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