* [LARTC] [tcng] PSCHED_CPU ?
@ 2002-09-18 13:26 raptor
2002-09-18 13:38 ` Werner Almesberger
` (5 more replies)
0 siblings, 6 replies; 7+ messages in thread
From: raptor @ 2002-09-18 13:26 UTC (permalink / raw)
To: lartc
hi,
Will it be a problem if my kernel is compiled with PSCHED_CPU, but for the success of the compilation of tcism I use PSCHED_JIFFES ?
-----------------------------------------------------------------
In file included from klink.c:19:
klib/include/net/pkt_sched.h:285:2: #error PSCHED_CLOCK_SOURCE=PSCHED_CPU is not supported on this arch.
In file included from trace.c:20:
klib/include/net/pkt_sched.h:285:2: #error PSCHED_CLOCK_SOURCE=PSCHED_CPU is not supported on this arch.
make[1]: *** [.depend] Error 1
make[1]: Leaving directory `/arh/compile/tcng/tcsim'
make: *** [all] Error 1
Thanx
raptor
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [LARTC] [tcng] PSCHED_CPU ?
2002-09-18 13:26 [LARTC] [tcng] PSCHED_CPU ? raptor
@ 2002-09-18 13:38 ` Werner Almesberger
2002-09-18 14:01 ` raptor
` (4 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: Werner Almesberger @ 2002-09-18 13:38 UTC (permalink / raw)
To: lartc
raptor wrote:
> Will it be a problem if my kernel is compiled with PSCHED_CPU, but for
> the success of the compilation of tcism I use PSCHED_JIFFES ?
tcsim should just use PSCHED_JIFFIES, no matter what your kernel
is configured to do.
Quite obviously, this doesn't seem to be the case on your system.
Is this a i386 platform ? And which kernel and which version of
tcng are you using ?
- Werner
--
_________________________________________________________________________
/ Werner Almesberger, Buenos Aires, Argentina wa@almesberger.net /
/_http://www.almesberger.net/____________________________________________/
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [LARTC] [tcng] PSCHED_CPU ?
2002-09-18 13:26 [LARTC] [tcng] PSCHED_CPU ? raptor
2002-09-18 13:38 ` Werner Almesberger
@ 2002-09-18 14:01 ` raptor
2002-09-18 14:25 ` Werner Almesberger
` (3 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: raptor @ 2002-09-18 14:01 UTC (permalink / raw)
To: lartc
|Quite obviously, this doesn't seem to be the case on your system.
|Is this a i386 platform ? And which kernel and which version of
|tcng are you using ?
]- i386, tcng-8u, Mandrake 2.4.19mdk-9
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [LARTC] [tcng] PSCHED_CPU ?
2002-09-18 13:26 [LARTC] [tcng] PSCHED_CPU ? raptor
2002-09-18 13:38 ` Werner Almesberger
2002-09-18 14:01 ` raptor
@ 2002-09-18 14:25 ` Werner Almesberger
2002-09-18 16:07 ` Vladimír Trebický
` (2 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: Werner Almesberger @ 2002-09-18 14:25 UTC (permalink / raw)
To: lartc
[-- Attachment #1: Type: text/plain, Size: 418 bytes --]
raptor wrote:
> ]- i386, tcng-8u, Mandrake 2.4.19mdk-9
Does the attached patch help ? With it, setup.klib simply reverts
include/net/pkt_sched.h back to using PSCHED_JIFFIES.
- Werner
--
_________________________________________________________________________
/ Werner Almesberger, Buenos Aires, Argentina wa@almesberger.net /
/_http://www.almesberger.net/____________________________________________/
[-- Attachment #2: patch --]
[-- Type: text/plain, Size: 427 bytes --]
--- setup.klib.old Wed Sep 18 11:14:27 2002
+++ setup.klib Wed Sep 18 11:24:23 2002
@@ -100,7 +100,14 @@
u16 mask); \
trace_u32_offset(skb,n->handle,ptr-skb->nh.raw+n->sel.offoff,n->sel.offmask);\
& }/'>cls_u32.c
-
+
+#
+# De-Mandrakize net/pkt_sched.h
+#
+
+sed 's/\(#define PSCHED_CLOCK_SOURCE[^ -~]*PSCHED_\)CPU/\1JIFFIES/' \
+ <$KSRC/include/net/pkt_sched.h >include/net/pkt_sched.h
+
ln -s $KSRC kernel
#
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [LARTC] [tcng] PSCHED_CPU ?
2002-09-18 13:26 [LARTC] [tcng] PSCHED_CPU ? raptor
` (2 preceding siblings ...)
2002-09-18 14:25 ` Werner Almesberger
@ 2002-09-18 16:07 ` Vladimír Trebický
2002-09-19 6:24 ` raptor
2002-09-19 6:33 ` Vladimír Trebický
5 siblings, 0 replies; 7+ messages in thread
From: Vladimír Trebický @ 2002-09-18 16:07 UTC (permalink / raw)
To: lartc
The problem with PSCHED_CPU is that the time is derived by reading of TSC
registry which is measure counter of the processor. TSC exists on Intel
platform from the times of Pentium but sometimes cannot be used as a
counter, for example with APM (advanced power management) turned on.
----- Original Message -----
From: "raptor" <raptor@tvskat.net>
To: <lartc@mailman.ds9a.nl>
Sent: Wednesday, September 18, 2002 10:21 PM
Subject: [LARTC] [tcng] PSCHED_CPU ?
> hi,
>
> Will it be a problem if my kernel is compiled with PSCHED_CPU, but for the
success of the compilation of tcism I use PSCHED_JIFFES ?
> -----------------------------------------------------------------
> In file included from klink.c:19:
> klib/include/net/pkt_sched.h:285:2: #error PSCHED_CLOCK_SOURCE=PSCHED_CPU
is not supported on this arch.
> In file included from trace.c:20:
> klib/include/net/pkt_sched.h:285:2: #error PSCHED_CLOCK_SOURCE=PSCHED_CPU
is not supported on this arch.
> make[1]: *** [.depend] Error 1
> make[1]: Leaving directory `/arh/compile/tcng/tcsim'
> make: *** [all] Error 1
>
> Thanx
>
> raptor
> _______________________________________________
> LARTC mailing list / LARTC@mailman.ds9a.nl
> http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [LARTC] [tcng] PSCHED_CPU ?
2002-09-18 13:26 [LARTC] [tcng] PSCHED_CPU ? raptor
` (3 preceding siblings ...)
2002-09-18 16:07 ` Vladimír Trebický
@ 2002-09-19 6:24 ` raptor
2002-09-19 6:33 ` Vladimír Trebický
5 siblings, 0 replies; 7+ messages in thread
From: raptor @ 2002-09-19 6:24 UTC (permalink / raw)
To: lartc
Vladimír Trebický <druid@mail.cz> wrote:
|The problem with PSCHED_CPU is that the time is derived by reading of TSC
|registry which is measure counter of the processor. TSC exists on Intel
|platform from the times of Pentium but sometimes cannot be used as a
|counter, for example with APM (advanced power management) turned on.
]- that's good then 'cause I didn't compiled power-management into the kernel :")
Do u know any other reason not to use PSCHED_CPU ?
In the past I have setup "HZ = 1000" when building QoS is it wise to do it if the only purpose of this computer is QoS+Firewall and of course it is powerfull enought 1.8GHz.
And I don't expect it to exceed 1000 slow-qos-channels and handle not more than 1Mb/s most of the time.
raptor
PS.Sorry for the ignorance what is TSC-regitry and its use ? thanx..
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [LARTC] [tcng] PSCHED_CPU ?
2002-09-18 13:26 [LARTC] [tcng] PSCHED_CPU ? raptor
` (4 preceding siblings ...)
2002-09-19 6:24 ` raptor
@ 2002-09-19 6:33 ` Vladimír Trebický
5 siblings, 0 replies; 7+ messages in thread
From: Vladimír Trebický @ 2002-09-19 6:33 UTC (permalink / raw)
To: lartc
In my opinion there is no reason not to use PSCHED_CPU except those around
APM and architecture. If you don't want to use APM and do have Athlon use
PSCHED_CPU.
----- Original Message -----
From: "raptor" <raptor@tvskat.net>
To: "Vladimír Trebický" <druid@mail.cz>
Cc: <lartc@mailman.ds9a.nl>
Sent: Thursday, September 19, 2002 3:20 PM
Subject: Re: [LARTC] [tcng] PSCHED_CPU ?
> Vladimír Trebický <druid@mail.cz> wrote:
> |The problem with PSCHED_CPU is that the time is derived by reading of TSC
> |registry which is measure counter of the processor. TSC exists on Intel
> |platform from the times of Pentium but sometimes cannot be used as a
> |counter, for example with APM (advanced power management) turned on.
>
> ]- that's good then 'cause I didn't compiled power-management into the
kernel :")
> Do u know any other reason not to use PSCHED_CPU ?
>
> In the past I have setup "HZ = 1000" when building QoS is it wise to do it
if the only purpose of this computer is QoS+Firewall and of course it is
powerfull enought 1.8GHz.
> And I don't expect it to exceed 1000 slow-qos-channels and handle not more
than 1Mb/s most of the time.
>
> raptor
> PS.Sorry for the ignorance what is TSC-regitry and its use ? thanx..
> _______________________________________________
> LARTC mailing list / LARTC@mailman.ds9a.nl
> http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2002-09-19 6:33 UTC | newest]
Thread overview: 7+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2002-09-18 13:26 [LARTC] [tcng] PSCHED_CPU ? raptor
2002-09-18 13:38 ` Werner Almesberger
2002-09-18 14:01 ` raptor
2002-09-18 14:25 ` Werner Almesberger
2002-09-18 16:07 ` Vladimír Trebický
2002-09-19 6:24 ` raptor
2002-09-19 6:33 ` Vladimír Trebický
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.