Is There a Place for a $500 Ethernet Card?

prostoalex writes "ComputerWorld magazine runs a story on Level 5 Networks, which emerged from the stealth startup status with its own brand of network cards and software called EtherFabric. The company claims they are reducing the load on the servers CPUs and improve the communications between the servers. And it's not vaporware: 'The EtherFabric software shipping Monday runs on the Linux kernel 2.4 and 2.6, with support for Windows and Unix coming in the first half of next year. High volume pricing is $295 for a two-port, 1GB-per-port EtherFabric network interface card and software, while low volume quantities start from $495.'"

Comments

Linux before Windows

[mepperpint]

It's nice to see a piece of hardware that ships with linux drivers and promises Windows support later. So frequently applications and hardware are first supported under Windows and occasionally ported to other platforms.

Re:A look into the past

[bluelip]

I've noticed a slowdown in computer response when using gig cards and moving lotsa' data. I thought the bottleneck may have moved to the file systems. Didn't seem to be the case as pumping dummy data throught the nic also caused issues.

I didn't pursue it far enough to see where where the actual problem was. These cards may help, but my money is on a faster cpu.

spend the money on more CPU, not specialized stuff

[SuperBanana]

. Intel had the 586-driven smart-cards, and I believe 3Com had them as well. They were intended to offload the CPU by putting parts of the stack on the card.

You're probably thinking of the i960-based cards, though Intel's PRO series adapters (not i960 based) do something similar (TCP checksumming is now builtin to the chipset and most OS drivers now know how to take advantage of that). That processor, and variants, were used in everything from network cards to RAID controllers.

They failed because the performance gain and CPU offload numbers were never enough to justify the price difference.

Ding ding ding. I forget who said it (maybe Alan Cox, but I'm REALLY not sure about that), but the opinion was along the lines that it would always be more benefitial to throw the money at a faster processor (or a second processor etc), because you'd get a performance boost everywhere. $300 buys quite a bit extra CPU horsepower these days, and there's no need for the hassles of custom drivers and such. Nowadays CPUs are just so damn fast, it's also not really necessary.

In a word, no

[bofkentucky]

Take sun, some of their new server kit this year is going to ship 10Gbit/s ethernet on the board, which acording to their docs, is going to take 3 USIV procs to keep the bus saturated (6 cores). But when you are looking at 8 to 64 way server boxes, who cares about those 3 procs, especially when in 24-30 months it will take less than one proc to handle that load (Quad Cored + Moore's Law), and the eventually one thread will have the horsepower.

Surely those smart dudes at Via, AMD, Intel, Samsung, Nat Semi, and/or Motorolla aren't going to:
A) FUD this to death if it really works
B) File patent suit until doomsday to keep it locked up
C) Buy them out
D) Let them wither on the vine and then buy the IP.

Re:A look into the past

[__aaclcg7560]

Jerry Pournelle had a column in the February 2005 issue of Dr. Dobb's Journal about Gigabit hardware. If you have a Gigabit PCI card, expect to see a doubling of speed over 100Mb PCI card. If the motherboard has a built-in Gigabit port, you can see a five to six times speed over 100Mb PCI card or port. PCI cards are limited by the PCI bus, but built-in ports have direct access.

Re:A look into the past

[Fweeky]

I expect you can get an Intel 1000/Pro for around $30; full TCP/IP checksum offloads in both directions, interrupt moderation, jumbo frames, and Intel even write their own open source drivers.

Heh, my on-board Realtek GigE chip has checksum offloads too, but even with them on, 300Mbps would have me up to 70% system/interrupt CPU load (and I hear the checksumming is a bit.. broken); I barely scrape 30% with a PRO/1000GT.

Um, no.

[holysin]

If you have a machine (say on a machine running linux kernel 2.4.20-30.9smp) with a built in gig port (say with eth0 identified as eth0: Tigon3 [partno(BCM95704A6) rev 2003 PHY(5704)] (PCI:66MHz:64-bit) 10/100/1000BaseT) connected to a decent gigabit switch, and another machine (same card, same os)with a gigabit card, those two machines will achieve 940Mbps talking to each other (results via iperf, 0.0-10.0 sec 1.09 GBytes 940 Mbits/sec).

However, if you plug a windows box (2000 or xp, didn't have a 2003 handy) with either an add on card, OR built in gig (2000 vs xp) you get a rather less impressive figure of 550-630. Coincidentally, you'll get the same basic number if you run two instances of iperf on the same computer... This tells me the bottleneck isn't the PCI bus, it's the OS. If you can prove me wrong please do so...

Re:A look into the past

[EtherMonkey]

Agreed, but it's even been more recent than the early 90's. The late 90's also had its run of so-called "Intelligent" network cards.

I worked for a large HP/Intel VAR at the time and I we were selling $500 Intel Intelligent Server NICs like they were Big Macs. Then one day one of our biggest customers called in a fit. It seems that his manager asked him to do a quick comparison between a smart Intel NIC and a regular Intel NIC, so he could tell his bean-counters to get stuffed. It turns out that we were NOT ABLE TO FIND ANY SYSTEM OR TRAFFIC CONFIGURATION that would result in higher throughput, lower CPU utilization or lower memory utilization when using the smart NIC.

In other words, the standard $100 Intel NIC (PILA8465B, as I recall) beat the piss out of the much more expensive Intel intelligent NIC with on-board co-processor.

Within 3 months we stopped getting any orders for the smart NICS. In 6 months Intel retailiated by disabling server features (adapter fault tolerence, VLAN tagging, load balancing and Cisco Fast Etherchannel support) on the basic NIC, in an effort to save the smart NIC. When this didn't work they modified the driver so the server features would only work with a re-released version of the "dumb" NIC at a higher price (the only difference between the cheapest and most expensive version was an ID string burned into a PAL on the NIC).

Similiar experiences with earlier cards from Intel, IBM, and others. In every instance I tested, a plain old NIC (not junk, but the basic model from a reputable manufacturer) always outperformed the NIC's with on-board brains and/or co-processors.

Maybe this Level-5 NIC has some new voodoo engineering, but I'd have to see real-world testing to believe it. Especially from a company that apparently intentionally is playing-off Level-3 Communications' name recognition for its own benefit.