So the big bug that happened after the server code was updated was that there wasn't a working limit for GPU work, which means a lot of clients downloaded thousands of workunits, crippling the database; and even worse crippling the disk of the server even harder reporting all of those workunits.

I'm pretty sure the only way we're going to be able to get the server back up and running in any reasonable amount of time is to clear out the entire workunit and result tables. They're so large I can't even query their size.

So basically to get things up and running again I'll be clearing out the result and workunit tables of the database -- we're hoping we can get that done sometime this weekend. As well as cleaning out our upload and download directories, which are slow almost to the point of unresponsiveness. After things are cleared out, we'll bring things back up (with working workunit limits for both CPUs and GPUs) and I'm hoping things will run fairly smoothly after that.

I know it sucks and I wish we had a better solution, but I think this is the best we can do. Feel free to cancel any workunits/results you have currently crunching; and try not to flame us too hard. :P

---

Confucius he say "no point putting fist through PC Screen - only have to go buy another one, and it changes squat". Clever guy Confucius.

There's always a silver lining, you'll be able to do all those nice-to-have minor jobs you meant to get around to, but had no time - and with DNETC down, Collatz and PrimeGrid will think Xmas came early.

Its life, the way it goes sometimes, hope your coffee machine is a good one. Hang in there, and dont forget to sleep .....

Regards
Zy

Modern Magellans: New NSF Grant at Rensselaer Uses the Power of the Masses to Map Dark Matter in the Galaxy



A simulation developed with MilkyWay@Home shows the formation of several stellar streams (Sagittarius, Orphan, and GD-1) around the Milky Way. The animation represents four billion years in the Milky Way, ending at the present day. Credit: Rensselaer/Benjamin A. Willett

A simulation developed with MilkyWay@Home shows the formation of several stellar streams (Sagittarius, Orphan, and GD-1) around the Milky Way.
The animation represents four billion years in the Milky Way, ending at the present day. Credit: Rensselaer/Benjamin A. Willett

Rensselaer Polytechnic Institute astronomer Heidi Newberg is using a new grant from the National Science Foundation (NSF) to begin mapping the distribution of dark matter in our galaxy. The more than $382,000 grant will utilize the massive computing power of the international MilkyWay@Home project to help uncover the whereabouts of the elusive dark matter and provide another piece in the puzzle to map the Milky Way.

Any third grader can tell you the order of the planets from the sun, but astronomers know surprisingly little about exactly how and where the mass in our galaxy is distributed across the cosmos. One large conundrum with the effort to map the Milky Way is that much of the known mass of the galaxy is completely unaccounted for. Add up the planets, sun, stars, moons, asteroids, and other known mass and only a fraction of the mass is accounted for. Many scientists purport that the difference is made up by the presence of dark matter, which is undetectable to all modern telescopic technology. But Newberg thinks that with MilkyWay@Home, the computer may be able to accomplish what no telescope has done before – show astronomers where dark matter is likely to reside in the galaxy.

Led by researchers at Rensselaer, the MilkyWay@Home project is among the fastest distributed computing programs ever in operation. At its peak, it has run at a combined computing power of over 2 petaflops donated by a total of 93,206 people in 195 countries and counting. That is more countries than the United Nations. The combined computing power of all these personal computers, which rivals the most powerful supercomputers in the world, is being used by researchers like Newberg to uncover some important and basic things about our galaxy.

“MilkyWay@Home is allowing us to consider bigger thinking when it comes to understanding the galaxy,” said Newberg, who is professor of physics, applied physics, and astronomy at Rensselaer. “With this grant we will combine my previous research mapping tidal debris streams with the power of MilkyWay@Home to simulate the creation of these streams and begin, very importantly, to start to constrain the properties of dark matter.”

Tidal debris streams, also called stellar streams, are the scattered remains of dwarf galaxies that have been ripped apart after coming too close to a larger galaxy such as the Milky Way. Several of these glowing streams currently orbit the Milky Way as part of what is aptly called the galactic halo.

Given the gross amount of dark matter thought to be present in the galaxy, the collision of dwarf galaxy and massive Milky Way that created tidal debris streams would have included the strong involvement of dark matter. This makes study of tidal debris stream formation a good window into understanding how and where dark matter comes into play in the galaxy, according to Newberg. Know how the debris stream was formed, she said, and astronomers would start to understand where dark matter may reside.

Newberg’s previous research has successfully mapped the position and distribution of stars in several stellar streams, including the Sagittarius stream, the Orphan Stream, GD-1, and the Cetus Polar Stream, using data from the Sloan Digital Sky Survey (SDSS). With this new funding, she will use MilkyWay@Home to simulate how exactly the stars in those streams got to where they currently reside in the sky.

To simulate stream creation, she will use MilkyWay@Home to model what happens when a dwarf galaxy meets up with the Milky Way and is ripped apart and spread around the galaxy like an intergalactic paint splatter. To confirm the model, she will match it to the known distribution of stars in the streams mapped by her previous work with SDSS. The first step in this process will be to constrain the properties of an initial dwarf galaxy that would be input into the MilkyWay@Home system.

“We are currently running some simulations on MilkyWay@Home right now on a single dwarf galaxy,” Newberg said. “This is a small part of the problem, but an important step in the effort to map the overall distribution of mass in the galaxy.”

The NSF grant is expected to total $382,513 over three years.

More on Newberg’s research can be found at http://www.rpi.edu/~newbeh/.

A news release on MilkyWay@Home can be found at http://news.rpi.edu/update.do?artcenterkey=2685.
Published March 15, 2011
source: http://news.rpi.edu/update.do?artcenterkey=2842
linking: http://board.mpits.net/viewtopic.php?f=14&t=49
so how about using a few $ to buy a new server ???

---

Join Support science! Joinc Team BOINC United now!

Geez, I don't think Heidi even told me about that grant. :P But I think when a grant is awarded it takes some time before we actually get the money. Chances are some of it will be used for upgrades whenever it comes in.

---

Geez, I don't think Heidi even told me about that grant. :P But I think when a grant is awarded it takes some time before we actually get the money. Chances are some of it will be used for upgrades whenever it comes in.

Well it was posted almost a month ago. I guess you better talk to her soon ;)
A resonable 5 to 6k$ would get you finally some nice server and headrome to operate MW properly.

EDIT:

This news might be worth a proper news announcement after the dust has settled.

---

Join Support science! Joinc Team BOINC United now!

Geez, I don't think Heidi even told me about that grant. :P But I think when a grant is awarded it takes some time before we actually get the money. Chances are some of it will be used for upgrades whenever it comes in.

Well it was posted almost a month ago. I guess you better talk to her soon ;)
A resonable 5 to 6k$ would get you finally some nice server and headrome to operate MW properly.

Our big problem is really with MYSQL keeping up (especially if we upgrade the ATI application ever). I think we need some kind of distributed database.

But this problem was really less hardware and more the server being up and running for a few hours without and upper limit on the GPU workuits being sent out. The workunit table was well over a million.

---

Geez, I don't think Heidi even told me about that grant. :P But I think when a grant is awarded it takes some time before we actually get the money. Chances are some of it will be used for upgrades whenever it comes in.

Well it was posted almost a month ago. I guess you better talk to her soon ;)
A resonable 5 to 6k$ would get you finally some nice server and headrome to operate MW properly.

Our big problem is really with MYSQL keeping up (especially if we upgrade the ATI application ever). I think we need some kind of distributed database.

Well if you're IO bound, a massive increase in RAM is needed or some fast SSDs.
Anyway, AFIK the whole MW project still runs on FreeBSD and some crappy old server... so .. you need a new one, that's for sure.

---

Join Support science! Joinc Team BOINC United now!

Geez, I don't think Heidi even told me about that grant. :P But I think when a grant is awarded it takes some time before we actually get the money. Chances are some of it will be used for upgrades whenever it comes in.

Well it was posted almost a month ago. I guess you better talk to her soon ;)
A resonable 5 to 6k$ would get you finally some nice server and headrome to operate MW properly.

Our big problem is really with MYSQL keeping up (especially if we upgrade the ATI application ever). I think we need some kind of distributed database.

Well if you're IO bound, a massive increase in RAM is needed or some fast SSDs.
Anyway, AFIK the whole MW project still runs on FreeBSD and some crappy old server... so .. you need a new one, that's for sure.

I think we did upgrade the RAM not too long ago. But yes, a shiny new server with some SSDs would be lovely. When I bitch everyone out monday (for breaking everything and letting me know at 2am this tuesday), i'll be sure to bring it up.

And I was just finally making some progress with DNA@Home. :P

---

I think we did upgrade the RAM not too long ago. But yes, a shiny new server with some SSDs would be lovely. When I bitch everyone out monday (for breaking everything and letting me know at 2am this tuesday), i'll be sure to bring it up.

And I was just finally making some progress with DNA@Home. :P

Well, to be honest, DNA@Home is broken too ;) UoTD page is stuck, Profile pages broken, pending credit page is stuck/ not updating (here as well) ... So lot's of things todo!!!

And a linux app for DNA is first priority!!! OSX is not important boinc wise ;)

---

Join Support science! Joinc Team BOINC United now!

Too bad that this is the only non private science project in BOINC that officially can use the AMD \ ATI cards.

Thanks Travis for posting all the information on the main site and here. So we know what is happening.

I wish you and the team all the best for dealing with this issue.

But get some rest as well. When we can't (the pc's) crunch for a few days, that is not the end of the world. There is more in live to explore...

Keep up the good work and good luck.

---

Greetings from,
TJ

Thanks Travis for posting all the information on the main site and here. So we know what is happening.

I wish you and the team all the best for dealing with this issue.

But get some rest as well. When we can't (the pc's) crunch for a few days, that is not the end of the world. There is more in live to explore...

Like theFolding@Home v7 Client Beta Release

I would kill the guy who is responsible for this :P
about 1 million results was simply burned in the oven?!
such a waste =(

Adios Milkyway...

Adios Milkyway...

I say goodbye too.

---

I would think after all these years you would know how to set up things when you make changes. It seems every time something is changed it all just breaks instead.

---

Doesn't expecting the unexpected make the unexpected the expected?
If it makes sense, DON'T do it.

I'm philosophical about it. They were just credits and a few bucks of electricity - equivalent of maybe a coffee or 2 lost. Ho hum...

;-) Philosophical is one way to look at it. The other way
is rational. The more crunchers that leaves Milkyway, the
more wu`s there will be for the rest of us! ;-D

Just get it up running again!
Good Luck! ;-)

---

;-) Philosophical is one way to look at it. The other way
is rational. The more crunchers that leaves Milkyway, the
more wu`s there will be for the rest of us! ;-D

Just get it up running again!
Good Luck! ;-)

haha i like this way of thinking ^^

but it would be a lie if i would say something like i hadnt thought about leaving this project after the last night...

I ll stay as long as i have no nvidia card ... and then we ll see =)

;-) Philosophical is one way to look at it. The other way
is rational. The more crunchers that leaves Milkyway, the
more wu`s there will be for the rest of us! ;-D

Just get it up running again!
Good Luck! ;-)

haha i like this way of thinking ^^

but it would be a lie if i would say something like i hadnt thought about leaving this project after the last night...

I ll stay as long as i have no nvidia card ... and then we ll see =)

Its amazing what a tiny Baileys can do with your thoughts. LoL
Dont worry. Just Crunch. ;-)

---