dynamic, heterogeneous environments. In this paper we
170 present SimGrid, a simulation toolkit for the study of scheduling
171 algorithms for distributed application. This paper gives the main
172 concepts and models behind SimGrid, describes its API and
173 highlights current implementation issues. We also give some
174 experimental results and describe work that builds on SimGrid's
176 http://grail.sdsc.edu/papers/simgrid_ccgrid01.ps.gz
178 \page publis_extern Papers that use SimGrid-generated results (not counting our owns)
180 This list is a selection of articles. We list only papers written by people
181 external to the development group, but we also use our tool ourselves (see
185 - <b>Reactive Grid Scheduling of DAG Applications.</b>\n by
186 <em>I. Hernandez and M. Cole (UK)</em>. In Parallel and Distributed Computing and Networks, 2007.\n
187 http://www.actapress.com/PaperInfo.aspx?PaperID=29625
188 - <b>Dynamic Scheduling of Multi-Processor Tasks on Clusters of Clusters</b>\n
189 by <em>S. Hunold, T. Rauber and G. Rünger</em>.\n
190 Proceedings of the Sixth International Workshop on Algorithms,
191 Models and Tools for Parallel Computing on Heterogeneous Networks
192 (Heteropar'07), Austin, TX, September 2007.
193 - <b>Scheduling Δ-Critical Tasks in Mixed-Parallel Applications on a National Grid</b>\n
194 by <em>Frédéric Suter</em>.\n
195 In 8th IEEE/ACM International Conference on Grid Computing (Grid 2007), Austin, TX, September 2007.
196 - <b>Brokering strategies in computational grids using stochastic
197 prediction models.</b>\n by <em>Vandy Berten and Bruno
198 Gaujal</em>. In Parallel Computing, vol. 33(4-5): 238-249, 2007.\n
199 http://dev.ulb.ac.be/sched/articles/PARCO.pdf
200 - <b>Managing Scheduling and Replication in the LHC Grid.</b>\n by
201 <em>Thomas Ferrandiz and Vania Marangozova</em>. In CoreGrid
202 Workshop on middleware, 2007.\n
205 - <b>Simbatch: an API for simulating and predicting the performance of parallel resources and batch systems.</b>\n
206 by <em>Jean-Sébastien Gay and Yves Caniou</em>\n
207 INRIA Research Report 6040, November 2006.\n
208 https://hal.inria.fr/inria-00115880
209 - <b>Simbatch : une API pour la simulation et la prédiction de performances de systèmes batch</b>\n
210 by <em>Jean-Sébastien Gay and Yves Caniou</em>.\n
211 In 17ème Rencontres Francophones du Parallélisme, des Architectures et des Systèmes, RenPar'17.\n
212 October 4-6, Perpignan, France
213 - <b>Metascheduling Multiple Resource Types using the MMKP</b>\n
214 by <em>D. Vanderster, N. Dimopoulos, R. Sobie</em>\n
215 7th IEEE/ACM International Conference on Grid Computing\n
216 Barcelona, September 28th-29th 2006
217 - <b>Master-Slave Tasking on Asymmetric Networks</b>\n
218 by <em>Cyril Banino-Rokkones, Olivier Beaumont and Lasse Natvig</em>.\n
219 In Proceedings of 12th International Euro-Par Conference, Euro-Par 2006.\n
220 August 29 - September 1, Pages 167--176, Dresden, Germany.
221 - <b>Critical Path and Area Based Scheduling of Parallel Task Graphs on Heterogeneous Platforms</b>\n
222 by <em>Tchimou N'Takpé and Frédéric Suter</em>\n
223 Proceedings of the Twelfth International Conference on Parallel and Distributed Systems (ICPADS)\n
224 Minneapolis, MN, July 12-15, 2006.
225 - <b>Sensitivity Analysis of Knapsack-based Task Scheduling on the Grid</b>\n
226 by <em>D.C. Vanderster and N.J. Dimopoulos</em>.\n
227 In Proceedings of The 20th ACM International Conference on Supercomputing\n
228 Cairns, Australia, June 28-July 1, 2006.\n
229 http://portal.acm.org/citation.cfm?id=1183401.1183446&coll=GUIDE&dl=%23url.coll
230 - <b>Hierarchical Scheduling of Independent Tasks with Shared Files</b>\n
231 by <em>H. Senger, F. Silva, W. Nascimento</em>.\n
232 Proceedings of the Sixth IEEE International Symposium on Cluster
233 Computing and the Grid Workshop (CCGRIDW'06)\n
234 Singapore, 16-19 May 2006.\n
235 http://www.unisantos.br/mestrado/informatica/hermes/File/senger-HierarchicalScheduling-Workshop-TB120.pdf
236 - <b>Evaluation of Knapsack-based Scheduling using the NPACI JOBLOG</b>\n
237 by <em>D. Vanderster, N. Dimopoulos, R. Parra-Hernandez and R. Sobie</em>.\n
238 20th International Symposium on High-Performance Computing in an
239 Advanced Collaborative Environment (HPCS'06)\n
240 St. John's, Newfoundland, Canada, 14-17 May 2006\n
241 http://doi.ieeecomputersociety.org/10.1109/HPCS.2006.23
244 - <b>On Dynamic Resource Management Mechanism using Control
245 Theoretic Approach for Wide-Area Grid Computing</b>\n
246 by <em>Hiroyuki Ohsaki, Soushi Watanabe, and Makoto Imase</em>\n
247 in Proceedings of IEEE Conference on Control Applications (CCA 2005), Aug. 2005.\n
248 http://www.ispl.jp/~oosaki/papers/Ohsaki05_CCA.pdf
249 - <b>Evaluation of Meta-scheduler Architectures and Task Assignment Policies for
250 high Throughput Computing</b>\n
251 by <em>Eddy Caron, Vincent Garonne and Andrei Tsaregorodtsev</em>\n
252 Proceedings of 4th Internationnal Symposium on Parallel and
253 Distributed Computing Job Scheduling Strategies for Parallel
254 Processing (ISPDC'05), July 2005.\n
255 http://www.ens-lyon.fr/LIP/Pub/Rapports/RR/RR2005/RR2005-27.pdf
256 - <b>Algorithmes de redistribution de données pour anneaux de processeurs hétérogènes</b>\n
257 by <em>Héléne Renard, Yves Robert and Frédéric Vivien</em>\n
258 In 16ième Rencontres Francophones du Parallélisme des Architectures et des Systèmes, Le Croisic, France, 6-8 avril 2005.\n
259 http://www.polytech.unice.fr/~hrenard/recherche/Renpar16.ps
261 - <b>Deadline Scheduling with Priority for Client-Server Systems on the Grid</b>\n
262 by <em>Eddy Caron, PK Chouhan, Frédéric Desprez</em>\n
263 in IEEE International Conference On Grid Computing. Super Computing 2004, oct 2004.
264 - <b>Efficient Scheduling Heuristics for GridRPC Systems</b>\n
265 by <em>Yves Caniou and Emmanuel Jeannot.</em>\n
266 in IEEE QoS and Dynamic System workshop (QDS) of International Conference
267 on Parallel and Distributed Systems (ICPADS), New-Port Beach California, USA,
268 pages 621-630, July 2004\n
269 http://graal.ens-lyon.fr/~ycaniou/QDS04.ps
270 - <b>Exploiting Replication and Data Reuse to Efficiently Schedule
271 Data-intensive Applications on Grids</b>\n
272 by <em> E. Santos-Neto, W. Cirne, F. Brasileiro, A. Lima.</em>\n
273 Proceedings of 10th Job Scheduling Strategies for Parallel Processing, June 2004.\n
274 http://www.lsd.ufcg.edu.br/~elizeu/articles/jsspp.v6.pdf
275 - <b>Resource Management and Knapsack Formulations on the Grid</b>\n
276 by <em>R. Parra-Hernandez, D. Vanderster and N. J. Dimopoulos</em>\n
277 Fifth IEEE/ACM International Workshop on Grid Computing (GRID'04)\n
278 http://doi.ieeecomputersociety.org/10.1109/GRID.2004.54
279 - <b>Scheduling BoT Applications in Grids using a Slave Oriented Adaptive
281 by <em>T. Ferreto, C. A. F. De Rose and C. Northfleet.</em>\n
282 Second International Symposium on Parallel and Distributed Processing
283 and Applications (ISPA), 2004, Hong Kong. Published in Lecture Notes in
284 Computer Science (LNCS), Volume 3358, by Springer-Verlag. p. 392-398.
285 - <b>Data redistribution algorithms for heterogeneous processor rings</b>\n
286 by <em>Héléne Renard, Yves Robert and Frédéric Vivien</em>\n
287 In International Conference on High Performance Computing HiPC'2004\n
288 http://www.polytech.unice.fr/~hrenard/recherche/Hipc.pdf
290 - <b>Link-Contention-Aware Genetic Scheduling Using Task Duplication in Grid Environments</b>\n
291 by <em>Wensheng Yao, Xiao Xie and Jinyuan You</em>\n
292 in Grid and Cooperative Computing: Second International Workshop, GCC 2003, Shanghai, China, December 7-10, 2003 (LNCS)\n
293 http://www.chinagrid.edu.cn/chinagrid/download/GCC2003/pdf/266.pdf
294 - <b>New Dynamic Heuristics in the Client-Agent-Server Model</b>\n
295 by <em>Yves Caniou and Emmanuel Jeannot</em>\n
296 in IEEE 13th Heteregeneous Computing Workshop - HCW'03, Nice, France, April 2003.\n
297 http://graal.ens-lyon.fr/~ycaniou/HCW03.ps
298 - <b>A Hierarchical Resource Reservation Algorithm for Network Enabled Servers</b>\n
299 by <em>Eddy Caron, Frédéric Desprez, Franck Petit, V. Villain</em>\n
300 in the 17th International Parallel and Distributed Processing Symposium -- IPDPS'03, Nice - France, April 2003.
302 \page publis_intra Our own papers that use SimGrid-generated results
304 This list is a selection of the articles we have written that used results
305 generated by SimGrid.
308 - <b>Assessing the Quality of Automatically Built Network Representations</b>\n
309 by <em>Lionel Eyraud-Dubois and Martin Quinson</em>\n
310 In Seventh IEEE International Symposium on Cluster Computing and
311 the Grid (CCGrid 2007), 14-17 May 2007, Rio de Janeiro, Brazil.
312 - <b>A Comparison of Scheduling Approaches for Mixed-Parallel Applications on Heterogeneous Platforms</b>\n
313 by <em>Tchimou N'takpé, Frédéric Suter, and Henri Casanova</em>\n
314 In 6th International Symposium on Parallel and Distributed Computing, Hagenberg, Austria, July 2007.
315 - <b>A First Step Towards Automatically Building Network Representations</b>\n
316 by <em>Lionel Eyraud-Dubois, Arnaud Legrand, Martin Quinson and Frédéric Vivien</em>\n
317 In 12th International Euro-Par Conference 28-31 August, Rennes, France.
318 - <b>Centralized Versus Distributed Schedulers Multiple Bag-of-Tasks Applications</b>\n
319 by <em>Olivier Beaumont, Larry Carter, Jeanne Ferrante, Arnaud Legrand, Loris Marchal, and Yves Robert</em>\n
320 In IEEE Trans. Parallel Distributed Systems, 2007.
322 - <b>On the Harmfulness of Redundant Batch Requests</b>\n
323 by <em>H. Casanova</em>\n
324 Proceedings of the IEEE International Symposium on High Performance Distributed Computing (HPDC-15), Paris, France, May 2006.\n
325 http://navet.ics.hawaii.edu/~casanova/homepage/papers/hpdc_2006.pdf
326 - <b>An evaluation of Job Scheduling Strategies for Divisible Loads on Grid Platforms</b>\n
327 by <em>Y. Cardinale, H. Casanova</em>\n
328 in Proceedings of the High Performance Computing & Simulation Conference (HPC&S'06), Bonn, Germany, May 2006.\n
329 http://navet.ics.hawaii.edu/~casanova/homepage/papers/cardinale_2006.pdf
330 - <b>Centralized Versus Distributed Schedulers Multiple Bag-of-Tasks Applications</b>\n
331 by <em>Olivier Beaumont, Larry Carter, Jeanne Ferrante, Arnaud Legrand, Loris Marchal, and Yves Robert</em>\n
332 International Parallel and Distributed Processing Symposium IPDPS'2006, 2006
333 - <b>Interference-Aware Scheduling</b>\n
334 by <em>B. Kreaseck, L. Carter, H. Casanova, J. Ferrante, S. Nandy</em>\n
335 International Journal of High Performance Computing Applications (IJHPCA).\n
336 http://navet.ics.hawaii.edu/~casanova/homepage/papers/kreaseck_ijhpca_2005.pdf
338 - <b>From Heterogeneous Task Scheduling to Heterogeneous Mixed Data and Task Parallel Scheduling</b>\n
339 by <em>F. Suter, V. Boudet, F. Desprez, H. Casanova</em>\n
340 Proceedings of Europar, 230--237, (LCNS volume 3149), Pisa, Italy, August 2004.
341 - <b>On the Interference of Communication on Computation</b>\n
342 by <em>B. Kreaseck, L. Carter, H. Casanova, J. Ferrante</em>\n
343 Proceedings of the workshop on Performance Modeling, Evaluation, and Optimization of Parallel and Distributed Systems, Santa Fe, April 2004.\n
344 http://navet.ics.hawaii.edu/~casanova/homepage/papers/k_pmeo2004.pdf
347 - <b>RUMR: Robust Scheduling for Divisible Workloads</b>\n
348 by <em>Y. Yang, H. Casanova</em>\n
349 Proceedings of the 12th IEEE Symposium on High Performance and Distributed Computing (HPDC-12), Seattle, June 2003.\n
350 http://navet.ics.hawaii.edu/~casanova/homepage/papers/yang_hpdc2003.pdf
351 - <b>Resource Allocation Strategies for Guided Parameter Space Searches</b>\n
352 by <em>M. Faerman, A. Birnbaum, F. Berman, H. Casanova</em>\n
353 International Journal of High Performance Computing Applications (IJHPCA), 17(4), 383--402, 2003.\n
354 http://grail.sdsc.edu/papers/faerman_ijhpca04.pdf
356 - <b>Resource Allocation for Steerable Parallel Parameter Searches</b>\n
357 by <em>M. Faerman, A. Birnbaum, H. Casanova, F. Berman</em>\n
358 Proceedings of the Grid Computing Workshop, Baltimore, 157--169, November 2002.\n
359 http://grail.sdsc.edu/projects/vi_itr/grid02.pdf
361 - <b>Applying Scheduling and Tuning to On-line Parallel Tomography </b>\n
362 by <em>Shava Smallen, Henri Casanova, Francine Berman</em>\n
363 in Proceedings of Supercomputing 2001\n
364 http://grail.sdsc.edu/papers/tomo_journal.ps.gz
366 - <b>Heuristics for Scheduling Parameter Sweep applications in Grid environments</b>\n
367 by <em>Henri Casanova, Arnaud Legrand, Dmitrii Zagorodnov and Francine Berman</em>\n
368 in Proceedings of the 9th Heterogeneous Computing workshop (HCW'2000), pp349-363.\n
369 http://navet.ics.hawaii.edu/~casanova/homepage/papers/hcw00_pst.pdf
374 \li <b>Optimal algorithms for scheduling divisible workloads on
375 heterogeneous systems</b>\n
376 by <em>Olivier Beaumont and Arnaud Legrand and Yves Robert</em>\n
377 in Proceedings of the 17th International Parallel and Distributed Processing Symposium (IPDPS'03).\n
378 Preliminary version on ftp://ftp.ens-lyon.fr/pub/LIP/Rapports/RR/RR2002/RR2002-36.ps.gz
381 \li <b>On-line Parallel Tomography</b>\n
382 by <em>Shava Smallen</em>\n
383 Masters Thesis, UCSD, May 2001