Procket Gets Unstealthy

After four years in stealth mode and $272 million in funding, Procket Networks Inc. is finally ready to talk.

With big names like routing guru Tony Li and former Sun Microsystems Inc. (Nasdaq: SUNW) executive Bill Lynch on board, there has been much speculation about the company. Some said it was building a huge core router to take on Cisco Systems Inc. (Nasdaq: CSCO) and Juniper Networks Inc. (Nasdaq: JNPR) (see Procket's Strategy Taking Shape). Others said it was building an edge router (see Is Procket Heading Toward the Edge?).

The company is actually doing both. Each of the three boxes in the PRO/8800 series has the capability of being either an edge router or a core router, depending on what software is loaded onto it.

“The power of the product is that the same DNA is used across the whole portfolio of products,” says Randall Kruep, CEO of the company.

He claims the main differentiators lie in the company’s unique approach to developing its software and hardware.

Having helped develop routing software at Cisco and Juniper, Tony Li, Procket’s main software architect, avoided some of the problems that currently limit those routing codes today, according to Kruep. For one, Procket avoided off-the-shelf software code, such as Gate D or BSD. Instead, Li and his team developed source code from scratch. As a result, the company was able to put each routing function, including individual routing protocols, onto its own processes.

The modular software code offers many advantages, says Kruep. It provides carriers flexibility in terms of which features to add and when. And it allows them to troubleshoot software bugs more easily. It also ensures an easier and stabler environment for loading software upgrades.

According to Network Strategy Partners LLC, in-service software upgrades account for 22 percent of network downtime per year. This is because most routers -- namely Cisco’s -- run monolithic software code, which means every function runs on the same process. Whenever an upgrade or patch is needed, the entire IOS routing code is reloaded onto the router, which often causes other parts of the software to fail.

“Upgrading a Cisco router is like trying to fix the engine of a jet while it's still flying,” says Dorian Kim, director of IP engineering and network development for the global IP business unit of NTT/Verio Inc. Kim and his team have been testing Procket’s software for almost two years. Verio is still evaluating the Procket gear, says Kim, but because it likes to dual-source vendors, it has already deployed Juniper T640 routers in its core (see Juniper Goes Terabit With the T640).

Juniper’s software, Junos, is semi-modular in design, but Procket contends it didn’t modularize far enough. While it has separated some of the routing functions onto different processes, it still has bundled individual routing protocols together.

Another major software difference is that the Procket code is completely portable, meaning it can be loaded onto other IP devices. The company already has plans to port the code to strategic partners. This is a completely different strategy from that pursued by Cisco and Juniper, which do not share code with anyone. What’s more, Procket's software is self-monitored and can fix minor problems without bringing down an entire device.

The company has also taken an innovative approach to developing hardware. Instead of burning the routing functionality and features into ASICs, the company has leveraged Very Large Scale Integration (VLSI) microprocessor technology to build high-speed packet processors. Unlike the older generation of network processors, VLSI microprocessors are highly integrated, allowing for packet processing speeds up to 40 Gbit/s on 40-byte packets.

Procket attributes this performance gain to the fabrication process used in developing VLSI chips. It allows more transistors and memory onto chips than is possible with current ASIC designs.

Because VLSI microprocessors are completely programmable, adding new features can be done much more quickly. The current ASIC development cycle is about 18 months. VLSIs can be programmed within days or weeks.

Procket’s platform comes in three sizes. The single-slot PRO/8801 router is shipping now. It offers 80 Gbit/s of total capacity and can support up to 40 high-speed interfaces in an eighth of a seven-foot telco rack; it starts at $65,000 for a base system. The 12-slot PRO/8812 routers will ship in the second quarter of 2003. It features 960 Gbit/s of total capacity and can forward 1.2 billion packets per second; it's priced at $237,000 for a base configuration. The four-slot PRO/8804 will be available later this year. All PRO/8000 Series routers support a wide range of interfaces, including OC3c, OC12c, OC48c, OC192c, Gigabit Ethernet, and 10-Gigabit Ethernet.

So far, Procket has been getting traction with customers. Kruep claims the company is in trials with 20 carriers throughout the world, and it names three customers: NTTPC Communications Inc., NTT/Verio, and PacketExchange. But some experts are skeptical that carriers will really bite on the company’s claim that it can lower capital and operational costs by 65 percent.

“The techie in me loves what they are doing,” says Dave Passmore, research director at the Burton Group. “But when I put on my business hat, I’m concerned whether their differentiators will really matter enough for service providers to migrate away from the Ciscos and Junipers of the world.”

Indeed, it won’t be an easy road for Procket, taking on the two Goliaths of the IP routing business. The core router market, which Procket will target first, is relatively small. In 2002, core IP routers generated $1.4 billion in revenue, according to Dell'Oro Group, the market research firm. That’s only about 2.9 percent of the entire worldwide carrier capital expenditure for 2002. Compare this to spending on optical and Sonet gear, which made up 30 to 40 percent of total capex. Even during the Internet boom, IP routing gear only generated $2.7 billion in 2001.

Other startups -- like Pluris and Ironbridge Networks -- that have tried to take on Juniper and Cisco have failed miserably. Even public players have found little success against them. Foundry Networks Inc. (Nasdaq: FDRY), Lucent Technologies Inc. (NYSE: LU), and Nortel Networks Corp. (NYSE/Toronto: NT) have all cancelled their core routing products. And Alcatel SA (NYSE: ALA; Paris: CGEP:PA) and Avici Systems Inc. (Nasdaq: AVCI; Frankfurt: BVC7) have gained little marketshare over the past several quarters.

Coincidentally or not, another core router player, Caspian Networks, is also coming out of stealth mode today (more on that later).

— Marguerite Reardon, Senior Editor, Light Reading

Page 1 / 11   >   >>
indianajones 12/5/2012 | 12:12:13 AM
re: Procket Gets Unstealthy Looks like Procket sends a Rambo along with their systems to insert/pull cards from their chassis. Clearly, the connectors shown in the pictures imply an insertion force of ~ 100 to 150 pounds and the cards do not seem to have any ejectors of any kind. Please do not tell me that you need some kind of tool to pull the cards out. That is such a non-starter with carriers!!!
lawsofphysics 12/5/2012 | 12:12:45 AM
re: Procket Gets Unstealthy Sure you can create a burst onto one port for a non-blocking type test. A simple bernoulli distributed input traffic can create a significant burst if you run long enough. In fact that is the best test for true non-blocking behavior.
tsat 12/5/2012 | 12:13:56 AM
re: Procket Gets Unstealthy If you want your router to be an edge access
device, which Procket claims, you need extensive
L2 functionality... Cisco/Juniper usually does
this in their line cards. Can Procket do it
just in their NPU?

signmeup 12/5/2012 | 12:14:03 AM
re: Procket Gets Unstealthy I think that you are confusing the differentiation between L2 and L3. Procket obviously wanted to raise the bar for the current generation of Internet core routers by adding reliability and scalability. IMO this is what CSCO and JNPR should have been focusing on - if they had done what they had been claiming for years, there would have never been a market for Procket or any other HA startup in the core space.

I'm pretty sure that Procket doesn't want to make cheap L2 boxes to compete with F10, Extreme and Foundry. Nothing I have read so far regarding their hardware or software appears to be positioning for that. What remains to be seen is how much mileage their VLSI chipset gives them in terms of features and futures. Look at the slides on VLSI from this Japanese site (posted earlier about 2 months ago on LR):

It shows that the PRO/Silicon chip set consists of 6 processors, ranging from 30.5 to 214 million transistors. The average count is ~121 million transistors. Another slide shows the Terabit Switch Engine and the Adaptive Packet Processor in relation to some competitive processors. Correct me if I am wrong, but isn't ~121 million transistors per processor enormous?

It certainly sounds like a lot of development time and effort went into this PRO/Silicon chipset; I would be suprised if they didn't take future requirements into account when they designed it. Then again, perhaps I'm just an optimist who would for once like to see a company do exactly what they have promised, without all of the excuses and delays.

tsat 12/5/2012 | 12:14:04 AM
re: Procket Gets Unstealthy >Procket's NPU design seems to be capable of taking up >the gauntlet for such a task. Now if they can provide >channelized OC-3/OC-12 media adapters with T1/E1 >MLPPP, PPPMux, RFC2508/2509/3095/3241 support and >SONET/SDH APS at a reasonable price point, we would >love to buy 50+ boxes a year.

Thats the real question about procket. Is there NPU design
capible of complex layer-2 functionality along with the
layer-3 functionality? For example, can they do ethernet
VLAN, accounting, queueing, ect just by reprogramming
their NPU? Nobody knows. Nobody knows how many
functions their NPUs can do at line rate. I would not
invest in Procket products until I was confident I fully
understood their "new services by just reprogramming
the NPU" claims. It sounds real nice, but without hard
data and proven examples... sounds risky to me.

indianajones 12/5/2012 | 12:14:11 AM
re: Procket Gets Unstealthy tmc1,

My point was to refute your observation that speedup can solve issues in crossbar architectures. As Nick himself has admitted, real-systems behave very differently compared to theoretical results. I have no position on whether it is cheap or expensive to build a switch with 4x speedup. All I can say is that a 4x speedup would be better than a 2x speedup, though I agree with simpleton that if T-640 had only 2x speedup, its performance would be awful.
tmc1 12/5/2012 | 12:14:12 AM
re: Procket Gets Unstealthy Arbitration and scheduling is a different issue. distributed/output scheduling can help.

however if speedup does not even help as nick says then why would anyone (Juniper) create an expensive 4x speedup fabric.

simpleton and indianajones, this would still be an order of magnitude higher than any other speedup out there. when you are talking about 320 Gbps on the T640 - it means you have to have a fabric that is doing 1.2 Terabits internally. The data path size and frequency are still extremely difficult and expensive at that amount of speedup with that throughput. i honestly don't believe that there is ANY production fabric with more than ~2x speedup.

show me, i am from missouri.

He has written a paper in SIGCOMM2002, August which further re-emphasizes this point. In fact, in that paper he has come out and said that Virtual Output Queued architectures (even with switch speedup) cannot offer any predictability and no delay, bandwidth or loss guarantees can be made. I can send you a pointer to the link if you so wish.
DocGonzo 12/5/2012 | 12:14:13 AM
re: Procket Gets Unstealthy "I agree that strenuous real-world testing is crucial, but if the software has actually been cooking for 2 years I would expect that it would be pretty solid - anyone one who has worked with it care to speak up?"

I don't have first-hand knowledge of the code. However, I will point out that the code was likely provided early on to potential customers on a PC to help test it. Usually this testing is done in the lab and very innocuous roles in the network (peering router). Since the PC is limited in available interfaces and performance the code really can not be deployed in a serious way until the hardware arrives. My guess is that the actual hardware platforms probably didn't hit customer sites until about six months ago. So there is really not much serious deployment experience of either the code or hardware.

SP's have differing rules for pre-deployment experience prior to their roll out of new stuff. If my assumptions are correct, I suspect that you will not see any major deployments in the next few months unless someone is desperate or likes living on the edge. Major outages caused by router/code failures brings a storm of PR to the SP; and none of it positive.

Procket will be quite busy over the remainder of 2003 trying to gain some momentum in the market. They also will be challenged to make every customer deployment successful and eliminate the skepticism inherent with new stuff.

simpleton 12/5/2012 | 12:14:14 AM
re: Procket Gets Unstealthy andropat says:
"and another thing.. embedded software in my opinion is much harder than a routing protocol."

IMO: Both are hard in a box of this size - different issues. Scaling, performance, stability and features are major issues for the protocols, while, for embedded work, keeping a large system working seamlessly as one and dealing with bezillion conditions in timely manner on a variety of pretty complex hardware (various blades) are the key issues.
simpleton 12/5/2012 | 12:14:14 AM
re: Procket Gets Unstealthy tmc1 says:
"i am no expert on switch fabrics but i would say your understanding of switch fabrics is very wrong. i really doubt that juniper has a 4x speedup on the t-640 xbar. most speedup is in the 1.2x - 2x range as it is difficult, expensive and usually unnecessary to do more. read anything by nick mckeown from stanford to understand."

It was difficult back in 1989. Juniper started working on T640 around three/four years ago. A year ago, I derived my info from Juniper's docs about T640 Architecture. If any Juniper people are reading this, maybe they can confirm/deny that the T640 crossbar has a 4X speedup, meaning, each switching element in the crosbar can switch 40G. BTW, go read Nick's paper that "indianajones" referred us to - you will know what I am talking about.

tmc1 says:
"secondly, oversubscribing an egress has NOTHING to do with non-blocking behaviour. non-blocking simply means that traffic sent across the fabric in a full mesh will pass at wire-rate without drops. every box ever created is blocking when you oversubscribe the egress. you just cannot get 11 Gig or more out a 10 gig interface... DUH!"

I was not referring to oversubscription, but "bursts" into the same egress port. That is why I said 30 uS (micro seconds). 30 uS @ 10 bits/nS (oc192 line rate) translates to 30*10**-6*10**9/8 ~37 KB burst. This is not much. It is entirely possible that certain number of ingress ports burst into the same egress port at the same time. This blocking will occur on the ingress port - meaning, some ports may see better performance than others. This leads to least common denominator "gaurantees", if at all, to all sources.

Anyways, this is not about Juniper or crossbar. Procket claims to have Shared Memory architecture. I believe the key to the performance of this box is the switching part - lots of companies have solved the NPU side of the story. More light on the switch is what I would like to see. So far, nothing is forthcoming.

Page 1 / 11   >   >>
Sign In