Volunteer Computing using BOINC

Cover from Linux magazine, BOINC

Berkeley Open Infrastructure
for Network Computing
http://bit.ly/boinc_srbiau
To get more references visit:
Pooyan
Mehrparvar

i. A brief introduction to volunteer computing & BOINC
ii. BOINC’s applications
iii. BOINC’s architecture
iv. How to join a popular BOINC project
v. How to set-up your own BOINC project

 Why do we choose this topic?
 What is volunteer computing?
 What is BOINC?

 An established technology that enables
ordinary citizens donate their computing
resources to one or more "projects".
 BOINC is the most widely-used
middleware system
 a client program runs on the volunteer's
computer
 BOINC was introduced by David P.
Anderson

 BOINC is designed to support applications that
have large computation requirements, storage
requirements, or both. The main requirement of
the application is that it be divisible into a large
number (thousands or millions) of jobs that can
be done independently.
Goal:
Use all the computers in the world, all
the time, to do worthwhile things

 Security: BOINC uses code signing to prevent
distribution of malicious executables. Each
project has a key pair for code signing and the
private key kept on network-isolated machine
 Virtualization as a solution for client’s security

 Project:
• An entity that does distributed computing using BOINC.
 Application:
• A project can include multiple applications
• an application includes several programs (for different platforms) and a set of
workunits and results
 Application versions:
• A particular application program version,compiled for a particular platform
 Workunit:
a computation to be performed.
• associated with an application, not with an application version
 Result:
• an instance of a computation, either unstarted, in progress, or completed.
• Each result is associated with a workunit.

 Cycle scavenging
 BOINC uses computers’s idle cycles of CPU/GPU and other resources to operate
(by default)
 To avoid high battery consumption/3G charge the BOINC android app runs on
A/C power & WiFi connection (by default)
Client can run BOINC as:
Screensaver (with fancy graphics)
Window service (running in the background)
Application (displaying results in tabular form)

 SETI@home development (1998)
 Ifrastructure issues, United devices (2000)
 Uited devices falling out, SETI@home failed, hacked(2001)
 BOINC was introduced (2002)
 Climateprediction.net, SETI@home, LHC@home were implemented on BOINC (2004)
 Rosseta@home, Einstein@home, IBM World community Grid, Primegride (2005)
 BOINCstats (BAM!), Gridrepublic, BOINC wrapper (2006)
 GPU support, Multi-core apps (2008)
 BOINC packages for debian (2010)
 Apps in virtual machines, vbox wrapper (Server-side) (2011)
 Android, Condor/OSG collaboration, Git (2012)
 Virtualbox client (2013)
 Samsung app (Power sleep), HTC app (Power to give) (2014)

 Server: Unix-based operating sytems (Debian based linux is recommended)
Microsoft Windows Vista or later (POSIX ready)
 Client:
 Linux (x86/x64)
 Microsoft windows (x86/x64)
 MacOS (x86/x64)
 Playstation3
 Android
Virtualization as a solution for cross-platform distributed
systems (Virtualbox, Vmware, VirtualPC,...)

 FLOPS as a measure for computer performance in scientific fields
 (Floating point operations per second)
 Some computer systems are unable to to run FLOPS benchamrk
 MIPS/MOPS: suitable for database query, word processing,
spreadsheets, or to run multiple virtual operating systems

 Fastest supercomputer: China's Tianhe-2 running 33.86 petaflops (June 10, 2013)
 BOINC: Active: 232,691 volunteers, 718,577 computers.
24-hour average: 8.308 petaFLOPS (December 19, 2014)

 General-purpose computing on graphics processing units (GPGPU)
 Playstation 4 (ATI) :
18 compute units, 64 cores per unit = 1,152 cores
Theorical peak performance = 1.84 TFLOPS
 Playstation 3’s CUDA (NVIDIA) is widley used in BOINC projects
e.g Folding@home

 Computational Science : rosseta@home
 Virtual campus supercomputing : univ. of
Westminster in London
 Desktop grids for business : Slicify project
 Integration with HTCondor to allow Globus-based
grids to run jobs for BOINC projects : Einstein@OSG

Computational science is concerned with constructing
mathematical models and quantitative analysis techniques and
using computers to analyze and solve scientific problems.

BOINC is used in:
 Physics, Astrophysics
 Mathematics
 Biology and medicince (Protein folding)
 Distributed sensing
 Climate modeling
 Games, 3D animation Rendering,...

BOINC popular projects:
 Physics, Astrophysics: LHC@home, Einstein@home, SETI@home
 Mathematics: SZTAKI Desktop Grid, Primegride
 Biology and medicince: Folding@home, Rosseta@home
 Distributed sensing: Quake Catcher Network
 Climate modeling: Climateprediction.net
 Games, 3D animation Rendering,... : Chess@home, Enigma@home
Find more projects on:
http://boinc.berkeley.edu/projects.php

 Amino Acids, Proteins, DNA
 Protein structure prediction / Modeling proteins structure
 Rosseta@home helps to find a cure for:
 Alzheimer’s disease
 HIV
 Malaria
 Anthrax
 Herpes simplex virus 1

 Crowdsourcing is the process of getting work or funding,
usually online, from a crowd of people.
 Human vs Computer

 From the creators of Rosseta@home (Washington Univ.)
 Similar to Rosetta@home, Foldit is aimed as a means of
discovering native protein structures faster, through a
combination of crowdsourcing and distributed computing.
 Game with a purpose
 In 2011 gamers helped to decipher the crystal structure of
M-PMV (virus causing AIDS in monkeys)

Challenges while using a BOINC system:
How can we depend on clients? Are they permanent?
Will they reach the deadlines?
Is the produced result valid?
How can we trust a BOINC server?
How can we trust a BOINC client?
How to send jobs to various platforms?

Some features of a BOINC system:
homogeneous redundancy (sending workunits only to computers of the
same platform—e.g.: Win XP SP2 only.)
workunit trickling (sending information to the server before the workunit
completes)
locality scheduling (sending workunits to computers that already have the
necessary files and creating work on demand)
work distribution based on host parameters (workunits requiring 512
MB of RAM, for example, will only be sent to hosts having at least that much
RAM, We send more jobs to multi-core CPUs/GPUs)
Double checking: (server sends the same workunit to at least two clients,
then it compares the result by validation techniques (bitwise, sample trivial,
fuzzy) or a customized validation technique
Job scheduling is needed in both server & client: priority between
different tasks, reaching deadlines
 To avoid cheating, credits are given when after the job is validated by the server

In multitasking computer systems, a daemon is a computer
program that runs as a background process, rather than being
under the direct control of an interactive user
 Generator
 Transitioner
 Feeder
 Scheduler
 Validator
 Assimilator
 File deleter

 Regiter at Boincstats (BAM)
 Choose your project(s)
 Join/create a team (optional)
 Download the BOINC client (BOINC manager)
 Log into software
 Immediately the project(s) will be attached
 Tasks will be downloaded
 Completed tasks will be uploaded to the server
 You will gain due to your performance
 New job will be downloaded
Step by step manual is available at:

BOINC client manager running four tasks (three projects)

Project configuration in a nutshell!:
 Configure a LAMP (Linux, Apache server, Mysql, Php/Phyton)
A virtualbox debian linux is available at BOINC’s website
 Develope your own project (mostly done in C++ (GCC), Fortran)
 Attach your project url in boincmanager (Client)
“your server ip/projectname” (exp: http://192.168.1.80/testproject)
 Monitor your project perfomance/administaration at
“your server ip/projectname_ops” (exp: http://192.168.1.80/testproject_ops)
Step by step video is available at:

BOINC server (left) + BOINC manager client (right) using virualization

 Conceived to be used by scientists, not IT professionals
 BOINC offers tools for
◦ Creating, starting, stopping and querying projects
◦ Adding new applications, new platforms, …
◦ Creating workunits
◦ Monitoring server performance
(All these procedures could be done by UNIX shell commands directly)

 A precise evaluation before choosing BOINC as a solution, comparing to
other alternatives (JPPF, other cloud or distributed systems)
 Fundamental undrestaning of BOINC architecture including it’s
daemons, repositories, shell-script commands, etc
 Good knowledge and experience of linux environment (shell)
 C/C++, Fortran programming skills (GCC, VC++, etc)
 Server/network configuration
 Security issues

 The architecture is centeriliezed in contrast of most Grid systems
 Insufficient Interest from Computer Science
 Insufficient Interest from scientists
 Insufficient Interest from funding agencies
 According to official reports volunteers are not increasing
 Complexity of server and job submission
 Insufficient documentations (obsolete docs)
 Rare experiment in web society (You can’t find your answers in BOINC
forums, Stack-overflow, etc), Risk of failure

Volunteer Computing using BOINC

More Related Content

Viewers also liked (6)

Similar to Volunteer Computing using BOINC (20)

Recently uploaded (20)

Volunteer Computing using BOINC