Re: [hlds_linux] Kernel Options and Clocksource

2009-03-08 Thread Ben B
okay, i compiled the kernel, and I see all of them.
you think i should use tsc or hpet? there are opinions for both throughout
the list it seems.

On Sat, Mar 7, 2009 at 1:25 PM, listac...@lvwnet.com wrote:

  So to get a list of which clocksources your hardware has
  available:
 
 # cat /sys/devices/system/clocksource/clocksource0/current_clocksource
 
  I think you meant available_clocksource not current_clocksource ?

 Yes, already corrected myself TYVM



 ___
 To unsubscribe, edit your list preferences, or view the list archives,
 please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux




-- 
From Ben B. (Goerge)
___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-08 Thread Gary Stanley
At 02:45 PM 3/8/2009, Ben B wrote:
okay, i compiled the kernel, and I see all of them.
you think i should use tsc or hpet? there are opinions for both throughout
the list it seems.


TSC is fast to read because it lives in the CPU..
HPET lives off somewhere behind a bridge, so reading it requires an ioport read

Use TSC if you're on intel hardware and HPET if you're on AMD hardware.



On Sat, Mar 7, 2009 at 1:25 PM, listac...@lvwnet.com wrote:

   So to get a list of which clocksources your hardware has
   available:
  
  # cat /sys/devices/system/clocksource/clocksource0/current_clocksource
  
   I think you meant available_clocksource not current_clocksource ?
 
  Yes, already corrected myself TYVM
 
 
 
  ___
  To unsubscribe, edit your list preferences, or view the list archives,
  please visit:
  http://list.valvesoftware.com/mailman/listinfo/hlds_linux
 



--
 From Ben B. (Goerge)
___
To unsubscribe, edit your list preferences, or view the list 
archives, please visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-08 Thread Gary Stanley
At 02:45 PM 3/8/2009, Ben B wrote:
okay, i compiled the kernel, and I see all of them.
you think i should use tsc or hpet? there are opinions for both throughout
the list it seems.


TSC is fast to read because it lives in the CPU..
HPET lives off somewhere behind a bridge, so reading it requires an ioport read

Use TSC if you're on intel hardware and HPET if you're on AMD hardware.



On Sat, Mar 7, 2009 at 1:25 PM, listac...@lvwnet.com wrote:

   So to get a list of which clocksources your hardware has
   available:
  
  # cat /sys/devices/system/clocksource/clocksource0/current_clocksource
  
   I think you meant available_clocksource not current_clocksource ?
 
  Yes, already corrected myself TYVM
 
 
 
  ___
  To unsubscribe, edit your list preferences, or view the list archives,
  please visit:
  http://list.valvesoftware.com/mailman/listinfo/hlds_linux
 



--
 From Ben B. (Goerge)
___
To unsubscribe, edit your list preferences, or view the list 
archives, please visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread Ben B
I feel like such a linux nub... how do you set your clocksource?

On Fri, Mar 6, 2009 at 11:56 PM, The Universes ad...@theuniverses.comwrote:

 Do you think dropping it down to 500HZ is a better choice or do you
 suggest something else? If yes, does 500HZ still maintain 500FPS?

 Thanks!

 Gary Stanley wrote:
  At 10:33 PM 3/6/2009, The Universes wrote:
  I'm running 4 32 man TF2 servers at 500fps (66 tick) and I'm wondering
  if having kernel at 1000HZ (not tickless) with PREEMPT is necessary?
  Is that putting unnecessary strain on my CPU (Q9300)?
 
  My second question is if  you guys use HPET as your clocksource
  $ cat /sys/devices/system/clocksource/clocksource0/available_clocksource
  tsc hpet acpi_pm jiffies
 
  $ cat /sys/devices/system/clocksource/clocksource0/current_clocksource
  tsc
 
 
  1000hz kernels make nanosleep() expensive to call.. on a core2quad
  calling usleep (which calls nanosleep)
 
  nanosleep: 6157 cycles
 
  That's alot of cpu time. Cranking up HZ makes interrupts fire so
  often, so you get more accurate sleep behavior..
 
  TSC lives on the CPU, so calling it is fairly cheap. HPET lives off
  somewhere on a bridge, so you need to go out to PCI land to
  read it. HPET is a decent choice, but overall the fastest one is TSC.
 
 
 
 
  Would you recommend changing that to HPET?
 
  I'm basically trying to lower CPU usage so it doesnt shoot up to 90%
  sometimes.
 
  Thanks,
  Dan
 
  ___
  To unsubscribe, edit your list preferences, or view the list
  archives, please visit:
  http://list.valvesoftware.com/mailman/listinfo/hlds_linux
 
 
  ___
  To unsubscribe, edit your list preferences, or view the list archives,
 please visit:
  http://list.valvesoftware.com/mailman/listinfo/hlds_linux

 ___
 To unsubscribe, edit your list preferences, or view the list archives,
 please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux




-- 
From Ben B. (Goerge)
___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread The Universes
cat hpet  /sys/devices/system/clocksource/clocksource0/current_clocksource

Ben B wrote:
 I feel like such a linux nub... how do you set your clocksource?
 
 On Fri, Mar 6, 2009 at 11:56 PM, The Universes ad...@theuniverses.comwrote:
 
 Do you think dropping it down to 500HZ is a better choice or do you
 suggest something else? If yes, does 500HZ still maintain 500FPS?

 Thanks!

 Gary Stanley wrote:
 At 10:33 PM 3/6/2009, The Universes wrote:
 I'm running 4 32 man TF2 servers at 500fps (66 tick) and I'm wondering
 if having kernel at 1000HZ (not tickless) with PREEMPT is necessary?
 Is that putting unnecessary strain on my CPU (Q9300)?

 My second question is if  you guys use HPET as your clocksource
 $ cat /sys/devices/system/clocksource/clocksource0/available_clocksource
 tsc hpet acpi_pm jiffies

 $ cat /sys/devices/system/clocksource/clocksource0/current_clocksource
 tsc

 1000hz kernels make nanosleep() expensive to call.. on a core2quad
 calling usleep (which calls nanosleep)

 nanosleep: 6157 cycles

 That's alot of cpu time. Cranking up HZ makes interrupts fire so
 often, so you get more accurate sleep behavior..

 TSC lives on the CPU, so calling it is fairly cheap. HPET lives off
 somewhere on a bridge, so you need to go out to PCI land to
 read it. HPET is a decent choice, but overall the fastest one is TSC.




 Would you recommend changing that to HPET?

 I'm basically trying to lower CPU usage so it doesnt shoot up to 90%
 sometimes.

 Thanks,
 Dan

 ___
 To unsubscribe, edit your list preferences, or view the list
 archives, please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux

 ___
 To unsubscribe, edit your list preferences, or view the list archives,
 please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux
 ___
 To unsubscribe, edit your list preferences, or view the list archives,
 please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux

 
 
 

___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread Taavi
The Universes wrote:
 cat hpet  /sys/devices/system/clocksource/clocksource0/current_clocksourc

You mean:

echo hpet  /sys/devices/system/clocksource/clocksource0/current_clocksource




Taavi

___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread The Universes
Oops, thats right.

Taavi wrote:
 The Universes wrote:
 cat hpet  /sys/devices/system/clocksource/clocksource0/current_clocksourc
 
 You mean:
 
 echo hpet  /sys/devices/system/clocksource/clocksource0/current_clocksource
 
 
 
 
 Taavi
 
 ___
 To unsubscribe, edit your list preferences, or view the list archives, please 
 visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux

___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread listacct2
 I feel like such a linux nub... how do you set your clocksource?

On any fairly recent 2.6-series kernel you can put this right on the
kernel boot commandline:

clocksource=$whatever

like

clocksource=hpet

or

clocksource=tsc

so that it is set at boot.

The echoing of available options into the /sys entry is valid as well, ie:

# echo hpet 
/sys/devices/system/clocksource/clocksource0/current_clocksource

but is more of a post-boot type thing.  That's not bad, necessarily.  You
can use it to change the clocksource post-boot.  This is useful if you are
experimenting with different ones because you can change the clocksource
without rebooting.

So to get a list of which clocksources your hardware has available:

# cat /sys/devices/system/clocksource/clocksource0/current_clocksource

you'll get something like this back (but it will vary from system to system):

tsc jiffies hpet acpi_pm



Someone else asked whether running a 500Hz timer resolution will allow you
to get a stable 500 server fps.  I'm not going to say it is impossible,
but I will say that *I* have yet to find a server machine (server-class
hardware) that would let me get 500fps with a 500Hz kernel.

I've only ever been able to get 500 server fps with a 1000Hz or tickless
kernel, and setting fps_max to 600 or higher.

Entirely possible I'm just not doing it right though.  But what I do
works, so I keep doing it. :)

Setting fps_max to 600 usually gets me around 490-496 server fps.  CPU
utilization for the core a full 30-slot server runs on is usually around
60-65% on a 2.5GHz Harpertown but it does briefly peak higher at times.

This is under F10 x86_64 with a stock 2.6.27 kernel (which I'm pretty sure
is built dynamic/tickless) and I can get ~1000 server fps out of it for
our CS:S games by setting fps_max to 2000.  I'm using clocksource=hpet
currently, but have considered experimenting with tsc since I've read that
there are some recent userspace optimizations in glibc for it on x86_64
which may be of benefit.

(And yes, I know you don't need to run 1000 server fps on CS:S to get a
good smooth game, or 500 server fps on TF2, but our server has the spare
cycles. And let's face it, for server ops this game is ALL about
attracting players to your servers and since with GSP advertising etc.
many players are convinced they have to be on a 100 tick 1000fps
counterstrike server to be on a good server.. well you get the idea)

I also use isolcpus= on the kernel cmdline to set aside processor cores
for the high-demand games.  The cores our TF2 games run on are the only
processes allowed to execute on those cores. All hardware IRQ service is 
pinned to specific other cores by disabling irqbalance and programming
the smp_affinity for each valid numeric IRQ.

http://kbase.redhat.com/faq/docs/DOC-15596


Cheers





 On Fri, Mar 6, 2009 at 11:56 PM, The Universes
 ad...@theuniverses.comwrote:

 Do you think dropping it down to 500HZ is a better choice or do you
 suggest something else? If yes, does 500HZ still maintain 500FPS?

 Thanks!

 Gary Stanley wrote:
  At 10:33 PM 3/6/2009, The Universes wrote:
  I'm running 4 32 man TF2 servers at 500fps (66 tick) and I'm
 wondering
  if having kernel at 1000HZ (not tickless) with PREEMPT is necessary?
  Is that putting unnecessary strain on my CPU (Q9300)?
 
  My second question is if  you guys use HPET as your clocksource
  $ cat
 /sys/devices/system/clocksource/clocksource0/available_clocksource
  tsc hpet acpi_pm jiffies
 
  $ cat
 /sys/devices/system/clocksource/clocksource0/current_clocksource
  tsc
 
 
  1000hz kernels make nanosleep() expensive to call.. on a core2quad
  calling usleep (which calls nanosleep)
 
  nanosleep: 6157 cycles
 
  That's alot of cpu time. Cranking up HZ makes interrupts fire so
  often, so you get more accurate sleep behavior..
 
  TSC lives on the CPU, so calling it is fairly cheap. HPET lives off
  somewhere on a bridge, so you need to go out to PCI land to
  read it. HPET is a decent choice, but overall the fastest one is TSC.
 
 
 
 
  Would you recommend changing that to HPET?
 
  I'm basically trying to lower CPU usage so it doesnt shoot up to 90%
  sometimes.
 
  Thanks,
  Dan
 
  ___
  To unsubscribe, edit your list preferences, or view the list
  archives, please visit:
  http://list.valvesoftware.com/mailman/listinfo/hlds_linux
 
 
  ___
  To unsubscribe, edit your list preferences, or view the list archives,
 please visit:
  http://list.valvesoftware.com/mailman/listinfo/hlds_linux

 ___
 To unsubscribe, edit your list preferences, or view the list archives,
 please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux




 --
 From Ben B. (Goerge)
 ___
 To unsubscribe, edit your list preferences, or view the list archives,
 please visit:
 

Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread listacct2

 So to get a list of which clocksources your hardware has available:

 # cat /sys/devices/system/clocksource/clocksource0/current_clocksource

 you'll get something like this back (but it will vary from system to
 system):

 tsc jiffies hpet acpi_pm

Oops... that is supposed to be:

# cat /sys/devices/system/clocksource/clocksource0/available_clocksource



___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread Gary Stanley
At 08:27 AM 3/7/2009, listac...@lvwnet.com wrote:
  I feel like such a linux nub... how do you set your clocksource?

On any fairly recent 2.6-series kernel you can put this right on the
kernel boot commandline:

clocksource=$whatever

like

clocksource=hpet

or

clocksource=tsc

so that it is set at boot.

The echoing of available options into the /sys entry is valid as well, ie:

# echo hpet 
/sys/devices/system/clocksource/clocksource0/current_clocksource

but is more of a post-boot type thing.  That's not bad, necessarily.  You
can use it to change the clocksource post-boot.  This is useful if you are
experimenting with different ones because you can change the clocksource
without rebooting.

So to get a list of which clocksources your hardware has available:

# cat /sys/devices/system/clocksource/clocksource0/current_clocksource

you'll get something like this back (but it will vary from system to system):

tsc jiffies hpet acpi_pm



Someone else asked whether running a 500Hz timer resolution will allow you
to get a stable 500 server fps.  I'm not going to say it is impossible,
but I will say that *I* have yet to find a server machine (server-class
hardware) that would let me get 500fps with a 500Hz kernel.

I was able to get it running on a test machine.

I've only ever been able to get 500 server fps with a 1000Hz or tickless
kernel, and setting fps_max to 600 or higher.

Entirely possible I'm just not doing it right though.  But what I do
works, so I keep doing it. :)

Setting fps_max to 600 usually gets me around 490-496 server fps.  CPU
utilization for the core a full 30-slot server runs on is usually around
60-65% on a 2.5GHz Harpertown but it does briefly peak higher at times.

This is under F10 x86_64 with a stock 2.6.27 kernel (which I'm pretty sure
is built dynamic/tickless) and I can get ~1000 server fps out of it for
our CS:S games by setting fps_max to 2000.  I'm using clocksource=hpet
currently, but have considered experimenting with tsc since I've read that
there are some recent userspace optimizations in glibc for it on x86_64
which may be of benefit.

That only happens if the binaries are x86_64.



___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread Gary Stanley
At 08:27 AM 3/7/2009, listac...@lvwnet.com wrote:
  I feel like such a linux nub... how do you set your clocksource?

On any fairly recent 2.6-series kernel you can put this right on the
kernel boot commandline:

clocksource=$whatever

like

clocksource=hpet

or

clocksource=tsc

so that it is set at boot.

The echoing of available options into the /sys entry is valid as well, ie:

# echo hpet 
/sys/devices/system/clocksource/clocksource0/current_clocksource

but is more of a post-boot type thing.  That's not bad, necessarily.  You
can use it to change the clocksource post-boot.  This is useful if you are
experimenting with different ones because you can change the clocksource
without rebooting.

So to get a list of which clocksources your hardware has available:

# cat /sys/devices/system/clocksource/clocksource0/current_clocksource

you'll get something like this back (but it will vary from system to system):

tsc jiffies hpet acpi_pm



Someone else asked whether running a 500Hz timer resolution will allow you
to get a stable 500 server fps.  I'm not going to say it is impossible,
but I will say that *I* have yet to find a server machine (server-class
hardware) that would let me get 500fps with a 500Hz kernel.

I was able to get it running on a test machine.

I've only ever been able to get 500 server fps with a 1000Hz or tickless
kernel, and setting fps_max to 600 or higher.

Entirely possible I'm just not doing it right though.  But what I do
works, so I keep doing it. :)

Setting fps_max to 600 usually gets me around 490-496 server fps.  CPU
utilization for the core a full 30-slot server runs on is usually around
60-65% on a 2.5GHz Harpertown but it does briefly peak higher at times.

This is under F10 x86_64 with a stock 2.6.27 kernel (which I'm pretty sure
is built dynamic/tickless) and I can get ~1000 server fps out of it for
our CS:S games by setting fps_max to 2000.  I'm using clocksource=hpet
currently, but have considered experimenting with tsc since I've read that
there are some recent userspace optimizations in glibc for it on x86_64
which may be of benefit.

That only happens if the binaries are x86_64.



___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread Ben B
i just have jiffies in as an available clocksource... there a way to get
htpet and tsc?

On Sat, Mar 7, 2009 at 8:34 AM, Gary Stanley g...@velocity-servers.netwrote:

 At 08:27 AM 3/7/2009, listac...@lvwnet.com wrote:
   I feel like such a linux nub... how do you set your clocksource?
 
 On any fairly recent 2.6-series kernel you can put this right on the
 kernel boot commandline:
 
 clocksource=$whatever
 
 like
 
 clocksource=hpet
 
 or
 
 clocksource=tsc
 
 so that it is set at boot.
 
 The echoing of available options into the /sys entry is valid as well, ie:
 
 # echo hpet 
 /sys/devices/system/clocksource/clocksource0/current_clocksource
 
 but is more of a post-boot type thing.  That's not bad, necessarily.  You
 can use it to change the clocksource post-boot.  This is useful if you are
 experimenting with different ones because you can change the clocksource
 without rebooting.
 
 So to get a list of which clocksources your hardware has available:
 
 # cat /sys/devices/system/clocksource/clocksource0/current_clocksource
 
 you'll get something like this back (but it will vary from system to
 system):
 
 tsc jiffies hpet acpi_pm
 
 
 
 Someone else asked whether running a 500Hz timer resolution will allow you
 to get a stable 500 server fps.  I'm not going to say it is impossible,
 but I will say that *I* have yet to find a server machine (server-class
 hardware) that would let me get 500fps with a 500Hz kernel.

 I was able to get it running on a test machine.

 I've only ever been able to get 500 server fps with a 1000Hz or tickless
 kernel, and setting fps_max to 600 or higher.
 
 Entirely possible I'm just not doing it right though.  But what I do
 works, so I keep doing it. :)
 
 Setting fps_max to 600 usually gets me around 490-496 server fps.  CPU
 utilization for the core a full 30-slot server runs on is usually around
 60-65% on a 2.5GHz Harpertown but it does briefly peak higher at times.
 
 This is under F10 x86_64 with a stock 2.6.27 kernel (which I'm pretty sure
 is built dynamic/tickless) and I can get ~1000 server fps out of it for
 our CS:S games by setting fps_max to 2000.  I'm using clocksource=hpet
 currently, but have considered experimenting with tsc since I've read that
 there are some recent userspace optimizations in glibc for it on x86_64
 which may be of benefit.

 That only happens if the binaries are x86_64.



 ___
 To unsubscribe, edit your list preferences, or view the list archives,
 please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux




-- 
From Ben B. (Goerge)
___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread Gary Stanley
At 12:47 PM 3/7/2009, Ben B wrote:
i just have jiffies in as an available clocksource... there a way to get
htpet and tsc?

TSC should be always be available as a clocksource, unless something 
is seriously wrong with your setup.
Actually, a normal kernel will panic if TSC isn't compiled into the kernel :P



On Sat, Mar 7, 2009 at 8:34 AM, Gary Stanley g...@velocity-servers.netwrote:

  At 08:27 AM 3/7/2009, listac...@lvwnet.com wrote:
I feel like such a linux nub... how do you set your clocksource?
  
  On any fairly recent 2.6-series kernel you can put this right on the
  kernel boot commandline:
  
  clocksource=$whatever
  
  like
  
  clocksource=hpet
  
  or
  
  clocksource=tsc
  
  so that it is set at boot.
  
  The echoing of available options into the /sys entry is valid as well, ie:
  
  # echo hpet 
  /sys/devices/system/clocksource/clocksource0/current_clocksource
  
  but is more of a post-boot type thing.  That's not bad, necessarily.  You
  can use it to change the clocksource post-boot.  This is useful if you are
  experimenting with different ones because you can change the clocksource
  without rebooting.
  
  So to get a list of which clocksources your hardware has available:
  
  # cat /sys/devices/system/clocksource/clocksource0/current_clocksource
  
  you'll get something like this back (but it will vary from system to
  system):
  
  tsc jiffies hpet acpi_pm
  
  
  
  Someone else asked whether running a 500Hz timer resolution will allow you
  to get a stable 500 server fps.  I'm not going to say it is impossible,
  but I will say that *I* have yet to find a server machine (server-class
  hardware) that would let me get 500fps with a 500Hz kernel.
 
  I was able to get it running on a test machine.
 
  I've only ever been able to get 500 server fps with a 1000Hz or tickless
  kernel, and setting fps_max to 600 or higher.
  
  Entirely possible I'm just not doing it right though.  But what I do
  works, so I keep doing it. :)
  
  Setting fps_max to 600 usually gets me around 490-496 server fps.  CPU
  utilization for the core a full 30-slot server runs on is usually around
  60-65% on a 2.5GHz Harpertown but it does briefly peak higher at times.
  
  This is under F10 x86_64 with a stock 2.6.27 kernel (which I'm pretty sure
  is built dynamic/tickless) and I can get ~1000 server fps out of it for
  our CS:S games by setting fps_max to 2000.  I'm using clocksource=hpet
  currently, but have considered experimenting with tsc since I've read that
  there are some recent userspace optimizations in glibc for it on x86_64
  which may be of benefit.
 
  That only happens if the binaries are x86_64.
 
 
 
  ___
  To unsubscribe, edit your list preferences, or view the list archives,
  please visit:
  http://list.valvesoftware.com/mailman/listinfo/hlds_linux
 



--
 From Ben B. (Goerge)
___
To unsubscribe, edit your list preferences, or view the list 
archives, please visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread Gary Stanley
At 12:47 PM 3/7/2009, Ben B wrote:
i just have jiffies in as an available clocksource... there a way to get
htpet and tsc?

TSC should be always be available as a clocksource, unless something 
is seriously wrong with your setup.
Actually, a normal kernel will panic if TSC isn't compiled into the kernel :P



On Sat, Mar 7, 2009 at 8:34 AM, Gary Stanley g...@velocity-servers.netwrote:

  At 08:27 AM 3/7/2009, listac...@lvwnet.com wrote:
I feel like such a linux nub... how do you set your clocksource?
  
  On any fairly recent 2.6-series kernel you can put this right on the
  kernel boot commandline:
  
  clocksource=$whatever
  
  like
  
  clocksource=hpet
  
  or
  
  clocksource=tsc
  
  so that it is set at boot.
  
  The echoing of available options into the /sys entry is valid as well, ie:
  
  # echo hpet 
  /sys/devices/system/clocksource/clocksource0/current_clocksource
  
  but is more of a post-boot type thing.  That's not bad, necessarily.  You
  can use it to change the clocksource post-boot.  This is useful if you are
  experimenting with different ones because you can change the clocksource
  without rebooting.
  
  So to get a list of which clocksources your hardware has available:
  
  # cat /sys/devices/system/clocksource/clocksource0/current_clocksource
  
  you'll get something like this back (but it will vary from system to
  system):
  
  tsc jiffies hpet acpi_pm
  
  
  
  Someone else asked whether running a 500Hz timer resolution will allow you
  to get a stable 500 server fps.  I'm not going to say it is impossible,
  but I will say that *I* have yet to find a server machine (server-class
  hardware) that would let me get 500fps with a 500Hz kernel.
 
  I was able to get it running on a test machine.
 
  I've only ever been able to get 500 server fps with a 1000Hz or tickless
  kernel, and setting fps_max to 600 or higher.
  
  Entirely possible I'm just not doing it right though.  But what I do
  works, so I keep doing it. :)
  
  Setting fps_max to 600 usually gets me around 490-496 server fps.  CPU
  utilization for the core a full 30-slot server runs on is usually around
  60-65% on a 2.5GHz Harpertown but it does briefly peak higher at times.
  
  This is under F10 x86_64 with a stock 2.6.27 kernel (which I'm pretty sure
  is built dynamic/tickless) and I can get ~1000 server fps out of it for
  our CS:S games by setting fps_max to 2000.  I'm using clocksource=hpet
  currently, but have considered experimenting with tsc since I've read that
  there are some recent userspace optimizations in glibc for it on x86_64
  which may be of benefit.
 
  That only happens if the binaries are x86_64.
 
 
 
  ___
  To unsubscribe, edit your list preferences, or view the list archives,
  please visit:
  http://list.valvesoftware.com/mailman/listinfo/hlds_linux
 



--
 From Ben B. (Goerge)
___
To unsubscribe, edit your list preferences, or view the list 
archives, please visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread Ben B
dont ask me, this is how it was when i found it.  So if I compile my own
kernel, it should have them clocksources?

On Sat, Mar 7, 2009 at 11:01 AM, Gary Stanley g...@velocity-servers.netwrote:

 At 12:47 PM 3/7/2009, Ben B wrote:
 i just have jiffies in as an available clocksource... there a way to get
 htpet and tsc?

 TSC should be always be available as a clocksource, unless something
 is seriously wrong with your setup.
 Actually, a normal kernel will panic if TSC isn't compiled into the kernel
 :P



 On Sat, Mar 7, 2009 at 8:34 AM, Gary Stanley g...@velocity-servers.net
 wrote:
 
   At 08:27 AM 3/7/2009, listac...@lvwnet.com wrote:
 I feel like such a linux nub... how do you set your clocksource?
   
   On any fairly recent 2.6-series kernel you can put this right on the
   kernel boot commandline:
   
   clocksource=$whatever
   
   like
   
   clocksource=hpet
   
   or
   
   clocksource=tsc
   
   so that it is set at boot.
   
   The echoing of available options into the /sys entry is valid as well,
 ie:
   
   # echo hpet 
   /sys/devices/system/clocksource/clocksource0/current_clocksource
   
   but is more of a post-boot type thing.  That's not bad, necessarily.
  You
   can use it to change the clocksource post-boot.  This is useful if you
 are
   experimenting with different ones because you can change the
 clocksource
   without rebooting.
   
   So to get a list of which clocksources your hardware has available:
   
   # cat /sys/devices/system/clocksource/clocksource0/current_clocksource
   
   you'll get something like this back (but it will vary from system to
   system):
   
   tsc jiffies hpet acpi_pm
   
   
   
   Someone else asked whether running a 500Hz timer resolution will allow
 you
   to get a stable 500 server fps.  I'm not going to say it is
 impossible,
   but I will say that *I* have yet to find a server machine
 (server-class
   hardware) that would let me get 500fps with a 500Hz kernel.
  
   I was able to get it running on a test machine.
  
   I've only ever been able to get 500 server fps with a 1000Hz or
 tickless
   kernel, and setting fps_max to 600 or higher.
   
   Entirely possible I'm just not doing it right though.  But what I do
   works, so I keep doing it. :)
   
   Setting fps_max to 600 usually gets me around 490-496 server fps.  CPU
   utilization for the core a full 30-slot server runs on is usually
 around
   60-65% on a 2.5GHz Harpertown but it does briefly peak higher at
 times.
   
   This is under F10 x86_64 with a stock 2.6.27 kernel (which I'm pretty
 sure
   is built dynamic/tickless) and I can get ~1000 server fps out of it
 for
   our CS:S games by setting fps_max to 2000.  I'm using clocksource=hpet
   currently, but have considered experimenting with tsc since I've read
 that
   there are some recent userspace optimizations in glibc for it on
 x86_64
   which may be of benefit.
  
   That only happens if the binaries are x86_64.
  
  
  
   ___
   To unsubscribe, edit your list preferences, or view the list archives,
   please visit:
   http://list.valvesoftware.com/mailman/listinfo/hlds_linux
  
 
 
 
 --
  From Ben B. (Goerge)
 ___
 To unsubscribe, edit your list preferences, or view the list
 archives, please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux


 ___
 To unsubscribe, edit your list preferences, or view the list archives,
 please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux




-- 
From Ben B. (Goerge)
___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread Gary Stanley
At 01:12 PM 3/7/2009, Ben B wrote:
dont ask me, this is how it was when i found it.  So if I compile my own
kernel, it should have them clocksources?

What's the motherboard? is it a virtual machine?


On Sat, Mar 7, 2009 at 11:01 AM, Gary Stanley 
g...@velocity-servers.netwrote:

  At 12:47 PM 3/7/2009, Ben B wrote:
  i just have jiffies in as an available clocksource... there a way to get
  htpet and tsc?
 
  TSC should be always be available as a clocksource, unless something
  is seriously wrong with your setup.
  Actually, a normal kernel will panic if TSC isn't compiled into the kernel
  :P
 
 
 
  On Sat, Mar 7, 2009 at 8:34 AM, Gary Stanley g...@velocity-servers.net
  wrote:
  
At 08:27 AM 3/7/2009, listac...@lvwnet.com wrote:
  I feel like such a linux nub... how do you set your clocksource?

On any fairly recent 2.6-series kernel you can put this right on the
kernel boot commandline:

clocksource=$whatever

like

clocksource=hpet

or

clocksource=tsc

so that it is set at boot.

The echoing of available options into the /sys entry is valid as well,
  ie:

# echo hpet 
/sys/devices/system/clocksource/clocksource0/current_clocksource

but is more of a post-boot type thing.  That's not bad, necessarily.
   You
can use it to change the clocksource post-boot.  This is useful if you
  are
experimenting with different ones because you can change the
  clocksource
without rebooting.

So to get a list of which clocksources your hardware has available:

# cat /sys/devices/system/clocksource/clocksource0/current_clocksource

you'll get something like this back (but it will vary from system to
system):

tsc jiffies hpet acpi_pm



Someone else asked whether running a 500Hz timer resolution will allow
  you
to get a stable 500 server fps.  I'm not going to say it is
  impossible,
but I will say that *I* have yet to find a server machine
  (server-class
hardware) that would let me get 500fps with a 500Hz kernel.
   
I was able to get it running on a test machine.
   
I've only ever been able to get 500 server fps with a 1000Hz or
  tickless
kernel, and setting fps_max to 600 or higher.

Entirely possible I'm just not doing it right though.  But what I do
works, so I keep doing it. :)

Setting fps_max to 600 usually gets me around 490-496 server fps.  CPU
utilization for the core a full 30-slot server runs on is usually
  around
60-65% on a 2.5GHz Harpertown but it does briefly peak higher at
  times.

This is under F10 x86_64 with a stock 2.6.27 kernel (which I'm pretty
  sure
is built dynamic/tickless) and I can get ~1000 server fps out of it
  for
our CS:S games by setting fps_max to 2000.  I'm using clocksource=hpet
currently, but have considered experimenting with tsc since I've read
  that
there are some recent userspace optimizations in glibc for it on
  x86_64
which may be of benefit.
   
That only happens if the binaries are x86_64.
   
   
   
___
To unsubscribe, edit your list preferences, or view the list archives,
please visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux
   
  
  
  
  --
   From Ben B. (Goerge)
  ___
  To unsubscribe, edit your list preferences, or view the list
  archives, please visit:
  http://list.valvesoftware.com/mailman/listinfo/hlds_linux
 
 
  ___
  To unsubscribe, edit your list preferences, or view the list archives,
  please visit:
  http://list.valvesoftware.com/mailman/listinfo/hlds_linux
 



--
 From Ben B. (Goerge)
___
To unsubscribe, edit your list preferences, or view the list 
archives, please visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread Gary Stanley
At 01:12 PM 3/7/2009, Ben B wrote:
dont ask me, this is how it was when i found it.  So if I compile my own
kernel, it should have them clocksources?

What's the motherboard? is it a virtual machine?


On Sat, Mar 7, 2009 at 11:01 AM, Gary Stanley 
g...@velocity-servers.netwrote:

  At 12:47 PM 3/7/2009, Ben B wrote:
  i just have jiffies in as an available clocksource... there a way to get
  htpet and tsc?
 
  TSC should be always be available as a clocksource, unless something
  is seriously wrong with your setup.
  Actually, a normal kernel will panic if TSC isn't compiled into the kernel
  :P
 
 
 
  On Sat, Mar 7, 2009 at 8:34 AM, Gary Stanley g...@velocity-servers.net
  wrote:
  
At 08:27 AM 3/7/2009, listac...@lvwnet.com wrote:
  I feel like such a linux nub... how do you set your clocksource?

On any fairly recent 2.6-series kernel you can put this right on the
kernel boot commandline:

clocksource=$whatever

like

clocksource=hpet

or

clocksource=tsc

so that it is set at boot.

The echoing of available options into the /sys entry is valid as well,
  ie:

# echo hpet 
/sys/devices/system/clocksource/clocksource0/current_clocksource

but is more of a post-boot type thing.  That's not bad, necessarily.
   You
can use it to change the clocksource post-boot.  This is useful if you
  are
experimenting with different ones because you can change the
  clocksource
without rebooting.

So to get a list of which clocksources your hardware has available:

# cat /sys/devices/system/clocksource/clocksource0/current_clocksource

you'll get something like this back (but it will vary from system to
system):

tsc jiffies hpet acpi_pm



Someone else asked whether running a 500Hz timer resolution will allow
  you
to get a stable 500 server fps.  I'm not going to say it is
  impossible,
but I will say that *I* have yet to find a server machine
  (server-class
hardware) that would let me get 500fps with a 500Hz kernel.
   
I was able to get it running on a test machine.
   
I've only ever been able to get 500 server fps with a 1000Hz or
  tickless
kernel, and setting fps_max to 600 or higher.

Entirely possible I'm just not doing it right though.  But what I do
works, so I keep doing it. :)

Setting fps_max to 600 usually gets me around 490-496 server fps.  CPU
utilization for the core a full 30-slot server runs on is usually
  around
60-65% on a 2.5GHz Harpertown but it does briefly peak higher at
  times.

This is under F10 x86_64 with a stock 2.6.27 kernel (which I'm pretty
  sure
is built dynamic/tickless) and I can get ~1000 server fps out of it
  for
our CS:S games by setting fps_max to 2000.  I'm using clocksource=hpet
currently, but have considered experimenting with tsc since I've read
  that
there are some recent userspace optimizations in glibc for it on
  x86_64
which may be of benefit.
   
That only happens if the binaries are x86_64.
   
   
   
___
To unsubscribe, edit your list preferences, or view the list archives,
please visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux
   
  
  
  
  --
   From Ben B. (Goerge)
  ___
  To unsubscribe, edit your list preferences, or view the list
  archives, please visit:
  http://list.valvesoftware.com/mailman/listinfo/hlds_linux
 
 
  ___
  To unsubscribe, edit your list preferences, or view the list archives,
  please visit:
  http://list.valvesoftware.com/mailman/listinfo/hlds_linux
 



--
 From Ben B. (Goerge)
___
To unsubscribe, edit your list preferences, or view the list 
archives, please visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread gameadmin
 So to get a list of which clocksources your hardware has
 available:

# cat /sys/devices/system/clocksource/clocksource0/current_clocksource

I think you meant available_clocksource not current_clocksource ?

 -Original Message-
 From: hlds_linux-boun...@list.valvesoftware.com [mailto:hlds_linux-
 boun...@list.valvesoftware.com] On Behalf Of Gary Stanley
 Sent: 07 March 2009 18:40
 To: Half-Life dedicated Linux server mailing list; Half-Life dedicated
 Linux server mailing list
 Subject: Re: [hlds_linux] Kernel Options and Clocksource
 
 At 01:12 PM 3/7/2009, Ben B wrote:
 dont ask me, this is how it was when i found it.  So if I compile my
 own
 kernel, it should have them clocksources?
 
 What's the motherboard? is it a virtual machine?
 
 
 On Sat, Mar 7, 2009 at 11:01 AM, Gary Stanley
 g...@velocity-servers.netwrote:
 
   At 12:47 PM 3/7/2009, Ben B wrote:
   i just have jiffies in as an available clocksource... there a way
 to get
   htpet and tsc?
  
   TSC should be always be available as a clocksource, unless
 something
   is seriously wrong with your setup.
   Actually, a normal kernel will panic if TSC isn't compiled into the
 kernel
   :P
  
  
  
   On Sat, Mar 7, 2009 at 8:34 AM, Gary Stanley g...@velocity-
 servers.net
   wrote:
   
 At 08:27 AM 3/7/2009, listac...@lvwnet.com wrote:
   I feel like such a linux nub... how do you set your
 clocksource?
 
 On any fairly recent 2.6-series kernel you can put this right
 on the
 kernel boot commandline:
 
 clocksource=$whatever
 
 like
 
 clocksource=hpet
 
 or
 
 clocksource=tsc
 
 so that it is set at boot.
 
 The echoing of available options into the /sys entry is valid
 as well,
   ie:
 
 # echo hpet 

 /sys/devices/system/clocksource/clocksource0/current_clocksource
 
 but is more of a post-boot type thing.  That's not bad,
 necessarily.
You
 can use it to change the clocksource post-boot.  This is
 useful if you
   are
 experimenting with different ones because you can change the
   clocksource
 without rebooting.
 
 So to get a list of which clocksources your hardware has
 available:
 
 # cat
 /sys/devices/system/clocksource/clocksource0/current_clocksource
 
 you'll get something like this back (but it will vary from
 system to
 system):
 
 tsc jiffies hpet acpi_pm
 
 
 
 Someone else asked whether running a 500Hz timer resolution
 will allow
   you
 to get a stable 500 server fps.  I'm not going to say it is
   impossible,
 but I will say that *I* have yet to find a server machine
   (server-class
 hardware) that would let me get 500fps with a 500Hz kernel.

 I was able to get it running on a test machine.

 I've only ever been able to get 500 server fps with a 1000Hz
 or
   tickless
 kernel, and setting fps_max to 600 or higher.
 
 Entirely possible I'm just not doing it right though.  But
 what I do
 works, so I keep doing it. :)
 
 Setting fps_max to 600 usually gets me around 490-496 server
 fps.  CPU
 utilization for the core a full 30-slot server runs on is
 usually
   around
 60-65% on a 2.5GHz Harpertown but it does briefly peak higher
 at
   times.
 
 This is under F10 x86_64 with a stock 2.6.27 kernel (which I'm
 pretty
   sure
 is built dynamic/tickless) and I can get ~1000 server fps out
 of it
   for
 our CS:S games by setting fps_max to 2000.  I'm using
 clocksource=hpet
 currently, but have considered experimenting with tsc since
 I've read
   that
 there are some recent userspace optimizations in glibc for it
 on
   x86_64
 which may be of benefit.

 That only happens if the binaries are x86_64.



 ___
 To unsubscribe, edit your list preferences, or view the list
 archives,
 please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux

   
   
   
   --
From Ben B. (Goerge)
   ___
   To unsubscribe, edit your list preferences, or view the list
   archives, please visit:
   http://list.valvesoftware.com/mailman/listinfo/hlds_linux
  
  
   ___
   To unsubscribe, edit your list preferences, or view the list
 archives,
   please visit:
   http://list.valvesoftware.com/mailman/listinfo/hlds_linux
  
 
 
 
 --
  From Ben B. (Goerge)
 ___
 To unsubscribe, edit your list preferences, or view the list
 archives, please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux
 
 
 ___
 To unsubscribe, edit your list preferences, or view the list archives,
 please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux


___
To unsubscribe

Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread Ben B
Duno about the mobo, but it's not a virtual.  It's Q9400, 4gig ram, 64 bit
Centos 5.2

On Sat, Mar 7, 2009 at 11:40 AM, Gary Stanley g...@velocity-servers.netwrote:

 At 01:12 PM 3/7/2009, Ben B wrote:
 dont ask me, this is how it was when i found it.  So if I compile my own
 kernel, it should have them clocksources?

 What's the motherboard? is it a virtual machine?


 On Sat, Mar 7, 2009 at 11:01 AM, Gary Stanley
 g...@velocity-servers.netwrote:
 
   At 12:47 PM 3/7/2009, Ben B wrote:
   i just have jiffies in as an available clocksource... there a way to
 get
   htpet and tsc?
  
   TSC should be always be available as a clocksource, unless something
   is seriously wrong with your setup.
   Actually, a normal kernel will panic if TSC isn't compiled into the
 kernel
   :P
  
  
  
   On Sat, Mar 7, 2009 at 8:34 AM, Gary Stanley 
 g...@velocity-servers.net
   wrote:
   
 At 08:27 AM 3/7/2009, listac...@lvwnet.com wrote:
   I feel like such a linux nub... how do you set your
 clocksource?
 
 On any fairly recent 2.6-series kernel you can put this right on
 the
 kernel boot commandline:
 
 clocksource=$whatever
 
 like
 
 clocksource=hpet
 
 or
 
 clocksource=tsc
 
 so that it is set at boot.
 
 The echoing of available options into the /sys entry is valid as
 well,
   ie:
 
 # echo hpet 
 /sys/devices/system/clocksource/clocksource0/current_clocksource
 
 but is more of a post-boot type thing.  That's not bad,
 necessarily.
You
 can use it to change the clocksource post-boot.  This is useful if
 you
   are
 experimenting with different ones because you can change the
   clocksource
 without rebooting.
 
 So to get a list of which clocksources your hardware has
 available:
 
 # cat
 /sys/devices/system/clocksource/clocksource0/current_clocksource
 
 you'll get something like this back (but it will vary from system
 to
 system):
 
 tsc jiffies hpet acpi_pm
 
 
 
 Someone else asked whether running a 500Hz timer resolution will
 allow
   you
 to get a stable 500 server fps.  I'm not going to say it is
   impossible,
 but I will say that *I* have yet to find a server machine
   (server-class
 hardware) that would let me get 500fps with a 500Hz kernel.

 I was able to get it running on a test machine.

 I've only ever been able to get 500 server fps with a 1000Hz or
   tickless
 kernel, and setting fps_max to 600 or higher.
 
 Entirely possible I'm just not doing it right though.  But what I
 do
 works, so I keep doing it. :)
 
 Setting fps_max to 600 usually gets me around 490-496 server fps.
  CPU
 utilization for the core a full 30-slot server runs on is usually
   around
 60-65% on a 2.5GHz Harpertown but it does briefly peak higher at
   times.
 
 This is under F10 x86_64 with a stock 2.6.27 kernel (which I'm
 pretty
   sure
 is built dynamic/tickless) and I can get ~1000 server fps out of
 it
   for
 our CS:S games by setting fps_max to 2000.  I'm using
 clocksource=hpet
 currently, but have considered experimenting with tsc since I've
 read
   that
 there are some recent userspace optimizations in glibc for it on
   x86_64
 which may be of benefit.

 That only happens if the binaries are x86_64.



 ___
 To unsubscribe, edit your list preferences, or view the list
 archives,
 please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux

   
   
   
   --
From Ben B. (Goerge)
   ___
   To unsubscribe, edit your list preferences, or view the list
   archives, please visit:
   http://list.valvesoftware.com/mailman/listinfo/hlds_linux
  
  
   ___
   To unsubscribe, edit your list preferences, or view the list archives,
   please visit:
   http://list.valvesoftware.com/mailman/listinfo/hlds_linux
  
 
 
 
 --
  From Ben B. (Goerge)
 ___
 To unsubscribe, edit your list preferences, or view the list
 archives, please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux


 ___
 To unsubscribe, edit your list preferences, or view the list archives,
 please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux




-- 
From Ben B. (Goerge)
___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-07 Thread listacct2
 So to get a list of which clocksources your hardware has
 available:

# cat /sys/devices/system/clocksource/clocksource0/current_clocksource

 I think you meant available_clocksource not current_clocksource ?

Yes, already corrected myself TYVM



___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-06 Thread ServerAlex
Its not the timing that wastes the CPU time. You can't lower it with that.
90% is absolutly normal for such a big server.

2009/3/7 The Universes ad...@theuniverses.com:
 I'm running 4 32 man TF2 servers at 500fps (66 tick) and I'm wondering
 if having kernel at 1000HZ (not tickless) with PREEMPT is necessary?
 Is that putting unnecessary strain on my CPU (Q9300)?

 My second question is if  you guys use HPET as your clocksource
 $ cat /sys/devices/system/clocksource/clocksource0/available_clocksource
 tsc hpet acpi_pm jiffies

 $ cat /sys/devices/system/clocksource/clocksource0/current_clocksource
 tsc

 Would you recommend changing that to HPET?

 I'm basically trying to lower CPU usage so it doesnt shoot up to 90% 
 sometimes.

 Thanks,
 Dan

 ___
 To unsubscribe, edit your list preferences, or view the list archives, please 
 visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux


___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-06 Thread The Universes
Would changing to HPET help at all?



ServerAlex wrote:
 Its not the timing that wastes the CPU time. You can't lower it with that.
 90% is absolutly normal for such a big server.
 
 2009/3/7 The Universes ad...@theuniverses.com:
 I'm running 4 32 man TF2 servers at 500fps (66 tick) and I'm wondering
 if having kernel at 1000HZ (not tickless) with PREEMPT is necessary?
 Is that putting unnecessary strain on my CPU (Q9300)?

 My second question is if  you guys use HPET as your clocksource
 $ cat /sys/devices/system/clocksource/clocksource0/available_clocksource
 tsc hpet acpi_pm jiffies

 $ cat /sys/devices/system/clocksource/clocksource0/current_clocksource
 tsc

 Would you recommend changing that to HPET?

 I'm basically trying to lower CPU usage so it doesnt shoot up to 90% 
 sometimes.

 Thanks,
 Dan

 ___
 To unsubscribe, edit your list preferences, or view the list archives, 
 please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux

 
 ___
 To unsubscribe, edit your list preferences, or view the list archives, please 
 visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux

___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-06 Thread Gary Stanley
At 10:33 PM 3/6/2009, The Universes wrote:
I'm running 4 32 man TF2 servers at 500fps (66 tick) and I'm wondering
if having kernel at 1000HZ (not tickless) with PREEMPT is necessary?
Is that putting unnecessary strain on my CPU (Q9300)?

My second question is if  you guys use HPET as your clocksource
$ cat /sys/devices/system/clocksource/clocksource0/available_clocksource
tsc hpet acpi_pm jiffies

$ cat /sys/devices/system/clocksource/clocksource0/current_clocksource
tsc


1000hz kernels make nanosleep() expensive to call.. on a core2quad 
calling usleep (which calls nanosleep)

nanosleep: 6157 cycles

That's alot of cpu time. Cranking up HZ makes interrupts fire so 
often, so you get more accurate sleep behavior..

TSC lives on the CPU, so calling it is fairly cheap. HPET lives off 
somewhere on a bridge, so you need to go out to PCI land to
read it. HPET is a decent choice, but overall the fastest one is TSC.




Would you recommend changing that to HPET?

I'm basically trying to lower CPU usage so it doesnt shoot up to 90% 
sometimes.

Thanks,
Dan

___
To unsubscribe, edit your list preferences, or view the list 
archives, please visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-06 Thread Gary Stanley
At 10:33 PM 3/6/2009, The Universes wrote:
I'm running 4 32 man TF2 servers at 500fps (66 tick) and I'm wondering
if having kernel at 1000HZ (not tickless) with PREEMPT is necessary?
Is that putting unnecessary strain on my CPU (Q9300)?

My second question is if  you guys use HPET as your clocksource
$ cat /sys/devices/system/clocksource/clocksource0/available_clocksource
tsc hpet acpi_pm jiffies

$ cat /sys/devices/system/clocksource/clocksource0/current_clocksource
tsc


1000hz kernels make nanosleep() expensive to call.. on a core2quad 
calling usleep (which calls nanosleep)

nanosleep: 6157 cycles

That's alot of cpu time. Cranking up HZ makes interrupts fire so 
often, so you get more accurate sleep behavior..

TSC lives on the CPU, so calling it is fairly cheap. HPET lives off 
somewhere on a bridge, so you need to go out to PCI land to
read it. HPET is a decent choice, but overall the fastest one is TSC.




Would you recommend changing that to HPET?

I'm basically trying to lower CPU usage so it doesnt shoot up to 90% 
sometimes.

Thanks,
Dan

___
To unsubscribe, edit your list preferences, or view the list 
archives, please visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux


Re: [hlds_linux] Kernel Options and Clocksource

2009-03-06 Thread The Universes
Do you think dropping it down to 500HZ is a better choice or do you 
suggest something else? If yes, does 500HZ still maintain 500FPS?

Thanks!

Gary Stanley wrote:
 At 10:33 PM 3/6/2009, The Universes wrote:
 I'm running 4 32 man TF2 servers at 500fps (66 tick) and I'm wondering
 if having kernel at 1000HZ (not tickless) with PREEMPT is necessary?
 Is that putting unnecessary strain on my CPU (Q9300)?

 My second question is if  you guys use HPET as your clocksource
 $ cat /sys/devices/system/clocksource/clocksource0/available_clocksource
 tsc hpet acpi_pm jiffies

 $ cat /sys/devices/system/clocksource/clocksource0/current_clocksource
 tsc
 
 
 1000hz kernels make nanosleep() expensive to call.. on a core2quad 
 calling usleep (which calls nanosleep)
 
 nanosleep: 6157 cycles
 
 That's alot of cpu time. Cranking up HZ makes interrupts fire so 
 often, so you get more accurate sleep behavior..
 
 TSC lives on the CPU, so calling it is fairly cheap. HPET lives off 
 somewhere on a bridge, so you need to go out to PCI land to
 read it. HPET is a decent choice, but overall the fastest one is TSC.
 
 
 
 
 Would you recommend changing that to HPET?

 I'm basically trying to lower CPU usage so it doesnt shoot up to 90% 
 sometimes.

 Thanks,
 Dan

 ___
 To unsubscribe, edit your list preferences, or view the list 
 archives, please visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux
 
 
 ___
 To unsubscribe, edit your list preferences, or view the list archives, please 
 visit:
 http://list.valvesoftware.com/mailman/listinfo/hlds_linux

___
To unsubscribe, edit your list preferences, or view the list archives, please 
visit:
http://list.valvesoftware.com/mailman/listinfo/hlds_linux