Che cos’è BOINC? Se proviamo a cercare sulla famosa enciclopedia libera Wikipedia la frase “calcolo distribuito”, troveremo: Il calcolo distribuito (distributed computing) utilizza le risorse di diversi computer collegati in rete tra di loro (solitamente attraverso internet) per risolvere problemi computazionali a larga scala.

Tutti sappiamo che i mezzi informatici negli ultimi anni sono evoluti moltissimo in fatto di capacità di calcolo. Ciò che 10 anni fa impiegava un giorno, oggi impiega 1 minuto di computazione. La scienza, di pari passo ha seguito l’evoluzione, con progetti scientifici sempre più grandi e ambiziosi, che però richiedono grandi capacità di elaborazione. Purtroppo le università ed i relativi centri di ricerca hanno spesso mezzi molto limitati.

Qui entra in gioco il calcolo distribuito. Un grande problema viene così ripartito in problemi più piccoli e spedito a tutti gli utenti internet che decidono liberamente di partecipare a questa attività, accelerando enormemente la soluzione del problema iniziale.

Vediamo nel dettaglio con dei disegni come funziona il sistema:
Immaginiamo che una Università abbia la necessità di sviluppare un progetto di grandi dimensioni (ad esempio la casa della figura sotto). Ora, questo lavoro sarebbe troppo oneroso e richiederebbe molti anni per essere portato a termine se il lavoro venisse svolto da una sola persona.

I ricercatori quindi, collegati alla rete internet, chiedono aiuto alla comunità mondiale di PC affinché collaborino alla risoluzione del problema in moltissimo meno tempo. Migliaia di computer possono trovare una soluzione in molto meno tempo rispetto ad un singolo I direttori del progetto universitario si metteranno al lavoro per smembrare il grande progetto, in tantissimi, piccolissimi sottoprogetti (Wok Unit) che possono essere agevolmente gestiti dai PC dei singoli utenti. Ogni computer elaborerà grave la sua Work Unit ed invierà i risultati ai ricercatori, che dopo l’acquisizione, invieranno dei nuovi lavori ai PC, fino alla risoluzione del problema.

Un gruppo di ricercatori dell’università di Berkeley, interessati a sviluppare un software di calcolo distribuito da donare alla ricerca, ha creato il programma “http://boinc.berkeley.edu/ BOINC! (Berkeley Open Infrastructure for Network Computing). In pratica, ognuno di noi, installando il programma può donare la propria capacità di calcolo per la ricerca.

Come funziona allora? Ci si aggancia ad un progetto che si ritiene interessante, si scaricano automaticamente dei pacchetti, chiamate Work Unit ed il proprio computer, inizia ad elaborare silenziosamente senza neanche accorgersi.E’importante sapere che il programma lavora come screensaver oppure sfruttando i tempi morti di utilizzo della CPU, usando solo la parte di potenza che normalmente andrebbe sprecata! Se ad esempio state usando Excel o Word, il vostro computer sarà occupato per il 90% del tempo a non far niente: qui entra in gioco BOINC!.

In pratica lui non fa altro che riciclare questa potenza che andrebbe comunque perduta,e la dedica alla risoluzione delle Work Unit. Al termine di ogni elaborazione viene calcolato un punteggio ed assegnato al computer che l’ha elaborato. Si crea così una sorta di sfida tra utenti e team, a chi scala le classifiche mondiali! Un modo come un’altro per invogliare la gente a partecipare e sognare un posto al sole tra le centinaia di migliaia di utenti. Quali sono le finalità? I progetti portati avanti su piattaforma BOINC hanno le più svariate finalià. Troviamo problemi di carattere medico, astronomici, climatici, e matematico. La cosa basilare da sapere è che sono portati avanti da gente che si fida di noi e noi di loro. Ogni progetto ha grande trasparenza, e spesso è aggiornato quotidianamente o settimanalmente con commenti e stato dei lavoro, per tenere informati gli utenti dei progressi. Noi del Team Boinc@Marche siamo convinti che l’unione fa la forza e che la nostra comunità può far molto per aiutare la medicina, l’astronomia e qualsiasi altro settore della scienza porti benessere al mondo intero. La nostra intenzione è creare un team vincente e solidale tra tutti gli utenti marchigiani, scalare le classifiche italiane (e perchè no, mondiali) ed essere tra i primi in classifica!

Nuova versione per Boinc che arriva alla release 6.10.17. Con questo software potete donare una parte della potenza di calcolo del vostro PC ad uno dei tanti progetti no-profit. Grazie a questo software si riescono a raggiungere potenze di calcolo pari ai supercomputer (Licenza: LGPL , OS: Jaunty Jackalope 32/64bits, Formato: Repository).

Fonte/Download: GetDeb – HomePage: Boinc

Sending scheduler request: Project initialization.  Requesting 1 seconds of work, reporting 0 completed tasks
Project communication failed: attempting access to reference site
Scheduler request failed: Peer certificate cannot be authenticated with known CA certificates
Internet access OK – project servers may be temporarily down.

This error messages appeared when my world community grid project was trying to connect to the server after I installed Ubuntu 9.10.
According to this forum, they suggest replacing a new file called “ca-bundle.crt” in

/var/lib/boinc-client/

with this new one.

Just that. It works for me .

Sending scheduler request: Project initialization.  Requesting 1 seconds of work, reporting 0 completed tasks
Project communication failed: attempting access to reference site
Scheduler request failed: Peer certificate cannot be authenticated with known CA certificates
Internet access OK – project servers may be temporarily down.

This error messages appeared when my world community grid project was trying to connect to the server after I installed Ubuntu 9.10.
According to this forum, they suggest replacing a new file called “ca-bundle.crt” in

/var/lib/boinc-client/

with this new one.

Just that. It works for me .

Since installing Karmic on my laptop, it has consistently failed to connect to the World Community Grid server.

Symptoms: When going the the ‘Messages’ tab of the ‘Advanced View’, one is greeted by lines of the form:

2009-11-05T12:56:47 CET|World Community Grid|Sending scheduler request: Project initialization. Requesting 1 seconds of work, reporting 0 completed tasks
2009-11-05T12:56:50 CET||Project communication failed: attempting access to reference site
2009-11-05T12:56:52 CET|World Community Grid|Scheduler request failed: Peer certificate cannot be authenticated with known CA certificates
2009-11-05T12:56:53 CET||Internet access OK - project servers may be temporarily down.

Solution: After some googling I came across this page, which basically gives a simple workaround:

sudo su
cd /var/lib/boinc-client
mv ca-bundle.crt ca-bundle.crt.backup
wget http://boinc.berkeley.edu/trac/export/16195/trunk/boinc/curl/ca-bundle.crt

I’m not convinced that it will survive an update though.

Colaboração conjunta na internet atinge novos níveis estruturais

Por Natally Gama

Um projeto desenvolvido pelo pesquisador científico David P. Anderson, juntamente com seus colegas da Universidade da Berkeley, tem permitido há alguns anos usuários da internet de todo o mundo de contribuírem com pesquisas científicas sem mover um dedo sequer.

O responsável por promover este ineditismo é o programa BOINC (Berkeley Open Infrastucture For Network Computing) que consiste em aproveitar a capacidade de processamento de computadores conectados à internet, quando estes não estão sendo utilizados, para a análise de projetos científicos sem fins lucrativos. A plataforma é de uso gratuito e pode ser instalada em qualquer sistema operacional.

Em relação aos projetos que utilizam o BOINC, seus segmentos são dos mais variados. Atualmente existem  o Climateprediction.net, que visa produzir modelos climáticos para o nosso século, até iniciativas de cunho mais sensível e humano como o World Community Grid, que estuda avanços na área de combate ao câncer e a AIDS.  Mas, até o momento a criação de maior particpação por parte dos internautas  é o SETI@HOME.

O SETI – que em inglês significa Busca por Inteligência Extra-Terrestre – foi também fundado por David Anderson e tem desde 1999 analisado frequências de rádio captadas por radiotelescópios, na tentativa de encontrar algum sinal de comunicação viável de algum ser vivo do espaço. Para que isso se torne possível, cidadãos comuns se voluntariam para participar do programa e recebem um pequeno pacote de dados da instituição pelo computador, que também os analisa por meio do processador.

Independente da origem, deve-se considerar positiva qualquer influência de cooperativismo virtual que incentive a integração dos mais diferentes tipos de pessoas em prol de uma causa comum e benéfica às demais.

]]> http://needq.wordpress.com/2009/10/24/taskresult/ Fri, 23 Oct 2009 16:44:29 +0000 needq http://needq.wordpress.com/2009/10/24/taskresult/ http://needq.wordpress.com/2009/10/24/double_mb/ Fri, 23 Oct 2009 15:38:18 +0000 needq http://needq.wordpress.com/2009/10/24/double_mb/ http://l33tgeek.wordpress.com/2009/10/10/save-the-world-with-your-extra-cycles/ Sat, 10 Oct 2009 06:42:37 +0000 l33tgeek http://l33tgeek.wordpress.com/2009/10/10/save-the-world-with-your-extra-cycles/

BOINC is a client for volunteer computing projects. What is “volunteer computing”, you ask? Volunteer computing is a term for using the ‘donated’ CPU power of participants to contribute to different projects, such as searching for extraterrestrial intelligence, or finding a cure for cancer. Users of BOINC can create groups and compete for the most points (points being awarded for donating gigaflops of processing power and completing assignments based on the projects that have been subscribed to). All in all, BOINC is a great program to look into if you’re the kind of person who never shuts down their computer or are just looking to help solve some unsolved problems. TechCircuit approved!

Today at roughly 10:00 PM EDT, Team Lakerbago formed its own BOINC group (currently of one) to aid the planet in its quest to stop getting all hot and sweaty.

Science + Lakers = Tru Luv 4ever

Team Lakerbago aims to become the largest distributed super computer network the species has ever known. The BOINC project currently being bit-hammered by Team Lakerbago is Climateprediction.net. The world will be saved and Lakers fans will be the ones who saved it. It won’t be Celtics fans, since I’m pretty sure BOINC doesn’t come in a Speak & Spell format. Oh, snap. I just went there.

This, on top of the myriad championships soon to be won during the Kobe/Artest/Gasol era will create awkward and amusing moments at the expense of everyone else on the planet who is not a Lakers fan. And really, if Lakers fans don’t take it upon themselves to undo all of the harm done to the biosphere by those mouthbreathing Rockets, Spurs, and Mavs fans, who will?

What is BOINC? This guy does a good job of explaining.

Download the BOINC client. Then join Team Lakerbago. It’s free. It’s easy. Your grandma will be proud of you. Let do this.

In an age of ever increasing information collection and the need to evaluate it, building systems which utilize the yet untapped and available compute resources in everyone’s home and hands  should be driving the development of more sophisticated distributed computing systems. Today, large data processing facilities provide significant compute capabilities. Utilizing the worldwide plethora of distributed resources in a coherent way is much more powerful.

Distributed programming and processing tools and techniques are currently a reality but are in their infancy. Potential rapid growth of distributed systems is already supported by:

• Storage, bandwidth and CPUs staying on course to becoming nearly free. (Free. The Future of a Radical Price)
• The number of people and devices connected to the internet continually grows.
• Data storage requirements increase as data accumulation from all sources grows as does the number of sources.

It is becoming more  common to see Terrabyte storage devices in homes. Desktop and laptop appliances have become somewhat of a commodity affordable to your average consumer. You can stake out claim to a table for a period of time at your local coffee shop and access the internet for free. Becoming a social citizen on the internet with portable compute resource was once cost prohibitive and is now plummeting to a price affordable to a significant portion of the population.

Distribution of affordable, cheap and free compute devices to the general public continues to grow. Most of the resources sit idle much of the time. Game consoles, cell phones, laptops, desktops, etc. can now all participate in the storage and processing of data.

Like it or not, the ability to capture and share data is becoming increasingly easy. You can watch your favorite gorilla in the jungle or using collective intelligence to extract social and individual’s patterns with service apis provided by large corporations like Google and Amazon. Today’s transient data coming from sources in real time will eventually be stored. Much of the data is and will be captured and stored in perpetuity at corporate web sites and in data centers. Some of what should be available may be accessible through the gates of these data centers.

The approach to managing and controlling processing remains focused on huge data centers. In this sense, social and engineering thought is still akin to 19th century practice of building monolithic systems with centralized control. As data generation increases and the cost of storage decreases, huge data centers are being built to house and process data. Google, Apple, Codera and NTT America to name just a few. What will they do with all this data and how much will be shared?

IBM announced its plans to build a petaflop machine for the SKA telescope program. It is a laudable and beneficial effort. Undoubtedly, research and lessons learned from the effort will be valuable. But efforts should be made to build distributed systems of equal or greater benefit. Efforts such as BOINC provide a rudimentary effective start. File sharing peers using DHT have already demonstrated power and influence. Both illustrate cost effective usage of existing distributed compute resources where most data is accessible to everyone.

Distributed Computing is in its infancy (I’m not referring to Cloud Computing). A number of technologies supporting distributed computing have been developed. Some have survived and some waned. A sophisticated distributed system is on par with the importance of nanotechnologies and artificial intelligence. It will support those other technologies as well. It has the potential to distribute energy needs for processing rather than requiring a power plant dedicated to running a data center. It has the potential to distribute data storage so it’s never lost and provides a means for individuals to control their own personal information. It has the potential to provide mechanisms which capture data in real time and process as needed where needed with most efficient usage of resources. In so doing, mirroring the real world (ala Gelernter’s Mirror World).

So although building data center citadels and powerful HPC computers is valuable so is developing and building sophisticated  distributed computing systems. In fact, it’s likely much more important.

World Community Grid logo

If you have never heard about worldcommunity project it’s a good time to learn about it. it’s a project to create the largest public computing grid in the globe. With his client based on the boinc project, you can share your unused cpu cicles to compute data for this project. The data your computer will compute is for the growing of the culture, medicine and science.

If you have an Ubuntu server somewhere it’s very easy to set up the worldcommunity client there. Just open a terminal and write:

sudo aptitude install boinc-client

After you have installed the client, you can create an account in the worldcommunitygrid.org website. When you set it up you can do login and go to the  My profile page. In that page you will read the BOINC Account Key. Take note of it. Now open a terminal and type

boinccmd –project_attach www.worldcommunitygrid.org [BOINC Account Key]

And that’s all, boinc will connect to worldcommunity and download data to compute. When you don’t use your cp, it will start computing for the grid and when you need your cpu cicles, it will stop computing.

Completely off-topic (but hey, this is my blog!): today I celebrate my tenth anniversary as a participant of Seti@home. In case you’ve never heard of it: in this scientific program, about five million desktop computers around the world – like the one you are using right now – are connected to analyze data from radio telescopes searching for signals of extraterrestrial intelligence.

If you want to participate, you must download the basic software, BOINC (Berkeley Open Infrastructure for Network Computing), and once you’ve installed that, you can chose the program you want to support. For me, that’s Seti@home, because I like the idea to make contact with an alien civilization, and ClimatePrediction, for obvious reasons. Every time I switch on my computer, these programs start themselves up, and there’s nothing I have to do. It’s so simple – and yet, I am contributing to science.

So, if you want to be the first human to make contact with E.T.: go here and download the software.

If you own a Mac, you need Snow Leopard.

If you’re out of the loop and don’t pray five times a day toward Macca, Snow Leopard is the newest version of the Mac OS. (It only costs $25, so we’re not talking a major investment here.)

Because it’s been covered to death elsewhere, I’ll offer only a few general feelings and a couple of warnings.

The installation could not be easier. Insert DVD. Click “Install.” Wait. Done. (I recalibrated my external display upon completion, though this is mostly habit, and possibly the sign of a deranged mind. [It can be found at: System Preferences / Display / Color / Calibrate])

Prior to installation, I had 81.73GB free on my hard drive. After installation, I had an astonishing 96.33GB free. This is because Snow Leopard strips away vast swaths of legacy code. I’ve been installing operating systems both mainstream and obscure for twenty years; this is the first time I’ve seen one narrow the footprint. It’s a remarkable achievement that should be trumpeted at every opportunity.

The operating system itself runs faster. The experience echoes the first time I used the iPhone. It flows and ripples and springs and sparks. It’s very impressive.

Expose is fixed! (I have it hot-cornered to the top right of my screen.) Unlike before, where Expose displayed all open programs but only sporadically accepted a selected window, it now works 100% of the time. That’s worth $25 right there.

The dock is more organized, now offering scrollable stacks to reduce clutter, and additional features upon right-click.

Safari now blazes–even the “Top Sites” screen. Stupidly, they continue to ignore the mousewheel-click auto-scroll feature present in every single Microsoft Windows application and most good Mac programs. As a result, I remain devoted to Firefox. Sadly, Firefox appears to have taken a performance hit. I cannot qualify this with hard data, but I’m telling you: it’s less snappy.

Finder is way, way faster.

All of my critical programs work well, to include:

• Microsoft Office 2008
• Adobe Photoshop CS3 (Power users report minor issues, but I’ve yet to run across a problem.)
• Picasa
• Transmission
• Burn
• Toast Titanium
• Evernote
• MacTheRipper
• Espresso (Note: everything offered by this year’s MacHeist seems to work without issue.)
• Google Notifier
• Dropbox
• Jing

That’s the good.

The bad:

My printer is currently unsupported. I use a dirt-cheap HP LaserJet P1006 connected via my Time Capsule. HP is supposedly working on a fix. Wide printer support isn’t so much a feature as a categorical imperative. I cannot for the life of me figure out how Apple could make such a stupid, arrogant mistake. The P1006 isn’t even a sophisticated printer! Lesson learned: before upgrading, verify that your printer is supported.

Some of my minor software does not work, to include:

• iStat (Update in the works.) Update: Fixed with 2.0.
  
• Cyberduck (Update expected any minute now.) Update: Working beta now available.
• Flip4Mac (The current beta DOES work.)
• Growl (Technically it works, except for the System Preferences element. But this is a pass/fail test. Growl fails.) Update: Working beta now available.
• Disc Inventory X (Requires Rosetta, which I’m not willing to do.)
• Xscreensaver (Jamie Zawinski, Xscreensaver’s programmer, vents his fury at Apple in this thread.) Update: Fixed.
  
• Boinc / SETI@home (Again, this is a screen saver issue, though the administrators are acting willfully clueless. In every discussion forum I’ve visited, the powers that be seem to stick their heads in the sand and say “Everything is working fine!” I’m here to tell you it does NOT work.) Update: Fixed with beta release.
  

Aside from the Boinc team’s general obstinate stupidity, I expect all of these software issues to be resolved in the coming days. In the mean time, here is a beautifully comprehensive Snow Leopard compatibility list that will assuage your deepest concerns. Don’t be dissuaded, though. Snow Leopard is well worth the upgrade, and a tremendous value by every conceivable measure. It can be purchased here.

Nuova versione per Boinc che arriva alla release 6.4.5. Con questo software potete donare una parte della potenza di calcolo del vostro PC ad uno dei tanti progetti no-profit. Con questo progetto si riescono a raggiungere potenze di calcolo pari ai supercomputer (Licenza: LGPL , OS: Jaunty Jackalope 32/64bits, Formato: Deb).

Fonte/Download: GetDeb – HomePage: Boinc

Whoever said that social networking juggernaut Facebook would never help find a cure for cancer, combat global warming or quell the spread of malaria in Africa was just wrong, wrong, wrong. I mean, they were right until Intel came along to turn these hypothetical assertions into realities, but now, they deserve to be ridiculed for their lack of foresight.

As Ars Technica reports, Intel has partnered with Facebook and GridRepublic to create the new Progress Thru Processors application that lets users contribute their computers’ unused processing power to various BOINC (grid computing)-based programs, including Rosetta@home, Climateprediction.net, and Africa@home. One of the application’s most notable features is that it lets users differentiate between multiple projects, rather than having to commit all of their resources to just one destination.

Ultimately, the purpose of Intel’s partnership deals is to use Facebook’s ubiquity to get the word out on BOINC and its capabilities as it relates to this new application. Plus, you can post your processing contributions to your profile, so you can rub your superior humanitarianism in all of your friends’ faces.

From G4