June 25, 2015 1 GrenchMark: Synthetic workloads for Grids First Demo at TU Delft A. Iosup, D.H.J. Epema PDS Group, ST/EWI, TU Delft.

Slides:



Advertisements
Similar presentations
A Workflow Engine with Multi-Level Parallelism Supports Qifeng Huang and Yan Huang School of Computer Science Cardiff University
Advertisements

7 april SP3.1: High-Performance Distributed Computing The KOALA grid scheduler and the Ibis Java-centric grid middleware Dick Epema Catalin Dumitrescu,
Introduction Background Knowledge Workload Modeling Related Work Conclusion & Future Work Modeling Many-Task Computing Workloads on a Petaflop Blue Gene.
June 1, Inter-Operating Grids through Delegated MatchMaking Alexandru Iosup, Dick Epema PDS Group, TU Delft, NL Todd Tannenbaum, Matt Farrellee,
June 1, GrenchMark : Towards a Generic Framework for Analyzing, Testing, and Comparing Grids ASCI Conference 2006 A. Iosup, D.H.J. Epema PDS Group,
June 2, GrenchMark : A Framework for Analyzing, Testing, and Comparing Grids CCGrid 2006 A. Iosup, D.H.J. Epema PDS Group, ST/EWI, TU Delft.
June 3, ServMark A Hierarchical Architecture for Testing Grids Santiago, Chile A. Iosup, H. Mohamed, D.H.J. Epema PDS Group, ST/EWI, TU Delft C.
June 3, 2015 Synthetic Grid Workloads with Ibis, K OALA, and GrenchMark CoreGRID Integration Workshop, Pisa A. Iosup, D.H.J. Epema Jason Maassen, Rob van.
Workload Management Workpackage Massimo Sgaravatto INFN Padova.
DAS-3/Grid’5000 meeting: 4th December The KOALA Grid Scheduler over DAS-3 and Grid’5000 Processor and data co-allocation in grids Dick Epema, Alexandru.
1 A Performance Study of Grid Workflow Engines Alexandru Iosup and Dick Epema PDS Group Delft University of Technology The Netherlands Corina Stratan Parallel.
1 Trace-Based Characteristics of Grid Workflows Alexandru Iosup and Dick Epema PDS Group Delft University of Technology The Netherlands Simon Ostermann,
June 25, GrenchMark: A synthetic workload generator for Grids KOALA Workshop A. Iosup, H. Mohamed, D.H.J. Epema PDS Group, ST/EWI, TU Delft.
June 28, Resource and Test Management in Grids Rapid Prototyping in e-Science VL-e Workshop, Amsterdam, NL Dick Epema, Catalin Dumitrescu, Hashim.
June 29, Grenchmark: A workload generator for Grid schedulers First Demo at TU Delft A. Iosup, D.H.J. Epema PDS Group, ST/EWI, TU Delft.
Workload Management Massimo Sgaravatto INFN Padova.
University of Dortmund June 30, On Grid Performance Evaluation using Synthetic Workloads JSSPP 2006 Alexandru Iosup, Dick Epema PDS Group, ST/EWI,
July 13, GrenchMark: A workload generator for Grids Demo at TU Delft A. Iosup, D.H.J. Epema PDS Group, ST/EWI, TU Delft.
Status of Globus activities within INFN (update) Massimo Sgaravatto INFN Padova for the INFN Globus group
July 13, “How are Real Grids Used?” The Analysis of Four Grid Traces and Its Implications IEEE Grid 2006 Alexandru Iosup, Catalin Dumitrescu, and.
Euro-Par 2008, Las Palmas, 27 August DGSim : Comparing Grid Resource Management Architectures Through Trace-Based Simulation Alexandru Iosup, Ozan.
DIRAC API DIRAC Project. Overview  DIRAC API  Why APIs are important?  Why advanced users prefer APIs?  How it is done?  What is local mode what.
SUN HPC Consortium, Heidelberg 2004 Grid(Lab) Resource Management System (GRMS) and GridLab Services Krzysztof Kurowski Poznan Supercomputing and Networking.
Euro-Par 2007, Rennes, 29th August 1 The Characteristics and Performance of Groups of Jobs in Grids Alexandru Iosup, Mathieu Jan *, Ozan Sonmez and Dick.
GRID job tracking and monitoring Dmitry Rogozin Laboratory of Particle Physics, JINR 07/08/ /09/2006.
(C) 2009 J. M. Garrido1 Object Oriented Simulation with Java.
1 EuroPar 2009 – POGGI: Puzzle-Based Online Games on Grid Infrastructures POGGI: Puzzle-Based Online Games on Grid Infrastructures Alexandru Iosup Parallel.
Workload Management WP Status and next steps Massimo Sgaravatto INFN Padova.
03/27/2003CHEP20031 Remote Operation of a Monte Carlo Production Farm Using Globus Dirk Hufnagel, Teela Pulliam, Thomas Allmendinger, Klaus Honscheid (Ohio.
Young Suk Moon Chair: Dr. Hans-Peter Bischof Reader: Dr. Gregor von Laszewski Observer: Dr. Minseok Kwon 1.
Through the development of advanced middleware, Grid computing has evolved to a mature technology in which scientists and researchers can leverage to gain.
JRA1/Job Submission and Monitoring Moreno Marzolla on behalf of JRA1/Job Submission Task INFN Sezione di Padova,
Grid Workload Management & Condor Massimo Sgaravatto INFN Padova.
3-2.1 Topics Grid Computing Meta-schedulers –Condor-G –Gridway Distributed Resource Management Application (DRMAA) © 2010 B. Wilkinson/Clayton Ferner.
CSF4 Meta-Scheduler Name: Zhaohui Ding, Xiaohui Wei
1 Challenge the future KOALA-C: A Task Allocator for Integrated Multicluster and Multicloud Environments Presenter: Lipu Fei Authors: Lipu Fei, Bogdan.
Grid Workload Management Massimo Sgaravatto INFN Padova.
Evaluation of Agent Teamwork High Performance Distributed Computing Middleware. Solomon Lane Agent Teamwork Research Assistant October 2006 – March 2007.
Condor Week 2005Optimizing Workflows on the Grid1 Optimizing workflow execution on the Grid Gaurang Mehta - Based on “Optimizing.
Resource Brokering in the PROGRESS Project Juliusz Pukacki Grid Resource Management Workshop, October 2003.
Ganga A quick tutorial Asterios Katsifodimos Trainer, University of Cyprus Nicosia, Feb 16, 2009.
Tool Integration with Data and Computation Grid GWE - “Grid Wizard Enterprise”
Migrating Desktop Marcin Płóciennik Marcin Płóciennik Kick-off Meeting, Santander, Graphical.
VO-Ganglia Grid Simulator Catalin Dumitrescu, Mike Wilde, Ian Foster Computer Science Department The University of Chicago.
LHCb Software Week November 2003 Gennady Kuznetsov Production Manager Tools (New Architecture)
Object-Oriented Design and Implementation of the OE-Scheduler in Real-time Environments Ilhyun Lee Cherry K. Owen Haesun K. Lee The University of Texas.
Chapter 3 System Performance and Models Introduction A system is the part of the real world under study. Composed of a set of entities interacting.
Going Large-Scale in P2P Experiments Using the JXTA Distributed Framework Mathieu Jan & Sébastien Monnet Projet PARIS Paris, 13 February 2004.
OPERATING SYSTEMS CS 3530 Summer 2014 Systems and Models Chapter 03.
Globus Grid Tutorial Part 2: Running Programs Across Multiple Resources.
Software Quality Assurance and Testing Fazal Rehman Shamil.
Tool Integration with Data and Computation Grid “Grid Wizard 2”
EGI-InSPIRE RI EGI-InSPIRE EGI-InSPIRE RI How to integrate portals with the EGI monitoring system Dusan Vudragovic.
Status of Globus activities Massimo Sgaravatto INFN Padova for the INFN Globus group
Millions of Jobs or a few good solutions …. David Abramson Monash University MeSsAGE Lab X.
Grid Workload Management (WP 1) Massimo Sgaravatto INFN Padova.
Grid Activities in CMS Asad Samar (Caltech) PPDG meeting, Argonne July 13-14, 2000.
1 CMS Virtual Data Overview Koen Holtman Caltech/CMS GriPhyN all-hands meeting, Marina del Rey April 9, 2001.
1 DIRAC Project Status A.Tsaregorodtsev, CPPM-IN2P3-CNRS, Marseille 10 March, DIRAC Developer meeting.
The EPIKH Project (Exchange Programme to advance e-Infrastructure Know-How) gLite Grid Introduction Salma Saber Electronic.
Workload Management Workpackage
OPERATING SYSTEMS CS 3502 Fall 2017
GWE Core Grid Wizard Enterprise (
Pipeline Execution Environment
Class project by Piyush Ranjan Satapathy & Van Lepham
On Dynamic Resource Availability in Grids
Resource and Test Management in Grids
An Adaptive Middleware for Supporting Time-Critical Event Response
Module 01 ETICS Overview ETICS Online Tutorials
Presentation transcript:

June 25, GrenchMark: Synthetic workloads for Grids First Demo at TU Delft A. Iosup, D.H.J. Epema PDS Group, ST/EWI, TU Delft

June 25, Evaluating Grid schedulers performance Grid schedulers performance Qualitative metrics supported application types, advanced fault tolerance, advanced... Quantitative metrics resource consumption, system performance, success rate Other metrics cost, single number system description Needs Applications, workloads, more workloads…

June 25, Synthetic workloads for Grid schedulers Good synthetic workloads for Grid schedulers Specific scheduler comparison requirements (metrics, jobs inter-arrival time,...) Many different types of representative Grid applications Traditional software engineering requirements (flexibility, extensibility, usability,...) Can also be used for... Functionality testing and system tuning Application performance testing Systems design and procurement …

June 25, Representative Grid applications Unitary applications Just one scheduling unit (otherwise recursive definition) Examples: Sequential, MPI, Java RMI, Ibis, … Composite applications Composed of several unitary or composite applications Examples: Parameter sweeps, chains of tasks, DAGs, workflows, …

June 25, Outline Introduction The GrenchMark framework Experience with GrenchMark Extending GrenchMark Conclusions [done] [here]

June 25, The GrenchMark framework What’s in a name? grid benchmark → help standardizing the testing procedures, but benchmarks are too early… GrenchMark A systematic approach to testing Grid schedulers A set of metrics for comparing schedulers A set of representative Grid applications Both real and synthetic Easy-to-use tools to create synthetic workloads Flexible, portable, extensible Can also be used for testing other Grid components

June 25, The GrenchMark framework

June 25, GrenchMark: Preliminary notions Job, workload, workload unit Job = Set of components (support for co-allocation) [Job = one program execution / the basic scheduling unit / … ] Workload = Set of Jobs Workload Unit = Set of jobs with the same property, generated from one description line (definition useful only for workload generator) Other JDF = Job description file Inter arrival time

June 25, GrenchMark: Some more notions Job site type / per site description Single – run at one site Fixed – run at several sites, all specified my license is on those machines Un-Fixed – run at several sites, all unspecified I can run anywhere, just give me the resources Semi-fixed – run at several sites, some specified I prefer those machines, but I can work anywhere Inter-arrival time distributions Constant, Uniform, Normal, Exponential(λ), Poisson(Mean), HExp2, HPoisson2, Weibull, LogNormal, Gamma (~)

June 25, WL description: an example Describe the workload to be generated in a few lines Very simple language + custom extensions (Native) (ExternalFile field) Support Co-allocation Start time, inter-arrival time Mixes of jobs

June 25, The GrenchMark process $./wl-gen.py wl-desc.in $./wl-submit.py out/wl-to-submit.wl Semi-automated Sample run: 4 lines of description 100 jobs / 411 components 100 files / 132 directories 300KB data Sample run: defined inter-arrival rate – submission delay +/- 0.01s 100 JDFs

June 25, GrenchMark status Already done in Python [ Generator + Globus, KOALA generators + RSL printer Submitter Results analyzer (crude) Applications Unitary, 3 types: sequential, MPI, Ibis (Java) +35 different applications Ongoing work Composite applications Automated results analyzer

June 25, Demo: Generating mixes of jobs 10 jobs 8 MPI, multi-component jobs (need co-allocation) 2 sequential

June 25, Outline Introduction The GrenchMark framework Experience with GrenchMark Extending GrenchMark Conclusions [done] [here] [done]

June 25, GrenchMark for testing KOALA… Testing 3 different runners: drunner, grunner, krunner Pre-release status: supposed stable Workloads with different jobs requirements, inter-arrival rates, co-allocated v. single site jobs… Evaluate Jobs success rate, KOALA’s overhead and bottlenecks Results +5,000 jobs successfully run 2 major bugs first day, +10 bugs overall (all fixed) KOALA is officially released (full credit to KOALA developers, 10x for testing with GrenchMark)

June 25, GrenchMark for testing KOALA: A full workload example KOALA test workload, run 10 times: Globus MPICH-G2 / MPI jobs Components: 4 and 8 Component Sizes: 4, 8 and 16 Inter-arrival time: Poisson(5s), spikes Co-allocation, 1 site Submit time 1 day Generate: Submit: Total: 3200 jobs, components / 3k files, 4k dirs Timing: 30s generate / 86,400s submit (1 day) $ wl-gen.py --duration= wl-desc.in $ wl-submit.py –onefile out/wl-desc.in

June 25, … and DAS-2’s functionality Already done Evaluate for KOALA + Globus + DAS-2 jobs success rate, turnaround time, middleware overhead, types and sources of errors Results 5 workloads 500 jobs A.Iosup, J.Maassen, R.V.van Nieuwpoort, D.H.J.Epema, Synthetic Grid Workloads with Ibis, KOALA, and GrenchMark, 2005 (submitted). Currently examine DAS-2 support for composite applications

June 25, Outline Introduction The GrenchMark framework Experience with GrenchMark Extending GrenchMark Conclusions [done] [here] [done]

June 25, Extending GrenchMark (1) Motto: Extending GrenchMark is easy! Need: Good knowledge about the application type Good understanding of workflows, or Good understanding of grid middleware Minimal Python knowledge (follow the official 2hrs tutorial:

June 25, Extending GrenchMark (2) 1.Write your own Job Generators a function with a predefined name in a Python module auto-loaded 2.Write your own Unit Generators a function with a predefined name in a Python module auto-loaded 3.Interface with C/C++, Ruby, Perl, Java, … define your own protocol 4.Write your own printers a function with a predefined name in a Python module auto-loaded

June 25, Outline Introduction The GrenchMark framework Experience with GrenchMark Extending GrenchMark Conclusions [done] [here] [done]

June 25, Conclusions and future work GrenchMark generates diverse workloads of Grid applications easy-to-use, flexible, portable, extensible, … Experience used GrenchMark to test KOALA’s functionality and performance. used GrenchMark to test some DAS Grid functionality. +5,000 jobs generated and run … and counting. (more) advertisment Have specific Grid applications types you would like to test? Test with GrenchMark!

June 25, Thank you! Questions? Remarks? Observations? All welcome! Grenchmark [10x Paulo] Alexandru IOSUP TU Delft [google: “iosup”]