Contest: Name that Server Company (Offering Prizes)

[StarzSpirit]

RawPower Gaming Servers

Demon Servers

Over Powerd Servers

Ridiculous Performance Gaming Servers

Overlapping Servers

Streamlined Servers

any of those sound good

[xQuality]

TickedOutServers
tickedoutservers.com - available

Server Hype
serverhype.com - available

Hercules Servers
herculeservers.com - available

Gaming Hype
gaminghype.com - available

Hyped Up Servers
hypedupservers.com - available

Old School Servers
oldschoolservers.com - available

Superman Servers
supermanservers.com - available

Server Sumo
serversumo.com - available

Spike Servers
spikeservers.com - available

Server Suite [Premium Domain (its over $3800 at GoDaddy)]
serversuite.com - available

Server Standoff
serverstandoff.com - available

Soothing Servers
soothingservers.com - available

Infused Servers
infusedservers.com - available





P.S. If you need a web designer, we can negotiate.. =D.


POSTING MORE!!

[iliketohostservers]

Please use google to search for past and present companies with similar names...

HypedGaming is an old company
NextGen Servers is a current company

xQuality Wrote:HeadStart Servers
headstartservers.com - available

Server Hype
serverhype.com - available

Hercules Servers
herculeservers.com - available

Gaming Hype
gaminghype.com - available

Hyped Up Servers
hypedupservers.com - available

Next Generation Servers
ngenservers.com - available

POSTING MORE!!

[xQuality]

Okay my bad..
I can design websites. If you need one, we can talk..

AIM: aznbadboy203
email: timmyiang@live.com

[Canquain]

Heres 3 of my Names.

Ballistic Gaming

ExtraordinaryServers

Millenia Servers

[Spartanfrog]

iliketohostservers Wrote:

Spartanfrog Wrote:

iliketohostservers Wrote:We do not offer the cheapest servers around, $65 to $75 a month is not a cheap server. BUT out of all of the companies who offer 1 game server per cpu core, we are the cheapest.

Other companies who offer 1 game server per cpu core cost $75 to $115 per month, so we are pretty close in price to some companies, but much cheaper than others. The companies that are on the higher end of the scale are most likely renting their server hardware, and do not own the servers, thus they must charge more money because their expenses are higher.

When I meant less expensive servers, I mean in the price range of $30 to $50.

The reason we are slightly cheaper than our competition (out of the companies who offer 1 game server per cpu core) is because we own our hardware, we do not rent it, and we have private agreements with the data centers which allows us to get our bandwidth much cheaper than most of our competitors. We are also being run by gamers, so we aren't really opening this company to make a lot of money, we are here to provide competitive league gamers with an affordable solution to 1 game server per cpu core.

Gotcha

Don't get me wrong, just because a game server costs $30 to $50 does not mean it will be a bad game server. It's just that the possibilities of your server lagging is much higher with a less expensive game server, because it usually means the company is running more per machine/server box.

And, if a server costs $30 to $50, it most likely will not be a 1000 FPS game server, and if it is... it probably won't be very good.

Raising the FPS of the game server allows the system/CPU to run faster, which will improve the performance of the game server - it's usually noticed in the bullet registry.

This is how the Tickrate works... at 100 tickrate every player sends a packet/update to the server every 10ms (milliseconds). So if you're playing a 5 vs 5 match that means there are 10 players in your game server. If each player sends a packet to the game server every 10ms that equals to about 1 packet every 1ms (10 packets divided by 10ms).

In order for the game server to process all of these packets, the server FPS must be able to handle it.

At 250 FPS the game server is able to process 1 packet every 4ms. At 500 FPS it is able to process 1 packet every 2ms. And at 1000 FPS it is able to process a packet every 1ms. So obviously the best gaming environment would be 1000 FPS.

Since 100 tickrate means each player sends 1 packet to the game server every 10ms (you take 10 packets divided by 10ms), that is 1 packet per 1ms. So the game server needs to be able to update every 1ms, the only way to have it do this is to run the game server at 1000 FPS and keep the FPS stable at that number.

Sometimes when I play in 500 FPS game servers I notice the bullet registry is better when some players are Dead. The reason is simple, at 500 FPS the game server can not process all of the packets being sent from all 10 players. So when some players are Dead, there are less than 10 players sending packets to the game server, which means there are less packets in total - this allows the game server to process more of the updates being sent since there are less. This doesn't always pose a problem unless you are serious about your game server and want the best performance possible. But it's just common sense, if 10 players are sending a packet to the game server every 10ms, that is 1 packet every 1ms. At 500 FPS the game server can only process a packet every 2ms... that means it's literally only processing about 50% of the packets being sent to the game server... do you really want something like that for a high performance match server?


P.S. Some companies offer 2000 FPS but I honestly do not see the point. At 100 tickrate there is 1 packet being sent by each player every 10ms. So if you have 10 players in a server, every player sends a packet every 10ms, that is 1 packet every 1ms. 1000 FPS processes a packet every 1ms.

2000 FPS will process a packet every .5ms...but there will never be that many updates being sent to the server UNLESS you have 20 players in the game server.

You can read more here: http://blog.cevo.com/articles/2008/03/06/game-server-settings-fps-and-tickrate/

and here: http://forums.nfoservers.com/viewtopic.php?f=21&t=3266

I wasnt being sarcastic, I believed you lol. Seems you know your stuff.

[css]

iliketohostservers Wrote:At 250 FPS the game server is able to process 1 packet every 4ms. At 500 FPS it is able to process 1 packet every 2ms.

I think you've slightly misinterpreted the articles.

A 250 FPS server means the server will check 250 times per second what network data has arrived. It means the server knows when the command packet arrived on the server with 1/250 second accuracy. That's the 4 ms. In-game it means that the server doesn't see any difference on command packets that arrive in 4 ms range. For the server those commands happen exactly at the same time, although in reality there could be the 4 ms difference. With more FPS the server knows more accurately when the event happened. It will "process", ie. timestamp, all packets that the ethernet card has received since last frame.

The server doesn't do anything with the packets except mark them with timestamp on a "frame". On a "tick" the server processes the data received on the frames. Then it'll know who shot first, and if the enemy dodged the bullet in time. If server FPS is low, then the "fire" and "dodge" commands may get the same timestamp, and that causes "omfg I was already behind the box" .

I've pondered this issue earlier in my post at http://forums.srcds.com/showthread.php?tid=7165&pid=39471#pid39471

The thing I don't get is why Source server is so inaccurate about the network timestamps. If I run "tcpdump -n 'dst port 27015'" on my server, I get timestamps with nanosecond accuracy. Here's dump:

Code:

(IPs obfuscated)
19:48:56.511568 IP xy.152.233.83 > server: UDP, length 35
19:48:56.512224 IP xy.221.15.159 > server: UDP, length 64
19:48:56.512226 IP xy.124.53.17 > server: UDP, length 41
19:48:56.512838 IP xy.210.48.236 > server: UDP, length 41
19:48:56.513924 IP xy.52.189.27 > server: UDP, length 52
19:48:56.515868 IP xy.57.33.2 > server: UDP, length 35
19:48:56.517015 IP xy.29.183.175 > server: UDP, length 49
19:48:56.517018 IP xy.174.63.1 > server: UDP, length 40
       ^   ^  ^
       1   2  3
1 = second
2 = millisecond
3 = nanosecond

The server is 66 tickrate running 24 players.

A game server with 100 FPS would see these commands happen at the same time. My ~500 FPS server sees them apparently quite well apart, because it can make difference in 2 ms intervals.

I don't get it why the Source server doesn't get to the nanosecond accuracy. I could probably pipe the output of the tcpdump to the game server and still reach better accuracy

@iliketohostservers.
Great post. I also like the one-core-one-server concept.

If you're interested I can add server FPS tracking for some of your server. I've already set up neat 1000 FPS assurance for Ryan's servers . I'm also interested to see how the FPS would perform on a public ~20 slot server, so if you've got any "demo" servers for public use, that'd be nice.

[iliketohostservers]

Yes I may be slightly wrong, I kind of read the articles and made my own 'small' theory of the way it worked, but my theory is basically the best performing server would be 1000, and that's basically what you're saying as well. I may not know 100% why the server is better at 1000 fps..I just know every single server I've played on has been better at 1000 FPS and there has to be a reason.

css Wrote:

iliketohostservers Wrote:At 250 FPS the game server is able to process 1 packet every 4ms. At 500 FPS it is able to process 1 packet every 2ms.

I think you've slightly misinterpreted the articles.

A 250 FPS server means the server will check 250 times per second what network data has arrived. It means the server knows when the command packet arrived on the server with 1/250 second accuracy. That's the 4 ms. In-game it means that the server doesn't see any difference on command packets that arrive in 4 ms range. For the server those commands happen exactly at the same time, although in reality there could be the 4 ms difference. With more FPS the server knows more accurately when the event happened. It will "process", ie. timestamp, all packets that the ethernet card has received since last frame.

The server doesn't do anything with the packets except mark them with timestamp on a "frame". On a "tick" the server processes the data received on the frames. Then it'll know who shot first, and if the enemy dodged the bullet in time. If server FPS is low, then the "fire" and "dodge" commands may get the same timestamp, and that causes "omfg I was already behind the box" .

I've pondered this issue earlier in my post at http://forums.srcds.com/showthread.php?tid=7165&pid=39471#pid39471

The thing I don't get is why Source server is so inaccurate about the network timestamps. If I run "tcpdump -n 'dst port 27015'" on my server, I get timestamps with nanosecond accuracy. Here's dump:

Code:

(IPs obfuscated)
19:48:56.511568 IP xy.152.233.83 > server: UDP, length 35
19:48:56.512224 IP xy.221.15.159 > server: UDP, length 64
19:48:56.512226 IP xy.124.53.17 > server: UDP, length 41
19:48:56.512838 IP xy.210.48.236 > server: UDP, length 41
19:48:56.513924 IP xy.52.189.27 > server: UDP, length 52
19:48:56.515868 IP xy.57.33.2 > server: UDP, length 35
19:48:56.517015 IP xy.29.183.175 > server: UDP, length 49
19:48:56.517018 IP xy.174.63.1 > server: UDP, length 40
       ^   ^  ^
       1   2  3
1 = second
2 = millisecond
3 = nanosecond

The server is 66 tickrate running 24 players.

A game server with 100 FPS would see these commands happen at the same time. My ~500 FPS server sees them apparently quite well apart, because it can make difference in 2 ms intervals.

I don't get it why the Source server doesn't get to the nanosecond accuracy. I could probably pipe the output of the tcpdump to the game server and still reach better accuracy

@iliketohostservers.
Great post. I also like the one-core-one-server concept.

If you're interested I can add server FPS tracking for some of your server. I've already set up neat 1000 FPS assurance for Ryan's servers . I'm also interested to see how the FPS would perform on a public ~20 slot server, so if you've got any "demo" servers for public use, that'd be nice.

[Spartanfrog]

css Wrote:I'm also interested to see how the FPS would perform on a public ~20 slot server, so if you've got any "demo" servers for public use, that'd be nice.

I would not be suprise to see the FPS drop very suddenly to tell you the truth. At the begining of the round, I ALWAYS see my public server FPS fall dramatically.

[iliketohostservers]

Yes it is very hard to keep 1000fps stable with that many players, 500 would be better for that.

Spartanfrog Wrote:

css Wrote:I'm also interested to see how the FPS would perform on a public ~20 slot server, so if you've got any "demo" servers for public use, that'd be nice.

I would not be suprise to see the FPS drop very suddenly to tell you the truth. At the begining of the round, I ALWAYS see my public server FPS fall dramatically.

[Drocona]

Please stay on topic

Don't want to let this nice thread get wasted by a FPS/tickrate discussion (even though I have nothing against that, this is about the contest!)

[css]

I'm also supporting the contest. I wish you get a good name for you servers, because you've got good servers for the cause.

Maybe you want to PM me to get the details to get the FPS statistics for your server(s). I've got long lasting, already three years running servers on my disposal, so I could "boost" your servers while having stats for my own interest.

One-core-one-server is truly the thing that everybody should support. I hope you've got ~20 slot server for marketing use. That would be blast.

[iliketohostservers]

What do you mean fps statistics?

We will be compiling custom kernels for srcds 1000fps, and we can boost them ourselves but thank you for the offer.

What do you mean 20 slot server?
We will only be hosting private 12 player servers for match/league play. We are not hosting any public servers.

css Wrote:I'm also supporting the contest. I wish you get a good name for you servers, because you've got good servers for the cause.

Maybe you want to PM me to get the details to get the FPS statistics for your server(s). I've got long lasting, already three years running servers on my disposal, so I could "boost" your servers while having stats for my own interest.

One-core-one-server is truly the thing that everybody should support. I hope you've got ~20 slot server for marketing use. That would be blast.

[css]

iliketohostservers Wrote:What do you mean fps statistics?

There are server hosters selling "1000 FPS servers", but they're not 1000 FPS after there are 10 players. I've got stats from a "1000 FPS server", which turned out to be ~900 FPS server after players joined. Those who had the server thought they have good solid 1000 FPS server because the server said ~999 if they exec'd "stats" from RCON. But what they didn't know was that when they were having a match, the FPS was around ~900.

The statistics system is described at http://forums.srcds.com/viewtopic/7026

iliketohostservers Wrote:We will be compiling custom kernels for srcds 1000fps, and we can boost them ourselves but thank you for the offer.

I was offering statistics service. It's not related to the actual tweaking of the server.

About the 1000fps, that's what you say. Nobody knows for sure. Those who had their "1000 FPS server" thought they had the best money can buy. Later when it turned out to be non-1000fps they thought the monitoring system was faulty. That's how well the company (I won't say the name) had created illusion of being very reliable 1000 fps game server hoster. Even if the players saw with their own eyes that the server does not hold solid ~1000fps, they didn't believe it. Later they changed the server hoster, so I guess someone realized it was all just 1000 fps bluff. This happened about year ago. Server CPU performance has grown from that time, so I guess it's easier nowdays to reach solid 1000 fps. There's no need to bluff for "1000fps empty server" anymore. Anyway, I wouldn't take GPS's word about "solid 1000 fps" after that "incident" without good evidence.

I hope you've got some sort of demo server or "See it for yourself" server where you can show that your servers are capable of solid ~1000 FPS under load.

iliketohostservers Wrote:What do you mean 20 slot server?
We will only be hosting private 12 player servers for match/league play. We are not hosting any public servers.

Some GSPs have public game servers for demo purposes. Players can join there and see the server run lag-free with 20 players. I'd be interested to see how FPS performs on such "20 slot 1000 FPS server". If you don't have it, then so be it. I'll have to wait for some other GSP admin to come along .

[iliketohostservers]

I'm not sure how much experience you have with server hosting but...

It is NORMAL for a 1000 fps server to fluctuate a bit, dropping to 900 is not a big deal, it is very common. It takes a lot to keep 1000 stable, I've owned servers from Hidef, Velocity, and even NxGs, all of them would occasionally drop to 800 or 900, and they were still really good servers.

css Wrote:

iliketohostservers Wrote:What do you mean fps statistics?

There are server hosters selling "1000 FPS servers", but they're not 1000 FPS after there are 10 players. I've got stats from a "1000 FPS server", which turned out to be ~900 FPS server after players joined. Those who had the server thought they have good solid 1000 FPS server because the server said ~999 if they exec'd "stats" from RCON. But what they didn't know was that when they were having a match, the FPS was around ~900.

The statistics system is described at http://forums.srcds.com/viewtopic/7026

iliketohostservers Wrote:We will be compiling custom kernels for srcds 1000fps, and we can boost them ourselves but thank you for the offer.

I was offering statistics service. It's not related to the actual tweaking of the server.

About the 1000fps, that's what you say. Nobody knows for sure. Those who had their "1000 FPS server" thought they had the best money can buy. Later when it turned out to be non-1000fps they thought the monitoring system was faulty. That's how well the company (I won't say the name) had created illusion of being very reliable 1000 fps game server hoster. Even if the players saw with their own eyes that the server does not hold solid ~1000fps, they didn't believe it. Later they changed the server hoster, so I guess someone realized it was all just 1000 fps bluff. This happened about year ago. Server CPU performance has grown from that time, so I guess it's easier nowdays to reach solid 1000 fps. There's no need to bluff for "1000fps empty server" anymore. Anyway, I wouldn't take GPS's word about "solid 1000 fps" after that "incident" without good evidence.

I hope you've got some sort of demo server or "See it for yourself" server where you can show that your servers are capable of solid ~1000 FPS under load.

iliketohostservers Wrote:What do you mean 20 slot server?
We will only be hosting private 12 player servers for match/league play. We are not hosting any public servers.

Some GSPs have public game servers for demo purposes. Players can join there and see the server run lag-free with 20 players. I'd be interested to see how FPS performs on such "20 slot 1000 FPS server". If you don't have it, then so be it. I'll have to wait for some other GSP admin to come along .