On Mon, Aug 27, 2007 at 12:02:24PM +0200, Guennadi Liakhovetski wrote:
As long as your non-realtime tasks are allowed to take locks, that also
prevent real-time tasks from preempting them, and as long as you haven't
proved that all those locks in all your non-realtime sources can never
under
Hello,
I've been using the latency tracing tool in -rt.
Linux version 2.6.22.1-rt9 (gcc version 3.4.4) #1 PREEMPT RT
prctl(0, 1); /* start tracing */
TsOut.Write(buf, packet_size);
prctl(0, 0); /* stop tracing */
Write() calls the driver through an ioctl, which schedules a DMA to
On Mon, 27 Aug 2007 11:26:29 -0700
Pallipadi, Venkatesh [EMAIL PROTECTED] wrote:
- Another thing to try is to disable HPET and boot with PIT in the
first kernel. Just to check whether PIT never works on this platform
or the first kernel is doing something to stop PIT. You can try
On Tue, 2007-08-28 at 12:39 +0200, John Sigler wrote:
Why does pdflush kick in to ruin my party? :-)
The expected latency is ~600 µs.
http://linux.kernel.free.fr/latency/pdflush.trace
Does ide_inb mean I'm reading from the disk?
Does your real time application lock it's memory, or allow
Hi,
I was recently testing 2.6.22.3-16.1-rt from SUSE (seems to be an
2.6.22.1-rt9 as base), and I noticed that XFS does not know about the
'usrquota' mount option anymore, causing all mounts to fail (since I
have it set on by default). Any idea what's going on?
Jan
--
-
To
On Tue, 2007-08-28 at 17:20 +0200, Jan Engelhardt wrote:
Hi,
I was recently testing 2.6.22.3-16.1-rt from SUSE (seems to be an
2.6.22.1-rt9 as base), and I noticed that XFS does not know about the
'usrquota' mount option anymore, causing all mounts to fail (since I
have it set on by
On Tue, 2007-08-28 at 19:50 +0200, Jan Engelhardt wrote:
On Aug 28 2007 08:40, Sven-Thorsten Dietrich wrote:
I was recently testing 2.6.22.3-16.1-rt from SUSE (seems to be an
2.6.22.1-rt9 as base), and I noticed that XFS does not know about the
'usrquota' mount option anymore, causing all
This enables the /proc/preempt_max_latency facility for timing modes,
even if event tracing is disabled. Wakeup latency was the only one
that had this feature in the past.
Signed-off-by: Daniel Walker [EMAIL PROTECTED]
---
kernel/sysctl.c |2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
Replace the old PICK_OP style macros with PICK_FUNCTION. Although,
seqlocks has some alien code, which I also replaced as can be seen
from the line count below.
Signed-off-by: Daniel Walker [EMAIL PROTECTED]
---
include/linux/pickop.h |4
include/linux/seqlock.h | 235
Reaplace old PICK_OP style macros with the new PICK_FUNCTION macro.
Signed-off-by: Daniel Walker [EMAIL PROTECTED]
---
include/linux/sched.h| 13 -
include/linux/spinlock.h | 345 ++-
kernel/rtmutex.c |2
lib/dec_and_lock.c |
I dropped parts of the prior reset method, and added a file called
reset into the /proc/latency_hist/ timing directories. It allows
any of the timing options to get their histograms reset.
I also fixed a couple of oddities in the code. Instead of creating a
file for all NR_CPUS , I just used
On Wed, 2007-08-29 at 09:44 +1000, Nick Piggin wrote:
Daniel Walker wrote:
PICK_FUNCTION() is similar to the other PICK_OP style macros, and was
created to replace them all. I used variable argument macros to handle
PICK_FUNC_2ARG/PICK_FUNC_1ARG. Otherwise the marcos are similar to the
On Sat, 2007-06-23 at 08:25 -0400, Steven Rostedt wrote:
--- linux-2.6.21.orig/net/ipv4/tcp_ipv4.c 2007-06-17
17:19:02.0 +0200
+++ linux-2.6.21/net/ipv4/tcp_ipv4.c2007-06-17 17:20:27.0 +0200
@@ -2033,7 +2033,12 @@ static void *established_get_first(struc
From: Masayuki Nakagawa [EMAIL PROTECTED]
Date: Tue, 28 Aug 2007 18:41:38 -0700
+static inline void __inet_hash_setbit(unsigned long *bitmask,
+ unsigned int index)
+{
+ if (bitmask)
+ set_bit(index, bitmask);
+}
+
+static inline void __inet_hash_clearbit(unsigned long
14 matches
Mail list logo