From: "Rui Nuno Capela" <rncbc@rncbc.org>
To: "Ingo Molnar" <mingo@elte.hu>
Cc: linux-kernel@vger.kernel.org, "Lee Revell" <rlrevell@joe-job.com>,
mark_h_johnson@raytheon.com, "K.R. Foley" <kr@cybsft.com>,
"Bill Huey" <bhuey@lnxw.com>, "Adam Heath" <doogie@debian.org>,
"Florian Schmidt" <mista.tapas@gmx.net>,
"Thomas Gleixner" <tglx@linutronix.de>,
"Michal Schmidt" <xschmi00@stud.feec.vutbr.cz>,
"Fernando Pablo Lopez-Lezcano" <nando@ccrma.stanford.edu>,
"Karsten Wiese" <annabellesgarden@yahoo.de>,
"Gunther Persoons" <gunther_persoons@spymac.com>,
emann@mrv.com, "Shane Shrybman" <shrybman@aei.ca>,
"Amit Shah" <amit.shah@codito.com>,
"Esben Nielsen" <simlo@phys.au.dk>,
"Andrew Morton" <akpm@osdl.org>
Subject: Re: [patch] Real-Time Preemption, -RT-2.6.10-rc2-mm3-V0.7.31-19
Date: Wed, 1 Dec 2004 22:31:49 -0000 (WET) [thread overview]
Message-ID: <32786.192.168.1.5.1101940309.squirrel@192.168.1.5> (raw)
In-Reply-To: <20041201220916.GA24992@elte.hu>
Ingo Molnar wrote:
>
> the latency does seem to be related to clients, as in the following
> trace:
>
> xruntrace1-2.6.10-rc2-mm3-RT-V0.7.31-19-20041201202926.trc
>
> jackd-16714 goes into sys_poll() at timestamp 0.850ms, and does a pipe
> related wait:
>
> jackd-16714 00000000 0.853ms (+0.000ms): pipe_poll (do_pollfd)
>
> and goes to sleep:
>
> jackd-16714 00000000 0.857ms (+0.000ms): schedule_timeout (do_poll)
>
> almost 3 milliseconds later, at timestamp 3.404ms, the pipe related
> timer expires and jackd gets scheduled again:
>
> ksoftirq-3 00000000 3.403ms (+0.000ms): wake_up_process
> (run_timer_softirq)
> ksoftirq-3 ........ 3.404ms (+0.000ms): -> jackd-16714
> [ 00000027 00000003 ]: try_to_wake_up
>
> obviously an xrun has happened during this 2.6 msec wait:
>
> IRQ 5-3078 00000000 2.277ms (+0.000ms): xrun (snd_pcm_period_elapsed)
>
> but ... this brings up the question, is this a valid scenario? How can
> jackd block on clients for so long? Perhaps this means that every audio
> buffer has run empty and jackd desperately needed some new audio input,
> which it didnt get from the clients, up until after the xrun? In theory
> this should only be possible if there's CPU saturation (that's why i
> asked about how much CPU% time there was in use).
>
> One indication that this might have been the case is that in the full
> 3.5 msecs trace there's not a single cycle spent idle. But, lots of time
> was spent by e.g. X or gkrellm-4356, which are not RT tasks - so from
> the RT task POV i think there were cycles left to be utilized. Could
> this be a client bug? That seems a bit unlikely because to let jackd
> 'run empty', each and every client would have to starve it, correct?
>
Did I mention that the XRUNs seem to occur only when xmms-jack is in the
graph? AFAICT xmms-jack uses a sort of double-buffering wrapper
(bio2jack), or in other words, its not a "native" jack client.
>
> anyway, your plan to try jack_test3.1 again looks like the correct
> approach: we first need to check the behavior of 'trivial clients',
> before more complex scenarios with real clients can be considered.
>
Yes, and I'll have to rebuild a new RT-V0.7.31-19 kernel without latency
timing stuff, just to make sure we'll compare apples to apples ;)
Bye now.
--
rncbc aka Rui Nuno Capela
rncbc@rncbc.org
next prev parent reply other threads:[~2004-12-01 22:37 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-11-26 12:12 Real-Time Preemption, -RT-2.6.10-rc2-mm3-V0.7.31-7 Rui Nuno Capela
2004-11-29 11:05 ` Ingo Molnar
2004-11-29 11:16 ` Ingo Molnar
2004-11-29 11:24 ` Ingo Molnar
2004-11-29 15:42 ` Ingo Molnar
2004-11-29 13:13 ` Rui Nuno Capela
2004-11-29 14:33 ` Ingo Molnar
2004-11-29 15:23 ` Ingo Molnar
2004-11-29 23:16 ` Real-Time Preemption, -RT-2.6.10-rc2-mm3-V0.7.31-13 Gene Heskett
2004-11-30 1:50 ` K.R. Foley
2004-11-30 3:19 ` Gene Heskett
2004-11-30 4:54 ` Gene Heskett
2004-11-30 15:26 ` K.R. Foley
2004-11-30 16:24 ` Gene Heskett
2004-11-30 16:52 ` Zwane Mwaikambo
2004-12-01 7:16 ` Gene Heskett
2004-11-30 16:57 ` K.R. Foley
2004-11-30 10:29 ` Real-Time Preemption, -RT-2.6.10-rc2-mm3-V0.7.31-7 Rui Nuno Capela
2004-11-30 13:19 ` Ingo Molnar
2004-11-30 15:39 ` Rui Nuno Capela
2004-11-30 16:42 ` Ingo Molnar
2004-12-01 10:32 ` Ingo Molnar
2004-12-01 11:25 ` Ingo Molnar
2004-12-01 12:49 ` Rui Nuno Capela
2004-12-01 12:47 ` Rui Nuno Capela
2004-12-01 15:40 ` Ingo Molnar
2004-12-01 16:06 ` Ingo Molnar
2004-12-01 16:20 ` [patch] Real-Time Preemption, -RT-2.6.10-rc2-mm3-V0.7.31-19 Ingo Molnar
2004-12-01 16:31 ` Ingo Molnar
2004-12-01 18:59 ` Rui Nuno Capela
2004-12-01 21:29 ` Ingo Molnar
2004-12-01 21:30 ` Ingo Molnar
[not found] ` <32788.192.168.1.8.1101938057.squirrel@192.168.1.8>
2004-12-01 21:58 ` Ingo Molnar
2004-12-01 22:04 ` Rui Nuno Capela
2004-12-01 22:09 ` Ingo Molnar
2004-12-01 22:31 ` Rui Nuno Capela [this message]
2004-12-02 9:12 ` Rui Nuno Capela
2004-12-02 12:59 ` Rui Nuno Capela
2004-12-02 16:38 ` Fernando Lopez-Lezcano
2004-12-01 22:43 ` Florian Schmidt
2004-12-02 8:40 ` Ingo Molnar
2004-12-02 12:22 ` Florian Schmidt
2004-12-02 12:29 ` Ingo Molnar
2004-12-02 13:06 ` Florian Schmidt
2004-12-02 13:10 ` Ingo Molnar
2004-12-02 13:40 ` Florian Schmidt
2004-12-02 13:49 ` Ingo Molnar
2004-12-02 16:08 ` Florian Schmidt
2004-12-02 17:44 ` Florian Schmidt
2004-12-02 21:12 ` Florian Schmidt
2004-12-02 13:18 ` Rui Nuno Capela
2004-12-03 1:41 ` Fernando Lopez-Lezcano
2004-12-03 2:23 ` Fernando Lopez-Lezcano
2004-11-30 18:13 ` Real-Time Preemption, -RT-2.6.10-rc2-mm3-V0.7.31-7 Remi Colinet
2004-11-30 8:15 ` Ingo Molnar
2004-12-01 8:30 ` Eran Mann
2004-12-01 8:53 ` Ingo Molnar
2004-12-01 18:19 ` Adam Heath
2004-12-02 21:01 [patch] Real-Time Preemption, -RT-2.6.10-rc2-mm3-V0.7.31-19 Mark_H_Johnson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=32786.192.168.1.5.1101940309.squirrel@192.168.1.5 \
--to=rncbc@rncbc.org \
--cc=akpm@osdl.org \
--cc=amit.shah@codito.com \
--cc=annabellesgarden@yahoo.de \
--cc=bhuey@lnxw.com \
--cc=doogie@debian.org \
--cc=emann@mrv.com \
--cc=gunther_persoons@spymac.com \
--cc=kr@cybsft.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mark_h_johnson@raytheon.com \
--cc=mingo@elte.hu \
--cc=mista.tapas@gmx.net \
--cc=nando@ccrma.stanford.edu \
--cc=rlrevell@joe-job.com \
--cc=shrybman@aei.ca \
--cc=simlo@phys.au.dk \
--cc=tglx@linutronix.de \
--cc=xschmi00@stud.feec.vutbr.cz \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®