There may be other cases that require a special case, so I chose the switch
approach.
Please note, that all other messages from ipmr[6].c correctly set the family,
while these do not.
Thanks
Sven
Subject: Set correct RTNL family for multicast netconf messages
From: Sven-Thorsten Dietrich s
On Sat, 2008-02-23 at 13:31 +0100, Andi Kleen wrote:
> > *) compute the context-switch pair time average for the system. This is
> > your time threshold (CSt).
>
Hi Andi,
> This is not a uniform time. Consider the difference between
> context switch on the same hyperthread, context switch bet
On Tue, 2008-02-26 at 00:00 +0100, Pavel Machek wrote:
> Hi!
>
> > > > index c913d48..c24c53d 100644
> > > > --- a/kernel/sysctl.c
> > > > +++ b/kernel/sysctl.c
> > > > @@ -175,6 +175,10 @@ extern struct ctl_table inotify_table[];
> > > > int sysctl_legacy_va_layout;
> > > > #endif
> > > >
>
On Mon, 2008-02-25 at 22:53 +0100, Pavel Machek wrote:
> Hi!
>
> > From: Sven-Thorsten Dietrich <[EMAIL PROTECTED]>
> >
> > Add /proc/sys/kernel/lateral_steal, to allow switching on and off
> > equal-priority mutex stealing between threads.
> >
> &g
On Mon, 2008-02-25 at 23:06 +0100, Pavel Machek wrote:
> On Mon 2008-02-25 11:01:08, Gregory Haskins wrote:
> > From: Sven Dietrich <[EMAIL PROTECTED]>
>
> Why is this good idea?
>
The timeout is useful to eliminate excessive CPU utilization when
waiting for long-held critical sections.
The p
On Fri, 2008-02-22 at 13:36 -0700, Peter W. Morreale wrote:
> On Fri, 2008-02-22 at 11:55 -0800, Sven-Thorsten Dietrich wrote:
> >
> > In high-contention, short-hold time situations, it may even make sense
> > to have multiple CPUs with multiple waiters spinning, dependin
On Fri, 2008-02-22 at 11:43 -0800, Paul E. McKenney wrote:
> On Fri, Feb 22, 2008 at 11:21:14AM -0800, Bill Huey (hui) wrote:
> > On Fri, Feb 22, 2008 at 11:19 AM, Bill Huey (hui) <[EMAIL PROTECTED]> wrote:
> > > Yeah, I'm not very keen on having a constant there without some
> > > contention in
On Thu, 2008-02-21 at 17:41 +0100, Andi Kleen wrote:
> > +config RTLOCK_DELAY
> > + int "Default delay (in loops) for adaptive rtlocks"
> > + range 0 10
> > + depends on ADAPTIVE_RTLOCK
>
> I must say I'm not a big fan of putting such subtle configurable numbers
> into Kconfig. Comp
this. Your list_splice_tail() will insert the
>> new_chain just before it which will muck up the order of the DMA
>> requests.
>>
>> You might have more success with
>> list_splice_tail(&new_chain, ioat_chan->used_desc);
>> where used_desc poi
On Mon, 2007-11-26 at 14:00 -0800, Greg KH wrote:
> On Sun, Nov 25, 2007 at 06:21:35AM -0800, Sven-Thorsten Dietrich wrote:
> > Hi Greg,
> >
> > I think this hunk in the 2.6.22.14 stable patch may be a mis-patch --
> > compared to Linus's current git -- the n
Hi Greg,
I think this hunk in the 2.6.22.14 stable patch may be a mis-patch --
compared to Linus's current git -- the new code should be inserted below
the while loop that follows.
Also see commit 9f96cb1e8bca179a92afa40dfc3c49990f1cfc71
Sven
On Wed, 2007-11-21 at 09:57 -0800, Greg Kroah-Hartma
lyzed.
Signed-off-by: Sven-Thorsten Dietrich <[EMAIL PROTECTED]>
---
drivers/dma/ioat_dma.c |2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
Index: linux-2.6.23/drivers/dma/ioat_dma.c
===
--- linux-2.6.23.orig/
On Fri, 2007-08-24 at 11:15 +0200, Ingo Molnar wrote:
> * Sven-Thorsten Dietrich <[EMAIL PROTECTED]> wrote:
>
> > Same issue has been fixed in mainline by:
> >
> > diff-tree de0cf899bbf06b6f64a5dce9c59d74c41b6b4232 (from
> > 5d2b3d3695a841231b65b55
> &g
e
is loaded into the RT Kernel.
From: Michael S. Tsirkin <[EMAIL PROTECTED]>
"Basically, if you just make spin_lock_irqsave (and spin_lock_irq) not disable
interrupts for non-raw spinlocks, I think all of infiniband will be fine without
changes."
signed-off-by: Sven-Thorsten Dietr
e9c59d74c41b6b4232
Author: Oleg Nesterov <[EMAIL PROTECTED]>
Date: Sun Aug 12 18:08:19 2007 +0200
signed-off-by: Sven-Thorsten Dietrich <[EMAIL PROTECTED]>
Index: linux-2.6.22.1-rt9-broken-out/kernel/sched.c
===
Hi Ingo,
the trivial code is in various RT patches as well as in 2.6.23-rc git's
scheduler.
Thanks
Sven
Remove trivial conditional branch in Linux RT CFS
scheduler's can_migrate_task function.
signed-off-by: Sven-Thorsten Dietrich <[EMAIL PROTECTED]>
Index: linux-2.6.2
Hi Ingo,
here is a lockdep trace I just encountered in the latest rt patch series.
(which has gotten a bit stale, btw.)
Enjoy,
Sven
=
On Thu, 2007-07-26 at 11:56 -0700, H. Peter Anvin wrote:
> Joe Korty wrote:
> > Create /proc/all-interrupts for some architectures.
> >
> > Create a version of /proc/interrupts that displays _every_
> > IRQ vector, not just those that someone thought might be
> > interesting, and add an entry in
On Fri, 2007-07-13 at 16:22 -0700, Kevin Hilman wrote:
> [Minor update to avoid a compiler warning in the case of DEBUG_KERNEL=n]
>
The resent patch (v2) had white space damage -
Here is a reconstituted version that applies for me on 2.6.22-rt3
Acked-by: Sven-Thorsten Dietrich &
On Fri, 2007-07-13 at 10:52 -0700, Kevin Hilman wrote:
> plain text document attachment (trace-cpu-idle.patch)
>
> The per-cpu trace_cpu_idle variable is used when timing *either*
> IRQs-off or preempt sections.
>
This also applies to 2.6.22-rt*
Acked-by: Sven-Thorsten D
uation.
I'll look at the interdiffs and see what I can find.
Regards,
Sven
> Ingo
--
Sven-Thorsten Dietrich
+1 415 694-2930
( www.novell.com/linux )
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED
A change between rt6 and rt7 dropped a #endif in rtc.c.
Compile fails on imbalanced pre-processor directives.
I think that this is correct for Sparc and MIPS, and it definitely
eliminates complaints about PCI_IRQ_NONE definitions for x86.
signed-off-by: Sven-Thorsten Dietrich <[EMAIL PROTEC
Restore the declaration of rcu_batches_completed_bh
It is needed to compile with Classic RCU
signed-off-by: Sven-Thorsten Dietrich <[EMAIL PROTECTED]>
Index: linux-2.6.21-rt-patched/include/linux/rcupdate.h
===
--- linux-
This patch properly exports __spin_lock_irqsave_nested.
signed-off-by: Sven-Thorsten Dietrich <[EMAIL PROTECTED]>
Index: linux-2.6.21/kernel/spinlock.c
===
--- linux-2.6.21.orig/kernel/spinlock.c
+++ linux-2.6.21/kernel/spin
Add declaration for setup_apic_routing
This duplicates the declaration from i386 to x86_64 in the header.
The code, in genapic.c is shared between i386/x86_64.
Steven was trying to clean up that mess a while back, and this adds to
it.
In any case this gets compiling with
-Werror-implicit-funct
On Tue, 2007-05-22 at 15:59 -0700, Sven-Thorsten Dietrich wrote:
> Add
> header and export for rt_write_trylock_irqsave.
Disregard the last patch, flags parameter was missing in the header.
Index: linux-2.6.21/include/linux/spin
Add header and export for rt_write_trylock_irqsave.
Index: linux-2.6.21/include/linux/spinlock.h
===
--- linux-2.6.21.orig/include/linux/spinlock.h
+++ linux-2.6.21/include/linux/spinlock.h
@@ -294,6 +294,7 @@ do {
On Thu, 2007-04-12 at 04:31 -0400, [EMAIL PROTECTED] wrote:
> Since the new 2.6.x O(1) scheduler I'm having latency problems.
1. Have you elevated the process priority?
2. Have you tried running SCHED_FIFO, or SCHED_RR?
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" i
On Tue, 2005-08-23 at 13:10 -0700, Danial Thom wrote:
>
> None of this is helpful, but since no one has
> been able to tell me how to tune it to provide
> absolute priority to the network stack I'll
> assume it can't be done.
History has proven that camp wrong almost 100% of the time.
You were t
On Tue, 2005-08-23 at 10:10 -0700, Danial Thom wrote:
>
> > >Ok, well you'll have to explain this one:
> > >
> > >"Low latency comes at the cost of decreased
> > >throughput - can't have both"
> > >
> > >
> > Configuring "preempt" gives lower latency,
> > because then
> > almost anything can be
On Mon, 2005-08-08 at 11:06 +0200, Ingo Molnar wrote:
>
> it just occured to me that !PREEMPT_RT builds would be affected by the
> #else branch, so i committed the build fix below into -52-15.
>
> Ingo
>
That fixes it. Thanks
Sven
> Index: linux/net/ipv4/route.c
>
T PICK_OP function.
Adds explicit casting to spinlock_t (whatever that happens to be for the
given .config)
Signed-off-by: Sven-Thorsten Dietrich <[EMAIL PROTECTED]>
Index: linux-2.6.13-rc4-RT-V0.7.52-14/net/ipv4/route.c
===
--- l
On Mon, 2005-08-01 at 19:05 +, Luca Falavigna wrote:
> > The patch you wanted to send was:
> >
> > Signed-off-by: Steven Rostedt <[EMAIL PROTECTED]>
> >
> > Index: linux_realtime_ernie/drivers/char/watchdog/cpu5wdt.c
> > ===
> >
On Sun, 2005-04-17 at 22:30 -0700, Bill Huey wrote:
> On Fri, Apr 15, 2005 at 04:37:05PM -0700, Inaky Perez-Gonzalez wrote:
> > By following your method, the pi engine becomes unnecesarily complex;
> > you have actually two engines following two different propagation
> > chains (one kernel, one use
On Fri, 2005-04-08 at 08:28 +0200, Ingo Molnar wrote:
> * Daniel Walker <[EMAIL PROTECTED]> wrote:
>
> > This patch adds the priority list data structure from Inaky
> > Perez-Gonzalez to the Preempt Real-Time mutex.
>
> this one looks really clean.
>
> it makes me wonder, what is the curren
hank You
Sven
***
Sven-Thorsten Dietrich
Real-Time Software Architect
MontaVista Software, Inc.
1237 East Arques Ave.
Sunnyvale, CA 94085
Phone: 408.992.4515
Fax: 408.328.9204
Email: [EMAIL PROTECTED]
http://www.mvista.com
Platform To Innovate
***
-
36 matches
Mail list logo
