RE: [hlds] Re: What does RCON STATS CPU Really mean?
Look at the FPS though... it drops, right? And maybe the stats command stress the CPU or HLDS? :-) -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Whisper Sent: 20. mai 2005 06:05 To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? -- [ Picked text/plain from multipart/alternative ] Clayton the sampling might be correct, but how would that explain the results I get when I spam rcon stats into console and receive numbers that are all within 10% of each other? Here is exmple: 14:03:37 stats 14:03:37 CPU In Out Uptime Users FPS Players 86.53 73784.24 227882.64 177 6 56.87 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.53 74690.58 228744.00 177 6 63.98 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 75565.57 229665.05 177 6 35.32 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 76380.45 231317.58 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77197.75 232984.47 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77256.87 234898.08 177 6 30.10 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77242.05 236992.31 177 6 26.96 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77264.55 238138.23 177 6 33.02 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 95.31 77243.81 238387.27 177 6 33.04 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77214.17 238615.45 177 6 40.99 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77057.98 238889.06 177 6 34.12 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 76746.83 239109.53 177 6 33.05 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.57 76242.27 239287.92 177 6 57.57 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75778.00 238699.22 177 6 37.94 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75704.43 238780.63 177 6 60.21 39 14:03:41 stats 14:03:42 CPU In Out Uptime Users FPS Players 94.30 75405.64 238652.98 177 6 25.60 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75245.19 238275.91 177 6 28.43 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75358.87 238213.38 177 6 27.67 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75571.36 237885.63 177 6 28.46 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 93.41 76112.34 237668.05 177 6 30.11 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 89.06 76824.73 237348.69 177 6 60.34 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 89.06 77527.95 237276.89 177 6 36.56 39 14:03:43 stats 14:03:44 CPU In Out Uptime Users FPS Players 89.06 77854.19 237533.16 177 6 46.56 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 77517.18 238679.83 177 6 34.15 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 77084.93 240084.63 177 6 36.57 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 76791.86 241383.80 177 6 31.04 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 90.63 76871.59 242368.47 177 6 22.76 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 91.71 77053.85 242882.44 177 6 23.81 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 91.71 77454.66 242307.06 177 6 32.04 39 14:03:45 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.71 78062.38 240988.48 177 6 35.32 39 14:03:46 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.71 78272.21 239666.45 177 6 32.02 39 14:03:46 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.83 78384.60 238314.08 177 6 36.57 39 14:03:46 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.83 78409.96 237305.31 177 6 33.04 39 Now you cannot tell me that this is not odd and that this is some sort of time sampling mismatch task manager ought to damn well show something that approximates what SRCDS is reporting back or vice versa, but it does not! On 5/20/05, Clayton Macleod [EMAIL PROTECTED] wrote: true, but you have to sample for a certain period of time to get a percentage reading. Obviously I'm just guessing that the period that the game's using is shorter than the period that task manager uses, but it would seem to make sense considering the observations. Why would that be so hard to accept? If you're only sampling usage for 0.1 seconds and you see a 99% value there's nothing wrong with that, even if task manager only showed 10% usage at the same time, since task manager samples for 1.0 seconds and it could have been idle for the other 0.9 seconds, which would indeed mean 10% usage for task manager's period. On 5/19/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] Well it is not like anybody has stepped up and stated categorically what it really means and is able
Re: [hlds] Re: What does RCON STATS CPU Really mean?
-- [ Picked text/plain from multipart/alternative ] There does appear to be a correlation between the FPS and the CPU numbers The 18 player server though seems to cope quite well with: fps_max 600 sv_maxrate 2000 sv_maxupdaterate 120 tickrate 100 whilst maintaining 500 FPS The 40 player server though (which I never expect to run constantly at 500 fps) seems to cope quite well with: fps_max 600 sv_maxrate 2000 sv_maxupdaterate 100 tickrate 66 The but the overall playing experience on the 40 Player server for people with client computers that can keep up, results in a excellent end result especially considering the numbers of players. On 5/20/05, Alexander Kobbevik [EMAIL PROTECTED] wrote: Look at the FPS though... it drops, right? And maybe the stats command stress the CPU or HLDS? :-) -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Whisper Sent: 20. mai 2005 06:05 To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? -- [ Picked text/plain from multipart/alternative ] Clayton the sampling might be correct, but how would that explain the results I get when I spam rcon stats into console and receive numbers that are all within 10% of each other? Here is exmple: 14:03:37 stats 14:03:37 CPU In Out Uptime Users FPS Players 86.53 73784.24 227882.64 177 6 56.87 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.53 74690.58 228744.00 177 6 63.98 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 75565.57 229665.05 177 6 35.32 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 76380.45 231317.58 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77197.75 232984.47 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77256.87 234898.08 177 6 30.10 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77242.05 236992.31 177 6 26.96 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77264.55 238138.23 177 6 33.02 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 95.31 77243.81 238387.27 177 6 33.04 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77214.17 238615.45 177 6 40.99 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77057.98 238889.06 177 6 34.12 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 76746.83 239109.53 177 6 33.05 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.57 76242.27 239287.92 177 6 57.57 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75778.00 238699.22 177 6 37.94 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75704.43 238780.63 177 6 60.21 39 14:03:41 stats 14:03:42 CPU In Out Uptime Users FPS Players 94.30 75405.64 238652.98 177 6 25.60 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75245.19 238275.91 177 6 28.43 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75358.87 238213.38 177 6 27.67 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75571.36 237885.63 177 6 28.46 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 93.41 76112.34 237668.05 177 6 30.11 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 89.06 76824.73 237348.69 177 6 60.34 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 89.06 77527.95 237276.89 177 6 36.56 39 14:03:43 stats 14:03:44 CPU In Out Uptime Users FPS Players 89.06 77854.19 237533.16 177 6 46.56 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 77517.18 238679.83 177 6 34.15 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 77084.93 240084.63 177 6 36.57 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 76791.86 241383.80 177 6 31.04 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 90.63 76871.59 242368.47 177 6 22.76 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 91.71 77053.85 242882.44 177 6 23.81 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 91.71 77454.66 242307.06 177 6 32.04 39 14:03:45 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.71 78062.38 240988.48 177 6 35.32 39 14:03:46 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.71 78272.21 239666.45 177 6 32.02 39 14:03:46 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.83 78384.60 238314.08 177 6 36.57 39 14:03:46 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.83 78409.96 237305.31 177 6 33.04 39 Now you cannot tell me that this is not odd and that this is some sort of time sampling mismatch task manager ought to damn well show something that approximates what SRCDS is reporting back or vice versa, but it does not! On 5/20/05, Clayton Macleod [EMAIL PROTECTED] wrote: true, but you have
Re: [hlds] Re: What does RCON STATS CPU Really mean?
Out of interest, how much cpu do others think a 40 slot game server would take when fully loaded? Not sure if you said what spec the CPUs are. I'd probably guess its about right (can't be that far off whatever) and expect most current CPUs to hit 85% or so with that. On 5/20/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] There does appear to be a correlation between the FPS and the CPU numbers The 18 player server though seems to cope quite well with: fps_max 600 sv_maxrate 2000 sv_maxupdaterate 120 tickrate 100 whilst maintaining 500 FPS The 40 player server though (which I never expect to run constantly at 500 fps) seems to cope quite well with: fps_max 600 sv_maxrate 2000 sv_maxupdaterate 100 tickrate 66 The but the overall playing experience on the 40 Player server for people with client computers that can keep up, results in a excellent end result especially considering the numbers of players. On 5/20/05, Alexander Kobbevik [EMAIL PROTECTED] wrote: Look at the FPS though... it drops, right? And maybe the stats command stress the CPU or HLDS? :-) -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Whisper Sent: 20. mai 2005 06:05 To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? -- [ Picked text/plain from multipart/alternative ] Clayton the sampling might be correct, but how would that explain the results I get when I spam rcon stats into console and receive numbers that are all within 10% of each other? Here is exmple: 14:03:37 stats 14:03:37 CPU In Out Uptime Users FPS Players 86.53 73784.24 227882.64 177 6 56.87 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.53 74690.58 228744.00 177 6 63.98 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 75565.57 229665.05 177 6 35.32 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 76380.45 231317.58 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77197.75 232984.47 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77256.87 234898.08 177 6 30.10 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77242.05 236992.31 177 6 26.96 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77264.55 238138.23 177 6 33.02 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 95.31 77243.81 238387.27 177 6 33.04 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77214.17 238615.45 177 6 40.99 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77057.98 238889.06 177 6 34.12 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 76746.83 239109.53 177 6 33.05 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.57 76242.27 239287.92 177 6 57.57 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75778.00 238699.22 177 6 37.94 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75704.43 238780.63 177 6 60.21 39 14:03:41 stats 14:03:42 CPU In Out Uptime Users FPS Players 94.30 75405.64 238652.98 177 6 25.60 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75245.19 238275.91 177 6 28.43 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75358.87 238213.38 177 6 27.67 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75571.36 237885.63 177 6 28.46 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 93.41 76112.34 237668.05 177 6 30.11 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 89.06 76824.73 237348.69 177 6 60.34 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 89.06 77527.95 237276.89 177 6 36.56 39 14:03:43 stats 14:03:44 CPU In Out Uptime Users FPS Players 89.06 77854.19 237533.16 177 6 46.56 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 77517.18 238679.83 177 6 34.15 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 77084.93 240084.63 177 6 36.57 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 76791.86 241383.80 177 6 31.04 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 90.63 76871.59 242368.47 177 6 22.76 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 91.71 77053.85 242882.44 177 6 23.81 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 91.71 77454.66 242307.06 177 6 32.04 39 14:03:45 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.71 78062.38 240988.48 177 6 35.32 39 14:03:46 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.71 78272.21 239666.45 177 6 32.02 39 14:03:46 stats 14:03:46 CPU In Out Uptime Users FPS Players
Re: [hlds] Re: What does RCON STATS CPU Really mean?
-- [ Picked text/plain from multipart/alternative ] Ian thats my(our) problem SRCDS stats shows numbers like 90%, ok fair enough when the round starts and and there are 40 players on the server. The server still appears to run fine from a players perspective, everything is as responsive as normal, or better than normal because the server is actually under utilised atm. BUT every Windows performance monitoring tool says neither physical CPU is going past 50% and none of us can afford to sit there all day typing rcon stats or just plain stats directly into the console just to keep an eye on the CPU usage for SRCDS and trying to guage player experience. The server is a Dual P4 3.6GHz Xeon with 4GB of RAM (I was mistaken I was quoting 3GB before, but its actually 4GB) It is very difficult to maximise the benefit of this sort of hardware if you cannot get decent performace numbers. I think we have all seen SRCDS crap out and players start warping all over the place, pings skyrocket or pings are substantially higher than average, ie. you are getting 80ms average pings when 40ms is the norm, no shot registration etc etc. All the things CS players whine and bitch about and what all server adminsitrators try to avoid if at all possible, if for no reason other than not having to listen to bitching CS players! :) That being said, its bloody well difficult to do the tweaking of you setups if the in game player experience (good or bad) is not being matched by the numbers Windows reports back to you, in terms of CPU usage (overall), CPU usage (per CPU), and CPU usage (per process). On 5/20/05, Ian mu [EMAIL PROTECTED] wrote: Out of interest, how much cpu do others think a 40 slot game server would take when fully loaded? Not sure if you said what spec the CPUs are. I'd probably guess its about right (can't be that far off whatever) and expect most current CPUs to hit 85% or so with that. On 5/20/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] There does appear to be a correlation between the FPS and the CPU numbers The 18 player server though seems to cope quite well with: fps_max 600 sv_maxrate 2000 sv_maxupdaterate 120 tickrate 100 whilst maintaining 500 FPS The 40 player server though (which I never expect to run constantly at 500 fps) seems to cope quite well with: fps_max 600 sv_maxrate 2000 sv_maxupdaterate 100 tickrate 66 The but the overall playing experience on the 40 Player server for people with client computers that can keep up, results in a excellent end result especially considering the numbers of players. On 5/20/05, Alexander Kobbevik [EMAIL PROTECTED] wrote: Look at the FPS though... it drops, right? And maybe the stats command stress the CPU or HLDS? :-) -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Whisper Sent: 20. mai 2005 06:05 To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? -- [ Picked text/plain from multipart/alternative ] Clayton the sampling might be correct, but how would that explain the results I get when I spam rcon stats into console and receive numbers that are all within 10% of each other? Here is exmple: 14:03:37 stats 14:03:37 CPU In Out Uptime Users FPS Players 86.53 73784.24 227882.64 177 6 56.87 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.53 74690.58 228744.00 177 6 63.98 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 75565.57 229665.05 177 6 35.32 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 76380.45 231317.58 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77197.75 232984.47 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77256.87 234898.08 177 6 30.10 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77242.05 236992.31 177 6 26.96 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77264.55 238138.23 177 6 33.02 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 95.31 77243.81 238387.27 177 6 33.04 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77214.17 238615.45 177 6 40.99 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77057.98 238889.06 177 6 34.12 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 76746.83 239109.53 177 6 33.05 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.57 76242.27 239287.92 177 6 57.57 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75778.00 238699.22 177 6 37.94 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75704.43 238780.63 177 6 60.21 39 14:03:41 stats 14:03:42
Re: [hlds] Re: What does RCON STATS CPU Really mean?
I run 2 40 person servers on a p4 3.0 ghz 1 gig of ram with about 40 people total im running about 85% usage(working on getting a duel processor computer) that should fix alot of my problems with low fps - Original Message - From: Ian mu [EMAIL PROTECTED] To: hlds@list.valvesoftware.com Sent: Friday, May 20, 2005 3:09 AM Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? Out of interest, how much cpu do others think a 40 slot game server would take when fully loaded? Not sure if you said what spec the CPUs are. I'd probably guess its about right (can't be that far off whatever) and expect most current CPUs to hit 85% or so with that. On 5/20/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] There does appear to be a correlation between the FPS and the CPU numbers The 18 player server though seems to cope quite well with: fps_max 600 sv_maxrate 2000 sv_maxupdaterate 120 tickrate 100 whilst maintaining 500 FPS The 40 player server though (which I never expect to run constantly at 500 fps) seems to cope quite well with: fps_max 600 sv_maxrate 2000 sv_maxupdaterate 100 tickrate 66 The but the overall playing experience on the 40 Player server for people with client computers that can keep up, results in a excellent end result especially considering the numbers of players. On 5/20/05, Alexander Kobbevik [EMAIL PROTECTED] wrote: Look at the FPS though... it drops, right? And maybe the stats command stress the CPU or HLDS? :-) -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Whisper Sent: 20. mai 2005 06:05 To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? -- [ Picked text/plain from multipart/alternative ] Clayton the sampling might be correct, but how would that explain the results I get when I spam rcon stats into console and receive numbers that are all within 10% of each other? Here is exmple: 14:03:37 stats 14:03:37 CPU In Out Uptime Users FPS Players 86.53 73784.24 227882.64 177 6 56.87 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.53 74690.58 228744.00 177 6 63.98 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 75565.57 229665.05 177 6 35.32 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 76380.45 231317.58 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77197.75 232984.47 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77256.87 234898.08 177 6 30.10 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77242.05 236992.31 177 6 26.96 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77264.55 238138.23 177 6 33.02 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 95.31 77243.81 238387.27 177 6 33.04 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77214.17 238615.45 177 6 40.99 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77057.98 238889.06 177 6 34.12 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 76746.83 239109.53 177 6 33.05 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.57 76242.27 239287.92 177 6 57.57 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75778.00 238699.22 177 6 37.94 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75704.43 238780.63 177 6 60.21 39 14:03:41 stats 14:03:42 CPU In Out Uptime Users FPS Players 94.30 75405.64 238652.98 177 6 25.60 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75245.19 238275.91 177 6 28.43 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75358.87 238213.38 177 6 27.67 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75571.36 237885.63 177 6 28.46 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 93.41 76112.34 237668.05 177 6 30.11 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 89.06 76824.73 237348.69 177 6 60.34 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 89.06 77527.95 237276.89 177 6 36.56 39 14:03:43 stats 14:03:44 CPU In Out Uptime Users FPS Players 89.06 77854.19 237533.16 177 6 46.56 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 77517.18 238679.83 177 6 34.15 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 77084.93 240084.63 177 6 36.57 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 76791.86 241383.80 177 6 31.04 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 90.63 76871.59 242368.47 177 6 22.76 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 91.71 77053.85 242882.44 177 6 23.81 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 91.71 77454.66 242307.06 177 6 32.04 39 14:03:45 stats
Re: [hlds] Re: What does RCON STATS CPU Really mean?
-- [ Picked text/plain from multipart/alternative ] We like both types of music here Country AND Western! :D On 5/21/05, sprout [EMAIL PROTECTED] wrote: I run 2 40 person servers on a p4 3.0 ghz 1 gig of ram with about 40 people total im running about 85% usage(working on getting a duel processor computer) that should fix alot of my problems with low fps - Original Message - From: Ian mu [EMAIL PROTECTED] To: hlds@list.valvesoftware.com Sent: Friday, May 20, 2005 3:09 AM Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? Out of interest, how much cpu do others think a 40 slot game server would take when fully loaded? Not sure if you said what spec the CPUs are. I'd probably guess its about right (can't be that far off whatever) and expect most current CPUs to hit 85% or so with that. On 5/20/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] There does appear to be a correlation between the FPS and the CPU numbers The 18 player server though seems to cope quite well with: fps_max 600 sv_maxrate 2000 sv_maxupdaterate 120 tickrate 100 whilst maintaining 500 FPS The 40 player server though (which I never expect to run constantly at 500 fps) seems to cope quite well with: fps_max 600 sv_maxrate 2000 sv_maxupdaterate 100 tickrate 66 The but the overall playing experience on the 40 Player server for people with client computers that can keep up, results in a excellent end result especially considering the numbers of players. On 5/20/05, Alexander Kobbevik [EMAIL PROTECTED] wrote: Look at the FPS though... it drops, right? And maybe the stats command stress the CPU or HLDS? :-) -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Whisper Sent: 20. mai 2005 06:05 To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? -- [ Picked text/plain from multipart/alternative ] Clayton the sampling might be correct, but how would that explain the results I get when I spam rcon stats into console and receive numbers that are all within 10% of each other? Here is exmple: 14:03:37 stats 14:03:37 CPU In Out Uptime Users FPS Players 86.53 73784.24 227882.64 177 6 56.87 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.53 74690.58 228744.00 177 6 63.98 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 75565.57 229665.05 177 6 35.32 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 76380.45 231317.58 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77197.75 232984.47 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77256.87 234898.08 177 6 30.10 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77242.05 236992.31 177 6 26.96 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77264.55 238138.23 177 6 33.02 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 95.31 77243.81 238387.27 177 6 33.04 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77214.17 238615.45 177 6 40.99 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77057.98 238889.06 177 6 34.12 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 76746.83 239109.53 177 6 33.05 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.57 76242.27 239287.92 177 6 57.57 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75778.00 238699.22 177 6 37.94 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75704.43 238780.63 177 6 60.21 39 14:03:41 stats 14:03:42 CPU In Out Uptime Users FPS Players 94.30 75405.64 238652.98 177 6 25.60 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75245.19 238275.91 177 6 28.43 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75358.87 238213.38 177 6 27.67 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75571.36 237885.63 177 6 28.46 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 93.41 76112.34 237668.05 177 6 30.11 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 89.06 76824.73 237348.69 177 6 60.34 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 89.06 77527.95 237276.89 177 6 36.56 39 14:03:43 stats 14:03:44 CPU In Out Uptime Users FPS Players 89.06 77854.19 237533.16 177 6 46.56 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 77517.18 238679.83 177 6 34.15 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 77084.93 240084.63 177 6 36.57 39 14:03:44 stats
Re: [hlds] Re: What does RCON STATS CPU Really mean?
country and western? did I miss something? - Original Message - From: Whisper [EMAIL PROTECTED] To: hlds@list.valvesoftware.com Sent: Friday, May 20, 2005 12:00 PM Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? -- [ Picked text/plain from multipart/alternative ] We like both types of music here Country AND Western! :D On 5/21/05, sprout [EMAIL PROTECTED] wrote: I run 2 40 person servers on a p4 3.0 ghz 1 gig of ram with about 40 people total im running about 85% usage(working on getting a duel processor computer) that should fix alot of my problems with low fps - Original Message - From: Ian mu [EMAIL PROTECTED] To: hlds@list.valvesoftware.com Sent: Friday, May 20, 2005 3:09 AM Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? Out of interest, how much cpu do others think a 40 slot game server would take when fully loaded? Not sure if you said what spec the CPUs are. I'd probably guess its about right (can't be that far off whatever) and expect most current CPUs to hit 85% or so with that. On 5/20/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] There does appear to be a correlation between the FPS and the CPU numbers The 18 player server though seems to cope quite well with: fps_max 600 sv_maxrate 2000 sv_maxupdaterate 120 tickrate 100 whilst maintaining 500 FPS The 40 player server though (which I never expect to run constantly at 500 fps) seems to cope quite well with: fps_max 600 sv_maxrate 2000 sv_maxupdaterate 100 tickrate 66 The but the overall playing experience on the 40 Player server for people with client computers that can keep up, results in a excellent end result especially considering the numbers of players. On 5/20/05, Alexander Kobbevik [EMAIL PROTECTED] wrote: Look at the FPS though... it drops, right? And maybe the stats command stress the CPU or HLDS? :-) -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Whisper Sent: 20. mai 2005 06:05 To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? -- [ Picked text/plain from multipart/alternative ] Clayton the sampling might be correct, but how would that explain the results I get when I spam rcon stats into console and receive numbers that are all within 10% of each other? Here is exmple: 14:03:37 stats 14:03:37 CPU In Out Uptime Users FPS Players 86.53 73784.24 227882.64 177 6 56.87 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.53 74690.58 228744.00 177 6 63.98 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 75565.57 229665.05 177 6 35.32 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 76380.45 231317.58 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77197.75 232984.47 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77256.87 234898.08 177 6 30.10 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77242.05 236992.31 177 6 26.96 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77264.55 238138.23 177 6 33.02 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 95.31 77243.81 238387.27 177 6 33.04 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77214.17 238615.45 177 6 40.99 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77057.98 238889.06 177 6 34.12 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 76746.83 239109.53 177 6 33.05 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.57 76242.27 239287.92 177 6 57.57 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75778.00 238699.22 177 6 37.94 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75704.43 238780.63 177 6 60.21 39 14:03:41 stats 14:03:42 CPU In Out Uptime Users FPS Players 94.30 75405.64 238652.98 177 6 25.60 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75245.19 238275.91 177 6 28.43 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75358.87 238213.38 177 6 27.67 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75571.36 237885.63 177 6 28.46 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 93.41 76112.34 237668.05 177 6 30.11 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 89.06 76824.73 237348.69 177 6 60.34 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 89.06 77527.95 237276.89 177 6 36.56 39 14:03:43 stats 14:03:44 CPU In Out Uptime Users FPS Players 89.06 77854.19 237533.16 177 6 46.56 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 77517.18 238679.83 177 6 34.15 39 14:03:44 stats 14:03:44
Re: [hlds] Re: What does RCON STATS CPU Really mean?
-- [ Picked text/plain from multipart/alternative ] Yeah, sprout, you missed the point of the entire thread!!! On 5/21/05, sprout [EMAIL PROTECTED] wrote: country and western? did I miss something? - Original Message - From: Whisper [EMAIL PROTECTED] To: hlds@list.valvesoftware.com Sent: Friday, May 20, 2005 12:00 PM Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? -- [ Picked text/plain from multipart/alternative ] We like both types of music here Country AND Western! :D On 5/21/05, sprout [EMAIL PROTECTED] wrote: I run 2 40 person servers on a p4 3.0 ghz 1 gig of ram with about 40 people total im running about 85% usage(working on getting a duel processor computer) that should fix alot of my problems with low fps - Original Message - From: Ian mu [EMAIL PROTECTED] To: hlds@list.valvesoftware.com Sent: Friday, May 20, 2005 3:09 AM Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? Out of interest, how much cpu do others think a 40 slot game server would take when fully loaded? Not sure if you said what spec the CPUs are. I'd probably guess its about right (can't be that far off whatever) and expect most current CPUs to hit 85% or so with that. On 5/20/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] There does appear to be a correlation between the FPS and the CPU numbers The 18 player server though seems to cope quite well with: fps_max 600 sv_maxrate 2000 sv_maxupdaterate 120 tickrate 100 whilst maintaining 500 FPS The 40 player server though (which I never expect to run constantly at 500 fps) seems to cope quite well with: fps_max 600 sv_maxrate 2000 sv_maxupdaterate 100 tickrate 66 The but the overall playing experience on the 40 Player server for people with client computers that can keep up, results in a excellent end result especially considering the numbers of players. On 5/20/05, Alexander Kobbevik [EMAIL PROTECTED] wrote: Look at the FPS though... it drops, right? And maybe the stats command stress the CPU or HLDS? :-) -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Whisper Sent: 20. mai 2005 06:05 To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? -- [ Picked text/plain from multipart/alternative ] Clayton the sampling might be correct, but how would that explain the results I get when I spam rcon stats into console and receive numbers that are all within 10% of each other? Here is exmple: 14:03:37 stats 14:03:37 CPU In Out Uptime Users FPS Players 86.53 73784.24 227882.64 177 6 56.87 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.53 74690.58 228744.00 177 6 63.98 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 75565.57 229665.05 177 6 35.32 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 76380.45 231317.58 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77197.75 232984.47 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77256.87 234898.08 177 6 30.10 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77242.05 236992.31 177 6 26.96 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77264.55 238138.23 177 6 33.02 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 95.31 77243.81 238387.27 177 6 33.04 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77214.17 238615.45 177 6 40.99 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77057.98 238889.06 177 6 34.12 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 76746.83 239109.53 177 6 33.05 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.57 76242.27 239287.92 177 6 57.57 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75778.00 238699.22 177 6 37.94 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75704.43 238780.63 177 6 60.21 39 14:03:41 stats 14:03:42 CPU In Out Uptime Users FPS Players 94.30 75405.64 238652.98 177 6 25.60 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75245.19 238275.91 177 6 28.43 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75358.87 238213.38 177 6 27.67 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75571.36 237885.63 177 6 28.46 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 93.41 76112.34 237668.05 177 6 30.11 39 14:03:43 stats 14
Re: [hlds] Re: What does RCON STATS CPU Really mean?
On Fri, May 20, 2005 at 12:42:24PM -0500, sprout wrote: country and western? did I miss something? Yes, it's called The Blues Brothers. -- Hexis www.hxxl.com ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
RE: [hlds] Re: What does RCON STATS CPU Really mean?
I stopped reading this thread a few days back (when it went off the rails) but the code does the following every 5 seconds to determine CPU usage: GetProcessTimes (handle, creationTime, exitTime, kernelTime, totalTime); GetSystemTimeAsFileTime(nowTime); m_fCPUPercent = (totalTime-lastTotalTime)/(nowTime-lastNow); lastNow = nowTime; lastTotalTime = totalTime; So we ask windows how much time did you give me and how long have I been running, and we take those away from the last sample. In a HT or SMP configurations this could result in each process consuming 100% cpu (100% execution time on one CPU). - Alfred Original Message From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Whisper Sent: Friday, May 20, 2005 11:37 AM To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? -- [ Picked text/plain from multipart/alternative ] Yeah, sprout, you missed the point of the entire thread!!! On 5/21/05, sprout [EMAIL PROTECTED] wrote: country and western? did I miss something? - Original Message - From: Whisper [EMAIL PROTECTED] To: hlds@list.valvesoftware.com Sent: Friday, May 20, 2005 12:00 PM Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? -- [ Picked text/plain from multipart/alternative ] We like both types of music here Country AND Western! D On 5/21/05, sprout [EMAIL PROTECTED] wrote: I run 2 40 person servers on a p4 3.0 ghz 1 gig of ram with about 40 people total im running about 85% usage(working on getting a duel processor computer) that should fix alot of my problems with low fps - Original Message - From: Ian mu [EMAIL PROTECTED] To: hlds@list.valvesoftware.com Sent: Friday, May 20, 2005 3:09 AM Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? Out of interest, how much cpu do others think a 40 slot game server would take when fully loaded? Not sure if you said what spec the CPUs are. I'd probably guess its about right (can't be that far off whatever) and expect most current CPUs to hit 85% or so with that. On 5/20/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] There does appear to be a correlation between the FPS and the CPU numbers The 18 player server though seems to cope quite well with: fps_max 600 sv_maxrate 2000 sv_maxupdaterate 120 tickrate 100 whilst maintaining 500 FPS The 40 player server though (which I never expect to run constantly at 500 fps) seems to cope quite well with: fps_max 600 sv_maxrate 2000 sv_maxupdaterate 100 tickrate 66 The but the overall playing experience on the 40 Player server for people with client computers that can keep up, results in a excellent end result especially considering the numbers of players. On 5/20/05, Alexander Kobbevik [EMAIL PROTECTED] wrote: Look at the FPS though... it drops, right? And maybe the stats command stress the CPU or HLDS? :-) -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Whisper Sent: 20. mai 2005 06:05 To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? -- [ Picked text/plain from multipart/alternative ] Clayton the sampling might be correct, but how would that explain the results I get when I spam rcon stats into console and receive numbers that are all within 10% of each other? Here is exmple: 14:03:37 stats 14:03:37 CPU In Out Uptime Users FPS Players 86.53 73784.24 227882.64 177 6 56.87 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.53 74690.58 228744.00 177 6 63.98 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 75565.57 229665.05 177 6 35.32 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 76380.45 231317.58 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77197.75 232984.47 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77256.87 234898.08 177 6 30.10 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77242.05 236992.31 177 6 26.96 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77264.55 238138.23 177 6 33.02 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 95.31 77243.81 238387.27 177 6 33.04 39 14:03:40 stats 14:03
Re: [hlds] Re: What does RCON STATS CPU Really mean?
-- [ Picked text/plain from multipart/alternative ] Ok HyperThreading is turned off and Taskmangers CPU still does not look anything like what SRCDS STATS CPU usage states. The reason I want to know is that SRCDS CPU usage does give decent feedback as to how the game feels to players, and when the SRCDS CPU usage gets right up to the 85% mark the end user experience for clients connected to the server process degrades, but the CPU usage for the physical server doesn't seem to register any excessive CPU usage issues, thus making it difficult to correctly balance the physical servers loading and the SRCDS server setup. So anybody got any other idea's? On 5/13/05, Ian mu [EMAIL PROTECTED] wrote: Think you missed the point, what is snmp basing the information on? On 5/12/05, K2 [EMAIL PROTECTED] wrote: Exactly... and SNMP is your best bet for that. The counters you can grab the data from are going to be more accurate than anything a third-party app (read: valve) is going to put out. That's why I said 'hey fellas, learn how to use MRTG' ;-) Good site to check out to get the required MIB's for win32 and also how-to's on how to get everything setup - http://www.wtcs.org/snmp4tpc/default.htm - K2 -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of m0gely Sent: Thursday, May 12, 2005 9:02 AM To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? K2 wrote: Learn how to use MRTG fellas... That's about as accurate as it gets. nuff said ;-) http://bubba.hardfought.org/mrtg/67.19.85.2_cpu.html - K2 MRTG is only a graphing app. It needs to have something to tell it what to graph. So whatever script (or via SNMP) you're using to tell MRTG what the CPU usage is, that's where the info is coming from. -- - m0gely http://quake2.telestream.com/ Q2 | Q3A | Counter-strike ___ 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] Re: What does RCON STATS CPU Really mean?
What value does physical server show when its at 85% in rcon stats? On 5/19/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] Ok HyperThreading is turned off and Taskmangers CPU still does not look anything like what SRCDS STATS CPU usage states. The reason I want to know is that SRCDS CPU usage does give decent feedback as to how the game feels to players, and when the SRCDS CPU usage gets right up to the 85% mark the end user experience for clients connected to the server process degrades, but the CPU usage for the physical server doesn't seem to register any excessive CPU usage issues, thus making it difficult to correctly balance the physical servers loading and the SRCDS server setup. So anybody got any other idea's? On 5/13/05, Ian mu [EMAIL PROTECTED] wrote: Think you missed the point, what is snmp basing the information on? On 5/12/05, K2 [EMAIL PROTECTED] wrote: Exactly... and SNMP is your best bet for that. The counters you can grab the data from are going to be more accurate than anything a third-party app (read: valve) is going to put out. That's why I said 'hey fellas, learn how to use MRTG' ;-) Good site to check out to get the required MIB's for win32 and also how-to's on how to get everything setup - http://www.wtcs.org/snmp4tpc/default.htm - K2 -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of m0gely Sent: Thursday, May 12, 2005 9:02 AM To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? K2 wrote: Learn how to use MRTG fellas... That's about as accurate as it gets. nuff said ;-) http://bubba.hardfought.org/mrtg/67.19.85.2_cpu.html - K2 MRTG is only a graphing app. It needs to have something to tell it what to graph. So whatever script (or via SNMP) you're using to tell MRTG what the CPU usage is, that's where the info is coming from. -- - m0gely http://quake2.telestream.com/ Q2 | Q3A | Counter-strike ___ 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] Re: What does RCON STATS CPU Really mean?
-- [ Picked text/plain from multipart/alternative ] Never goes above 50% on a single CPU according to task manager set to show both CPU's Hell we never even use more than 400MB of RAM with 1 x 40 1 X 18 CSS Servers This is just a test server to establish baselines so we can work out how to reassign our CSS Servers and maximise players online gaming experience. To date, getting definitive answers to subjects such as CPU Usage and SRCDS settings (especially the Netcode variables) is next to impossible. I have worked a few things out with the help of bits and pieces of hints dropped here and there, but nothing that you would consider the definitive and reproduceable, regardless of the exception the quality of the Network is. Now Im going to get some stupid spam warning message from Brazil :( On 5/20/05, Ian mu [EMAIL PROTECTED] wrote: What value does physical server show when its at 85% in rcon stats? On 5/19/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] Ok HyperThreading is turned off and Taskmangers CPU still does not look anything like what SRCDS STATS CPU usage states. The reason I want to know is that SRCDS CPU usage does give decent feedback as to how the game feels to players, and when the SRCDS CPU usage gets right up to the 85% mark the end user experience for clients connected to the server process degrades, but the CPU usage for the physical server doesn't seem to register any excessive CPU usage issues, thus making it difficult to correctly balance the physical servers loading and the SRCDS server setup. So anybody got any other idea's? On 5/13/05, Ian mu [EMAIL PROTECTED] wrote: Think you missed the point, what is snmp basing the information on? On 5/12/05, K2 [EMAIL PROTECTED] wrote: Exactly... and SNMP is your best bet for that. The counters you can grab the data from are going to be more accurate than anything a third-party app (read: valve) is going to put out. That's why I said 'hey fellas, learn how to use MRTG' ;-) Good site to check out to get the required MIB's for win32 and also how-to's on how to get everything setup - http://www.wtcs.org/snmp4tpc/default.htm - K2 -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of m0gely Sent: Thursday, May 12, 2005 9:02 AM To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? K2 wrote: Learn how to use MRTG fellas... That's about as accurate as it gets. nuff said ;-) http://bubba.hardfought.org/mrtg/67.19.85.2_cpu.html - K2 MRTG is only a graphing app. It needs to have something to tell it what to graph. So whatever script (or via SNMP) you're using to tell MRTG what the CPU usage is, that's where the info is coming from. -- - m0gely http://quake2.telestream.com/ Q2 | Q3A | Counter-strike ___ 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 -- ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
Re: [hlds] Re: What does RCON STATS CPU Really mean?
Is it getting to about 42%? As thats what I'd expect basically. On 5/19/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] Never goes above 50% on a single CPU according to task manager set to show both CPU's Hell we never even use more than 400MB of RAM with 1 x 40 1 X 18 CSS Servers This is just a test server to establish baselines so we can work out how to reassign our CSS Servers and maximise players online gaming experience. To date, getting definitive answers to subjects such as CPU Usage and SRCDS settings (especially the Netcode variables) is next to impossible. I have worked a few things out with the help of bits and pieces of hints dropped here and there, but nothing that you would consider the definitive and reproduceable, regardless of the exception the quality of the Network is. Now Im going to get some stupid spam warning message from Brazil :( On 5/20/05, Ian mu [EMAIL PROTECTED] wrote: What value does physical server show when its at 85% in rcon stats? On 5/19/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] Ok HyperThreading is turned off and Taskmangers CPU still does not look anything like what SRCDS STATS CPU usage states. The reason I want to know is that SRCDS CPU usage does give decent feedback as to how the game feels to players, and when the SRCDS CPU usage gets right up to the 85% mark the end user experience for clients connected to the server process degrades, but the CPU usage for the physical server doesn't seem to register any excessive CPU usage issues, thus making it difficult to correctly balance the physical servers loading and the SRCDS server setup. So anybody got any other idea's? On 5/13/05, Ian mu [EMAIL PROTECTED] wrote: Think you missed the point, what is snmp basing the information on? On 5/12/05, K2 [EMAIL PROTECTED] wrote: Exactly... and SNMP is your best bet for that. The counters you can grab the data from are going to be more accurate than anything a third-party app (read: valve) is going to put out. That's why I said 'hey fellas, learn how to use MRTG' ;-) Good site to check out to get the required MIB's for win32 and also how-to's on how to get everything setup - http://www.wtcs.org/snmp4tpc/default.htm - K2 -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of m0gely Sent: Thursday, May 12, 2005 9:02 AM To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? K2 wrote: Learn how to use MRTG fellas... That's about as accurate as it gets. nuff said ;-) http://bubba.hardfought.org/mrtg/67.19.85.2_cpu.html - K2 MRTG is only a graphing app. It needs to have something to tell it what to graph. So whatever script (or via SNMP) you're using to tell MRTG what the CPU usage is, that's where the info is coming from. -- - m0gely http://quake2.telestream.com/ Q2 | Q3A | Counter-strike ___ 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 -- ___ 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] Re: What does RCON STATS CPU Really mean?
Yep but you have 2 physical CPUs no? (lost track a bit) On 5/19/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] For one physical CPU thats about right. HT is turned *OFF* so we are definitely measuring physical CPU usage. ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
Re: [hlds] Re: What does RCON STATS CPU Really mean?
The sampling period for Task Manager is an entire second. Just seems to me that the stats command here is using a much shorter sampling period, no? Seems like a fairly long conversation for almost no reason, sorry :) On 5/19/05, Ian mu [EMAIL PROTECTED] wrote: Yep but you have 2 physical CPUs no? (lost track a bit) On 5/19/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] For one physical CPU thats about right. HT is turned *OFF* so we are definitely measuring physical CPU usage. ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds -- Clayton Macleod ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
Re: [hlds] Re: What does RCON STATS CPU Really mean?
-- [ Picked text/plain from multipart/alternative ] Well it is not like anybody has stepped up and stated categorically what it really means and is able to explain the discrepancies between the 2 that a critically thinking human being would accept. On 5/20/05, Clayton Macleod [EMAIL PROTECTED] wrote: The sampling period for Task Manager is an entire second. Just seems to me that the stats command here is using a much shorter sampling period, no? Seems like a fairly long conversation for almost no reason, sorry :) On 5/19/05, Ian mu [EMAIL PROTECTED] wrote: Yep but you have 2 physical CPUs no? (lost track a bit) On 5/19/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] For one physical CPU thats about right. HT is turned *OFF* so we are definitely measuring physical CPU usage. ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds -- Clayton Macleod ___ 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] Re: What does RCON STATS CPU Really mean?
true, but you have to sample for a certain period of time to get a percentage reading. Obviously I'm just guessing that the period that the game's using is shorter than the period that task manager uses, but it would seem to make sense considering the observations. Why would that be so hard to accept? If you're only sampling usage for 0.1 seconds and you see a 99% value there's nothing wrong with that, even if task manager only showed 10% usage at the same time, since task manager samples for 1.0 seconds and it could have been idle for the other 0.9 seconds, which would indeed mean 10% usage for task manager's period. On 5/19/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] Well it is not like anybody has stepped up and stated categorically what it really means and is able to explain the discrepancies between the 2 that a critically thinking human being would accept. -- Clayton Macleod ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
Re: [hlds] Re: What does RCON STATS CPU Really mean?
-- [ Picked text/plain from multipart/alternative ] Clayton the sampling might be correct, but how would that explain the results I get when I spam rcon stats into console and receive numbers that are all within 10% of each other? Here is exmple: 14:03:37 stats 14:03:37 CPU In Out Uptime Users FPS Players 86.53 73784.24 227882.64 177 6 56.87 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.53 74690.58 228744.00 177 6 63.98 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 75565.57 229665.05 177 6 35.32 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 76380.45 231317.58 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77197.75 232984.47 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77256.87 234898.08 177 6 30.10 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77242.05 236992.31 177 6 26.96 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77264.55 238138.23 177 6 33.02 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 95.31 77243.81 238387.27 177 6 33.04 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77214.17 238615.45 177 6 40.99 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77057.98 238889.06 177 6 34.12 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 76746.83 239109.53 177 6 33.05 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.57 76242.27 239287.92 177 6 57.57 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75778.00 238699.22 177 6 37.94 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75704.43 238780.63 177 6 60.21 39 14:03:41 stats 14:03:42 CPU In Out Uptime Users FPS Players 94.30 75405.64 238652.98 177 6 25.60 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75245.19 238275.91 177 6 28.43 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75358.87 238213.38 177 6 27.67 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75571.36 237885.63 177 6 28.46 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 93.41 76112.34 237668.05 177 6 30.11 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 89.06 76824.73 237348.69 177 6 60.34 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 89.06 77527.95 237276.89 177 6 36.56 39 14:03:43 stats 14:03:44 CPU In Out Uptime Users FPS Players 89.06 77854.19 237533.16 177 6 46.56 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 77517.18 238679.83 177 6 34.15 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 77084.93 240084.63 177 6 36.57 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 76791.86 241383.80 177 6 31.04 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 90.63 76871.59 242368.47 177 6 22.76 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 91.71 77053.85 242882.44 177 6 23.81 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 91.71 77454.66 242307.06 177 6 32.04 39 14:03:45 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.71 78062.38 240988.48 177 6 35.32 39 14:03:46 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.71 78272.21 239666.45 177 6 32.02 39 14:03:46 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.83 78384.60 238314.08 177 6 36.57 39 14:03:46 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.83 78409.96 237305.31 177 6 33.04 39 Now you cannot tell me that this is not odd and that this is some sort of time sampling mismatch task manager ought to damn well show something that approximates what SRCDS is reporting back or vice versa, but it does not! On 5/20/05, Clayton Macleod [EMAIL PROTECTED] wrote: true, but you have to sample for a certain period of time to get a percentage reading. Obviously I'm just guessing that the period that the game's using is shorter than the period that task manager uses, but it would seem to make sense considering the observations. Why would that be so hard to accept? If you're only sampling usage for 0.1 seconds and you see a 99% value there's nothing wrong with that, even if task manager only showed 10% usage at the same time, since task manager samples for 1.0 seconds and it could have been idle for the other 0.9 seconds, which would indeed mean 10% usage for task manager's period. On 5/19/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] Well it is not like anybody has stepped up and stated categorically what it really means and is able to explain the discrepancies between the 2 that a critically thinking human being would accept. -- Clayton Macleod ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds --
Re: [hlds] Re: What does RCON STATS CPU Really mean?
heh, like I said, obviously I'm guessing as to what's going on. Calm down :P On 5/19/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] Clayton the sampling might be correct, but how would that explain the results I get when I spam rcon stats into console and receive numbers that are all within 10% of each other? Here is exmple: 14:03:37 stats 14:03:37 CPU In Out Uptime Users FPS Players 86.53 73784.24 227882.64 177 6 56.87 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.53 74690.58 228744.00 177 6 63.98 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 75565.57 229665.05 177 6 35.32 39 14:03:38 stats 14:03:38 CPU In Out Uptime Users FPS Players 86.77 76380.45 231317.58 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77197.75 232984.47 177 6 34.13 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 86.77 77256.87 234898.08 177 6 30.10 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77242.05 236992.31 177 6 26.96 39 14:03:39 stats 14:03:39 CPU In Out Uptime Users FPS Players 95.31 77264.55 238138.23 177 6 33.02 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 95.31 77243.81 238387.27 177 6 33.04 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77214.17 238615.45 177 6 40.99 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 77057.98 238889.06 177 6 34.12 39 14:03:40 stats 14:03:40 CPU In Out Uptime Users FPS Players 94.57 76746.83 239109.53 177 6 33.05 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.57 76242.27 239287.92 177 6 57.57 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75778.00 238699.22 177 6 37.94 39 14:03:41 stats 14:03:41 CPU In Out Uptime Users FPS Players 94.30 75704.43 238780.63 177 6 60.21 39 14:03:41 stats 14:03:42 CPU In Out Uptime Users FPS Players 94.30 75405.64 238652.98 177 6 25.60 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75245.19 238275.91 177 6 28.43 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75358.87 238213.38 177 6 27.67 39 14:03:42 stats 14:03:42 CPU In Out Uptime Users FPS Players 93.41 75571.36 237885.63 177 6 28.46 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 93.41 76112.34 237668.05 177 6 30.11 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 89.06 76824.73 237348.69 177 6 60.34 39 14:03:43 stats 14:03:43 CPU In Out Uptime Users FPS Players 89.06 77527.95 237276.89 177 6 36.56 39 14:03:43 stats 14:03:44 CPU In Out Uptime Users FPS Players 89.06 77854.19 237533.16 177 6 46.56 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 77517.18 238679.83 177 6 34.15 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 77084.93 240084.63 177 6 36.57 39 14:03:44 stats 14:03:44 CPU In Out Uptime Users FPS Players 90.63 76791.86 241383.80 177 6 31.04 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 90.63 76871.59 242368.47 177 6 22.76 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 91.71 77053.85 242882.44 177 6 23.81 39 14:03:45 stats 14:03:45 CPU In Out Uptime Users FPS Players 91.71 77454.66 242307.06 177 6 32.04 39 14:03:45 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.71 78062.38 240988.48 177 6 35.32 39 14:03:46 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.71 78272.21 239666.45 177 6 32.02 39 14:03:46 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.83 78384.60 238314.08 177 6 36.57 39 14:03:46 stats 14:03:46 CPU In Out Uptime Users FPS Players 91.83 78409.96 237305.31 177 6 33.04 39 Now you cannot tell me that this is not odd and that this is some sort of time sampling mismatch task manager ought to damn well show something that approximates what SRCDS is reporting back or vice versa, but it does not! -- Clayton Macleod ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
Re: [hlds] Re: What does RCON STATS CPU Really mean?
Is it possible for you to copy/paste the full output you get? On 5/12/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] So I am not alone on this list on not being able to work out what that number mean? On 5/12/05, Renzo Rosales [EMAIL PROTECTED] wrote: Wait for a response from Valve. Patience... ___ 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] Re: What does RCON STATS CPU Really mean?
-- [ Picked text/plain from multipart/alternative ] 18:10:18 stats 18:10:18 CPU In Out Uptime Users FPS Players 84.38 79225.95 261394.63 1092 19 85.30 40 Yes, it is a 40 player server As I said, task manager it will be showing 10-15% tops no matter what SRCDS says 18:12:41 stats 18:12:41 CPU In Out Uptime Users FPS Players 25.00 80233.02 113006.83 1094 19 255.97 40 Anyhow Im not holding out much hope On 5/12/05, Ian mu [EMAIL PROTECTED] wrote: Is it possible for you to copy/paste the full output you get? On 5/12/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] So I am not alone on this list on not being able to work out what that number mean? On 5/12/05, Renzo Rosales [EMAIL PROTECTED] wrote: Wait for a response from Valve. Patience... ___ 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] Re: What does RCON STATS CPU Really mean?
Just wondering as a 40 player server will naturally take a fair bit of juice, could it be that stats shows a usage on a single hyperthreaded cpu (i.e 1/4) and task manager shows the total which isn't quite correct? (ie there isnt really 4 full cpu's). Don't really know windows well enough in how it reports cpu usage compared to Linux though, just wondered if it might be the cause of the different reporting. On 5/12/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] 18:10:18 stats 18:10:18 CPU In Out Uptime Users FPS Players 84.38 79225.95 261394.63 1092 19 85.30 40 Yes, it is a 40 player server As I said, task manager it will be showing 10-15% tops no matter what SRCDS says 18:12:41 stats 18:12:41 CPU In Out Uptime Users FPS Players 25.00 80233.02 113006.83 1094 19 255.97 40 Anyhow Im not holding out much hope On 5/12/05, Ian mu [EMAIL PROTECTED] wrote: Is it possible for you to copy/paste the full output you get? On 5/12/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] So I am not alone on this list on not being able to work out what that number mean? On 5/12/05, Renzo Rosales [EMAIL PROTECTED] wrote: Wait for a response from Valve. Patience... ___ 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] Re: What does RCON STATS CPU Really mean?
I'm in the same boat with RCON STATS and what the physical box tells me CPU usage is. What really boggles my mind is that while the 66 tickrate 20 player server I run says upwards of 95% CPU and downwards of 20 FPS when I do RCON STATS (when it's full), the physical box itself when checking usage says maybe around 20% CPU. It's troubling that while the physical box says it's hardly being used, CS:S say it's maxing out it's resources which causes it to drop updates to players (10/s instead of 66/s) and make the game unplayable. -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Whisper Sent: Thursday, May 12, 2005 3:12 AM To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? -- [ Picked text/plain from multipart/alternative ] 18:10:18 stats 18:10:18 CPU In Out Uptime Users FPS Players 84.38 79225.95 261394.63 1092 19 85.30 40 Yes, it is a 40 player server As I said, task manager it will be showing 10-15% tops no matter what SRCDS says 18:12:41 stats 18:12:41 CPU In Out Uptime Users FPS Players 25.00 80233.02 113006.83 1094 19 255.97 40 Anyhow Im not holding out much hope On 5/12/05, Ian mu [EMAIL PROTECTED] wrote: Is it possible for you to copy/paste the full output you get? On 5/12/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] So I am not alone on this list on not being able to work out what that number mean? On 5/12/05, Renzo Rosales [EMAIL PROTECTED] wrote: Wait for a response from Valve. Patience... ___ 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] Re: What does RCON STATS CPU Really mean?
That is the case Ian is surprising the amount of people who don't know how to interpret taskman results, ive had many an argument about CPU usage due to this :P Steve / K - Original Message - From: Ian mu [EMAIL PROTECTED] Just wondering as a 40 player server will naturally take a fair bit of juice, could it be that stats shows a usage on a single hyperthreaded cpu (i.e 1/4) and task manager shows the total which isn't quite correct? (ie there isnt really 4 full cpu's). Don't really know windows well enough in how it reports cpu usage compared to Linux though, just wondered if it might be the cause of the different reporting. 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] Re: What does RCON STATS CPU Really mean?
-- [ Picked text/plain from multipart/alternative ] May try then with HT turned off and see what happens. On 5/13/05, Steven Hartland [EMAIL PROTECTED] wrote: That is the case Ian is surprising the amount of people who don't know how to interpret taskman results, ive had many an argument about CPU usage due to this :P Steve / K - Original Message - From: Ian mu [EMAIL PROTECTED] Just wondering as a 40 player server will naturally take a fair bit of juice, could it be that stats shows a usage on a single hyperthreaded cpu (i.e 1/4) and task manager shows the total which isn't quite correct? (ie there isnt really 4 full cpu's). Don't really know windows well enough in how it reports cpu usage compared to Linux though, just wondered if it might be the cause of the different reporting. 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 -- ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
Re: [hlds] Re: What does RCON STATS CPU Really mean?
The problem is hyperthreading is typically pretty good to have on, depending on instances of different servers running on it, as a loose rule of thumb I'd personally have it on if you use more than 1 dedicated server per real cpu. So if you use 2 game servers on a dual, I'd try it on personally and see. I think the problem is there's no proper way to my knowledge (and again I don't know windows that well) to properly figure out how much spare there is on a virtual cpu, but that doesn't mean its not useful to have there. So I would guess valve can't do any more than the o.s will report. It wouldnt surprise me even if hyperthreading is turned off, it still shows as double what taskmanager has (assuming you have 2 real cpu's), which is actually sort of correct. I.e if it shows as 95% of one cpu, thats actually correct as it can never use the 2nd cpu once it hits 100%, only other processes can. Thats typically the problem with large servers, as huge slot count server would likely better run on an 64bit Ath4000 than a dual 3gig xeon, and the xeon naturally comes into its own once running multiple instances. Basically though, don't read too much into stats or the taskbar in my book. Watch what individual cpu's are doing. On 5/12/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] May try then with HT turned off and see what happens. On 5/13/05, Steven Hartland [EMAIL PROTECTED] wrote: That is the case Ian is surprising the amount of people who don't know how to interpret taskman results, ive had many an argument about CPU usage due to this :P Steve / K - Original Message - From: Ian mu [EMAIL PROTECTED] Just wondering as a 40 player server will naturally take a fair bit of juice, could it be that stats shows a usage on a single hyperthreaded cpu (i.e 1/4) and task manager shows the total which isn't quite correct? (ie there isnt really 4 full cpu's). Don't really know windows well enough in how it reports cpu usage compared to Linux though, just wondered if it might be the cause of the different reporting. 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 -- ___ 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] Re: What does RCON STATS CPU Really mean?
Learn how to use MRTG fellas... That's about as accurate as it gets. nuff said ;-) http://bubba.hardfought.org/mrtg/67.19.85.2_cpu.html - K2 -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Ian mu Sent: Thursday, May 12, 2005 8:22 AM To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? The problem is hyperthreading is typically pretty good to have on, depending on instances of different servers running on it, as a loose rule of thumb I'd personally have it on if you use more than 1 dedicated server per real cpu. So if you use 2 game servers on a dual, I'd try it on personally and see. I think the problem is there's no proper way to my knowledge (and again I don't know windows that well) to properly figure out how much spare there is on a virtual cpu, but that doesn't mean its not useful to have there. So I would guess valve can't do any more than the o.s will report. It wouldnt surprise me even if hyperthreading is turned off, it still shows as double what taskmanager has (assuming you have 2 real cpu's), which is actually sort of correct. I.e if it shows as 95% of one cpu, thats actually correct as it can never use the 2nd cpu once it hits 100%, only other processes can. Thats typically the problem with large servers, as huge slot count server would likely better run on an 64bit Ath4000 than a dual 3gig xeon, and the xeon naturally comes into its own once running multiple instances. Basically though, don't read too much into stats or the taskbar in my book. Watch what individual cpu's are doing. On 5/12/05, Whisper [EMAIL PROTECTED] wrote: -- [ Picked text/plain from multipart/alternative ] May try then with HT turned off and see what happens. On 5/13/05, Steven Hartland [EMAIL PROTECTED] wrote: That is the case Ian is surprising the amount of people who don't know how to interpret taskman results, ive had many an argument about CPU usage due to this :P Steve / K - Original Message - From: Ian mu [EMAIL PROTECTED] Just wondering as a 40 player server will naturally take a fair bit of juice, could it be that stats shows a usage on a single hyperthreaded cpu (i.e 1/4) and task manager shows the total which isn't quite correct? (ie there isnt really 4 full cpu's). Don't really know windows well enough in how it reports cpu usage compared to Linux though, just wondered if it might be the cause of the different reporting. 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 -- ___ 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] Re: What does RCON STATS CPU Really mean?
K2 wrote: Learn how to use MRTG fellas... That's about as accurate as it gets. nuff said ;-) http://bubba.hardfought.org/mrtg/67.19.85.2_cpu.html - K2 MRTG is only a graphing app. It needs to have something to tell it what to graph. So whatever script (or via SNMP) you're using to tell MRTG what the CPU usage is, that's where the info is coming from. -- - m0gely http://quake2.telestream.com/ Q2 | Q3A | Counter-strike ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
RE: [hlds] Re: What does RCON STATS CPU Really mean?
Exactly... and SNMP is your best bet for that. The counters you can grab the data from are going to be more accurate than anything a third-party app (read: valve) is going to put out. That's why I said 'hey fellas, learn how to use MRTG' ;-) Good site to check out to get the required MIB's for win32 and also how-to's on how to get everything setup - http://www.wtcs.org/snmp4tpc/default.htm - K2 -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of m0gely Sent: Thursday, May 12, 2005 9:02 AM To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? K2 wrote: Learn how to use MRTG fellas... That's about as accurate as it gets. nuff said ;-) http://bubba.hardfought.org/mrtg/67.19.85.2_cpu.html - K2 MRTG is only a graphing app. It needs to have something to tell it what to graph. So whatever script (or via SNMP) you're using to tell MRTG what the CPU usage is, that's where the info is coming from. -- - m0gely http://quake2.telestream.com/ Q2 | Q3A | Counter-strike ___ 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] Re: What does RCON STATS CPU Really mean?
Think you missed the point, what is snmp basing the information on? On 5/12/05, K2 [EMAIL PROTECTED] wrote: Exactly... and SNMP is your best bet for that. The counters you can grab the data from are going to be more accurate than anything a third-party app (read: valve) is going to put out. That's why I said 'hey fellas, learn how to use MRTG' ;-) Good site to check out to get the required MIB's for win32 and also how-to's on how to get everything setup - http://www.wtcs.org/snmp4tpc/default.htm - K2 -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of m0gely Sent: Thursday, May 12, 2005 9:02 AM To: hlds@list.valvesoftware.com Subject: Re: [hlds] Re: What does RCON STATS CPU Really mean? K2 wrote: Learn how to use MRTG fellas... That's about as accurate as it gets. nuff said ;-) http://bubba.hardfought.org/mrtg/67.19.85.2_cpu.html - K2 MRTG is only a graphing app. It needs to have something to tell it what to graph. So whatever script (or via SNMP) you're using to tell MRTG what the CPU usage is, that's where the info is coming from. -- - m0gely http://quake2.telestream.com/ Q2 | Q3A | Counter-strike ___ 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] Re: What does RCON STATS CPU Really mean?
Wait for a response from Valve. Patience... ___ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds
Re: [hlds] Re: What does RCON STATS CPU Really mean?
-- [ Picked text/plain from multipart/alternative ] So I am not alone on this list on not being able to work out what that number mean? On 5/12/05, Renzo Rosales [EMAIL PROTECTED] wrote: Wait for a response from Valve. Patience... ___ 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