Re: [hlds] Odd lag problem
- Original Message - From: "Ian mu" <[EMAIL PROTECTED]> So why are multiplay windows servers so intermittently yet frequently laggy as well known by all (linux servers are nice btw..so whats the difference) ? No ones reported an issue, if there is one please let us know. We dont run windows by preference but a number of our dedicated machine customers do and they frequently overload the machine :( That said please let u know any details and we'll look at them for sure. Steve / K This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of misdirection, illegible or incomplete transmission please telephone (023) 8024 3137 or return the E.mail to [EMAIL PROTECTED] ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
RE: [hlds] Odd lag problem
> Sorry to continue but there are two many issues left unanswered: > - Original Message - > From: "Chance Sullivan" <[EMAIL PROTECTED]> > > >> So why not just minimise them this would produce the same effect > >> according to your logic. > > It would not because doing it that way, your still using > the GDI and > > User resources where as if your running it as a service and > not using > > the Interact With Desktop option your not using them. > > Thats just a pile of rubbish. Start your server under a > service and query its resource handles with a debugger there > is no difference from using that run method to starting it > from the desktop you just cant see the output. If the server > was specificly written to run as a service yes this would be > the case but simple running it as one does not change is > resource requirements on single bit. I did query them, and the GDI and User Resources are at 0, otherwise I wouldn't have stated that they were. > >> Using svrany will never leave memory allocated or unclosed > >> filehandles, dont know where u got this impression. > > That is incorrect as your not taking into consideration > applications > > that don't respond well to the Logon/Logoff events when > being ran as a service. > > Wrong! If a app doesnt ignore the WM_ENDSESSION message ( > which is what prompts them to close on logoff ) your app will > just close. > This won't leave any memory / filehandles lying around. Even > if an app crashes windows reclaims those. Not all of the time it doesn't as not all applications follow the proper procedures, or listen to the proper events, in a perfect world they would. Windows can and does have zombie processes occur like *NIX does whether it be from a foreground app, or a service, and using srvany has caused that to happen. > >> So you put 4Gb of ram in your game server machines, nice > but waistful > >> :P > > 2GB usually, sometimes 3 or 4 depends on the system setup and cpu's. > > Might be waistful to you, but If you a person that wants a memory > > buffer of about 256 to 500mb to account for spikes in > usage, sometimes > > more than 2GB is needed. > > Hmm 100Mb average per you said, 8 servers thats 800Mb you > still got 1.2Gb free on a 2Gb machine. Didn't u say u ran Web > Server edition, as that only supports 2Gb where XP supports > 4Gb, or was that someone else? It was someone else because STD or ENT are the platforms I am reffering to. > >> They would only benifit if they OS ( kernel ) was using > significantly > >> less machine resources to do they job it did previously > without them. > >> I'd put it to you thats not the case as otherwise MS would be > >> shouting from the houses that 2k3 10% or more quicker at > running all > >> your apps. > > If your talking about applications that are basicly > > single/multi-threaded daemons that require little user > interaction and > > running multipe instances of those daemons, then it's a > different story. > > Why? You should be able to answer that. > >> Again so why isn't MS shouting about this nice performance > increase? > > MS seems to be saying that we should all upgrade to windows XP for > > workstations and 2003 for servers, seems like what one > would do with a > > product that's better than and older version. > > Of course they are they want u to spend money but there's no > big advertising campain touting huge performance increases > that I've seen. > > >> They do? Which? ( I'm talking real work threads here not basically > >> idle threads )? UT for example uses a seperatethread to do DNS > >> lookups but since they are so infrequent event doubling the > >> performance ( which your not doing to see ) would have no > persevable > >> effect on the servers performance. > > Doom3 for one. > > Looks like only one of the 3 threads does any work from the > trace I just did ( like in the case of UT ) could be wrong though. 6 threads there actually then after it finishes initialization, it's 4. > >> Yes you are, no one's saying your not but when you take those > >> opinions and give others advice based on them; when they are > >> unsubstansicated its like chinese whispers. People start > to believe > >> its true just because it was said, even though its not actually so. > > I give you the same advice. > > So what wisper did I start? I thought all my conclusions > where backed up by quantifiable sources. Correct me if I'm wong. Most of mine were as well. So we have different sources obviosly. > > I have agreed with your opinion as long as your not running > more than > > 2-3 game servers, when it gets between 4-16 is where you see the > > benefits. So if you're a GSP(they usually run more than 6 > servers per > > box) or just want every bit of performance you can get(Kid with the > > best stuff on the block) server 2003 will give you what you > want, otherwise XP pro will do fine. > > 16 game servers on one machine either thats pong or I'd hate > to have a server on a machine with that many talk
[hlds] net_synctags
Found this cvar: "net_synctags" = "0" cheat - Insert tokens into the net stream to find client/server mismatches. Can someone explain this to me? Could this stop non-steam, since non-steam differes from normal steam? Is someone able to test this? Thanks -Andrew - Original Message - From: "spartibus" <[EMAIL PROTECTED]> To: Sent: Saturday, February 12, 2005 2:14 PM Subject: RE: [hlds] So I hear VAC2 is coming... > They could also just be waiting to fix no-steam before they release VAC2. Oh > well, I'm just happy it's coming. > > -Original Message- > From: [EMAIL PROTECTED] > [mailto:[EMAIL PROTECTED] On Behalf Of Andrew Armstrong > Sent: Friday, February 11, 2005 7:06 PM > To: hlds@list.valvesoftware.com > Subject: Re: [hlds] So I hear VAC2 is coming... > > Well, that would be a fix for non-steam wouldnt it :) > > - Original Message - > From: "spartibus" <[EMAIL PROTECTED]> > To: > Sent: Saturday, February 12, 2005 1:54 PM > Subject: RE: [hlds] So I hear VAC2 is coming... > > > > I doubt this will happen or if it's even possible, but it's just a > thought. > > Maybe VAC2 will stop people from being able to use no-steam on secure > > servers? That would be neat ;p > > > > -Original Message- > > From: [EMAIL PROTECTED] > > [mailto:[EMAIL PROTECTED] On Behalf Of Andrew Armstrong > > Sent: Friday, February 11, 2005 6:29 PM > > To: hlds@list.valvesoftware.com > > Subject: [hlds] So I hear VAC2 is coming... > > > > Apparently VAC2 is comming 'soon' according to the latest steam login > > update... > > > > What good is it really, if it bans (as the same format as VAC1) when > > no-steam still exists? > > > > sigh > > > > > > ___ > > To unsubscribe, edit your list preferences, or view the list archives, > > please visit: > > http://list.valvesoftware.com/mailman/listinfo/hlds > > > > > > > > ___ > > To unsubscribe, edit your list preferences, or view the list archives, > please visit: > > http://list.valvesoftware.com/mailman/listinfo/hlds > > > ___ > To unsubscribe, edit your list preferences, or view the list archives, > please visit: > http://list.valvesoftware.com/mailman/listinfo/hlds > > > > ___ > To unsubscribe, edit your list preferences, or view the list archives, please visit: > http://list.valvesoftware.com/mailman/listinfo/hlds > ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
RE: [hlds] So I hear VAC2 is coming...
They could also just be waiting to fix no-steam before they release VAC2. Oh well, I'm just happy it's coming. -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Andrew Armstrong Sent: Friday, February 11, 2005 7:06 PM To: hlds@list.valvesoftware.com Subject: Re: [hlds] So I hear VAC2 is coming... Well, that would be a fix for non-steam wouldnt it :) - Original Message - From: "spartibus" <[EMAIL PROTECTED]> To: Sent: Saturday, February 12, 2005 1:54 PM Subject: RE: [hlds] So I hear VAC2 is coming... > I doubt this will happen or if it's even possible, but it's just a thought. > Maybe VAC2 will stop people from being able to use no-steam on secure > servers? That would be neat ;p > > -Original Message- > From: [EMAIL PROTECTED] > [mailto:[EMAIL PROTECTED] On Behalf Of Andrew Armstrong > Sent: Friday, February 11, 2005 6:29 PM > To: hlds@list.valvesoftware.com > Subject: [hlds] So I hear VAC2 is coming... > > Apparently VAC2 is comming 'soon' according to the latest steam login > update... > > What good is it really, if it bans (as the same format as VAC1) when > no-steam still exists? > > sigh > > > ___ > To unsubscribe, edit your list preferences, or view the list archives, > please visit: > http://list.valvesoftware.com/mailman/listinfo/hlds > > > > ___ > To unsubscribe, edit your list preferences, or view the list archives, please visit: > http://list.valvesoftware.com/mailman/listinfo/hlds ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
Re: [hlds] First CS:S Cheat released - Valve help us please. -update!
"And just a quick note for those of you who have been asking -- yes, VAC 2 is coming." Anyone read the update news today?¿? Like I said a few weeks ago, give it time (over the bots issue versus finishing a vac update). Vac 2. Fear it, if you cheat. 8) StealthMode http://www.teamlothosting.com/ #LoTgaming irc.gamesurge.net ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
Re: [hlds] So I hear VAC2 is coming...
Well, that would be a fix for non-steam wouldnt it :) - Original Message - From: "spartibus" <[EMAIL PROTECTED]> To: Sent: Saturday, February 12, 2005 1:54 PM Subject: RE: [hlds] So I hear VAC2 is coming... > I doubt this will happen or if it's even possible, but it's just a thought. > Maybe VAC2 will stop people from being able to use no-steam on secure > servers? That would be neat ;p > > -Original Message- > From: [EMAIL PROTECTED] > [mailto:[EMAIL PROTECTED] On Behalf Of Andrew Armstrong > Sent: Friday, February 11, 2005 6:29 PM > To: hlds@list.valvesoftware.com > Subject: [hlds] So I hear VAC2 is coming... > > Apparently VAC2 is comming 'soon' according to the latest steam login > update... > > What good is it really, if it bans (as the same format as VAC1) when > no-steam still exists? > > sigh > > > ___ > To unsubscribe, edit your list preferences, or view the list archives, > please visit: > http://list.valvesoftware.com/mailman/listinfo/hlds > > > > ___ > To unsubscribe, edit your list preferences, or view the list archives, please visit: > http://list.valvesoftware.com/mailman/listinfo/hlds ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
Re: [hlds] Odd lag problem
So why are multiplay windows servers so intermittently yet frequently laggy as well known by all (linux servers are nice btw..so whats the difference) ? Just interested whya different problem, or a wrong o.s (you may evnen use not xp, but somethings are starting to ring true) when busy (and yes do extensive tests on all as comparisons to how mine should compare)? Comes to the crunch, proof of the pudding.I never used to know why (it was obvious with Barrysworld years back before the later options), but interesting there is a correlation now that appears, as I seriously never assumed you would use anything like XP (still disturbed) so never even factored that into it with comparisons, just assumed it was down to other problems with multiple game hosting. So yes definitely XP may not be a factor if you use it, but wondering what angle you are looking at to improve? ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
RE: [hlds] So I hear VAC2 is coming...
I doubt this will happen or if it's even possible, but it's just a thought. Maybe VAC2 will stop people from being able to use no-steam on secure servers? That would be neat ;p -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Andrew Armstrong Sent: Friday, February 11, 2005 6:29 PM To: hlds@list.valvesoftware.com Subject: [hlds] So I hear VAC2 is coming... Apparently VAC2 is comming 'soon' according to the latest steam login update... What good is it really, if it bans (as the same format as VAC1) when no-steam still exists? sigh ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
RE: [hlds] Odd lag problem
TAKE THIS SHIT OFFLIST FOR CHRIST'S SAKE!!! This is why I didn't respond to this guy's bait. If you want to share dick sizes do it privately and maybe someone here will be interested in the outcome. Talk about HLDS or GTFO! -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Steven Hartland Sent: Friday, February 11, 2005 9:16 PM To: hlds@list.valvesoftware.com Subject: Re: [hlds] Odd lag problem Sorry to continue but there are two many issues left unanswered: - Original Message - From: "Chance Sullivan" <[EMAIL PROTECTED]> >> So why not just minimise them this would produce the same >> effect according to your logic. > It would not because doing it that way, your still using the GDI and User > resources where as if your running it as a service and not using the > Interact With Desktop option your not using them. Thats just a pile of rubbish. Start your server under a service and query its resource handles with a debugger there is no difference from using that run method to starting it from the desktop you just cant see the output. If the server was specificly written to run as a service yes this would be the case but simple running it as one does not change is resource requirements on single bit. >> Using svrany will never leave memory allocated or unclosed >> filehandles, dont know where u got this impression. > That is incorrect as your not taking into consideration applications that > don't respond well to the Logon/Logoff events when being ran as a service. Wrong! If a app doesnt ignore the WM_ENDSESSION message ( which is what prompts them to close on logoff ) your app will just close. This won't leave any memory / filehandles lying around. Even if an app crashes windows reclaims those. >> So you put 4Gb of ram in your game server machines, nice but >> waistful :P > 2GB usually, sometimes 3 or 4 depends on the system setup and cpu's. > Might be waistful to you, but If you a person that wants a memory buffer of > about 256 to 500mb to account for spikes in usage, sometimes more than 2GB > is needed. Hmm 100Mb average per you said, 8 servers thats 800Mb you still got 1.2Gb free on a 2Gb machine. Didn't u say u ran Web Server edition, as that only supports 2Gb where XP supports 4Gb, or was that someone else? >> They would only benifit if they OS ( kernel ) was using >> significantly less machine resources to do they job it did >> previously without them. I'd put it to you thats not the case >> as otherwise MS would be shouting from the houses that 2k3 >> 10% or more quicker at running all your apps. > If your talking about applications that are basicly single/multi-threaded > daemons that require little user interaction and running multipe instances > of those daemons, then it's a different story. Why? >> Again so why isn't MS shouting about this nice performance increase? > MS seems to be saying that we should all upgrade to windows XP for > workstations and 2003 for servers, seems like what one would do with a > product that's better than and older version. Of course they are they want u to spend money but there's no big advertising campain touting huge performance increases that I've seen. >> They do? Which? ( I'm talking real work threads here not >> basically idle threads )? UT for example uses a >> seperatethread to do DNS lookups but since they are so >> infrequent event doubling the performance ( which your not >> doing to see ) would have no persevable effect on the servers >> performance. > Doom3 for one. Looks like only one of the 3 threads does any work from the trace I just did ( like in the case of UT ) could be wrong though. >> Yes you are, no one's saying your not but when you take those >> opinions and give others advice based on them; when they are >> unsubstansicated its like chinese whispers. People start to >> believe its true just because it was said, even though its >> not actually so. > I give you the same advice. So what wisper did I start? I thought all my conclusions where backed up by quantifiable sources. Correct me if I'm wong. > I have agreed with your opinion as long as your not running more than 2-3 > game servers, when it gets between 4-16 is where you see the benefits. So if > you're a GSP(they usually run more than 6 servers per box) or just want > every bit of performance you can get(Kid with the best stuff on the block) > server 2003 will give you what you want, otherwise XP pro will do fine. 16 game servers on one machine either thats pong or I'd hate to have a server on a machine with that many talk about lag city. Yes we are a GSP one of the biggest in the UK along with running by far the largest LAN's in the country. We have tested and continue to test servers across many different platforms ( one of the very few who have conducted controlled tests on game server performance across multiple OS's ). I've seen 0 evidence so far that leads to the conclusion that 2k3 server is significantly better (
[hlds] So I hear VAC2 is coming...
Apparently VAC2 is comming 'soon' according to the latest steam login update... What good is it really, if it bans (as the same format as VAC1) when no-steam still exists? sigh ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
Re: [hlds] Odd lag problem
Sorry to continue but there are two many issues left unanswered: - Original Message - From: "Chance Sullivan" <[EMAIL PROTECTED]> So why not just minimise them this would produce the same effect according to your logic. It would not because doing it that way, your still using the GDI and User resources where as if your running it as a service and not using the Interact With Desktop option your not using them. Thats just a pile of rubbish. Start your server under a service and query its resource handles with a debugger there is no difference from using that run method to starting it from the desktop you just cant see the output. If the server was specificly written to run as a service yes this would be the case but simple running it as one does not change is resource requirements on single bit. Using svrany will never leave memory allocated or unclosed filehandles, dont know where u got this impression. That is incorrect as your not taking into consideration applications that don't respond well to the Logon/Logoff events when being ran as a service. Wrong! If a app doesnt ignore the WM_ENDSESSION message ( which is what prompts them to close on logoff ) your app will just close. This won't leave any memory / filehandles lying around. Even if an app crashes windows reclaims those. So you put 4Gb of ram in your game server machines, nice but waistful :P 2GB usually, sometimes 3 or 4 depends on the system setup and cpu's. Might be waistful to you, but If you a person that wants a memory buffer of about 256 to 500mb to account for spikes in usage, sometimes more than 2GB is needed. Hmm 100Mb average per you said, 8 servers thats 800Mb you still got 1.2Gb free on a 2Gb machine. Didn't u say u ran Web Server edition, as that only supports 2Gb where XP supports 4Gb, or was that someone else? They would only benifit if they OS ( kernel ) was using significantly less machine resources to do they job it did previously without them. I'd put it to you thats not the case as otherwise MS would be shouting from the houses that 2k3 10% or more quicker at running all your apps. If your talking about applications that are basicly single/multi-threaded daemons that require little user interaction and running multipe instances of those daemons, then it's a different story. Why? Again so why isn't MS shouting about this nice performance increase? MS seems to be saying that we should all upgrade to windows XP for workstations and 2003 for servers, seems like what one would do with a product that's better than and older version. Of course they are they want u to spend money but there's no big advertising campain touting huge performance increases that I've seen. They do? Which? ( I'm talking real work threads here not basically idle threads )? UT for example uses a seperatethread to do DNS lookups but since they are so infrequent event doubling the performance ( which your not doing to see ) would have no persevable effect on the servers performance. Doom3 for one. Looks like only one of the 3 threads does any work from the trace I just did ( like in the case of UT ) could be wrong though. Yes you are, no one's saying your not but when you take those opinions and give others advice based on them; when they are unsubstansicated its like chinese whispers. People start to believe its true just because it was said, even though its not actually so. I give you the same advice. So what wisper did I start? I thought all my conclusions where backed up by quantifiable sources. Correct me if I'm wong. I have agreed with your opinion as long as your not running more than 2-3 game servers, when it gets between 4-16 is where you see the benefits. So if you're a GSP(they usually run more than 6 servers per box) or just want every bit of performance you can get(Kid with the best stuff on the block) server 2003 will give you what you want, otherwise XP pro will do fine. 16 game servers on one machine either thats pong or I'd hate to have a server on a machine with that many talk about lag city. Yes we are a GSP one of the biggest in the UK along with running by far the largest LAN's in the country. We have tested and continue to test servers across many different platforms ( one of the very few who have conducted controlled tests on game server performance across multiple OS's ). I've seen 0 evidence so far that leads to the conclusion that 2k3 server is significantly better ( as originally claimed ) than XP. There is no doubting that there a large amount of improvements in 2003 over 2000 and also a number of improvements of XP but I've yet to see or experience anything that justifies spending £500 on an OS compared with £90. I'd much rather spend the same money buying another machine which would have very real performance benefits. Steve / K This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirecti
RE: [hlds] Odd lag problem
Some Final words from me as well. > -Original Message- > From: [EMAIL PROTECTED] > [mailto:[EMAIL PROTECTED] On Behalf Of > Steven Hartland > Sent: Friday, February 11, 2005 7:11 AM > To: hlds@list.valvesoftware.com > Subject: Re: [hlds] Odd lag problem > > Some final words as this is obviously leading no where: > > - Original Message - > From: "Chance Sullivan" <[EMAIL PROTECTED]> > > > A white paper would be a good idea, Also a nice white paper > on why XP > > is better than 2003 for running game servers would be good as well. > > No one is saying XP is better it is so a mute point. > > >> I cant see what you are trying to say here; OS's have versions? I > >> think we are all aware of that :P > > Versions would be the version of the programs and libraries you > > mentioned above. > > Thats perfectly obvious, if they where the same they wouldnt > be different :P > > > I mistated this, I was thinking one thing and saying > another. If it's > > running as a service, then it's not using the Graphics hardware and > > PCI bus for any of the graphics, IE the HAL is not used as well, > > leaving the resources free for running processes. > > So why not just minimise them this would produce the same > effect according to your logic. It would not because doing it that way, your still using the GDI and User resources where as if your running it as a service and not using the Interact With Desktop option your not using them. > >> Actually there are few or no factors which influence an > application > >> being able to run as a service, ever heard or svrany / instsrv? > > Being more precise I was referring to applications that > require user > > interaction to run, using srvany/instsrv will not solve > that problem > > without adding additional overhead. Some Applications run well sith > > srvany/instsrv and some do not. Fortunately most games work > well with > > it enough for us to use them to a point. However using > either of those > > is not a very good way to do so as it doesn't close the application > > properly and can leave system memory allocation fragments/unclosed > > filehandles and such. There are other methods to get game > servers running as a service. > > As far as "using either of those" goes you clearly don't know > what they are as instsrv is used to create service's and > srvany to run any application as a service ( created by > instsvr ) so you could never use instsrv to run a game server > as a service as you state. Actually you can use instsrv to run a game server. I have done so myself. > > Using svrany will never leave memory allocated or unclosed > filehandles, dont know where u got this impression. That is incorrect as your not taking into consideration applications that don't respond well to the Logon/Logoff events when being ran as a service. > >> You can even run an application that requires user > interaction as a > >> service, "Allow interaction with desktop" anyone? > >> Even if this where a restriction ( which it isnt ) it leaves about > >> 99.99% of servers out there; BHD and JO are the only two > that spring > >> to mind which required user interaction to start. But from > what your > >> saying all the others can perform better simply by running as a > >> service? I think NOT! > > I think so, and the reason is because it's assigned to the Service > > Control Manager as the parent process that controls them. > > I think you are under the total missunderstanding that the > SCM does anything other than monitor the processes it > started, to ensure they are running. It has now effect on > sheduling and hence performance what so ever. > > > > I am thinking in the realm of 2-4GB, so we are close there. > > So you put 4Gb of ram in your game server machines, nice but > waistful :P 2GB usually, sometimes 3 or 4 depends on the system setup and cpu's. Might be waistful to you, but If you a person that wants a memory buffer of about 256 to 500mb to account for spikes in usage, sometimes more than 2GB is needed. > >> Now back to the real stuff. The question was if it does NOT use it? > >> Why that specific question? Because if it did use it you > would need > >> either a seperate binary per OS or runtime checks to make > use of it. > >> Since we are primarily talking about Fiber's here and > given the fact > >> that game servers dont even use threads to any great > extent chances > >> of them making use of and hence gaining benefit from them > is so small > >> its untrue. Hence the answer your looking for was NO plain and > >> simple. > > The answer is that even if they do not use it, they benefit > from the > > OS using it to prioritize the processes it runs which in > turn is game > > servers in this topic, if it's handed over to SCM in windows or the > > appropriate process, or processes in Unix. > > They would only benifit if they OS ( kernel ) was using > significantly less machine resources to do they job it did > previously without them. I'd put it to you thats not t
Re: [hlds] Odd lag problem
Some final words as this is obviously leading no where: - Original Message - From: "Chance Sullivan" <[EMAIL PROTECTED]> A white paper would be a good idea, Also a nice white paper on why XP is better than 2003 for running game servers would be good as well. No one is saying XP is better it is so a mute point. I cant see what you are trying to say here; OS's have versions? I think we are all aware of that :P Versions would be the version of the programs and libraries you mentioned above. Thats perfectly obvious, if they where the same they wouldnt be different :P I mistated this, I was thinking one thing and saying another. If it's running as a service, then it's not using the Graphics hardware and PCI bus for any of the graphics, IE the HAL is not used as well, leaving the resources free for running processes. So why not just minimise them this would produce the same effect according to your logic. Actually there are few or no factors which influence an application being able to run as a service, ever heard or svrany / instsrv? Being more precise I was referring to applications that require user interaction to run, using srvany/instsrv will not solve that problem without adding additional overhead. Some Applications run well sith srvany/instsrv and some do not. Fortunately most games work well with it enough for us to use them to a point. However using either of those is not a very good way to do so as it doesn't close the application properly and can leave system memory allocation fragments/unclosed filehandles and such. There are other methods to get game servers running as a service. As far as "using either of those" goes you clearly don't know what they are as instsrv is used to create service's and srvany to run any application as a service ( created by instsvr ) so you could never use instsrv to run a game server as a service as you state. Using svrany will never leave memory allocated or unclosed filehandles, dont know where u got this impression. You can even run an application that requires user interaction as a service, "Allow interaction with desktop" anyone? Even if this where a restriction ( which it isnt ) it leaves about 99.99% of servers out there; BHD and JO are the only two that spring to mind which required user interaction to start. But from what your saying all the others can perform better simply by running as a service? I think NOT! I think so, and the reason is because it's assigned to the Service Control Manager as the parent process that controls them. I think you are under the total missunderstanding that the SCM does anything other than monitor the processes it started, to ensure they are running. It has now effect on sheduling and hence performance what so ever. I am thinking in the realm of 2-4GB, so we are close there. So you put 4Gb of ram in your game server machines, nice but waistful :P Now back to the real stuff. The question was if it does NOT use it? Why that specific question? Because if it did use it you would need either a seperate binary per OS or runtime checks to make use of it. Since we are primarily talking about Fiber's here and given the fact that game servers dont even use threads to any great extent chances of them making use of and hence gaining benefit from them is so small its untrue. Hence the answer your looking for was NO plain and simple. The answer is that even if they do not use it, they benefit from the OS using it to prioritize the processes it runs which in turn is game servers in this topic, if it's handed over to SCM in windows or the appropriate process, or processes in Unix. They would only benifit if they OS ( kernel ) was using significantly less machine resources to do they job it did previously without them. I'd put it to you thats not the case as otherwise MS would be shouting from the houses that 2k3 10% or more quicker at running all your apps. They don't use it directly, but indirectly, gaining indirect benefits. Also as was said before, the benefit is not there unless your running more than a few(2-3 roughly) instances, Also, saying that an application can't benefit from new features that it doesn't use, but the OS uses on the application, is not a very sane statement, as the OS controls the application in the instances we are talking about. As far as my ability to use analagies, I don't think there is a problem with it at all. Again so why isn't MS shouting about this nice performance increase? Also, not all game servers are single threaded, some use between 2-6 threads. They do? Which? ( I'm talking real work threads here not basically idle threads )? UT for example uses a seperatethread to do DNS lookups but since they are so infrequent event doubling the performance ( which your not doing to see ) would have no persevable effect on the servers performance. Everyone has their opinion and is entitled to it and your welcome to think what you like as I am. Yes you are, no one's saying your not but when you take those opini
RE: [hlds] Odd lag problem
> >>> I didn't say XP was altered. XP is optmized that way via It's > >>> kernel, > >>> 2003 was optimized with a different set of parameters. > >> The source for this information? Or just speculation? > > Microsoft and device driver engineers as well. > And the link to white paper on this subject is? Sorry, none that I know of. I was under the understanding that it is basic knowledge. As for the engineers, I can't show you a link for obvious reasons, I apologize for bringing them into the discussion since I can't produce qoutes from them. > > Right regular redhat vs enterprise. Windows XP vs 2003. > > If you tweek it, you can give more priority to userland or > kernel mode > > as well as network or file. > You can tweak things to do a lot of things, what tweaks do > you know have been made that are relavent to running game > servers? Again a nice white paper would be good. A white paper would be a good idea, Also a nice white paper on why XP is better than 2003 for running game servers would be good as well. > >> You still havent give a reason why a game server run as > service runs > >> "better"? > >> Does it run under a different part of the OS? > >> Nar! > > True, if your generalizing it. > > Each OS has it's own version. > >> Does it have a different sheduler? > >> Nar! > > True, if your generalizing it. > > Each OS has it's own version. > I cant see what you are trying to say here; OS's have > versions? I think we are all aware of that :P Versions would be the version of the programs and libraries you mentioned above. > >> Does it run as a different priority? > >> Quite possibly but there's nothing to stop you doing this with a > >> foreground app. > > Yes it can. Why would you want it to use your Gui resources > instead of > > running in the background not using any at all. > So you think running an app as a service automatically > removes any gui calls it makes hence uses less resources and > CPU? Hmm let me just go laugh in the corner for a while! I mistated this, I was thinking one thing and saying another. If it's running as a service, then it's not using the Graphics hardware and PCI bus for any of the graphics, IE the HAL is not used as well, leaving the resources free for running processes. > >> You cant magiclly make an application perform better simplely by > >> running it as a service. If this where true we would run > everything > >> as services wouldnt we? > > No one said you could make it magically happen. Running > something as a > > service depends many factors such as can it be ran without > loading a > > gui and requiring no user interaction. > Actually there are few or no factors which influence an > application being able to run as a service, ever heard or > svrany / instsrv? Being more precise I was referring to applications that require user interaction to run, using srvany/instsrv will not solve that problem without adding additional overhead. Some Applications run well sith srvany/instsrv and some do not. Fortunately most games work well with it enough for us to use them to a point. However using either of those is not a very good way to do so as it doesn't close the application properly and can leave system memory allocation fragments/unclosed filehandles and such. There are other methods to get game servers running as a service. > You can even run an application that requires user > interaction as a service, "Allow interaction with desktop" anyone? > Even if this where a restriction ( which it isnt ) it leaves > about 99.99% of servers out there; BHD and JO are the only > two that spring to mind which required user interaction to > start. But from what your saying all the others can perform > better simply by running as a service? I think NOT! I think so, and the reason is because it's assigned to the Service Control Manager as the parent process that controls them. > >>> SQL server does need huge memory support, and running > multiple game > >>> servers you need it as well. > >> If your game servers need multi GB's of memory I suggest there's > >> something wrong somewhere. > > Thanks for the suggestion, but nothing is wrong when your running > > multiple processes that each require and avg of 100MB of memory. > I think we have a very different idea about huge amounts of > memory a dual CPU machine with 2GB ( small amount of ram ) > will happily run all the servers the CPU can handle and still > have loads left for disk cache etc. So large amounts of RAM > such as that used on a good size DB machine e.g. 4+GB is just > not required on a game server. I am thinking in the realm of 2-4GB, so we are close there. > >>> Actually, wether it uses the API's or not, Windows itself > will use > >>> that model to optimize the processes it is running, including > >>> multiple gameservers. > >> So an application can benifit from the existence of an API > it doesnt > >> use directly or indirectly hmm perhaps not :P > > It can, if it doesn't use it directly and a parent process that
