EVGA Killer Xeno Pro: The Impact of Network Offloading
by Derek Wilson on July 3, 2009 4:20 AM EST- Posted in
- Networking
Final Words
The approach and design of the Killer Xeno Pro are more efficient than standard network cards. Bypassing the windows networking stack will reduce load on the operating system and the CPU. Bypassing the CPU and OS when sending and receiving audio using supported voice chat software is a cool thing as well. Built in hardware prioritization (QoS) and bandwidth throttling are also interesting features.
But the bottom line is that none of this makes a significant difference in the gaming experience on modern PCs when paired with current games, nor does it offer an advantage over alternatives.
The biggest advantage the Killer Xeno Pro showed was in it's ability to prioritize games over other applications. At the same time, this only works for the one PC that is doing both downloading and gaming. If there are other computers on the network at all, it would be much more cost effective to purchase a router that can handle QoS and bandwidth control on a per application (or per port) basis. Using a router to handle this means that I can download huge massive files on one PC and my wife can play Team Fortress 2 on another without experiencing problems.
I could even play a game on the computer that I'm downloading with in that case, but it remains our recommendation to simply not download in the background while playing a game. More than just networking is affected by downloading in the background, as the harddrive is constantly being hit and this can be a significant source of loading pauses and hitching in and of itself.
If you don't want to spend any money, most torrent and other downloading applications come with built in (or add on) bandwidth controls that can be employed to achieve the same end as hardware QoS. Hardware QoS and bandwidth control are nice features to have, but they are not worth $120.
The voice chat acceleration could be beneficial when gaming while chatting, but currently most applications are not supported. Teamspeak, Ventrillo, and Skype all need out of the box support at the very least. At best we would want all games with built in voice chat to support this as well, but that isn't likely unless and until the hardware becomes more popular. In addition to application support, voice chat doesn't take up a significant amount of CPU time and the most significant impact on latency is still going to be the network as a whole.
TCP/IP offload is a better way to do things, but the benefit to the gamer just isn't there. Network load just isn't high enough to really take advantage of the hardware in modern games. But it isn't like the potential benefit of an NPU can never be realized: it starts to matter in the server space where technology like this was originally targeted. Offloading the CPU of a heavily loaded database server can definitely leave more CPU time for processing tasks and can increase network responsiveness. This just isn't what the Killer Xeno Pro is targeted towards.
So, when you've already got an on-board network card, is the Killer Xeno Pro worth $120-$130 USD? When that money can be put into either CPU or graphics, the answer just has to be no. At the same price as a Radeon HD 4850, there is just no reason not to look toward upgrading older graphics solutions. If you've already got something on the level of the 4850, then that money should be saved for your next graphics hardware upgrade where it will still have a higher impact on performance and experience.
For professional gamers and those obsessed with twitch shooters, for the gamers running 1280x800 on a 30" panel with most of the settings turned down on the highest end hardware money can buy, for those who are always after whatever option might give them the slightest edge: the Killer Xeno Pro might be for you. But even then, this hardware is the icing on the cake rather than a core ingredient.
What the geek inside me really wants to see is more general access to the hardware. This is, after all, a PC on a PCIe card. If Bigfoot gave us deeper access to the hardware, we might find more (even if equally niche) uses for an extra PowerPC processor in our computers. Additionally, to satisfy our intellectual curiosity, we would like to get our hands on a couple more of these cards in order to do some LAN testing using combinations of standard and Killer network cards to see how overall network performance is changed (if at all) especially with respect to voice chat performance.
Beyond this, there is a caveat. Perhaps, as broadband becomes more pervasive, game developers might want to push networking. At some point in time, games may need the PCs they run on to handle a much larger volume of network traffic in order to function well. Right now, game developers are targeting current bandwidths using current commodity network hardware. Games can't be designed to require higher performance networking gear because consumers either don't have access to high speed internet or they don't have a network card that does TCP/IP offload (among other things).
At some point down the line, something like the Killer Xeno Pro might become a significant requirement. But right now, for the vast majority of gamers out there, our advice is to save your money.
121 Comments
View All Comments
marsbound2024 - Friday, July 3, 2009 - link
"Let's start by saying that this isn't going to be a network card for someone hanging on to a 7 Series NVIDIA card or a Radeon 1k part from ATI in a single core CPU system."Dang...did you guys sneak into my house last night and check out my computer? I've yet to upgrade from my antiquated 7600GT, Athlon64 3800+ 2.4GHz single-core processor! The time to upgrade is nigh though. I've been hanging on to that system for a while now because it does everything I need it to at the moment with Windows XP. After work, I don't really care about coming home and doing anything CPU intensive on my PC and I play my games on console. However, Crysis Warhead and such have led me to continue to want to get a new system.
Atechie - Friday, July 3, 2009 - link
1. Eve Oneline is TCP, games that benefit are UDP based.2. "Since we can't get an assessment of ping times in EVE, we did some testing on WoW in the same unpopulated area. Normalized to the average latency we experienced while not downloading a torrent, here's the latency incurred by downloading a torrent"
Unpopulated, not stressing area...why bother is yoo are going to scew the test?
3. Clueless reviewer
4. profit?
Looking at this test it almost look as it was meant to be a less than stellar test
DerekWilson - Friday, July 3, 2009 - link
The killer benefits both UDP and TCP games ... not just one or the other.We tested in an unpopulated area in WoW in order to keep things as deterministic as possible. Some of the tests we ran were not strictly deterministic, but it is incredibly hard to construct tests that work in populated areas that generate usable data at all.
the WoW test, even in an unpopulated area, did show that there is a difference in network performance while downloading a torrent. We didn't see this sort of difference while not downloading a torrent, however.
The real issue is that proper testing almost needs to be in a clean room sort of environment where multiple scenarios can be played back across the network and on the PC to show what the actual differences in performance would have been.
But even when that shows some actual performance differences (as I believe it would) the benefits just don't present themselves to the end user in any truly beneficial way.
DigitalFreak - Friday, July 3, 2009 - link
Quit your whining. Derek has already responded to these issues.hooflung - Friday, July 3, 2009 - link
And Derek was wrong. At least I am not the only one who pointed this out.DerekWilson - Friday, July 3, 2009 - link
Once again --EVE uses both TCP and UDP and not just TCP. WoW, it seems by all accounts I can find online, uses only TCP.
Aside from this, the Killer hardware accelerates both TCP and UDP not just one or the other, so the whole issue doesn't matter one bit.
stmok - Friday, July 3, 2009 - link
While I can see why they tried to target the gaming market, it just feels like its more suited for server or hacker/enthusiast audience. (So I agree with the author in that regard.)The irony of this product is that, while it uses an embedded version of Linux on the NIC, it isn't fully supported under Linux! ie: Say if you used Ubuntu, OpenSUSE, or "whatever is your fav distro" in your system; you wouldn't be able to have full access to all its features! Its a "Windows only" thing!
The product has potential...It just feels the company is focusing on an audience who won't really appreciate what the product can do. Its kind of wasted in that sense.
trochevs - Friday, July 3, 2009 - link
I agree. Until they open the access to the embedded OS and other people and hackers develop apps for it it will be doomed.If I had access to the hardware I would install scaled down version of my web server LAMP and shutdown the main PC. If the traffic jumps I would wake the main server and handle the demand.
Other cool use could be to upload the Asterisk and have 24/7 VoIP PBX without the need to run the PC 24/7
How about to run my torrent server without running the PC.
And the end. Keep the PC in hibernate and when I need it for remote access I can connect to the NIC and wake it up.
This has wonderful potentials, but until Xeno executives wake up from their dream to become the next Gates or Jobs with proprietary platform this would be yet one more great idea and impressive engineering that never going to see light of the day.
Open platform please. Just like the PC.
Stas - Friday, July 3, 2009 - link
Would be silly to bother with support for Linux when this is marketed as a GAMING product. Windows makes sense.stmok - Saturday, July 4, 2009 - link
"Would be silly to bother with support for Linux when this is marketed as a GAMING product. Windows makes sense."=> What kind of gamer would take the time to download the SDK for this product and help develop applications for the hardware?
This is EXACTLY what I mean when I say the product is aimed at the wrong market. Gamers won't bother. Gamers aren't developers.
Than again, how much sense does Windows make when you are replacing its network stack with this?