Slashdot Mirror
BusinessWeek On XORP vs. Cisco
cornfed writes "BusinessWeek is running this article talking about how XORP will take on Cisco's dominance in the router market. The article speculates that XORP could represent the next 'open-source rebellion.' One can only imagine the fallout within the telecommunications industry if an open-source project like this gained traction-- Cisco would not be the only giant to be slain."
Because XORP is more fun to say.
The result of XORP & similar technology will be a decentralization of networks. If you look at a typical enterprise network, the backbone of that network will be a single "enterprise" (ie. expensive) Layer-3 switch from a company like Extreme, Foundry, Cisco or whatever.
Those switches are cost-effective because of the needlessly high cost of low-end equipment.
If supported, flexible & cheap routing becomes a reality, you'll see clouds of cheap-commodity level hardware replace big networking iron... just as Linux displaced Solaris, HP-UX and AIX.
Conformity is the jailer of freedom and enemy of growth. -JFK
Go after the big guy first and the others will be afraid to fight. That worked so well in gradeschool
Here is more about XORP (the Extensible Open Router Platform), for those that don't know.
Cisco is the only company with an employment policy that is worse than the one at Intel. Cisco does quarterly performance reviews; they are strictly by the bell (i.e. gaussian) curve. The bottom 10% are automatically fired without a second chance.
Worse, Cisco has also demanded that it be allowed to hire foreign engineers from India and China. According to Cisco management, it absolutely needs H-1B engineers in order to be competitive and has continued to hire H-1B engineers, never minding that 80,000 Americans were unemployed in Silicon Valley during the 2001-2003 recession.
While it's hardly the first effort to make routing software in an open-source format, it may be the most promising, due to $3 million in funding from high-powered backers such as Intel, Microsoft (MSFT ), and the National Science Foundation.
Okay... anyone else here wondering why and how that came about? Why would MS be involved in such a project? Is the licensing such that MS could siphon the code off for its own use? I'd suspect as much... not that it's a bad thing -- on the contrary, it's quite good -- just not the sort of thing I'd expect from them.
That a bunch of general purpose commodity hardware is going to replace their highly engineered, specialized hardware. Because, you know, I'm sure that businesses of all sizes are *very* anxious to rely on general purpose PC's for their high-performance routing needs.
Don't get me wrong, I think XORP could be usefull in certain applications. I'm currently running Linux on an old Pentium for sharing internet access on my home network, so I understand that for small networks with relatively slow internet connections, general purpose hardware, running routing software, can be usefull.
But I doubt it's going to 'slay the giant'. So much hyperbole in tech journalism these days (oh well, how else are you going to get people to read the article?)
...Timewarp 1997...
You're absolutely correct! What major reasearch lab would ditch their multi-million dollar SGI Origin supercomputing clusters for low cost Lintel hardware?
I can stake my entire enterprise on proven software that costs $15,000+ for a workstation and $300,000+ for a server, or Linux... being a systems programmer for a large company I can say it will never happen.
Conformity is the jailer of freedom and enemy of growth. -JFK
Production networks can't tolerate down time, or waiting for few admins to hack some code and fix some buggy router. So that XORP might be open source, but it has to be commercialized as well.
"Evil thrives when good men do nothing"
It's not surprising that a Berkeley CS researcher thinks his open source project can "slay Cisco", though Ghosh never says anything like that in the article. It might not even be surprising when a Business Week reporter says something so naive, but it is disappointing. Even Linux isn't slaying anyone - it's apple and oranges (or maybe apples and ciscos): XORP might be comparable to Cisco's IOS router operating system, but XORP is hardly comparable to Cisco itself. If XORP works out, and becomes an effective competitor with IOS at any level, Cisco and its actual competitors will just start selling it, bundled with the support, marketing and corporate accountability that people buy when they buy "Cisco". Now if only the BizWeek reporter, Alex Salkever, had realized the compelling story here is Microsoft's funding a million-dollar routing project, and releasing the source as its central development strategy. That would make the Slashdot front page, too, without making Salkever famous for spreading Fearless Certainty, Undoubtedly (FC-U, (TM)).
--
make install -not war
You mean the stuff they got when they bought Linksys? That hardware is completely irrelevant to this discussion, because XORP is intended to replace the high-end cisco equipment, and the stuff they bought from linksys didn't even compete with their own products, with one or two limited exceptions like cisco's DOCSIS cable modem. I don't even know if the linksys cable modem runs linux.
It does seem highly likely that we will see commoditization of the router market. It makes more sense to provide a chassis that takes full-length PCI cards than to require special cards which use a PCI interface anyway. PCI-E is the logical choice since it provides (potentially) more bandwidth than even PCI-X and you could use a wonky form factor if you wanted to, for example blade-type cards that have their connector on the back instead of the bottom. Even using an ordinary rackmount PC form factor, with just 66MHz/64 bit PCI, you could equal or surpass the performance of a cisco router with COTS hardware, provided you had the right software to run it all. Using 64 bit processors over the 32 bit ones found in most networking gear means being able to process IPv6 addresses significantly faster, and most of those systems do not have much processing power because they are proprietary and it's expensive to implement. PC processors are cheap and reference designs are readily available. However, we will need new chipset designs to provide sufficient bus bandwidth.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
FTA: "I don't see open-source routing replacing high-end routers in enterprise or service provider networks," said Dave Passmore, an analyst at Burton Group. "But in the real low end, like in the D-Link and Linksys category of product, free software could be very useful."
Useful, yes. But to how many? I'm not sure that Joe Sixpack could configure a router through a command line. In order to compete with Linksys, Netgear, and D-Link, they will also have to include a real stateful firewall and DynDNS support (which is something that is being included in most retail firewalls now).
Also, if you have to setup a dedicated PC to run this, your average small business or home user isn't going to be interested when they can go to the local superstore and pickup a $59 Linksys that's ready to go, quiet, and small. Unfortunately, this software will not make it to the point where it would be a threat to any appliance-based router builder.
So which "PC components" do I use to implement a modular all hot-swappable (including the supervisory modules) device that would provide me with 16 GE interface per blade, a crypto accelerator, an optional firewall module and whatever else cisco has up their sleeve for the 6500 series? IOS isn't what you pay for when you buy a router, Cisco is a hardware company.
There is NO way software routing can compare to processing packets in hardware. The Linux kernel wasn't designed for this and has problems when faced with a large number of packets. I'll reference the work done by Luca Deri at NTOP.org and his pfring mod. Unless we start seeing specialized open source hardware I don't think Cisco will feel threatened in the least.
Never ascribe to malice what can be adequately attributed to ignorance. -Napoleon
That a bunch of general purpose commodity hardware is going to replace their highly engineered, specialized hardware.
Yes, and SGI probably never thought that PC hardware would drive them out of business either.
Also, only a small core needs to be high performance; hardware vendors can take this kind of open platform, add a small piece of specialized hardware and custom software, and save themselves a boatload of development effort, and their customers a lot of training costs.
- hardware
- that is reliable
- hot-pluggable
- redundant (spare powersupplies, etc)
- and routing software (that's where XORP fits), and
- warranty
- support
- documentation and support materials
- training
- certification / qualifications
- network design / professional services consultancy
- brand recognition
- big reference sites, and a proven track record
- marketing assistance (powered by... kind of stuff)
- accountability
Some of these areas are a real opportunity for third parties, once XORP gets to be a solid product, but the image, brand, reputation, etc will be hard to overcome in the short to medium term. In the longer term, the Linux model shows it is possible (though it's hardly inevitable - it's not the only open router free cisco type project, after all).Still, the marketing side matters less in a tech-savvy small/medium enterprise, or in a consultancy operation. It might get a start there, or in a more cost-sensitive environment.
And open source can even be argued to confer security advantages. It could get interesting...
Paul "Say no to feeping creaturism"
Now admittedly, if they didn't get -any- competent applicants, it might be acceptable to hire an H1B here or there, but those are, by far, the exception rather than the rule, and should be limited to senior engineering positions and only in very small companies. Larger companies, upon failing to find someone qualified for a senior position, should be able to promote someone from within to a senior position and hire someone into a junior position---someone who doesn't require an H1B. There are plenty of new college graduates in the valley looking for work.
Sorry, but there are far too many tech employees unemployed in the valley for your argument to hold weight. Companies in the valley should be utterly fined into oblivion if they are hiring H1B engineers right now in any significant quantity. As to whether Cisco is or not, I have no idea.
Check out my sci-fi/humor trilogy at PatriotsBooks.