BigFoot Networks Killer NIC: Killer Marketing or Killer Product?
by Gary Key on October 31, 2006 2:00 AM EST- Posted in
- Networking
Killer NIC Technology
Hopefully you are still with us after the previous segment as writing it was better than taking a dose of Lunesta. In all seriousness, the technology of offloading network transactions to a dedicated processor has proven to be very beneficial in the corporate server environment. The typical TNIC is designed to handle data payloads that are larger than 8KB and in certain instances will have reduced performance (lower throughput and higher latencies) with smaller and more frequent data payloads in the 1KB to 4KB range. This range is what most messaging traffic, web services, and real-time data applications such as games utilize at this time. TNICs are generally optimized for TCP (transmission control protocol) packets where the vast majority of games today utilize UDP (user datagram protocol) packets for data transmission.
The differences between the two protocols are numerous but we will hit the highlights. TCP has a standard header length of twenty bytes versus eight for UDP. The normal TCP header will contain metric information such as sequence and acknowledgement numbers along with a requirement for a checksum number. UDP packets do not include metrics and the checksum information is optional. In other words, UDP does not provide the reliability, security, or ordering (queue) guarantees that TCP can deliver. The datagrams in the UDP packet may arrive out order or not at all and your system or application may never notice. Unlike TCP, UDP provides no guarantees for delivery or proper queuing, so why use it? The answer is simple: UDP is faster and far more efficient for time sensitive applications such as gaming, and you don't need every data packet to game properly. (I.e., if you miss one packet that says player X is at coordinates (10,10,15) but you get the next packet that shows X at (12,11,15), the missing packet will not seriously impact the overall experience unless of course you missed a shot or took one.) With this simple premise in mind BigFoot Networks decided to take TOE technology and design a TNIC that focused on UDP protocols and latency reduction.
The main technology focus of BigFoot Networks is centered on their LLR technology. LLR (Lag and Latency Reduction) technology that implements a 1-packet 1-interrupt model to eliminate the entire queuing and buffering operations standard NICs do during the packet receipt and transmission process. When in game mode, the Killer NIC will also completely bypass the Windows networking stack which contributes to further latency or lag reductions depending upon the application. When BigFoot Networks discusses ping improvements in games they are not talking about reducing ping through your network or at the server. This is completely out of their control and although their marketing information is not clear about it the reduction in ping comes on the host machine. These reductions come from bypassing the Windows Network Stack while in Game mode. Depending upon the application and packet size there is generally a 1~3ms delay due to system buffering and another 3~10ms delay in the queuing and processing of data packets in the current Windows Network Stack.
What makes LLR work is the NPU (network processing unit) on the card. This processor powers both the Windows Network Stack bypass engine and the 1-packet 1-interrupt model. In short, this NPU gets the normal network transactions out of the graphics path in games. This can result in improvements in FPS (frames per second) and reduced lag. With a standard network card, before nearly every graphics frame is drawn, there is first a check to the server to see if a new data packet has arrived or if one needs to be sent. Checking the server for new data packets can use up processor clock cycles whether or not data is there. Instead of a multitude of interrupts as we discussed earlier, the Killer NIC will receive or send those data packets in a single instruction. The Killer NIC has the further ability of interrupting the game directly when new data arrives. The Killer NIC is designed around reducing latencies and not throughput.
While LLR technology is impressive to some degree we have to temper any enthusiasm with the fact that most games are designed very differently in their handling of network tasks. Some games do not check for new network data on every graphics frame so any FPS improvements will be minimal at best or completely nonexistent the majority of time. Several older games do not use UDP packets so performance could suffer as the Network Stack bypass model is not used and the card must act as standard NIC. The one thing that we have learned during testing is that many games do not report accurate latency (ping rates) so any improvements are not as measurable but at times can be felt do to smoother game play. The basic TOE and TNIC technology still applies to this card and has been proven over the past few years in the corporate server environment. Converting this technology to the desktop with the added spin of improving gaming is certainly an admirable feat but how well does it work? We will answer that question in a few pages but first let's take a look at the obligatory marketing information.
Hopefully you are still with us after the previous segment as writing it was better than taking a dose of Lunesta. In all seriousness, the technology of offloading network transactions to a dedicated processor has proven to be very beneficial in the corporate server environment. The typical TNIC is designed to handle data payloads that are larger than 8KB and in certain instances will have reduced performance (lower throughput and higher latencies) with smaller and more frequent data payloads in the 1KB to 4KB range. This range is what most messaging traffic, web services, and real-time data applications such as games utilize at this time. TNICs are generally optimized for TCP (transmission control protocol) packets where the vast majority of games today utilize UDP (user datagram protocol) packets for data transmission.
The differences between the two protocols are numerous but we will hit the highlights. TCP has a standard header length of twenty bytes versus eight for UDP. The normal TCP header will contain metric information such as sequence and acknowledgement numbers along with a requirement for a checksum number. UDP packets do not include metrics and the checksum information is optional. In other words, UDP does not provide the reliability, security, or ordering (queue) guarantees that TCP can deliver. The datagrams in the UDP packet may arrive out order or not at all and your system or application may never notice. Unlike TCP, UDP provides no guarantees for delivery or proper queuing, so why use it? The answer is simple: UDP is faster and far more efficient for time sensitive applications such as gaming, and you don't need every data packet to game properly. (I.e., if you miss one packet that says player X is at coordinates (10,10,15) but you get the next packet that shows X at (12,11,15), the missing packet will not seriously impact the overall experience unless of course you missed a shot or took one.) With this simple premise in mind BigFoot Networks decided to take TOE technology and design a TNIC that focused on UDP protocols and latency reduction.
The main technology focus of BigFoot Networks is centered on their LLR technology. LLR (Lag and Latency Reduction) technology that implements a 1-packet 1-interrupt model to eliminate the entire queuing and buffering operations standard NICs do during the packet receipt and transmission process. When in game mode, the Killer NIC will also completely bypass the Windows networking stack which contributes to further latency or lag reductions depending upon the application. When BigFoot Networks discusses ping improvements in games they are not talking about reducing ping through your network or at the server. This is completely out of their control and although their marketing information is not clear about it the reduction in ping comes on the host machine. These reductions come from bypassing the Windows Network Stack while in Game mode. Depending upon the application and packet size there is generally a 1~3ms delay due to system buffering and another 3~10ms delay in the queuing and processing of data packets in the current Windows Network Stack.
What makes LLR work is the NPU (network processing unit) on the card. This processor powers both the Windows Network Stack bypass engine and the 1-packet 1-interrupt model. In short, this NPU gets the normal network transactions out of the graphics path in games. This can result in improvements in FPS (frames per second) and reduced lag. With a standard network card, before nearly every graphics frame is drawn, there is first a check to the server to see if a new data packet has arrived or if one needs to be sent. Checking the server for new data packets can use up processor clock cycles whether or not data is there. Instead of a multitude of interrupts as we discussed earlier, the Killer NIC will receive or send those data packets in a single instruction. The Killer NIC has the further ability of interrupting the game directly when new data arrives. The Killer NIC is designed around reducing latencies and not throughput.
While LLR technology is impressive to some degree we have to temper any enthusiasm with the fact that most games are designed very differently in their handling of network tasks. Some games do not check for new network data on every graphics frame so any FPS improvements will be minimal at best or completely nonexistent the majority of time. Several older games do not use UDP packets so performance could suffer as the Network Stack bypass model is not used and the card must act as standard NIC. The one thing that we have learned during testing is that many games do not report accurate latency (ping rates) so any improvements are not as measurable but at times can be felt do to smoother game play. The basic TOE and TNIC technology still applies to this card and has been proven over the past few years in the corporate server environment. Converting this technology to the desktop with the added spin of improving gaming is certainly an admirable feat but how well does it work? We will answer that question in a few pages but first let's take a look at the obligatory marketing information.
Facebook
Twitter
RSS
87 Comments
View All Comments
Gary Key - Tuesday, October 31, 2006 - link
I fully agree the article was probably too long. It was a case of trying to cover all the bases and then some. If we had left out the technology sections and reduced the commentary it would have read better as a basic hardware item. We looked at this as not being your basic NIC review.However, I am sure there would have been comments that we did not properly review the card or provide this same information. Thanks for the comments.
Crassus - Wednesday, November 1, 2006 - link
I agree with the comment above. I would have like an even more expanded page detailing the technology and the roots in the corporate sector. What I didn't really care about was the endless description of the pains it took to benchmark the card.Two things about that:
1. If it was easy, everyone could do it. You (and Anandtech) stand above the crowd for going the extra mile and giving us some added (useful) information. This is usually self-evident and doesn't require elaboration.
2. My firm expects me to get the job done, as, I suppose, it is the same with yours. No one gives a hoot as to all the steps I had to go through to get the job done, unless they offer some added value. Thinking about throwing something out of the window (if you're blessed with having one in your office) occurs to everyone at some point and certainly doesn't hold any additional value - in other words: it comes with the job. If it was otherwise, see (1) above. There's really no need to mention it a couple of times - unless you're reviewing your work instead of the product.
Gary Key - Wednesday, November 1, 2006 - link
I appreciate your comments. I am alawys open to other viewpoints and opinions. What paragraphs contained endless descriptions that in your opinion could have been cut? Email me if you can please.
I agree it comes with the job. The message I was trying to convey was one of total frustration with the product after six weeks of almost non-stop testing. There were several choice words I wanted to use but felt like that statement would be universally understood. ;-)
Sunrise089 - Tuesday, October 31, 2006 - link
I really liked reading the article. When G80 comes out, we can cut strait to the benches, because I'm going to want to know whether or not to buy the card. None of us are going to buy this thing, but we're all enthusiests, so reading about it can still be fun. With performance changes so minor however, adding a little commentrary to spice up the review makes it a lot more entertaining for this reader.Frumious1 - Tuesday, October 31, 2006 - link
I'm in agreement with Sunrise - liked the article and the sarcasm. I can only imagine your pain during the review. Can't believe how many people apparently lack the ability to read and need pictures. "Just give us two paragraphs saying whether or not to buy the card!" Bah! That's what the conclusion page is for, where it's pretty clear the card "works as advertised" which means fractional gains in a few games.Zaitsev - Tuesday, October 31, 2006 - link
"Just give us two paragraphs saying whether or not to buy the card!"The only reason I still read Anandtech is because they do exactly the opposite. In articles like this one and the Conroe review, I think the pages discussing the technology are more interesting than the results. I can't talk from experience, but it also seems that it would get boring for the authors if they just punched out cookie cutter articles for every review.
As for the card, I wouldn't be able to sleep at night if I bought this instead of a Conroe.
michal1980 - Tuesday, October 31, 2006 - link
i can sum in up for you in one line."In most cases the Killer-Nic Does Nothing"
as for windows vista.
it has a total new audio stack that is seperate from the kenernal, so in theory it could run on a core other then the main os kerenal.
Googer - Tuesday, October 31, 2006 - link
FNA is the only thing that makes a killer nic really worthwhile.http://www.extremetech.com/article2/0,1697,2037279...">http://www.extremetech.com/article2/0,1697,2037279...
cryptonomicon - Tuesday, October 31, 2006 - link
Assuming the review quantified "ping measurements" correctly, this thing has a long way to go. If it gave even a consistent 10% faster pings all the time it would be very appealing to pro-gaming. But from those ping charts, the results were truely inconclusive. The side effect of increased FPS was even more significant than any ping reduction.Looking forward to revisions or later models from Bigfoot though!
floffe - Tuesday, October 31, 2006 - link
That's because in most cases 98% of the ping is not on the local computer, but from your internet connection point (DSL/cable modem or whatever) to the server. Tis means even cutting 5% off that will be very hard (in general. WoW seems to be an exception).