* Srivatsa Vaddagiri <[EMAIL PROTECTED]> wrote:
> +#define __NR_yield_to 280
> +__SYSCALL(__NR_move_pages, sys_sched_yield_to)
>
> s/__NR_move_pages/__NR_yield_to in the above line?
yeah, thanks.
Ingo
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel"
On Mon, Apr 23, 2007 at 08:21:16AM +0200, Ingo Molnar wrote:
> > Changing sys_yield_to to sys_sched_yield_to in
> > include/asm-x86_64/unistd.h fixes the problem.
>
> thanks. I edited the -v5 patch so new downloads should have the fix. (i
> also test-booted x86_64 with this patch)
I downloaded
* Christian Hesse <[EMAIL PROTECTED]> wrote:
> > Or do you mean that the default placement of single tasks starts at
> > CPU#0, while with mainline they were alternating?
>
> That was not your fault. I updated suspend2 to 2.2.9.13 and everything
> works as expected again. Sorry for the noise.
On Wednesday 25 April 2007, Ingo Molnar wrote:
> * Christian Hesse <[EMAIL PROTECTED]> wrote:
> > On Monday 23 April 2007, Ingo Molnar wrote:
> > > i'm pleased to announce release -v5 of the CFS scheduler patchset.
> >
> > Hi Ingo,
> >
> > I just noticed that with cfs all processes (except some
* Christian Hesse <[EMAIL PROTECTED]> wrote:
> On Monday 23 April 2007, Ingo Molnar wrote:
> > i'm pleased to announce release -v5 of the CFS scheduler patchset.
>
> Hi Ingo,
>
> I just noticed that with cfs all processes (except some kernel
> threads) run on cpu 0. I don't think this is
* Christian Hesse [EMAIL PROTECTED] wrote:
On Monday 23 April 2007, Ingo Molnar wrote:
i'm pleased to announce release -v5 of the CFS scheduler patchset.
Hi Ingo,
I just noticed that with cfs all processes (except some kernel
threads) run on cpu 0. I don't think this is expected cpu
* Christian Hesse [EMAIL PROTECTED] wrote:
Or do you mean that the default placement of single tasks starts at
CPU#0, while with mainline they were alternating?
That was not your fault. I updated suspend2 to 2.2.9.13 and everything
works as expected again. Sorry for the noise.
ok,
On Wednesday 25 April 2007, Ingo Molnar wrote:
* Christian Hesse [EMAIL PROTECTED] wrote:
On Monday 23 April 2007, Ingo Molnar wrote:
i'm pleased to announce release -v5 of the CFS scheduler patchset.
Hi Ingo,
I just noticed that with cfs all processes (except some kernel
threads)
On Mon, Apr 23, 2007 at 08:21:16AM +0200, Ingo Molnar wrote:
Changing sys_yield_to to sys_sched_yield_to in
include/asm-x86_64/unistd.h fixes the problem.
thanks. I edited the -v5 patch so new downloads should have the fix. (i
also test-booted x86_64 with this patch)
I downloaded -v5
* Srivatsa Vaddagiri [EMAIL PROTECTED] wrote:
+#define __NR_yield_to 280
+__SYSCALL(__NR_move_pages, sys_sched_yield_to)
s/__NR_move_pages/__NR_yield_to in the above line?
yeah, thanks.
Ingo
-
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the
On Monday 23 April 2007, Ingo Molnar wrote:
> i'm pleased to announce release -v5 of the CFS scheduler patchset.
Hi Ingo,
I just noticed that with cfs all processes (except some kernel threads) run on
cpu 0. I don't think this is expected cpu affinity for an smp system? I
remember about half
On Monday 23 April 2007, Ingo Molnar wrote:
i'm pleased to announce release -v5 of the CFS scheduler patchset.
Hi Ingo,
I just noticed that with cfs all processes (except some kernel threads) run on
cpu 0. I don't think this is expected cpu affinity for an smp system? I
remember about half of
* Guillaume Chazarain <[EMAIL PROTECTED]> wrote:
> 2007/4/23, Ingo Molnar <[EMAIL PROTECTED]>:
>
> Index: linux/kernel/sched.c
> ===
> --- linux.orig/kernel/sched.c
> +++ linux/kernel/sched.c
> +#include "sched_stats.h"
> +#include
2007/4/23, Ingo Molnar <[EMAIL PROTECTED]>:
Index: linux/kernel/sched.c
===
--- linux.orig/kernel/sched.c
+++ linux/kernel/sched.c
+#include "sched_stats.h"
+#include "sched_rt.c"
+#include "sched_fair.c"
+#include "sched_debug.c"
* Zach Carter <[EMAIL PROTECTED]> wrote:
> FYI, make headers_check seems to fail on this:
>
> [EMAIL PROTECTED] linux-2.6]$ make headers_check
> make[2]: *** No rule to make target
> `/src/linux-2.6/usr/include/linux/.check.sched.h', needed by
> `__headerscheck'. Stop.
> make[1]: ***
* Nick Piggin <[EMAIL PROTECTED]> wrote:
> > yeah - but they'll all be quad core, so the SMP timeslice
> > multiplicator should do the trick. Most of the CFS testers use
> > single-CPU systems.
>
> But desktop users could have have quad thread and even 8 thread CPUs
> soon, [...]
SMT is
* Nick Piggin <[EMAIL PROTECTED]> wrote:
> > do need reinforcement and test results on the basic part: _can_ this
> > design be interactive enough on the desktop? So far the feedback has
> > been affirmative, but more testing is needed.
>
> It seems to be fairly easy to make a scheduler
On Mon, Apr 23, 2007 at 09:10:50AM +0200, Ingo Molnar wrote:
>
> * Nick Piggin <[EMAIL PROTECTED]> wrote:
>
> > > yeah - but they'll all be quad core, so the SMP timeslice
> > > multiplicator should do the trick. Most of the CFS testers use
> > > single-CPU systems.
> >
> > But desktop users
* Nick Piggin <[EMAIL PROTECTED]> wrote:
> > yeah - but they'll all be quad core, so the SMP timeslice
> > multiplicator should do the trick. Most of the CFS testers use
> > single-CPU systems.
>
> But desktop users could have have quad thread and even 8 thread CPUs
> soon, so if the number
* Markus Trippelsdorf <[EMAIL PROTECTED]> wrote:
> > The new version does not link here (amd64,smp):
> >
> > LD .tmp_vmlinux1
> > arch/x86_64/kernel/built-in.o:(.rodata+0x1dd8): undefined reference to
> > `sys_yield_to'
>
> Changing sys_yield_to to sys_sched_yield_to in
>
* Markus Trippelsdorf [EMAIL PROTECTED] wrote:
The new version does not link here (amd64,smp):
LD .tmp_vmlinux1
arch/x86_64/kernel/built-in.o:(.rodata+0x1dd8): undefined reference to
`sys_yield_to'
Changing sys_yield_to to sys_sched_yield_to in
* Nick Piggin [EMAIL PROTECTED] wrote:
yeah - but they'll all be quad core, so the SMP timeslice
multiplicator should do the trick. Most of the CFS testers use
single-CPU systems.
But desktop users could have have quad thread and even 8 thread CPUs
soon, so if the number doesn't
On Mon, Apr 23, 2007 at 09:10:50AM +0200, Ingo Molnar wrote:
* Nick Piggin [EMAIL PROTECTED] wrote:
yeah - but they'll all be quad core, so the SMP timeslice
multiplicator should do the trick. Most of the CFS testers use
single-CPU systems.
But desktop users could have have
* Nick Piggin [EMAIL PROTECTED] wrote:
do need reinforcement and test results on the basic part: _can_ this
design be interactive enough on the desktop? So far the feedback has
been affirmative, but more testing is needed.
It seems to be fairly easy to make a scheduler interactive if
* Nick Piggin [EMAIL PROTECTED] wrote:
yeah - but they'll all be quad core, so the SMP timeslice
multiplicator should do the trick. Most of the CFS testers use
single-CPU systems.
But desktop users could have have quad thread and even 8 thread CPUs
soon, [...]
SMT is indeed an
* Zach Carter [EMAIL PROTECTED] wrote:
FYI, make headers_check seems to fail on this:
[EMAIL PROTECTED] linux-2.6]$ make headers_check
make[2]: *** No rule to make target
`/src/linux-2.6/usr/include/linux/.check.sched.h', needed by
`__headerscheck'. Stop.
make[1]: *** [linux] Error 2
2007/4/23, Ingo Molnar [EMAIL PROTECTED]:
Index: linux/kernel/sched.c
===
--- linux.orig/kernel/sched.c
+++ linux/kernel/sched.c
+#include sched_stats.h
+#include sched_rt.c
+#include sched_fair.c
+#include sched_debug.c
Index:
* Guillaume Chazarain [EMAIL PROTECTED] wrote:
2007/4/23, Ingo Molnar [EMAIL PROTECTED]:
Index: linux/kernel/sched.c
===
--- linux.orig/kernel/sched.c
+++ linux/kernel/sched.c
+#include sched_stats.h
+#include sched_rt.c
On Mon, Apr 23, 2007 at 03:12:29AM +0200, Ingo Molnar wrote:
>
> i'm pleased to announce release -v5 of the CFS scheduler patchset. The
> patch against v2.6.21-rc7 and v2.6.20.7 can be downloaded from:
...
> - feature: add initial sys_sched_yield_to() implementation. Not hooked
>into the
On Mon, Apr 23, 2007 at 07:16:59AM +0200, Markus Trippelsdorf wrote:
> On Mon, Apr 23, 2007 at 03:12:29AM +0200, Ingo Molnar wrote:
> >
> > i'm pleased to announce release -v5 of the CFS scheduler patchset. The
> > patch against v2.6.21-rc7 and v2.6.20.7 can be downloaded from:
> ...
> > -
On Mon, Apr 23, 2007 at 05:43:10AM +0200, Ingo Molnar wrote:
>
> * Nick Piggin <[EMAIL PROTECTED]> wrote:
>
> > > note that CFS's "granularity" value is not directly comparable to
> > > "timeslice length":
> >
> > Right, but it does introduce the kbuild regression, [...]
>
> Note that i
* Nick Piggin <[EMAIL PROTECTED]> wrote:
> > note that CFS's "granularity" value is not directly comparable to
> > "timeslice length":
>
> Right, but it does introduce the kbuild regression, [...]
Note that i increased the granularity from 1msec to 5msecs after your
kbuild report, could you
On Mon, Apr 23, 2007 at 04:55:53AM +0200, Ingo Molnar wrote:
>
> * Nick Piggin <[EMAIL PROTECTED]> wrote:
>
> > > the biggest user-visible change in -v5 are various interactivity
> > > improvements (especially under higher load) to fix reported
> > > regressions, and an improved way of
Ingo Molnar wrote:
i'm pleased to announce release -v5 of the CFS scheduler patchset. The
patch against v2.6.21-rc7 and v2.6.20.7 can be downloaded from:
FYI, make headers_check seems to fail on this:
[EMAIL PROTECTED] linux-2.6]$ make headers_check
[snip]
CHECK
* Gene Heskett <[EMAIL PROTECTED]> wrote:
> I haven't approached that yet, but I just noticed, having been booted
> to this for all of 5 minutes, that although I told it not to renice x
> when my script ran 'make oldconfig', and I answered n, but there it
> is, sitting at -19 according to
* Nick Piggin <[EMAIL PROTECTED]> wrote:
> > the biggest user-visible change in -v5 are various interactivity
> > improvements (especially under higher load) to fix reported
> > regressions, and an improved way of handling nice levels. There's
> > also a new sys_sched_yield_to() syscall
On Sunday 22 April 2007, Nick Piggin wrote:
>On Mon, Apr 23, 2007 at 03:12:29AM +0200, Ingo Molnar wrote:
>> i'm pleased to announce release -v5 of the CFS scheduler patchset. The
>> patch against v2.6.21-rc7 and v2.6.20.7 can be downloaded from:
>>
>> http://redhat.com/~mingo/cfs-scheduler/
On Mon, Apr 23, 2007 at 03:12:29AM +0200, Ingo Molnar wrote:
>
> i'm pleased to announce release -v5 of the CFS scheduler patchset. The
> patch against v2.6.21-rc7 and v2.6.20.7 can be downloaded from:
>
> http://redhat.com/~mingo/cfs-scheduler/
>
> this CFS release mainly fixes
i'm pleased to announce release -v5 of the CFS scheduler patchset. The
patch against v2.6.21-rc7 and v2.6.20.7 can be downloaded from:
http://redhat.com/~mingo/cfs-scheduler/
this CFS release mainly fixes regressions and improves interactivity:
13 files changed, 211 insertions(+), 199
i'm pleased to announce release -v5 of the CFS scheduler patchset. The
patch against v2.6.21-rc7 and v2.6.20.7 can be downloaded from:
http://redhat.com/~mingo/cfs-scheduler/
this CFS release mainly fixes regressions and improves interactivity:
13 files changed, 211 insertions(+), 199
On Mon, Apr 23, 2007 at 03:12:29AM +0200, Ingo Molnar wrote:
i'm pleased to announce release -v5 of the CFS scheduler patchset. The
patch against v2.6.21-rc7 and v2.6.20.7 can be downloaded from:
http://redhat.com/~mingo/cfs-scheduler/
this CFS release mainly fixes regressions and
On Sunday 22 April 2007, Nick Piggin wrote:
On Mon, Apr 23, 2007 at 03:12:29AM +0200, Ingo Molnar wrote:
i'm pleased to announce release -v5 of the CFS scheduler patchset. The
patch against v2.6.21-rc7 and v2.6.20.7 can be downloaded from:
http://redhat.com/~mingo/cfs-scheduler/
this CFS
* Nick Piggin [EMAIL PROTECTED] wrote:
the biggest user-visible change in -v5 are various interactivity
improvements (especially under higher load) to fix reported
regressions, and an improved way of handling nice levels. There's
also a new sys_sched_yield_to() syscall implementation
* Gene Heskett [EMAIL PROTECTED] wrote:
I haven't approached that yet, but I just noticed, having been booted
to this for all of 5 minutes, that although I told it not to renice x
when my script ran 'make oldconfig', and I answered n, but there it
is, sitting at -19 according to htop.
Ingo Molnar wrote:
i'm pleased to announce release -v5 of the CFS scheduler patchset. The
patch against v2.6.21-rc7 and v2.6.20.7 can be downloaded from:
FYI, make headers_check seems to fail on this:
[EMAIL PROTECTED] linux-2.6]$ make headers_check
[snip]
CHECK
On Mon, Apr 23, 2007 at 04:55:53AM +0200, Ingo Molnar wrote:
* Nick Piggin [EMAIL PROTECTED] wrote:
the biggest user-visible change in -v5 are various interactivity
improvements (especially under higher load) to fix reported
regressions, and an improved way of handling nice levels.
* Nick Piggin [EMAIL PROTECTED] wrote:
note that CFS's granularity value is not directly comparable to
timeslice length:
Right, but it does introduce the kbuild regression, [...]
Note that i increased the granularity from 1msec to 5msecs after your
kbuild report, could you perhaps
On Mon, Apr 23, 2007 at 05:43:10AM +0200, Ingo Molnar wrote:
* Nick Piggin [EMAIL PROTECTED] wrote:
note that CFS's granularity value is not directly comparable to
timeslice length:
Right, but it does introduce the kbuild regression, [...]
Note that i increased the granularity
On Mon, Apr 23, 2007 at 07:16:59AM +0200, Markus Trippelsdorf wrote:
On Mon, Apr 23, 2007 at 03:12:29AM +0200, Ingo Molnar wrote:
i'm pleased to announce release -v5 of the CFS scheduler patchset. The
patch against v2.6.21-rc7 and v2.6.20.7 can be downloaded from:
...
- feature: add
On Mon, Apr 23, 2007 at 03:12:29AM +0200, Ingo Molnar wrote:
i'm pleased to announce release -v5 of the CFS scheduler patchset. The
patch against v2.6.21-rc7 and v2.6.20.7 can be downloaded from:
...
- feature: add initial sys_sched_yield_to() implementation. Not hooked
into the futex
50 matches
Mail list logo
