Slashdot Mirror
Killer NIC Hands-On Testing
basscomm writes "IGN has gotten their hands on the 'Killer' NIC recently mentioned here on Slashdot and have written a two part article detailing their impressions: 'The performance boost we got out of the Killer NIC in this testing exceeds Bigfoot Networks' own claims of 10-15% gains by a long shot and certainly seems to validate the potential of the technology. We suspect, however, that the fact that these computers were marginal at running F.E.A.R. in the first place had an impact in the comparison. In many cases the non-Killer NIC machine became absolutely bogged down as particles flew and grenades exploded, enough so that the entire machine would hang for a moment as things got sorted out. Obviously this murdered average fps figures.'"
Killer NICs, hanging machines, framerates getting murdered ... oh, Jack Thompson, you were right all along!
there is no need to sign your posts. this isn't usenet. your username is right there above your post. stop it.
I've gotten so used to plain-jane NICs I never knew there could be anything else -- but at $279.99, I think I'll be able to live with a longer ping time. At least until I have the cash to build my ultimate b0x0r of DOOM!
(It's never too late to join the Renaissance)
Not to flame, but seriously, are these jokers serious?
Since the card runs Linux would it REALLY be that hard to have it intercept incoming 'ping' requests and respond from it's TCP/IP stack immediately, thus lowering the ping time if your CPU is under load?
My bet is it does what I suggested, then proceeds to pass the response to the OS TCP/IP stack and intercepts the response and disposes of it.
I can't believe people still buy this Snake Oil.
I would have never guessed that the "Killer NIC" really did that much. Impressive, but worth the price tag? I couldn't justify it.
The article is nothing but a slashvertisement. But, if you want a _real_ NIC killer, here you go.
The creatures outside looked from Alt-Right to Antifa; but already it was impossible to say which was which.
Yes it runs Linux...
If you did a double take at the spec's of the Killer NIC's NPU you weren't alone. It's dramatically overkill for common networking processing that the card will encounter. That doesn't mean it's useless, however. Far from it, as a matter of fact. The Killer NIC is actually running an onboard Linux build that handles all its networking duties, and, best of all, is entirely accessible to the end user via console prompt or with what Bigfoot Networks is calling Flexible Network Applications (FNA).
Now, does it run *IN* Linux? Probably not.
This is a pretty cool concept - a self-contained VM in hardware to handle your whole networking stack.
It could have potential security benefits as well, in that it would likely be impossible to use say a buffer overflow exploit in a networking protocol with this card, because the overflow would occur *inside the VM*. All that would happen is your NIC would suddenly die - not *great*, but better than having your machine compromized. The host OS could probably even detect this lockup and 'reboot' the VM on the card.
I'd just buy a gigabit-capable mobo.
/* No Comment */
It works (maybe)
We suspect, however, that the fact that these computers were marginal at running F.E.A.R. in the first place had an impact in the comparison.
Which is why spending 300 bucks on a NIC is such a retarded move. Why not spend that money to upgrade the video card, or add more ram, or do something that's going to bring the level of the machine up a few notches?
The theory of relativity doesn't work right in Arkansas.
The whole point of the thing is **there is no OS TCP/IP stack**.
The whole networking stack runs directly on the card. 100% of all networking load is offloaded from your main CPU onto the CPU on the card.
It is **supposed** to 'intercept incoming 'ping' requests and respond from it's TCP/IP stack immediately'.
wouldn't it be more reasonable to get a more powerful CPU or turn the detail level down? IIRC the manufacturer claimed this thing will give you better ping times (which is why it got branded as snake oil by Slashdotters in first place, you can't reduce the network latency that easily unless it's not really the network that's lagging) but does the ping time really matter when your game is chugging along at 5 FPS?
Justice is the sheep getting arrested while an impartial judge declares the vote void.
Awright, color me ignorant but I'm not finding a whole lot of technical info on this so I'll ask the crowd:
How is this different than any other high-end NIC with onboard processor?
By this I am referring to the high-capacity NICs which have been made for the server market for many years by various companies. E.g. Intel has had a series of NICs for ages which have (if I recall correctly) an onboard i860 CPU, RAM etc and it's own little OS in firmware to offload the number crunching from the OS. (And a damn tiny set of drivers as well since all that code was on the board instead of the driver files).
As near as I can tell this is just like any other of these NICs only somebody slapped some pretty graphics and plastic doodads on it and tripled the price.
Or am I completely off base and this really is a quantum leap in areas other than marketing...?
If you've ever wanted to stab someone with a network card, look no further!
Theres no way this could possibly make any difference in speed.
The test must be flawed. They should have used a seperate 3com nic or something not onboard.
Theres no way that there is a 65% performance gain becuase of the nic card. thats impossible.
I'll just use my special getting high powers one more time...
To quote the article: "Our test computers weren't fully fledged high-end gaming machines, but we don't have two identical high-end rigs, but we made do."
So what IGN is saying is that the Killer NIC performs better on a machine that is not the same as the control machine. IGN's results are entirely invalid. Heck, the little data that is presented isn't correctly formed.
Most people who game are plugged in behind a router, because they're sharing their internet connection. We know this decreases our ping, but what can we do? Well, if this card were itself a router, we might just have our answer! If it had a single LAN port, or maybe four (they'd fit), the gaming computer could be connected directly into the internet, with the rest of the home network behind it. Firewall and other network services could easily run from the on-card Linux. Really, it wouldn't need extra hardware apart from the ports themselves. Other software features could prioritize ping-sensitive packets like VoIP and game stuff, so that my roommate's bittorrent doesn't interfere with FEAR.
One disadvantage would be that the gaming computer would always need to be turned on for the router to do its job. Or maybe not: the card could have its own 12V plug and get its own power, so it stays on 24/7 even if the hosting computer is turned off. I expect this really could significantly improve ping numbers (vs standard NIC behind a router) plus it would be seriously cool.
Well, the result certainly is interesting, but I don't really trust their conclusion. If anything, they are showing what an onboard NIC tacked on for about $1.50 is really worth. I agree that it would be quite a bit more interesting to test the performance against a decent dedicated network card, many of which do quite a bit of offloading as it is.
It's also worthwhile to note that the card is bundled with F.E.A.R. and arguably biased towards it -- perhaps the game has code to better take advantage of the capabilities of the hardware or god forbid artifically cripple itself if not running with the hardware. It certainly wouldn't be the first time we've seen such a claim, with the PhysX drivers showing faster performance in software-only mode on very new, very fast cpu's despite a game generally refusing to run with the added physics settings without the hardware.
Looking at the driver disk it looks like a lightscribe disk or something. Anyone have any idea if this is pre-release package or if that is how the disk actually looks?
The idea itself is interesting, but I think the most interesting part is that it has a usb port and can theoretically be programmed to do certain other non-gaming tasks. Unfortunately it would probably have to catch on before any interesting hacks turn up for it. It doesn't seem likely catch on though unless they reduce the price at least by half.
http://www.popularculturegaming.com -- my blog about the culture of videogame players
As you noted, getting a better video card would be the more intelligent option.
But, the PRIMARY problem is that they're running the test on two different machines. Even if they're the same make/model/etc, it doesn't matter.
Another item is that you SCRIPT the test. You don't play the game itself.
And, finally, related to what you were saying, you get a machine that does not have trouble running the app in the first place. Upgrade the video card, get a better processor, OR RUN A LESS DEMANDING GAME!
And put a SNIFFER on the network to find out what is happening on the wire. If we're talking a hub, a card that spews packets is going to outperform a card that obeys the protocols if they're played on the same network.
This "review" reads like a crappy ad for that card. There's no real information.
What strikes me odd is that (in my ignorant opinion) a hardware TCP/IP stack should not be too hard to implement. This thing is heavily overpriced to try to get money from ppl who will throw $500+ at a GPU; so if it does work I imagine that several NIC manufacturers will start offering the feature at a much cheaper price. So... wait & see...
The ENIAC Demo Competition
...for this:
"The Killer NIC also has its own USB 2.0 port, which expands its capabilities even more. A BitTorrent client designed for the NPU could run on the card and use an external USB hard drive for storage, which would make it invisible as far as Windows is concerned. Thanks to the Killer NIC's traffic prioritization capabilities, users will conceivably be able to play the most demanding games while using extra bandwidth for BitTorrent, without any performance hits due to BitTorrent CPU load or hard drive access."
Mmm...invisible bittorrent...
Sounds like it has a more complicated setup (running Linux and all) but I doubt it's really much different from an Intel server NIC.
What a joke. Stick to reviewing games, IGN.
I'll wait for a proper review from Anand, Tom's or Ars, which will show this NIC as the snake oil that it is.
nforce 5 boards do the same thing as this card does.
That's what I would expect.
Essentially, in this "test", they chose a system with (accidentally) had a specific set of bottlenecks (on board NIC, under-powered graphics card, under-powered CPU, intensive game) and then tested against a similar system with a card designed to compensate for some of those bottlenecks.
Amazing how that works.
"What about the snake oil of being incredibly self-important without reading the article and blithely dismissing the product?"
And that's different from the MPAA/RIAA/Microsoft stories, how?
"You know, this whole "I'm holier than thou without even reading the article" bs on slashdot is getting really tiresome(I have fallen into the same pit many times myself, I know) It really does inhibit intelligent debate about the article and just makes people feel so much more pompous(as evidenced by frequent use of such words as "snake oil") Oy...."
Better than "olive oil", which just makes one sound like a salad dressing salesman.
With Vista's CPU hog of an interface, I might just need this...
I've been trying to discern meaning out of the numbers for quite a while with no real help. Logically a chart for a controlled experiment should have a comparison between the control and experimental data. The chart though only has one set of numbers for ping and one for fps. I noticed that some of these numbers have minus so I suspect these are differentials. Any clue then as to what the colors mean? I noticed that negative numbers appear in red and green but not blue. Im not sure what that means though.
And according to the description that IGN made, that's also how the Killer-NIC handles the problem :
- it's basically a small linux router that it shrunken to fit inside a PCI a card and drivers that directly tap network traffic from Windows before it even enters inside the win32 TCP/UDP stack.
- it's not supposed to magically make the *network* faster.
- it just hopes to that the onboard linux will be better at *prioritizing packets*, than the Windows host, which will have to cope with traffic originating from the FPS game, from the bittorrent-based update system of the game, the separate voice-chat software that the player uses to communicate with his team, the separate IM software that is still running in background (updatin its ads, and maybe finishing to download that funny picture that a buddy just sent before), microsoft's own updates, another P2P-client used to download stupid stuff from the net, a whole bunch of spywares/trojans running hidden, and a TCP/IP stack completly overloaded with a horribly complex and long rule-set like PeerGuardian.
- basically it's only doing as much magic as any other traffic shaper on a random *nix box. Except the box isn't on the network but directly diverts data from the Windows network stack (thus avoiding the added latenc of an additionnal *nix box between the modem and the computer).
- it's mostly similar to having one of those linux-powered router/DSL modems, and with great care mannually configuring optimal traffic shaping for gaming.
- for all linux gamers (all 3 of them) who have a nicely configured traffic shaping, this will be identical.
- for users that run their game from a clean environnement (traffic is mostly FPS, almost no other background traffic to prioritize), I doubt any huge imrpovements will be visible.
- for joe-6-packers that buy an AlienWare and except to run games at max FPS, it will probably be very effective at trying to give priority to the game network traffic among all the junk that flows thru the internets' pipes.
- instead of using it for FPS, the advanced power user may be interested on using it's Linux-on-a-card capability either for complex network administration (the embed linux could be used the same way as some server have a small OS embeded into their network controllers, that could be used to do diagnostics on the server) or for additionnal security (a real dedicated linux firewall, but without the added latency of an additionnal box on the network between computer and rest of net) or for low-power network jobs (some people leave their computer ON the whole night to download stuff from the internet. with such cards only the onboard linux and it's usb port need to run, the power hungry CPU and GPUs can all stay off).
So it may be interesting for the
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
Snakes in the Stack
Find a job you like and you will never work a day in your life.
The only problem with an approach like this is that if all these hardware drivers have to run in the kernel, the companies had better write bulletproof kernel code. Fortunately, networking stacks are already pretty bulletproof. Rendering and physics engines would have to get there. Other approaches to solving this problem - userspace drivers, maybe some sort of driver isolation - exist, but these add overhead. But I still think the cost and complexity of writing drivers is much cheaper than developing hardware, and I think some overhead for protection could be paid and you'd still see better performance.
AMD alluded to this convergence in its talk when it announced its acquisition of ATI. It's still 10 years away, but I believe it's going to happen.
If there's an exploit for your TCP/IP stack on the network card, and it manages to compromise your NIC's tcp/ip, then it's still some way off compromising your host machine's OS? Yes/no?
I'm no expert on these things, so I'd be interested to hear from someone who IS as to whether or not it's a useful security measure...
I run: Windows, OS X, Linux, FreeBSD. Just because you have a hammer, doesn't mean everything is a nail.
They did not have an identical computer. They were two different computers, and the one they were comparing against had a super shitty cheapass onboard NIC. Compare two identical computers, and against a real NIC.
I have had to reinstall the netwrok stack in windows quite a few times on various machines because of spyware or viruses that completely hosed any network functionality, I wonder if using this card would remove the possibility of the stack being corrupted or if the kernel/OS the card uses is just as vulnerable?
For 2-300$ it's still not worth it to me, but when the price becomes reasonable it might be something to think about if the embedded stack is not vulnerable to corruption by spyware or viruses...
Try reading the article yourself. They tested it on a CPU bound machine, against a shitty onboard NIC. Any $70 TCP offload Gb NIC will perform just as well as this $300 scam. Yes, its bypassing the OS for pings, and all other TCP/IP traffic. Just like any decent server NIC does.
A TOE is exactly that, a TCP Offload Engine. I tis not a replacement for a networking stack - what it does is assists in the constructoion and destruction of packets in the TCp protocol. it doe snothing for other protocols, such a UDP, ICMP, IGMP, etc.
This card is a complete top to bottom stack (as complete as Linux's stack is, since it *is* Linux's stack). The host OS's networking layer is totally bypassed and all commands are given to the card's stack. It's not really the same thing as TOE at all.
Damnit no wonder the lights went out. I thought it said NIC Killer.
It's an IGN article after all.