(Scott Adams has said this is his all time favorite Dilbert cartoon.)
Posted on 12/19/2017 10:51:15 AM PST by nickcarraway
All 500 machines on the TOP500 supercomputer list run Linux. Here’s how the little OS that could, did.
After years of pushing toward total domination, Linux finally did it. It is running on all 500 of the TOP500 supercomputers in the world, and who knows how many more after that. That’s even more impressive than Intel’s domination of the list, with 92 percent of the processors in the top 500.
So, how did Linux get here? How did this upstart operating system created by a college student from Finland 26 years ago steamroll Unix, a creation of Bell Labs and supported by giants like IBM and Sun Microsystems and HP, Microsoft’s Windows, and other Unix derivatives?
Also on Network World: 5 top Linux server distros for enterprises; 10 of the world's fastest supercomputers It was a confluence of things, all of which aligned perfectly for Linux. For starters, the Unixes were fragmented and tied to vendor processors. You had AT&T, through its Bell Labs arm, licensing Unix System V to vendors who then made their own specific flavor. Sun Microsystems made Solaris, IBM made AIX, HP had HP-UX and SGI had IRIX. None of them was compatible, and at best, porting required a recompile if you were lucky. “There wouldn’t be Linux if it weren’t for Unix,” said Steve Conway, research vice president for Hyperion Research, the high-performance computing (HPC) unit of IDC. “The Unix era gave way to the Linux era because Linux is more open and not vendor-specific. So, here was a chance with Linux for the whole community to have one main flavor of an operating system.”
None of the major Unix flavors supported the x86 architecture, either. Sun did with SunOS, which was a text-based OS, and it had Solaris on x86 but never made a big push for it. All the other Unixes were on custom RISC processors. Of course, no one saw the massive rise of x86 on the server, either.
Prior to Linux, the only heavily supported x86 Unixes out there was The Santa Cruz Operation with Xenix and FreeBSD out of the University of California at Berkeley. But Xenix was a desktop OS, never a server OS. By the time it sold out to Caldera Systems in 2001, its opportunity had long since passed and Linux was already gaining momentum.
Then there was Microsoft. It came out with clustering software as early as Windows NT 4.0 but made its first real effort in 2006 with Window Compute Cluster Server 2003. However, it never made much of an effort in that area, and by this decade it had folded some of the clustering technology into standard Server edition.
“For their part, Microsoft took aim at HPC for a couple of years but didn’t put a lot of wood behind that arrow, as it were,” said Conway. “They weren’t alone. It didn’t seem at the time that the HPC market was going to be as big as it became. This was the pre-cluster time, for the most part. Up to the 90s, the HPC market was worth $2 billion, with everything thrown in. Last year it was $22 billion.”
NASA helps HPC take off What made HPC take off? NASA, whose job is to explore space, made an amazing Earth-bound advancement. In the mid-1990s a team of programmers came up with a way to cluster x86-based servers for collective processing power for a cheap alternative to expensive, proprietary HPC systems at the time. Dubbed Beowulf, it was not tied to one particular operating system, any free and open source OS would do. But the inventors used Linux, and that started the momentum.
Sponsored Post Sponsored by Daikin 5 Ways to Curb Costs in Your Home
The first step to saving is to conserve energy! Here are several ways a new HVAC system can put money back into your wallet.
“What really carried Linux more than anything was the arrival of the cluster in around the year 2000,” said Conway. “That’s when clusters really entered the HPC market and the appeal was commodity technology, including Linux. Through the decade, the HPC market grew at a compound rate of 20 percent.”
Beowulf supported FreeBSD, so why didn’t FreeBSD take off? Conway attributes it to being one of those technologies that was a very good idea but just didn’t catch hold in large part because they weren’t promoted very well.
Linux has something FreeBSD doesn’t have: Linus Torvalds. Torvalds is a tough, demanding leader. Many say too tough. He has a nasty streak that can put Steve Jobs to shame. But he has been the leader Linux needed.
Vendor support for Linux The final piece of the pie was vendor support, something FreeBSD never had. Linux had organized companies behind it. I remember attending a computer fair in Hartford, Connecticut, in 1993 (where all the local screwdriver shops would set up tables and sell components for system builders) and seeing Bob Young hawking CD-ROMs of the very early versions of Red Hat Linux. Boy, if I had known then what I know now…
Anyway, Red Hat took off and helped drive Linux in a way UC Berkeley never did for FreeBSD. Eventually came Caldera, SuSe and Canonical. Then came the big dog: In 1999, IBM announced support for Linux. At that point, Unix was a dead OS walking. It just didn’t know it.
Linux, and Linus, didn’t get here alone. It stands on the shoulders of AT&T/Bell Labs, Dennis Ritchie, Ken Thompson, Keith Bostic, Richard Stallman (yes, I must give credit where it is due, however annoying he can be), Sun, HP, IBM, SGI, and many more characters and vendors. But it really does stand tall.
It came to dominate because it is made of Unix.
Exactly. No matter how big a business you are, there is always room to go cheap.
Well, he’s probably stupid, and a liberal... because only half of that statement makes sense.
I LOVE that programmers are willing to write code for free and put it out on their own for the world to use, but most of what I’ve seen as ‘open source’ was built while someone else was paying their salary- and would not have been pleased to know about.
But usually these types are liberal dweebs, and so I question their intelligence, and then the intelligence of the code they write.
(Scott Adams has said this is his all time favorite Dilbert cartoon.)
No kidding.
Don’t give money to the guy who changed the whole world.
That bastard.
I don’t care how many employees you have in a country it does not make sense to give something of value away.
But of course, it could have been a behind the scenes “give it to us or else” sort of thing.
Me in that situation I would have said to China; Bye Bye; If we leave and tell people why, see I you can get anyone else to come build in your gulag of a country.
Eh? that's way more than was claimed. Again, many of those claims were made in the original suit, only to be defeated. I remember SCO claiming Streams was copied and instead it turned out Linux Streams was a loadable kernel module supplied by a third party - in other words not part of the Linux Kernel itself.
There was no conspiracy or treason involved in chinese use of Linux. It can be reasonably argued that everyone who used and contributed to cluster computers benefited equally from the result, and there would have much less benefit to the world overall without the open source component. Certainly proprietary supercomputer OS have fallen off the map. However proprietary and specialized compute engines are exceptionally able to capitalize on the standardized infrastructure, witness the growth of GPU clouds which are manifestly more capable of compute tasks than x86 cpu clusters.
Oh sure it does. IBM sells hardware and software support. Operating systems are economic compliments to both. One of the most basic business strategies is commoditizing your compliments. For example, Ford Motor Company would never have gotten off the ground if gasoline, oil, and rubber tires had not become relatively cheap. IBM was just trying to commoditize the OS. BTW that's what they were doing when they let Gates keep control of MSDos way back when. That didn't work out so well for them, but the Linux strategy has been a winner.
I've never been able to figure out just what Sun Microsystems thought they were doing when they indroduced Java. Java commoditizes the OS and the hardware, which were Sun's two main lines of business. From my perspective, Sun put themselves out of business.
Geek-Out Warning!!!
In school I played with BSD on Vax750s (CompSci dept,) and System III & System V on 3B2s and 3B20s (EE dept.) After I left school in late 1986, I went to work for a DB coding company, developing databases and applications for businesses and realtors, on Altos systems running Altos Xenix. The "hot" system back then was the Altos 2086 (80286 system, with 4MB RAM and 40MB hard drive. I was able to get a used Altos 586 for myself (10MHz 8086 w/ 1MB RAM, also running Altos Xenix) and upgraded the hard drive to a used 20MB for only another $1000.
In 1988 or 1989, I picked up an Everex Step 20-386, loaded up with 2 MB RAM, and I replaced the hard drive controller with a WD1006V-SR2 RLL 1:1 HDC and a Seagate ST-4096 (120MB) and Mitsubushi MR-535 (65MB!) And I loaded it up with this:
(not my image, but I still have memories of the pink, yellow, or blue activation key pages in the manuals!)
I remember setting up a 4MB system for a company, and a couple of their people needed Lotus 123, so we sold them SCOs VP/ix dos emulator, and they were able to run Lotus on their character terminals! Another company needed additional software, including database applications they'd been developing for MS Dos, so they bought SCO Professional, which included Lotus and FoxBase, as well as some office automation software, like email and word processing (remember, this was all done on character terminals!)
In the late 1980s, the "SCO Forums" were a blast, Doug and Larry Michaels really knew how to throw a party!
It was a really terrific OS, allowing small and even medium size companies to run their businesses on what today seems like stone-age hardware. Years later, there was a retailer that bought a DEC multiprocessor 486 system, using SCO Unix MPX, with 4 x 80486 processors, 64MB RAM, a DPT Caching SCSI HBA, 2GB HD storage, and 128 serial ports. They ran the PICK OS on top of SCO Unix, as well as the SCO office automation applications, with about 30 serial POS stations (each with its own muxed printer, at multiple locations, via leased lines and MultiTech StatMuxes,) 60 or so serial terminals, and 10 or so shared printers. And it was FAST!
Geek Out terminated.
Mark
Incorrect. Most large universities and companies require vendor support. Initial cost is a secondary concern.
Incorrect. Linux is POSIX-compliant, like Unix, but Linux is not Unix.
He was entertaining during that time, though.
Can you imagine what 25,000 Windows licenses would go for. Plus, if you’re simulating a nuke, “Blue Screen of Death” takes on a whole other meaning.
Gnu?
Wow. After all this time, you’re still pushing this crapfest.
Completely wrong. My main argument was and is still is 100% correct - that China would become the world's leading supercomputer state, based on free technology given to them by the US by way of Linux and open source software.
An argument that you agreed with me in private e-mail conversations, I might add. Surely you still have those messages, but I can forward them to you if needed.
And I've been here quite regularly ever since. I just focus more on national security issues, when the tech threads like this are more devoted to the advancement of tech itself than how it can and will be used against us.
I highly doubt that.
Here’s one of your messages, which you should still have unless you manually deleted it:
From ShadowAce | 02/09/2005 9:55:20 PM PST
No problem. For what it’s worth, I semi agree with you. However, I also see that the horse has left this barn, and also that Linux isn’t complicated enough that the Chinese couldn’t study the POSIX specs and build one themselves.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.