IANAL, but as far as I understand, those 3 little words will bring any lawsuit brought by SCO (regarding Linux)to a screeching halt until the lawsuit with IBM is cleared up.
There is no "classified" information at Fermilab, other than payroll information, HR documents, etc. It's a purely scientific, basic energy laboratory.
Have you all forgotten that SCO has yet to provide any PROOF that Linux has infringed on their IP?!?? Until that has been proven, SCOs actions can be interpreted as RACKETEERING! Until the proof is layed out NO ONE SHOULD PAY A RED CENT!
Remember, September in the states is the beginning of Fall and it starts to get cold in 50% of the states about November 1st. Just keep that in mind.
So, starting in Washington DC and working counter-clockwise this is what I'd do. I'm sure there's a lot of places I'm missing, but it's pretty good start:
Smithsonian Institution - lots and lots of geek appeal here.
Pentagon - largest building in the world, iirc.
Gugenheim in DC - might as well get some culture.
Niagra Falls - one of the 7 natural wonders of the world. This is a must see from the Canadian side, of course (eh).
Pictured Rocks National Lakeshore - really, really tall sand dunes on the shore of Lake Superior, which is the 1st or 2nd largest fresh water lake in the world (bonus item).
Devil's Tower - remember "Close Encounters of the Third Kind"? That thing. Very cool.
Glacier National Park - September is getting late in the season to see this, though. They'll start closing the roads soon after you arrive here.
Yellowstone National Park - Old Faithful geyser. 'nuff said.
Craters of the Moon Nat'l Monument - where the astronauts practiced for their moon walks back in the day.
Grand Canyon - one of the other 7 natural wonders of the world.
Kitt Peak National Observatory - largest concentration of astronomical telescopes in the world. Definite geek appeal.
...to kill your TV. I'm sick and tired of it. The whole deal. TV. The MPAA. The RIAA. Everything. And everyone involved in the dumbing down of America, and the world. Excuse the pun, but it's time to Get Smart, people!
The coriolis effect on these, assumed miniature flywheels, would be negligible. The coriolis effect only has any noticeable impact on long range, unpowered weapons, i.e., cannons like Big Bertha from WWII.
My lovely Polish wife has been in the INS "machine" for nearly 5 years, due in part to our moving in the middle of the process. We originally applied in for her citizenship in '94 or '95 after we got married. Then we moved back to Chicago in '96 and had her paperwork transfered to the station here. That was the last we heard from them until we stood in their damn line in Nov '97 only to be told, "Oh, it's on somebodies desk. You should be getting a call for an interview soon." Well, it's now '00 and we haven't gotten any call.
I'm writing to my congressman - hey, that's Hastert, the Speaker of the House. Heh heh heh.
Just FWIW, CPU cycles may not be what's limiting the data analysis - it may be tweaking the reduction algorithms and re-iteration, which requires a lot of human intervention. Back when I was an astronomer, this was 90% of the battle with certain sets of data - taking out unwanted dark currents, dealing with strange flat images, bias levels that changed with position on the sky. I almost went insane with one set of data from the Curtis Schmidt at CTIO. Ugh.
So I checked out both LinuxHQ.com and kernelnotes.org and I'm still confused (no comments from the peanut gallery... Rob.). Is the old LinuxHQ guy back at LinuxHQ again or still operating kernelnotes?
Don't get your panties in a bunch - there was obviously a typo in the persons email, Probably due to the '0' key sticking.
Yes, I gave a tour to several students from my alma mater in Stillwater, MN.
No, I didn't show them a 600+ node cluster of old 486's (I can't even think of one 486 on site - they are there, I just don't know about them). I did show them the 20 node Run II prototype farm, the 10 node SAM farm and the production 37 node farm. We don't do Beuwulf clusters. We do compute farms. Why? They are 2 totally different things. A beowulf cluster is specifically designed to analyze a little bit of data with a lot of message passing between processors and nodes. This is for tightly bound compute processes. A farm is a cluster specifically designed to crunch huge amounts of data with absolutely no message passing between processes, CPU's, or nodes.
Quick physics lesson on what Fermilab does:
We take protons and anti-protons and accelerate them to darn near the speed of light. Then we collide them in the Tevatron at particular points on the ring that have detectors (currently CDF and D0 (D-Zero)). Each detector has about a million individual detectors and the amount of data that is actually produced is about a million megabytes of data per second... no, we don't keep it all! The 1st level trigger throws most of the data away 'cause it just isn't interesting. The second level trigger throws some more away. The 3rd level trigger, which will be a 128 node, dual CPU Linux farm, will throw some more away, but it will pass something like 20-250 MB/sec on to the tape library. This number is dependent on the budget allocated for tapes. Roughly, we'll be saving 1.5PB/year (that's Peta Bytes, or 10^15) to tape. After a while, the physicists will want to take better look at all that data. How? Linux farms. You see, the data that is taken, say, at 2:30:43.8238 on April 23, 2001 will have nothing to do with the data that is taken at 2:30:43.8239 on April 23, 2001, so it's safe to treat that as one individual data set. By doing so, we can put it on a single processor and let that processor grind on it for a while before spitting out the answer. Well, so the question is, should we send out one single data set to a worker node in the farm, let it analyze it, then send it another, or should we dump ALOT of data off to the worker node and let it grind for a lonf time before writing the finished data back to tape. It appears that it's best just to send a big ole chunk (~15GB) of data off to a node, and let it grind for some large (~24 hours) amount of time.
The "plan" for this year is to purchase about 200 (that's hundred) dual P-II/III machines, depending on our budget. The year after that the "plan" is to purchase about 400 machines, and the year after that (when Run II starts in the Tevatron) the "plan" is to purchase another 400 machines. So, let's do some math - (200+400+400)*2 = 2000 _processors_, but only a thousand nodes.
Slashdot Mirror
how, exactly?
Blah, blah, blah, Linux, blah, blah, blah.
I knew that you could.
IANAL, but as far as I understand, those 3 little words will bring any lawsuit brought by SCO (regarding Linux)to a screeching halt until the lawsuit with IBM is cleared up.
I could be wrong, of course.
There is no "classified" information at Fermilab, other than payroll information, HR documents, etc. It's a purely scientific, basic energy laboratory.
Consider purchasing a 2,4,8, or 12 port 3ware controller, depending on your need.
Thank you, MS for making Linux more appealing.
Jeez! Get smart, people!
Remember, September in the states is the beginning of Fall and it starts to get cold in 50% of the states about November 1st. Just keep that in mind.
So, starting in Washington DC and working counter-clockwise this is what I'd do. I'm sure there's a lot of places I'm missing, but it's pretty good start:
Smithsonian Institution - lots and lots of geek appeal here.
Pentagon - largest building in the world, iirc.
Gugenheim in DC - might as well get some culture.
Niagra Falls - one of the 7 natural wonders of the world. This is a must see from the Canadian side, of course (eh).
Pictured Rocks National Lakeshore - really, really tall sand dunes on the shore of Lake Superior, which is the 1st or 2nd largest fresh water lake in the world (bonus item).
Devil's Tower - remember "Close Encounters of the Third Kind"? That thing. Very cool.
Glacier National Park - September is getting late in the season to see this, though. They'll start closing the roads soon after you arrive here.
Yellowstone National Park - Old Faithful geyser. 'nuff said.
Craters of the Moon Nat'l Monument - where the astronauts practiced for their moon walks back in the day.
Grand Canyon - one of the other 7 natural wonders of the world.
Kitt Peak National Observatory - largest concentration of astronomical telescopes in the world. Definite geek appeal.
San Francisco and Silicon Valley
You really meant to say it *will* store, crunch, and distribute LHC data, since the LHC ain't done, yet.
Ride that dead horse! Ride 'im, boy!
Kill Your TV
Kill Your TV
Kill Your TV
Cigarettes are a nicotine delivery system. TV is an idiocy delivery system.
1. Download kerberos source
2. Unzip and untar
3. make all, make install.
What's so hard about that?
Oh, we're not talking about the port? Oh well.
Get this person a dictionary!
The coriolis effect on these, assumed miniature flywheels, would be negligible. The coriolis effect only has any noticeable impact on long range, unpowered weapons, i.e., cannons like Big Bertha from WWII.
I'm writing to my congressman - hey, that's Hastert, the Speaker of the House. Heh heh heh.
Just FWIW, CPU cycles may not be what's limiting the data analysis - it may be tweaking the reduction algorithms and re-iteration, which requires a lot of human intervention. Back when I was an astronomer, this was 90% of the battle with certain sets of data - taking out unwanted dark currents, dealing with strange flat images, bias levels that changed with position on the sky. I almost went insane with one set of data from the Curtis Schmidt at CTIO. Ugh.
So I checked out both LinuxHQ.com and kernelnotes.org and I'm still confused (no comments from the peanut gallery... Rob.). Is the old LinuxHQ guy back at LinuxHQ again or still operating kernelnotes?
Please, oh please straighten out my purty head!
Dan
Your welcome.
Dan
Don't get your panties in a bunch - there was obviously a typo in the persons email, Probably due to the '0' key sticking.
Yes, I gave a tour to several students from my alma mater in Stillwater, MN.
No, I didn't show them a 600+ node cluster of old 486's (I can't even think of one 486 on site - they are there, I just don't know about them). I did show them the 20 node Run II prototype farm, the 10 node SAM farm and the production 37 node farm. We don't do Beuwulf clusters. We do compute farms. Why? They are 2 totally different things. A beowulf cluster is specifically designed to analyze a little bit of data with a lot of message passing between processors and nodes. This is for tightly bound compute processes. A farm is a cluster specifically designed to crunch huge amounts of data with absolutely no message passing between processes, CPU's, or nodes.
Quick physics lesson on what Fermilab does:
We take protons and anti-protons and accelerate them to darn near the speed of light. Then we collide them in the Tevatron at particular points on the ring that have detectors (currently CDF and D0 (D-Zero)). Each detector has about a million individual detectors and the amount of data that is actually produced is about a million megabytes of data per second... no, we don't keep it all! The 1st level trigger throws most of the data away 'cause it just isn't interesting. The second level trigger throws some more away. The 3rd level trigger, which will be a 128 node, dual CPU Linux farm, will throw some more away, but it will pass something like 20-250 MB/sec on to the tape library. This number is dependent on the budget allocated for tapes. Roughly, we'll be saving 1.5PB/year (that's Peta Bytes, or 10^15) to tape. After a while, the physicists will want to take better look at all that data. How? Linux farms. You see, the data that is taken, say, at 2:30:43.8238 on April 23, 2001 will have nothing to do with the data that is taken at 2:30:43.8239 on April 23, 2001, so it's safe to treat that as one individual data set. By doing so, we can put it on a single processor and let that processor grind on it for a while before spitting out the answer. Well, so the question is, should we send out one single data set to a worker node in the farm, let it analyze it, then send it another, or should we dump ALOT of data off to the worker node and let it grind for a lonf time before writing the finished data back to tape. It appears that it's best just to send a big ole chunk (~15GB) of data off to a node, and let it grind for some large (~24 hours) amount of time.
The "plan" for this year is to purchase about 200 (that's hundred) dual P-II/III machines, depending on our budget. The year after that the "plan" is to purchase about 400 machines, and the year after that (when Run II starts in the Tevatron) the "plan" is to purchase another 400 machines. So, let's do some math - (200+400+400)*2 = 2000 _processors_, but only a thousand nodes.
Yes, the cabling is problem.
Hope that clears up some confusion.
Cheers,
Dan