From: Paul Thomas <pthomas8589@gmail.com>
To: John Ogness <john.ogness@linutronix.de>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
Thomas Gleixner <tglx@linutronix.de>,
linux-rt-users <linux-rt-users@vger.kernel.org>,
dunc.mcphie@gmail.com, Anders Roxell <anders.roxell@linaro.org>
Subject: Re: poor cyclictest results with 5.0 series rt for arm64
Date: Thu, 15 Aug 2019 09:30:48 -0400 [thread overview]
Message-ID: <CAD56B7fAsv-f8nnZE9OXzdomsYfcvOOaFun1bh57dLt6Ee3ZFA@mail.gmail.com> (raw)
In-Reply-To: <87a7ca4nh6.fsf@linutronix.de>
> Where in this trace is there a latency spike? I could not see one.
Hi John,
For the 5.2.0-rt1 trace data set I believe the latency is with
cyclicte-1935 at the end. If I just look at the "cyclicte-1935 ...
finish_task_switch <-__schedule" lines then the delta-t's are mostly
around 200us except for the last delta-t which is >5000us
cyclicte-1935 1d...3.. 84243668us : uao_thread_switch <-__switch_to
cyclicte-1935 1d...3.. 84249436us : finish_task_switch <-__schedule
The actual cyclictest output is shown below:
# ./cyclictest -S -m -n -p 99 -i 200 -h 700 -f -b 5000
# /dev/cpu_dma_latency set to 0us
INFO: debugfs mountpoint: /sys/kernel/debug/tracing/
policy: fifo: loadavg: 5.55 1.84 0.66 11/136 1941
T: 0 ( 1934) P:99 I:200 C: 411188 Min: 30 Act: 30 Avg: 93 Max: 652
T: 1 ( 1935) P:99 I:200 C: 382925 Min: 47 Act: 5713 Avg: 123 Max: 5713
T: 2 ( 1936) P:99 I:200 C: 395011 Min: 40 Act: 40 Avg: 117 Max: 561
T: 3 ( 1937) P:99 I:200 C: 392379 Min: 36 Act: 36 Avg: 109 Max: 636
thanks,
Paul
next prev parent reply other threads:[~2019-08-15 13:31 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-12 11:18 poor cyclictest results with 5.0 series rt for arm64 Paul Thomas
[not found] ` <CAD56B7c2=95r7r-6tr0Mby8jSeuQPDNSd4LELnUw1LVRn9Rqew@mail.gmail.com>
2019-07-12 11:32 ` Paul Thomas
2019-07-16 20:24 ` Thomas Gleixner
2019-07-16 21:50 ` Paul Thomas
2019-07-16 23:14 ` Thomas Gleixner
2019-07-17 0:44 ` Paul Thomas
2019-07-17 8:03 ` Thomas Gleixner
2019-07-17 8:10 ` Thomas Gleixner
2019-07-17 9:02 ` Thomas Gleixner
2019-07-17 10:21 ` Thomas Gleixner
2019-07-17 22:28 ` Paul Thomas
2019-08-13 9:53 ` Sebastian Andrzej Siewior
2019-08-13 18:02 ` Paul Thomas
2019-08-14 11:26 ` Sebastian Andrzej Siewior
2019-08-14 16:17 ` [PATCH RT] arm64: preempt: Check preemption level before looking at lazy-preempt Sebastian Andrzej Siewior
2019-08-14 16:17 ` [PATCH RT] x86: " Sebastian Andrzej Siewior
2019-08-14 17:04 ` poor cyclictest results with 5.0 series rt for arm64 Paul Thomas
2019-08-15 8:29 ` Sebastian Andrzej Siewior
2019-08-15 12:33 ` John Ogness
2019-08-15 13:30 ` Paul Thomas [this message]
2019-08-15 13:42 ` Sebastian Andrzej Siewior
2019-08-15 13:52 ` Paul Thomas
2019-08-15 14:19 ` Sebastian Andrzej Siewior
2019-08-15 15:12 ` Paul Thomas
2019-08-15 15:15 ` Sebastian Andrzej Siewior
2019-08-15 15:31 ` Paul Thomas
2019-08-15 18:00 ` Paul Thomas
2019-08-15 18:57 ` Sebastian Andrzej Siewior
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=CAD56B7fAsv-f8nnZE9OXzdomsYfcvOOaFun1bh57dLt6Ee3ZFA@mail.gmail.com \
--to=pthomas8589@gmail.com \
--cc=anders.roxell@linaro.org \
--cc=bigeasy@linutronix.de \
--cc=dunc.mcphie@gmail.com \
--cc=john.ogness@linutronix.de \
--cc=linux-rt-users@vger.kernel.org \
--cc=tglx@linutronix.de \
/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;
as well as URLs for NNTP newsgroup(s).