Slashdot Mirror

Allan Snavely... hmmm, sounds fishy to me - does he have good credentials?

Ok, hompage, Paper on scheduling threads on one processor, Write-up on speech about aforementioned paper... he sounds legit, but that name? Snavely is like sly (S nave ly) and knave (minus the "k") mushed together... I don't know if we can trust his recommendation.

Opaserv

network.vbs

There were some others I found before, but I'm not finding them now, probably need to refine my search, but I don't have the time atm.

Here's some more reading material...

911, etc.

port scan

I spent some time reading up on how buffer overflows were used for exploits on this port, UDP packets, and so on. I'm not convinced this is innocent activity, particularly since I do have a firewall configured and don't see any outgoing traffic.

Learning about attacks is an ongoing thing for me and until I have all the facts, or enough of them, I'm leaving it my firewall to keep intruders out. I have seen bursts, usually on weekends when I assume more infected computers have been turned on and the worms are active. At various times I've had as many as 100 hits within 2-3 minutes.

Since I have no current reason for anyone on the internet to access my system, I believe a complete lockdown is a good position to start with. If I put it on a high-speed connection, with fixed IP and fire up services, then I'll allow ports as necessary.

Look down at Chart 33-1
From 1998 to '99 funding drops. Then it is back to '98 level in 2000 (but no increase to offset inflation) then it is up in '01 and '02

http://www.sdsc.edu/SDSCwire/v1.8/5012.NASA.html

Amazing. Budget cuts under Clinton, but increases under Bush? I thought Bush was against more funding.

this is all rather ironic, since, along with babbage, she started it all

She was perhaps also the one that introduced the tradition of wearing crappy glasses to computer geekdom.

For the license.
If this product were to be released under a Free-software license I'd definately consider it on our network. As it is I (and probably many others) will use something else like syslong-ng or metalog, despite the fact that SDSC-syslog seems to be far more technically competent.

Last time I checked, DVDRAMs were about $10 per 9.4 GB, or $1/GB. Interestingly, that's the same price per GB you now pay for 5400 RPM IDE drives - about $90 for 80 GB, or slightly more for 7200 RPM drives (about $1.40 per GB). Just build a big server with 3ware raid cards and stick it in another building on campus.

http://staff.sdsc.edu/its/terafile/index.html

These people did this a while ago - instead of spending $4000 on a piece of specialized hardware that is officially Windows-only, buy a $2000 server and plenty of drives, with room to scale to over 4 TB :)

You mean chip designers like these

Or this

Apple does do hardware, and they do have their own chip designers. They're just sensibly not interested in making their own CPU.

A friend of mine set up a web site to map ALS incidence in the US. The website is called M-PALS, Mapping People with A.L.S.

Such a nasty disease. My family watched my uncle die of it over the last two years. Damn air force bases!

Hmmm, I thought it was a rather old variant of Red Hat. We're basing that on the kernel and RPM versions.

We're running a production DNS server for our main domain on our PS2. There's also a baby web server. "The Effect" will probably knock it over, so please be gentle with it.

Why the DNS server? Because I bet someone they couldn't get it all running in less than 2 hours. I lost :-)

We have a computational chemist who is really contemplating a Beowulf cluster of PS2s, if he can get to the floating point on the graphics chips. The only drawback is the limited (32MB) of RAM. But for *small*-memory, FLOP-intensive jobs it might be cost-effective.

Hmmm, I thought it was a rather old variant of Red Hat. We're basing that on the kernel and RPM versions.

We're running a production DNS server for our main domain on our PS2. There's also a baby web server. "The Effect" will probably knock it over, so please be gentle with it.

Why the DNS server? Because I bet someone they couldn't get it all running in less than 2 hours. I lost :-)

We have a computational chemist who is really contemplating a Beowulf cluster of PS2s, if he can get to the floating point on the graphics chips. The only drawback is the limited (32MB) of RAM. But for *small*-memory, FLOP-intensive jobs it might be cost-effective.

I can't wait until there will be nobody left that is capable of sending email because idiots like you are running things.

That won't happen, xbl.selwerd.cx is far more extreme that the major blocklists, but it blocks less than 30% of all email
(a comparison).

First off, if you just want to make sure the colors are visible on top of each other, you could calculate the luminance of each color using .30*R + .59*G + .11*B and make sure that those numbers differ signifigantly. Some other rules of thumb are here, under color rules.

As far as color discrimability, you might want to look for info on MacAdam's ellipses of just noticeable color differences. There's a picutre on this page which shows the main idea: how different a color has to be in order to notice the difference depends on what color it is. Humans can discern more shades of green than red or blue.

Check out this article referenced by slashdot on July 20 2001.

The nice thing about this article is that the people building it at SDSC really took extreme care in getting quality components that would work together to build a reliable, solid system, and still didn't spend more than $5K for a terabyte file server. In particular, the tradeoff of disk speed vs. power consumption was extremely insightful.

I built one of these to their spec for my company, and I couldn't be happier. It's worked flawlessly since then. It's not clear if the Escalade boards are still available -- 3ware had said that they were discontinuing them, but they still appear to be for sale.

thad

I can't believe you guys modded a troll up to 3...

I guess this sucks?

Or This?

This?

This?

These?

This stuff?

IDE is here to stay in the high end market, and it's going to kick SCSI's ass. Why pay 3X more per drive for the same HDA with a different interface board?

This is from the server in the first link above. Note that most of the write bottleneck is caused not by the drives but by the hardware RAID5 controller.

Machine Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP /sec %CP
bedford 1G 24436 11 22834 13 83890 43 361.2 2

1: H2O is quite light. It's only 18g/mol. There's no other combination _I_ can think of that would be as light, as we humans are made
up of a lot of water.

Water is light, but it is dense (1.) Most organic solvents are density roughly 2/3rds, although they are more compressable than water (so they'd be roughly density 1 under high enough pressure.) Water's gross physical properties (density, viscocity and so forth) are important for a multicellular organism but, actually, if you were just a single alien cell, might not matter.

2: H2O is slightly polar, so it 'sticks' to certain structures a little more. Oil would be an interesting substitute to water, but oil is
large polimer chains. Too hard to create. However Ions would disrupt other chemicals. Also, Ions require water to have charge.

Ions require something polar (alcohol would do) to pair with, or they won't disaccoiate with their counterion. It need not be water - it could be alcohol, or it could be something exotic like liquid SH2. Atoms heavier than sulfur or iodine are insuffiently electronegative to hold much of a negative charge in a polar bond, so probably wouldn't be suitable.

The real problem is that your non-water based cell needs some way to seperate itself from the environment. If you're willing to call any self-replicating molecule "life," this may not be a requirement, but if you're looking for anything that's at least a recognisable organism, even if microscopic, this is a hard requirement to fill without water (or HI or H2S.)

The way cell membranes work is they have an oily portion (the membrane) with ionic stuff on the inside and the outside. So, you have a little bubble of water (the cell) wrapped in the oily membrane which is much like a soap bubble.

Now, in an oily solvent, at the right temperature, you might be able to have the reverse - like a hollow bubble of water floating in liquid soap. However, the forces that push small amounts of something polar out of a non-polar solute are MUCH WEAKER than the forces that push something oily out of water. This results not from an energetic effect, but from an entropic effect:

Water in a solvent state is fairly disordered, capable of forming H-bonds with different waters on all sides of it, and of tumbling around and forming different H-bonds. If you introduce a big oil molecule into the water, there are a number of positions that the water can't tumble into (people describe this as a crystal-like cage but that is inaccurate) so the water molecule becomes more ordered. This increase in order is extremely unfavorable, so all of the oily molecules are pushed out of contact with the water and into oil droplets; like when you mix oil and vinegar together.

The above is called the "hydrophobic effect" and it is the basis of how cells form embranes AND of how proteins become structured. It is pretty much the basis of all life. A similar effect does NOT occur with oily solvents! In fact, it doesn't much occur with ethanol; as far as I know, only other molecules which are much like water show this property.

3: Most of all biological elements are within the top 10 elements on the peridic chart. The reason these are used is because nuclear
fusion within the sun allows these to be made with much greater abundance. This reason also coves why no Earthen creatures use
silicon instead of carbon.

Sorry, that's not true. The earth has more iron atoms on it than carbon atoms, and scads every element through 44 (Nickel). What you say IS true for the outer planets, which didn't have their light elements significantly blasted off by some kind of solar event. Alien planets, which got their heavy elements from different supernovae (that's where heavy elements come from) might have mercury and gold in abundance as well. We don't know.

4: If you can accept the above examples of why water is better than other mostly inert transfer chemicals, then tempature also
comes into play. I know of no animals that use solid or gaseous blood. All use liquid of some type, just because diffusion (or in
water, osmosis) is easier to transport chemicals. The tempature of water being a liquid is between 255K and 310K , so most planets
are eliminated just because of the tempature needs strict control.

I cannot see life arising in solid state, because if the molecules can't move, you can't do the kind of complex molecular recognition chemistry that we understand as life.

In a gaseous state, same problem for reverse reasons - the molecules can't find each other.

That said, you can have pockets of liquid water (underground, say, or under higher pressure) at much higher temperatures. Other molecules with many of the properties of water (possibly enough) could be liquid at much lower temperatures. There is an outside chance that much larger molecules might be suitable and liquid at higher temperatures.

Really exotic solvents - like molten table salt - require temperatures so high that processes dependent on a high degree of order (like life) could never arise.

Another big problem is that complex organic solvents (polybenzenes and such) do not arise spontaneously, while water and amino acids do.

Long story short - a few very water like solvents, like HCl, H2S or HI - might substitute for water and might extend the range of allowable temperatures somewhat. However, nonpolar solvents for life, and silicon based life, appear impossible.

The one thing that is important to remember in determining viability zones is that all of the planets and some of the moons give off their own nuclear heat from fission; especially the earth and other seismically active bodies like Io. This nuclear heat might substitute for solar heat for bodies well outside of the range of their primary's warmth; especially if these alien planets were formed in much closer proximity to a supernova.

Not wanting to get in a performance argument, but...

Slashdot Story on IDE terabyte fs

Linked article from story

In many present and (not so far) future experiments in HEP we deal with this kind of data rate. A nice overview can be found here here.

On page 14 you can find the data valume. It is at about 100 TB for present experiments (I am with BaBar).

page 25 gives some overview on the hardware we use at BaBar/SLAC (e.g. farms of STK Powderhorn tape silos with 6000 tapes each, etc..).

page 95 gives an overview on data rates. ATLAS records at 100Hz and 1MB per event, i.e. 100MB/s

Page 99 gives overview of the (estimated) costs of hardware and tapes for LHC experiments. They are in the order of 20 MCHF (Mega Swiss Franks ~ 0.8 Mega Dollar) initial + 10 MCHF per year. We use a mixture of large RAID farms and tape silos. Everything is managed by HPSS (High Performance Storage System). From my experience at BaBar I can tell you that these numbers are underestimated by at least a factor of 2.

XML can be preferable to an RDBMS for storage when long-term preservation is a goal. Store the preservation copy of the data in XML, then use other more efficient formats for immediate processing needs. The San Diego Supercomputer Center has done some work in this direction. If I want someone to be able to access data 50 years from now, I'm much more worried about software depedence than performance.

Basically, the Escalade cards make a bunch of cheap IDE drives look like a big SCSI drive. What could be better? You get the intelligence of SCSI, the protection of a RAID, at the price of IDE. With just a few IDE drives, you get scalding performance that more the beats the most expensive SCSI drives.

Sadly, 3ware has decided to get out of the controller card business. I've bought a couple of cards that I'm going to keep until I need to build some more file servers; they say that they are going to keep selling the cards until December, but only until then.

thad

I am working on a similar project but in the >1TB range same thing applys to http://staff.sdsc.edu/its/terafile/ On that page they have a link to another page with stuff about ide-raid. >http://www.research.att.com/~gjm/linux/ide-rai d.html The 3ware cards are the way to go as they do raid 0,1,5 in hardware, and support things like hot swap and hot spare. I priced out a system that was just over 1TB of raid 5 for around $5,000 while the prebuilt stuff is $20,000.

NCSA is certainly an important part of this partnership, but they're neither the only part nor the lead site.

This animation was actually done in 1999 or so. There's a lot more information at http://vis.sdsc.edu/research/orion.html. (The Washington Post article doesn't credit the San Diego Supercomputer Center.)

This animation was actually done in 1999 or so. There's a lot more information at http://vis.sdsc.edu/research/orion.html. (The Washington Post article doesn't credit the San Diego Supercomputer Center.)

As to TCP/IP attacks, it can be a real bitch to talk to a host outside your subnet but on the same LAN. Even setting an ARP entry, I couldn't get a response from my modem. I have to use a second machine with two shared ethernets, and set its DSL-side interface to the 10.0.0.x subnet. And I have to set it back to let that machine run normally. (I could put a third Ethernet card in, but it's not really worth the effort.) So I'm not too worried about spoofed UDP packets being bounced into it.

What did surprise me, though, was that the challenge/response code for my old 1000 was computable from the CGI script at http://security.sdsc.edu/self-help/alcatel/challen ge.cgi. So at least now I can telnet into the thing. But so can anyone else, if they can perform the necessary TCP/IP routing wizardry to get to it.

Unfortunately, there doesn't seem to be anything that I can do to it from telnet that I can't do with the web interface.

Especially the output of the nmap scan of the modem is interesting, since a huge number of security problems can be spotted, e.g.

open echo and chargen UDP ports (nice for a DOS attack)

very easy to do TCP sequence prediction (ideal for TCP spoofing to the device)

I'm glad I don't have such a modem at home!

Here's an aerial shot to illustrate how arbitrary soveregnity is. Quick - what part of the above photo is an independent nation of long and undisputed standing, and what parts are just an ordinary city?

Okay, let's try another country. The narrow strip of coastal buildings in this photo is a centuries old (far older than Germany, to cite one example) nation of undisputed sovereignity.

For that matter - I can think of a dozen nations that are a single rifle shot from end to end. You'd have an interesting time explaining why this structure made of coral is an independent nation (more precisely, a disjointed major fragment of an ocean nation -- just as the Sealand photo in the parent post showed only one platform of Sealand)

National jurisidiction is arbitrary. Who will get mad if the UK invades Sealand? The UK courts , who have already ruled that the UK could not assert territoriality or jurisdiction over these platforms. (The British press would have a nice field day with the 'underdog' angle, too. It's funny how stuff like that weakens or topples administrations in parliamentary systems -- it's kind of like counting chad...)

Thanks to everyone for their constructive response. It's looking like NetBIOS-NS "Name Query" probes are being sent by IIS servers that want to log a name in the access log.

This isn't a new discovery, as I discovered here and here. From a security point of view, it's noise that could be masking an attack from the Network.vbs worm.
--
Paul Gillingwater

If you have been reading anything to do with carnivore since the begining of this, you would know that carnivore only listens to specific people, it does not hunt down new criminals, only moniters predetermined suspects. A warrent similar to that of a telephone tap is required to use Carnivore as an evidence gathering tool on someone. The FBI *claims* that Carnivore is not used to spy on an entire network. Mabey this

Well this is kind of a good idea, but you will be happy to know that it has already been done.

The US government spends millions of dollars on supercomputers every year. Some of the computers are for Classified projects, but many of them are for research purposes. These research computers are like a national computing resource. You paid the tax money for them and, if you're so inclined, you can probably use them. If you think you have a project that would benefit from a supercomputer, you can apply for time on one.

If you buy your own Cray you'll be guaranteed time on it, but you'll also be burdened with maintenance and upgrades.

Try these links:

NPACI Allocations

www.sdsc.edu

www.ncsa.edu

"The FBI will always have to live with the legacy of the Hoover era, just as the Congress will have to constantly compare itself with the McCarthy hearings, and the Executive Branch must always remember Watergate. These and other incidents from our country's history have contributed to an unfortunate general distrust of our public institutions when they concern themselves with the rights of our citizens."

All it takes is one power hungry nutball to go after anyone they consider "devient" and you're being tracked by your "warm and friendly" FBI for being a member of the NRA, watching Rosie, or enjoying a cuban cigar.

History is prolog.

http://secureftp.glub.com or http://secureftp.sdsc.edu Go to the websites to get all the info.

http://secureftp.glub.com or http://secureftp.sdsc.edu

A kernel module falls under the GPL. Yes, I know, binary-only modules are allowed by convention, but it still sucks.

You're going to be out of luck should you find a later kernel gives better performance but breaks binary compatibility. Think about proper async I/O, which is coming and can give a handy boost. If you have the budget for Fibre Channel fabrics at some point, at least look at the Global File System.

BTW, if you're going to compare this cluster with a Cray T3E or IBM SP, actually compare them, don't just say they're comparible. The T3E's network is one-of-a-kind, with large bandwidth and almost no latency. (And I certainly wouldn't comare MPI implementations. Myricom's sucks and is causing no end of problems for some other projects.) You can't compare on that aspect with any commercially available interconnect. And there are much larger SPs around and coming, like San Diego's and the second phase of NERSC's.

Don't take this the wrong way. What you've put together is impressive, especially surviving the procurement process, but there's still a lot of work to be done to catch up with the big boys. You know that, but a good many people reading the iterview may walk away with a good-we're-at-the-leading-edge-now impression. We aren't. We're at the cost-effective edge, but we can make the leading edge...

Note that they did not publicize it in any way. They just set up the system and left. Not exactly entrapment.

SDSC honeypot Paul

It really depends what kind of accuracy you are looking for. You can write an engineering level code that solves basic equations for aerodynamic forces, and get first-order accuracy in predicting steady, inviscid, incompressible flow over a two dimensional airfoil at a small angle of attack on a standard pc; you can even get results within seconds if you make enough broad assumptions. However, this will give you very simplified results that are only valid inside the range of the assumptions used. If, for instance, you wanted to solve an off-design screech problem in a modern fighter engine combustor or afterburner, at temperatures outside the range of constant air properties, you would need to solve the full Navier-Stokes equations, probably including unsteady terms, turbulence terms, vitiates, gas chemistry anomalies, airfoil expansion due to temperature gradients (which in turn require complex grid generation/regeneration) etc. Try to do this on even the fastest PC and you will be waiting for years.

Quick example: to complete a full analysis of an 11.5 stage high pressure compressor on a 48 processor HP workstation (180 mhz) takes 50 days! of wall clock time. This isn't even a full engine, just one component. While obviously an extreme, since the code makes literally no assumptions (within the limits of human understanding of the physics involved in the problem), it comes to mind immediately as an example of the level of complexity involved in calculating any problem, whether it be molecules of air or sub-atomic particles, to the degree of accuracy required by modern scientists/engineers. Disclaimer: I am not completely familiar with the specifics of this code because it is/was a NASA Glenn project. I saw the tail end of a paper presented for it back when it was still Nasa Lewis... I have a copy of the paper, somewhere, but it escapes me. If I find it I will post the TR# and you can look it up at a tech library somewhere.

I have never used the x-planes program you mentioned, but from looking at it I believe they can probably do what they claim. They aren't really claiming a lot, however; the real applications for high performance computing are in high order engineering and design for detailed performance analysis. Engineering level analysis is pretty simple and their level of detail could probably even be accomplished with table look-ups.

Rev Neh

Mary Annings was born in 1799, I believe. Her discovery of the Ichthyosaur, at Lyme Regis, was in 1811. As for what she's doing now, not a lot, I'd guess. :)

All of her discoveries were made at the beach of Lyme Regis, which has blue-green mud cliffs. These cliffs house an amazing collection of fossil treasures, but are extremely dangerous to approach. (Mud slides are frequent - as in every few minutes.) However, this has the advantage that new fossils are forever being brought out to the surface. It's a rare day that you can't walk along the beach and find a hundred or so fossils of every kind. And there's always that chance that yet another new species is in there, somewhere, waiting to be found.

Some resources on Mary Annings:

• Summary of Mary Annings' life
• Mary Annings' Treasures (book)
• Mary Anning's Dinosaur Discovery (book)
• Ichthyosaurs - Virtual Classroom
• Pleiosaurus

i go to uc san diego, and for the most part, have been very happy here. you get a balance of theory and application which is nice. the programming is bent towards unix, although the computer graphics courses are taught on windows. the higher up you go in the courses, the more interesting things get. whether it's networking, parallel programming, computer security, or even the dreaded compiler class, you will leave ucsd with a good background in today's technology. in addition to learning c/c++, java, and perl in a variety of classes here, they also have a comparative languages course where you will learn others (my quarter it was python, ml, and prolog). another nice thing about ucsd is the fact that the san diego supercomputer center is on the campus. so, if you are bored with you cirriculum, you can at least go and play on the crays.

Here's some bugtraq discussion on removing the execute bits from the stack. A nicer reference in some senses is this fine paper describing a lot of technical details.