6 May
2006
6 May
'06
12:46 a.m.
Ok I don't know how I didn't find this out but I couldn't find any docs
on how to get apps running w/ realtime once you use the molnar patch. I
know ubuntustudio.com has a launcher app but i'm curious.
also this list is great. I've lurked / asked some noob questions for a
while now.
7 May
7 May
8:03 p.m.
On Fri, 2006-05-05 at 22:46 -0400, greg wrote:
Ok I don't know how I didn't find this out but
I couldn't find any docs
on how to get apps running w/ realtime once you use the molnar patch. I
know ubuntustudio.com has a launcher app but i'm curious.
also this list is great. I've lurked / asked some noob questions for a
while now.
Did you bother reading the rest of the stuff on my site? Or did you just
stop reading once you got to the kernel part? The kernel is only one
part of it, and even that is optional if you get acceptable performance
without Ingo's patch.
Here is a hint:
http://www.ubuntustudio.com/wiki/index.php/Breezy:Studio_Preparation#Real-T…
8 May
8 May
3:03 p.m.
On 5/7/06, Dana Olson <dana(a)ubuntustudio.com> wrote:
Did you bother reading the rest of the stuff on my
site? Or did you just
stop reading once you got to the kernel part? The kernel is only one
part of it, and even that is optional if you get acceptable performance
without Ingo's patch.
Here is a hint:
http://www.ubuntustudio.com/wiki/index.php/Breezy:Studio_Preparation#Real-T…
fyi, I've followed Dana's instructions more than once and found them
to be excellent. Just use a little common sense when following them
(there are newer versions of the kernel and the patch out) and you'll
be fine.
As Dana mentioned, there's a LOT more to getting realtime working than
just the kernel - be sure to read everything there.
--
Josh Lawrence
http://www.hardbop200.com
4:14 p.m.
On Mon, 8 May 2006 12:03:34 -0500
"Josh Lawrence" <hardbop200(a)gmail.com> wrote:
On 5/7/06, Dana Olson <dana(a)ubuntustudio.com>
wrote:
I browsed over that page and didn't find any info on setting up the irq
handler priorities which is _the_ essential feature of -rt.
Flo
--
Palimm Palimm!
http://tapas.affenbande.org
Did you bother reading the rest of the stuff on
my site? Or did you just
stop reading once you got to the kernel part? The kernel is only one
part of it, and even that is optional if you get acceptable performance
without Ingo's patch.
Here is a hint:
http://www.ubuntustudio.com/wiki/index.php/Breezy:Studio_Preparation#Real-T…
fyi, I've followed Dana's instructions more than once and found them
to be excellent. Just use a little common sense when following them
(there are newer versions of the kernel and the patch out) and you'll
be fine.
As Dana mentioned, there's a LOT more to getting realtime working than
just the kernel - be sure to read everything there. 
4:38 p.m.
On Mon, 2006-05-08 at 20:14 +0200, Florian Paul Schmidt wrote:
On Mon, 8 May 2006 12:03:34 -0500
"Josh Lawrence" <hardbop200(a)gmail.com> wrote:
You should look at the rtirq startup script by Rui Nuno Capela:
http://www.rncbc.org/jack/
I use it successfully to get everything prioritized right automagically.
Jack itself should be below the priority of the soundcard interrupt as
set by rtirq.
-- Fernando
On 5/7/06, Dana Olson
<dana(a)ubuntustudio.com> wrote:
I browsed over that page and didn't find any info on setting up the irq
handler priorities which is _the_ essential feature of -rt. Did you bother reading the rest of the stuff on
my site? Or did you just
stop reading once you got to the kernel part? The kernel is only one
part of it, and even that is optional if you get acceptable performance
without Ingo's patch.
Here is a hint:
http://www.ubuntustudio.com/wiki/index.php/Breezy:Studio_Preparation#Real-T…
fyi, I've followed Dana's instructions more than once and found them
to be excellent. Just use a little common sense when following them
(there are newer versions of the kernel and the patch out) and you'll
be fine.
As Dana mentioned, there's a LOT more to getting realtime working than
just the kernel - be sure to read everything there. 
5:58 p.m.
New subject: [linux-audio-user] -rt IRQ handler priorities (was: Re: molnar patch)
On Monday 08 May 2006 20:14, Florian Paul Schmidt wrote:
On Mon, 8 May 2006 12:03:34 -0500
"Josh Lawrence" <hardbop200(a)gmail.com> wrote:
Apropos: on your page on -rt setup (excellent page, btw., many thanks! :-),
you suggest raising "softirq-timer/0" to prio 99, to make sleep() function
right (http://tapas.affenbande.org/?page_id=40 sleep() based/system timer).
I did so, and got strange latencies (> 40 ms) exactly once every 10 minutes,
caused by some routing-related action (rt_secret_rebuild) being run by the
softirq-timer/0 thread. Don't you get bit by that, too? Kernel is 2.6.16-rt16
My solution is to configure with CONFIG_HIGH_RES_TIMERS=y. Then, sleep() wakes
up correctly even with softirq-timer/0 being low-priority (SCHED_FIFO 1 or
even SCHED_OTHER).
In general I find adjusting priorities of the various softirq kernel threads a
bit of secret art. I can't find much documentation about "what kernel thread
runs which job" that would help making some proper decisions here. I found my
desktop "feels" most responsive when demoting all softirq thread to
SCHED_OTHER. I did so after seeing that with a non-rt kernel, bottom-half
handler don't run SCHED_FIFO/_RR at all. So -rt now gives me robust low
latencies for jackd, and still proper desktop feeling.
Well, maybe this is getting off-topic for this list. But it seems to me
trimming priorities between kernel and userland threads is a bit like no
man's land.
Wolfgang
fyi, I've followed Dana's instructions
more than once and found them
to be excellent. Just use a little common sense when following them
(there are newer versions of the kernel and the patch out) and you'll
be fine.
As Dana mentioned, there's a LOT more to getting realtime working than
just the kernel - be sure to read everything there.
I browsed over that page and didn't find any info on setting up the irq
handler priorities which is _the_ essential feature of -rt.
8:47 p.m.
New subject: [linux-audio-user] -rt IRQ handler priorities (was: Re: molnar patch)
On Mon, 8 May 2006 21:54:53 +0200
Wolfgang Hoffmann <woho(a)woho.de> wrote:
I haven't been bitten by that. Do you also get xruns with [i suppose so,
just asking to make sure]? I haven't had as much time as before to play
around and test things, so maybe it has crept into the kernel recently
or maybe i just always had high-res timers enabled.
I browsed over
that page and didn't find any info on setting up the irq
handler priorities which is _the_ essential feature of -rt.
Apropos: on your page on -rt setup (excellent page, btw., many thanks! :-),
you suggest raising "softirq-timer/0" to prio 99, to make sleep() function
right (http://tapas.affenbande.org/?page_id=40 sleep() based/system timer).
I did so, and got strange latencies (> 40 ms) exactly once every 10 minutes,
caused by some routing-related action (rt_secret_rebuild) being run by the
softirq-timer/0 thread. Don't you get bit by that, too? Kernel is 2.6.16-rt16 My solution is to configure with
CONFIG_HIGH_RES_TIMERS=y. Then, sleep() wakes
up correctly even with softirq-timer/0 being low-priority (SCHED_FIFO 1 or
even SCHED_OTHER).
In general I find adjusting priorities of the various softirq kernel threads a
bit of secret art. I can't find much documentation about "what kernel thread
runs which job" that would help making some proper decisions here. I found my
desktop "feels" most responsive when demoting all softirq thread to
SCHED_OTHER. I did so after seeing that with a non-rt kernel, bottom-half
handler don't run SCHED_FIFO/_RR at all. So -rt now gives me robust low
latencies for jackd, and still proper desktop feeling.
Well, maybe this is getting off-topic for this list. But it seems to me
trimming priorities between kernel and userland threads is a bit like no
man's land.
I agree. Maybe Lee Revell knows more [CC'ing him]. Lee, you know
something about all these softirq threads? What exactly do they do?
Regards,
Flo
--
Palimm Palimm!
http://tapas.affenbande.org
9:08 p.m.
New subject: [linux-audio-user] -rt IRQ handler priorities (was: Re: molnar patch)
On Tue, 2006-05-09 at 00:47 +0200, Florian Paul Schmidt wrote:
On Mon, 8 May 2006 21:54:53 +0200
Wolfgang Hoffmann <woho(a)woho.de> wrote:
I haven't been bitten by that. Do you also get xruns with [i suppose so,
just asking to make sure]? I haven't had as much time as before to play
around and test things, so maybe it has crept into the kernel recently
or maybe i just always had high-res timers enabled.
Not really. The problem with making the softirq timer thread high
priority is that lots of random code gets run from softirq timer
context, including rt_secret_rebuild() which is a well known latency
killer.
Lately I've been focused on getting mainline usable for audio - I have
not run -rt in a while.
It is a bit of a black art because you need lots of knowledge of the
kernel to know how to set the priorities. But that's the nature of hard
realtime - you really need to know a lot about the system to get the
priorities right.
I've never had to alter the priority of the softirq timer thread myself
- does it work OK if you leave the softirq thread alone?
If not try setting the softirq thread to a lower RT priority than your
soundcard, JACK, and all other interrupt threads.
I've added Ingo to the cc: list, maybe he has some input.
Lee
I browsed
over that page and didn't find any info on setting up the irq
handler priorities which is _the_ essential feature of -rt.
Apropos: on your page on -rt setup (excellent page, btw., many thanks! :-),
you suggest raising "softirq-timer/0" to prio 99, to make sleep() function
right (http://tapas.affenbande.org/?page_id=40 sleep() based/system timer).
I did so, and got strange latencies (> 40 ms) exactly once every 10 minutes,
caused by some routing-related action (rt_secret_rebuild) being run by the
softirq-timer/0 thread. Don't you get bit by that, too? Kernel is 2.6.16-rt16 My solution is to configure with
CONFIG_HIGH_RES_TIMERS=y. Then, sleep() wakes
up correctly even with softirq-timer/0 being low-priority (SCHED_FIFO 1 or
even SCHED_OTHER).
In general I find adjusting priorities of the various softirq kernel threads a
bit of secret art. I can't find much documentation about "what kernel thread
runs which job" that would help making some proper decisions here. I found my
desktop "feels" most responsive when demoting all softirq thread to
SCHED_OTHER. I did so after seeing that with a non-rt kernel, bottom-half
handler don't run SCHED_FIFO/_RR at all. So -rt now gives me robust low
latencies for jackd, and still proper desktop feeling.
Well, maybe this is getting off-topic for this list. But it seems to me
trimming priorities between kernel and userland threads is a bit like no
man's land.
I agree. Maybe Lee Revell knows more [CC'ing him]. Lee, you know
something about all these softirq threads? What exactly do they do?
9 May
9 May
2:30 a.m.
New subject: [linux-audio-user] -rt IRQ handler priorities (was: Re: molnar patch)
On 5/8/06, Lee Revell <rlrevell(a)joe-job.com> wrote:
Lately I've been focused on getting mainline
usable for audio - I have
not run -rt in a while.
Lee,
Can you speak a little more to this, i.e., what have you done
specifically to make the mainline "usable for audio?" I'd be really
interested in learning a way to get out of having to patch often.
--
Josh Lawrence
http://www.hardbop200.com
12:13 p.m.
New subject: [linux-audio-user] -rt IRQ handler priorities (was: Re: molnar patch)
On Mon, 2006-05-08 at 23:30 -0500, Josh Lawrence wrote:
On 5/8/06, Lee Revell <rlrevell(a)joe-job.com>
wrote:
Page 21:
http://lac.zkm.de/2006/papers/lac2006_proceedings.pdf
Lee
Lately I've been focused on getting mainline
usable for audio - I have
not run -rt in a while.
Lee,
Can you speak a little more to this, i.e., what have you done
specifically to make the mainline "usable for audio?" I'd be really
interested in learning a way to get out of having to patch often.
3:24 a.m.
New subject: [linux-audio-user] -rt IRQ handler priorities (was: Re: molnar patch)
On Tuesday 09 May 2006 01:08, Lee Revell wrote:
Not really. The problem with making the softirq timer thread high
priority is that lots of random code gets run from softirq timer
context, including rt_secret_rebuild() which is a well known latency
killer.
Ah, ok. Now well known to me, too ;-)
On Tue, 2006-05-09 at 00:47 +0200, Florian Paul
Schmidt wrote:
> On Mon, 8 May 2006 21:54:53 +0200
>
> Wolfgang Hoffmann <woho(a)woho.de> wrote:
> > Apropos: on your page on -rt setup (excellent page, btw., many thanks!
> > :-), you suggest raising "softirq-timer/0" to prio 99, to make
sleep()
> > function right (http://tapas.affenbande.org/?page_id=40 sleep()
> > based/system timer).
> >
> > I did so, and got strange latencies (> 40 ms) exactly once every 10
> > minutes, caused by some routing-related action (rt_secret_rebuild)
> > being run by the softirq-timer/0 thread. Don't you get bit by that,
> > too? Kernel is 2.6.16-rt16
>
> I haven't been bitten by that. Do you also get xruns with [i suppose so,
> just asking to make sure]? I haven't had as much time as before to play
> around and test things, so maybe it has crept into the kernel recently
> or maybe i just always had high-res timers enabled.
To be more precise, I get xruns, not scheduling latencies. Scheduling latency
is low (~50us), but softirq-timer/0 preempts all other threads when boosted
to prio 99, leading to xruns in jackd.
It's not a scheduler or -rt latency problem, it's a priority problem, since
softirq-timer/0 runs different jobs that would require different priorities:
wakeup sleep() at highest prio, rt_secret_rebuild et. al. at low prio.
With CONFIG_HIGH_RES_TIMERS=y it seems thatt softirq-timer/0 is no longer
needed for waking up sleep()ing threads, so it can be left at it's default
low prio (or even demoted to SCHED_OTHER?).
My solution is to configure with
CONFIG_HIGH_RES_TIMERS=y. Then,
sleep() wakes up correctly even with softirq-timer/0 being low-priority
(SCHED_FIFO 1 or even SCHED_OTHER).
In general I find adjusting priorities of the various softirq kernel
threads a bit of secret art. I can't find much documentation about
"what kernel thread runs which job" that would help making some proper
decisions here. I found my desktop "feels" most responsive when
demoting all softirq thread to SCHED_OTHER. I did so after seeing that
with a non-rt kernel, bottom-half handler don't run SCHED_FIFO/_RR at
all. So -rt now gives me robust low latencies for jackd, and still
proper desktop feeling.
Well, maybe this is getting off-topic for this list. But it seems to me
trimming priorities between kernel and userland threads is a bit like
no man's land.
I agree. Maybe Lee Revell knows more [CC'ing him]. Lee, you know
something about all these softirq threads? What exactly do they do? Lately I've been focused on getting mainline
usable for audio - I have
not run -rt in a while.
It is a bit of a black art because you need lots of knowledge of the
kernel to know how to set the priorities. But that's the nature of hard
realtime - you really need to know a lot about the system to get the
priorities right.
I've never had to alter the priority of the softirq timer thread myself
- does it work OK if you leave the softirq thread alone?
With CONFIG_HIGH_RES_TIMERS=y, yes.
With CONFIG_HIGH_RES_TIMERS=n, no. Then, high-prio theads don't wake up from
sleep() if a mid-prio CPU hog is running. Typical scenario is a high-prio
watchdog like Florians rt_watchdog (http://tapas.affenbande.org/?page_id=38),
which fails to work unless softirq-timer/0 runs with higher prio than the CPU
hog. It seems that softirq-timer/0 has to be scheduled for any thread to wake
up. It's a bit like priority inversion.
If not try setting the softirq thread to a lower RT
priority than your
soundcard, JACK, and all other interrupt threads.
Yes, that should cure the xruns. But I wonder if jackd's watchdog can do it's
job when a jack client is running wild? Probably not. softirq-timer/0 would
not get to run then, so the watchdog wouldn't wake up.
I've added Ingo to the cc: list, maybe he has some
input.
That would be helpful. Also adding Steve to cc: as he mentioned writing a
section in an O'Reilly book about how to use the -rt patch in
http://www.ussg.iu.edu/hypermail/linux/kernel/0604.2/0340.html
Wolfgang
8:13 a.m.
New subject: [linux-audio-user] Re: -rt IRQ handler priorities (was: Re: molnar patch)
On 5/9/06, Wolfgang Hoffmann <woho(a)woho.de> wrote:
On Tuesday 09 May 2006 01:08, Lee Revell wrote:
Not really. The problem with making the softirq timer thread high
priority is that lots of random code gets run from softirq timer
context, including rt_secret_rebuild() which is a well known latency
killer.
Ah, ok. Now well known to me, too ;-)
Has anyone got a working x86_64 RT system? I can't boot rt kernels
here, hangs after loading the schedulers.
Loki
On Tue, 2006-05-09 at 00:47 +0200, Florian Paul
Schmidt wrote:
> On Mon, 8 May 2006 21:54:53 +0200
>
> Wolfgang Hoffmann <woho(a)woho.de> wrote:
> > Apropos: on your page on -rt setup (excellent page, btw., many thanks!
> > :-), you suggest raising "softirq-timer/0" to prio 99, to make
sleep()
> > function right (http://tapas.affenbande.org/?page_id=40 sleep()
> > based/system timer).
> >
> > I did so, and got strange latencies (> 40 ms) exactly once every 10
> > minutes, caused by some routing-related action (rt_secret_rebuild)
> > being run by the softirq-timer/0 thread. Don't you get bit by that,
> > too? Kernel is 2.6.16-rt16
>
> I haven't been bitten by that. Do you also get xruns with [i suppose so,
> just asking to make sure]? I haven't had as much time as before to play
> around and test things, so maybe it has crept into the kernel recently
> or maybe i just always had high-res timers enabled.
To be more precise, I get xruns, not scheduling latencies. Scheduling
latency
is low (~50us), but softirq-timer/0 preempts all other threads when boosted
to prio 99, leading to xruns in jackd.
It's not a scheduler or -rt latency problem, it's a priority problem, since
softirq-timer/0 runs different jobs that would require different priorities:
wakeup sleep() at highest prio, rt_secret_rebuild et. al. at low prio.
With CONFIG_HIGH_RES_TIMERS=y it seems thatt softirq-timer/0 is no longer
needed for waking up sleep()ing threads, so it can be left at it's default
low prio (or even demoted to SCHED_OTHER?).
> > My solution is to configure with
CONFIG_HIGH_RES_TIMERS=y. Then,
> > sleep() wakes up correctly even with softirq-timer/0 being
low-priority
> > (SCHED_FIFO 1 or even SCHED_OTHER).
> >
> > In general I find adjusting priorities of the various softirq kernel
> > threads a bit of secret art. I can't find much documentation about
> > "what kernel thread runs which job" that would help making some
proper
> > decisions here. I found my desktop "feels" most responsive when
> > demoting all softirq thread to SCHED_OTHER. I did so after seeing that
> > with a non-rt kernel, bottom-half handler don't run SCHED_FIFO/_RR at
> > all. So -rt now gives me robust low latencies for jackd, and still
> > proper desktop feeling.
> >
> > Well, maybe this is getting off-topic for this list. But it seems to
me
trimming priorities between kernel and userland
threads is a bit like
no man's land.
I agree. Maybe Lee Revell knows more [CC'ing him]. Lee, you know
something about all these softirq threads? What exactly do they do? Lately I've been focused on getting mainline
usable for audio - I have
not run -rt in a while.
It is a bit of a black art because you need lots of knowledge of the
kernel to know how to set the priorities. But that's the nature of hard
realtime - you really need to know a lot about the system to get the
priorities right.
I've never had to alter the priority of the softirq timer thread myself
- does it work OK if you leave the softirq thread alone?
With CONFIG_HIGH_RES_TIMERS=y, yes.
With CONFIG_HIGH_RES_TIMERS=n, no. Then, high-prio theads don't wake up from
sleep() if a mid-prio CPU hog is running. Typical scenario is a high-prio
watchdog like Florians rt_watchdog
(http://tapas.affenbande.org/?page_id=38),
which fails to work unless softirq-timer/0 runs with higher prio than the
CPU
hog. It seems that softirq-timer/0 has to be scheduled for any thread to
wake
up. It's a bit like priority inversion.
If not try setting the softirq thread to a lower
RT priority than your
soundcard, JACK, and all other interrupt threads.
Yes, that should cure the xruns. But I wonder if jackd's watchdog can do
it's
job when a jack client is running wild? Probably not. softirq-timer/0 would
not get to run then, so the watchdog wouldn't wake up.
I've added Ingo to the cc: list, maybe he has
some input.
That would be helpful. Also adding Steve to cc: as he mentioned writing a
section in an O'Reilly book about how to use the -rt patch in
http://www.ussg.iu.edu/hypermail/linux/kernel/0604.2/0340.html
Wolfgang
3:41 p.m.
New subject: [linux-audio-user] Re: -rt IRQ handler priorities
Has anyone got a working x86_64 RT system? I can't boot rt kernels
here, hangs after loading the schedulers.
Gentoo Kernel, patched with Ingo's patch, compiled for AMD Opteron(64
Bit) here if that is what you are looking for. Kernel is where my
knowledge is lacking though.
Seablade
3:49 p.m.
New subject: [linux-audio-user] Re: -rt IRQ handler priorities
On Tue, 2006-05-09 at 13:45 -0400, Thomas Vecchione wrote:
Need more info so we can compare working and non working configs. After
talking to some AMD64 users at LAC it seems that it's possible to create
a config that compiles but won't boot.
Can you both post your kernel .config?
Lee
Has anyone got a working x86_64 RT system? I can't boot rt kernels
here, hangs after loading the schedulers.
Gentoo Kernel, patched with Ingo's patch, compiled for AMD Opteron(64
Bit) here if that is what you are looking for. Kernel is where my
knowledge is lacking though.
4:07 p.m.
New subject: [linux-audio-user] Re: -rt IRQ handler priorities
Sure thought itll be a couple of days before I can do it. How you want
me to post it? I figure most of the list probably dont want it posted
to the list;)
Just to confirm by -rt all you are referring to is a stock kernel with
Ingo's patch right? The sources I got from the gentoo-sources package
outta emerge. Just makin sure I am understanding correctly.
Seablade
9:05 p.m.
New subject: [linux-audio-user] Re: -rt IRQ handler priorities
On 5/10/06, Lee Revell <rlrevell(a)joe-job.com> wrote:
On Tue, 2006-05-09 at 13:45 -0400, Thomas Vecchione
wrote:
Need more info so we can compare working and non working configs. After
talking to some AMD64 users at LAC it seems that it's possible to create
a config that compiles but won't boot.
Can you both post your kernel .config?
Lee
I'll upload my .config that compiles fine but doesn't boot when i get
back from work. I'd like to try someones that actually run okay too
though ;)
Loki
Has anyone got a working x86_64 RT system? I can't boot rt kernels
here, hangs after loading the schedulers.
Gentoo Kernel, patched with Ingo's patch, compiled for AMD Opteron(64
Bit) here if that is what you are looking for. Kernel is where my
knowledge is lacking though.
12 May
12 May
5:57 p.m.
New subject: [linux-audio-user] Re: -rt IRQ handler priorities
> Has anyone
got a working x86_64 RT system? I can't boot rt kernels
> > > here, hangs after loading the schedulers.
>
> Gentoo Kernel, patched with Ingo's patch, compiled for AMD Opteron(64
> Bit) here if that is what you are looking for. Kernel is where my
> knowledge is lacking though.
Need more info so we can compare working and non working configs. After
talking to some AMD64 users at LAC it seems that it's possible to create
a config that compiles but won't boot.
Can you both post your kernel .config?
Lee
6:15 p.m.
New subject: [linux-audio-user] Re: -rt IRQ handler priorities
On Fri, 2006-05-12 at 16:01 -0400, Thomas Vecchione wrote:
Took a couple days sorry... see if this is what you are looking for?
Also I wont complain about suggestions to improve performance, this
machine is getting dedicated to audio and 3D work now I think, will boot
straight up into Ardour ready to roll.
http://linuxaudio.leviathan-avc.com/files/.config
Sorry I lost track of the thread (please don't trim the '$PERSON
said...' line!).
Is this the config that works or hangs after loading the schedulers?
Lee
> Has anyone got a working x86_64 RT system? I
can't boot rt kernels
> > > here, hangs after loading the schedulers.
>
> Gentoo Kernel, patched with Ingo's patch, compiled for AMD Opteron(64
> Bit) here if that is what you are looking for. Kernel is where my
> knowledge is lacking though.
Need more info so we can compare working and non working configs. After
talking to some AMD64 users at LAC it seems that it's possible to create
a config that compiles but won't boot.
Can you both post your kernel .config?
Lee
13 May
13 May
1:45 a.m.
New subject: [linux-audio-user] Re: -rt IRQ handler priorities
Sorry I lost track of the thread (please don't
trim the '$PERSON
said...' line!).
Is this the config that works or hangs after loading the schedulers?
He not a matter of trimming it, mine doesnt set it up;) Primarily so I
dont accidently quote an entire long message and resend it to a list I
am a part of.
The aforementioned kernel config at...
Is a working config on a Tyan K8WE motherboard, with a single
Opteron(Even though it is compiled for SMP as I plan to add another,
possibly even upgrade to twin dual cores this summer) and patch with
Ingo's realtime preemption patch. I have had relatively few problems
running it, none that I believe to be a kernel issue. The ALSA modules
are compiled seperately to allow me to upgrade them easier.
Seablade
11 a.m.
New subject: [linux-audio-user] Re: -rt IRQ handler priorities
On Fri, 2006-05-12 at 23:49 -0400, Thomas Vecchione wrote:
I can't make sense out of this statement, but it's extremely rude to
quote without attribution like this.
Sorry I lost
track of the thread (please don't trim the '$PERSON
said...' line!).
Is this the config that works or hangs after loading the schedulers?
He not a matter of trimming it, mine doesnt set it up;) Primarily so I
dont accidently quote an entire long message and resend it to a list I
am a part of.
The aforementioned kernel config at...
Is a working config on a Tyan K8WE motherboard, with a single
Opteron(Even though it is compiled for SMP as I plan to add another,
possibly even upgrade to twin dual cores this summer) and patch with
Ingo's realtime preemption patch. I have had relatively few problems
running it, none that I believe to be a kernel issue. The ALSA modules
are compiled seperately to allow me to upgrade them easier.
Um, a working config is not helpful. I need the non-working config as
well (but I don't know who to ask for it as you've stripped all the
attributions from the email)!
Sigh...
Lee
2:15 p.m.
New subject: [linux-audio-user] Re: -rt IRQ handler priorities
Re: Lee
I can't make sense out of this statement, but
it's extremely rude to
quote without attribution like this.
Didnt realise it was considered rude, but what I was saying is my mail
program by default at the moment DOESNT quote so attribution is a bit
tougher. It isnt a matter of stripping, which requires actually
removing something, in order to quote I copy and paste from a previous
email and as a habit havent been putting the last name from who I
quoted, though in most cases I do copy the sig which covers that(Which
in this case, and previous cases, would have been yours) as I kinda
figured most people would know what they wrote within a couple of days.
It saves me a bit of typing and time which I dont have to much of.
In other words, I trimmed nothing, I just didnt manually retype.
Loki Davison is who I am showing in my archives as having a config that
compiles that wont run. However I dont think I have gotten an email yet
in as far as a non working kernel.
In regards to Yves Potion, sorry I havent tried XOrg 7 yet.
Seablade
2:31 p.m.
New subject: [linux-audio-user] Re: -rt IRQ handler priorities
On Sat, 2006-05-13 at 12:19 -0400, Thomas Vecchione wrote:
my mail
program by default at the moment DOESNT quote so attribution is a bit
tougher
...
It saves me a bit of typing and time which I dont
have to much of.
Well if you want to have more time it sounds like you should consider
upgrading to a better mail client ;-)
Lee
15 May
15 May
8:47 a.m.
New subject: [linux-audio-user] Re: -rt IRQ handler priorities
On Saturday 13 May 2006 17:19, Thomas Vecchione was like:
I kinda
figured most people would know what they wrote within a couple of days.
That is a really big assumption. I often look at things I wrote the previous
day and think "did I write that? Oops!"
--
cheers,
tim hall
http://glastonburymusic.org.uk/tim
We are the people We've been waiting for.
10 May
10 May
7:38 p.m.
On Mon, 2006-05-08 at 20:14 +0200, Florian Paul Schmidt wrote:
On Mon, 8 May 2006 12:03:34 -0500
"Josh Lawrence" <hardbop200(a)gmail.com> wrote:
FYI: It is a wiki, you can add to it. I do not know everything there is
to know, and I have been short on free time lately.
Also, if things like kernel versions and patches are outdated, then they
can be modified. Because, after all, it is a wiki.
Dana
On 5/7/06, Dana Olson
<dana(a)ubuntustudio.com> wrote:
I browsed over that page and didn't find any info on setting up the irq
handler priorities which is _the_ essential feature of -rt.
Flo Did you bother reading the rest of the stuff on
my site? Or did you just
stop reading once you got to the kernel part? The kernel is only one
part of it, and even that is optional if you get acceptable performance
without Ingo's patch.
Here is a hint:
http://www.ubuntustudio.com/wiki/index.php/Breezy:Studio_Preparation#Real-T…
fyi, I've followed Dana's instructions more than once and found them
to be excellent. Just use a little common sense when following them
(there are newer versions of the kernel and the patch out) and you'll
be fine.
As Dana mentioned, there's a LOT more to getting realtime working than
just the kernel - be sure to read everything there.
6843
days inactive
6853
days old
linux-audio-user@lists.linuxaudio.org
23 comments
10 participants
participants (10)
-
Dana Olson -
Fernando Lopez-Lezcano -
Florian Paul Schmidt -
greg -
Josh Lawrence -
Lee Revell -
Loki Davison -
Thomas Vecchione -
tim hall -
Wolfgang Hoffmann