Hosting Problems For distributed.net

Yoda2 writes "I've always found the distributed.net client to be a scientific, practical use for my spare CPU cycles. Unfortunately, it looks like they lost their hosting and need some help. The complete story is available on their main page but I've included a snippet with their needs below: 'Our typical bandwidth usage is 3Mb/s, and reliable uptime is of course essential. Please e-mail [e-mail] if you think you may be able to help us in this area.' As they are already having hosting problems, I hate to /. them, but their site is copyrighted so I didn't copy the entire story. Please help if you can." Before there was SETI@Home, Distributed.net was around - hopefully you can still join the team.

Suggestion

[Jouster]

Could they just move the project over to SourceForge?

Jouster

Stopping three quarters of the way

[Soft]

The RC5-64 challenge is currently [distributed.net] at 73%, moving fast. Can you imagine the project shutting down just now?

Re:Suggestion

[hkhanna]

No because the distributed.net client needs to communicate on it's own port in whatever internal protocol it uses. That's what causes the bandwidth usage, not the downloading of the client, if that's what you think.

You can't put your own server software on sourceforge's servers, at least not to my knowledge, so all sourceforge would be good for is hosting the client downloads...which it might actually already do. Hope that answers your question.
Hargun

Copy + Paste

[Anonymous Coward]

we need your help!

URGENT: We have recently learned that our long-standing arrangement with Texas.Net (formerly Insync) would end at noon, Friday, March 22. Through an agreement with Insync, we were hosted at no charge for many years. Though we have tried to make other arrangements with them or to continue our current service until we can make other arrangements, in the end we had no choice but to move.

Several of the Austin cows made a road trip Friday morning to retrieve our equipment from their colocation facility.

We have no reason to complain about Texas.Net or their current decision. As a business, they chose to donate to us for a long time, and have now decided that they must stop. In dbaker's words in a letter to Texas.Net: "Our experience with Insync has been excellent; I've never been happier with an Internet provider. I've recommended them (and indirectly, Texas.Net) to everyone and even this [situation] won't change that."

Though United Devices has kindly offered to colocate our primary servers for a short time at no expense, we find ourselves in the market for a new ISP. If any of our participants work for a major ISP in Texas (preferably within a few hours of Austin, but we're not picky), and would be willing to donate colocation space and connectivity, we would eagerly like to speak with you. Our typical bandwidth usage is 3Mb/s, and reliable uptime is of course essential.

Please e-mail [e-mail] if you think you may be able to help us in this area.

Re:Aliens, crypto or cancer - what's your choice?

[Sircus]

You're wrong, so I'll correct you :-)

d.net was around a long time before SETI@home - I've personally been running the client since 1997. SETI@home launched on May 13, 1999 (though they were fundraising and doing development for a couple of years before that).

I'm personally strongly interested in cryptography for various reasons, so d.net gets my processor time. I seem to recall various people have concerns about how exactly the cancer project will use the eventual data it collects - i.e. whether the products produced as a result of the project will be commercially exploited - they don't want companies just using this large distributed network to make a fast buck.

Re:Dnet, is it useful ?

[Graspee_Leemoor]

"Cancer research? I've yet to see a viable distributed project for cancer research. By that, I mean an organized effort with real data, a complete and concise goal, and a clean method for reaching that goal. "

http://members.ud.com/home.htm

This is real research, worked on by United Devices, helped by the University of Oxford, Intel and the National Foundation for Cancer Research.

It meets all your criteria- this is from their site:

"The research centers on proteins that have been determined to be a possible target for cancer therapy. Through a process called "virtual screening", special analysis software will identify molecules that interact with these proteins, and will determine which of the molecular candidates has a high likelihood of being developed into a drug. The process is similar to finding the right key to open a special lock--by looking at millions upon millions of molecular keys."

graspee

Re:Distributed hosting?

[BovineOne]

Our network already uses a somewhat distributed model to spread out bandwidth demand as best as we can. You can see a bit of it if you look at our Proxy Status page at http://n0cgi.distributed.net/rc5-proxyinfo.html

Each of the servers listed are in in different DNS rotation grouped roughly by geographically named groups (that try to take in general network topology/connectivity). The servers listed there (known as "fullservers") handle all of the data communication needs requested by clients, and the fullservers in turn keep in contact with the "keymaster". The keymaster is the server responsible for the coordination of unique work between all of the fullservers and assigning out large regions of keyspace to the fullservers (which in turn split up the regions and redistribute to clients).

The hardware that we had hosted at Insync/TexasNet was actually 3 machines which together served several roles: our keymaster, one of our dns secondaries, our irc network hub, one of our three web content mirrors, and our ftp software distribution mirror (for actual client downloads).

It's unfortunate that the change in management at Insync/TexasNet caused them to want to re-evaluate all of the free-loading machines that were receiving donated services (there were apparently several others besides us) and cut off anyone who wasn't paying. Regardless, it's a touch economy and companies that want to survive have to look at where their costs are going and do their best to cut spending.

Re:Distributed hosting?

[BovineOne]

This is effectively what we already do with our keymaster, fullserver, personal proxy tiering. Personal proxies can be several layers deep if needed (many of our teams set up their own team servers using personal proxies).

Re:Optimization of Network Usage

[BovineOne]

The "keymaster" (the machine that utilizes the ~3Mbit/sec) already distributes larger regions of uncomputed work to all of the "fullservers", which are the ones that in turn distribute the actual work to clients after splitting the blocks into sizes that correspond to what is needed by clients. You can see the list of all of the fullservers at http://n0cgi.distributed.net/rc5-proxyinfo.html

All of the chatty, multi-step network communications overhead with dealing directly with the clients is done at the fullserver level, including doing a windowed-history based coalescing on result submissions.

Re:Dnet, is it useful ?

[BovineOne]

Because distributed.net is a purely volunteer project, many of its staff also have their paid day-time jobs working for United Devices (who are responsible for the THINK Cancer project). That includes myself [distributed.net], Nugget [distributed.net], Decibel [distributed.net], Moose [distributed.net], Moonwick [distributed.net]

Re:Suggestion

[BovineOne]

Finding new hosting for our central "keymaster" is what the issue is. We have enough "fullsevers" for serving the computational data to clients (See http://n0cgi.distributed.net/rc5-proxyinfo.html [distributed.net]).

FWIW, Our clients actually can speak a pure HTTP protocol for requesting data, allowing a simple /cgi-bin/rc5.cgi script handle direct serving, but the default communications mode is a more compact raw binary mode.

Re:Distributed viruses?

[BovineOne]

Client downloads are PGP signed http://http.distributed.net/pub/dcti/v2.8015/ [distributed.net] and are served by machines that mirror it (via rsync over ssh) from a tightly controlled host, which is not one of the servers that actually publicly serve the files. Although the binaries are pre-compiled, the original source code is open for review at http://www.distributed.net/source/ [distributed.net]

Re:So 3Mb/s huh?

[BovineOne]

That figure is actually closer to the current average peak. We in fact currently have an ipfw bandwidth limit on the machine to limit it to 3Mbit/sec and it mostly stays under it. We just over-quoted that figure a little bit in our announcement so that there would be fewer concerns over some marginal potential growth and try to factor in some of the bandwidth peaks.

Re:keyservers?

[BovineOne]

Running our personal proxy [distributed.net] for large teams (particularly if they are all at a single corporation or a single school) can indeed help, because it reduces some of the overhead of communications with each individual client. There is also some optimization done by the personal proxy to allow it to request larger blocks of work and partition it into smaller portions when it finally distributes to the actual clients.

However, this doesn't reduce the bandwidth at the keymaster any further, since this sort of splitting is already also being done at a larger scale between the keymaster and fullservers (and the bandwidth issue is with the keymaster, not the fullservers).

Re:Issues Resolved?

[BovineOne]

Although United Devices is currently graciously hosting some of the displaced distributed.net hardware temporarily, they've indicated that they are not willing to do this long term (which is quite a reasonable decision, since it is a lot of bandwidth).

Note that several of the distributed.net volunteer staff (including myself) do indeed work for United Devices during the day, and that our employment there began awhile ago (more than 15 months ago), so that partnership announcement is not really related.