From: Steven Rostedt <rostedt@goodmis.org>
To: Joel Fernandes <joel@joelfernandes.org>
Cc: Daniel Bristot de Oliveira <bristot@kernel.org>,
Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Juri Lelli <juri.lelli@redhat.com>,
Vincent Guittot <vincent.guittot@linaro.org>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
Daniel Bristot de Oliveira <bristot@redhat.com>,
Valentin Schneider <vschneid@redhat.com>,
linux-kernel@vger.kernel.org,
Luca Abeni <luca.abeni@santannapisa.it>,
Tommaso Cucinotta <tommaso.cucinotta@santannapisa.it>,
Thomas Gleixner <tglx@linutronix.de>,
Vineeth Pillai <vineeth@bitbyteword.org>,
Shuah Khan <skhan@linuxfoundation.org>,
Phil Auld <pauld@redhat.com>
Subject: Re: [PATCH v5 6/7] sched/deadline: Deferrable dl server
Date: Tue, 7 Nov 2023 12:54:34 -0500 [thread overview]
Message-ID: <20231107125434.284c44da@gandalf.local.home> (raw)
In-Reply-To: <20231107123540.69038c6c@gandalf.local.home>
What's more interesting, when looking at the userspin task, I see a lot of this:
migrate-1153 [003] 1272.988097: sched_switch: migrate:1153 [90] S ==> userspin:1135 [120]
userspin-1135 [003] 1272.988111: sched_switch: userspin:1135 [120] R ==> migrate:1146 [97]
userspin sneaks in for 14 microseconds
migrate-1146 [003] 1272.988141: sched_switch: migrate:1146 [97] R ==> migrate:1159 [84]
migrate-1159 [003] 1272.988159: print: tracing_mark_write: thread 13 iter 15, took lock 15020 in 140726333419648 us
migrate-1159 [003] 1272.992161: print: tracing_mark_write: thread 13 iter 15, unlock lock 6
migrate-1159 [003] 1272.992169: print: tracing_mark_write: thread 13 iter 15 sleeping
migrate-1159 [003] 1272.992177: sched_switch: migrate:1159 [84] S ==> userspin:1135 [120]
userspin-1135 [003] 1272.992190: sched_switch: userspin:1135 [120] R ==> migrate:1150 [93]
Again for 13 microseconds.
migrate-1150 [003] 1272.995118: sched_switch: migrate:1150 [93] R ==> migrate:1153 [90]
migrate-1153 [003] 1272.995129: print: tracing_mark_write: thread 7 iter 15, taking lock 5
migrate-1153 [003] 1272.995164: print: tracing_mark_write: thread 7 iter 15, took lock 32 in 140726333419648 us
migrate-1153 [003] 1273.005166: print: tracing_mark_write: thread 7 iter 15, unlock lock 5
migrate-1153 [003] 1273.005174: print: tracing_mark_write: thread 7 iter 15 sleeping
migrate-1153 [003] 1273.005183: sched_switch: migrate:1153 [90] S ==> userspin:1135 [120]
userspin-1135 [003] 1273.005204: sched_switch: userspin:1135 [120] R ==> migrate:1159 [84]
For 21 microseconds.
migrate-1159 [003] 1273.005216: print: tracing_mark_write: thread 13 iter 15, taking lock 7
migrate-1159 [003] 1273.005271: print: tracing_mark_write: thread 13 iter 15, took lock 53 in 140726333419648 us
migrate-1159 [003] 1273.009273: print: tracing_mark_write: thread 13 iter 15, unlock lock 7
migrate-1159 [003] 1273.009281: print: tracing_mark_write: thread 13 iter 15 sleeping
migrate-1159 [003] 1273.009289: sched_switch: migrate:1159 [84] S ==> userspin:1135 [120]
userspin-1135 [003] 1273.009301: sched_switch: userspin:1135 [120] R ==> migrate:1147 [96]
12 microseconds
migrate-1147 [003] 1273.012205: sched_switch: migrate:1147 [96] R ==> migrate:1153 [90]
migrate-1153 [003] 1273.012217: print: tracing_mark_write: thread 7 iter 15, taking lock 6
migrate-1153 [003] 1273.012228: sched_switch: migrate:1153 [90] S ==> userspin:1135 [120]
userspin-1135 [003] 1273.012242: sched_switch: userspin:1135 [120] R ==> migrate:1146 [97]
migrate-1146 [003] 1273.014251: sched_switch: migrate:1146 [97] R ==> migrate:1148 [95]
2 milliseconds. (which is probably fine).
migrate-1148 [003] 1273.020300: print: tracing_mark_write: thread 2 iter 14, unlock lock 2
migrate-1148 [003] 1273.020302: print: tracing_mark_write: thread 2 iter 14 sleeping
migrate-1148 [003] 1273.020309: sched_switch: migrate:1148 [95] S ==> userspin:1135 [120]
userspin-1135 [003] 1273.020324: sched_switch: userspin:1135 [120] R ==> migrate:1147 [96]
15 microseconds.
migrate-1147 [003] 1273.020360: print: tracing_mark_write: thread 1 iter 14, unlock lock 1
migrate-1147 [003] 1273.020373: print: tracing_mark_write: thread 1 iter 14 sleeping
migrate-1147 [003] 1273.020381: sched_switch: migrate:1147 [96] S ==> userspin:1135 [120]
userspin-1135 [003] 1273.021397: sched_switch: userspin:1135 [120] R ==> migrate:1147 [96]
1 millisecond.
migrate-1147 [003] 1273.021402: print: tracing_mark_write: thread 1 iter 14, taking lock 2
migrate-1147 [003] 1273.021404: print: tracing_mark_write: thread 1 iter 14, took lock 1 in 140726333419648 us
migrate-1147 [003] 1273.022200: sched_switch: migrate:1147 [96] R ==> migrate:1152 [91]
migrate-1152 [003] 1273.022206: print: tracing_mark_write: thread 6 iter 15, taking lock 6
migrate-1152 [003] 1273.022217: sched_switch: migrate:1152 [91] S ==> migrate:1147 [96]
migrate-1147 [003] 1273.022289: sched_switch: migrate:1147 [96] R ==> migrate:1159 [84]
migrate-1159 [003] 1273.022299: print: tracing_mark_write: thread 13 iter 16, taking lock 0
migrate-1159 [003] 1273.022326: print: tracing_mark_write: thread 13 iter 16, took lock 25 in 140726333419648 us
migrate-1159 [003] 1273.026328: print: tracing_mark_write: thread 13 iter 16, unlock lock 0
migrate-1159 [003] 1273.026337: print: tracing_mark_write: thread 13 iter 16 sleeping
migrate-1159 [003] 1273.026346: sched_switch: migrate:1159 [84] S ==> userspin:1135 [120]
userspin-1135 [003] 1273.026359: sched_switch: userspin:1135 [120] R ==> migrate:1146 [97]
13 microseconds, and so on...
migrate-1146 [003] 1273.027170: sched_switch: migrate:1146 [97] R ==> migrate:1149 [94]
migrate-1149 [003] 1273.027189: print: tracing_mark_write: thread 3 iter 14, took lock 1927 in 140726333419648 us
migrate-1149 [003] 1273.027335: sched_switch: migrate:1149 [94] R ==> migrate:1153 [90]
migrate-1153 [003] 1273.027349: print: tracing_mark_write: thread 7 iter 15, took lock 15130 in 140726333419648 us
migrate-1153 [003] 1273.037352: print: tracing_mark_write: thread 7 iter 15, unlock lock 6
migrate-1153 [003] 1273.037362: print: tracing_mark_write: thread 7 iter 15 sleeping
migrate-1153 [003] 1273.037370: sched_switch: migrate:1153 [90] S ==> userspin:1135 [120]
userspin-1135 [003] 1273.037395: sched_switch: userspin:1135 [120] R ==> migrate:1147 [96]
migrate-1147 [003] 1273.037406: print: tracing_mark_write: thread 1 iter 14, unlock lock 2
migrate-1147 [003] 1273.037408: print: tracing_mark_write: thread 1 iter 14 sleeping
migrate-1147 [003] 1273.037414: sched_switch: migrate:1147 [96] S ==> userspin:1135 [120]
userspin-1135 [003] 1273.038428: sched_switch: userspin:1135 [120] R ==> migrate:1147 [96]
It looks like it sneaks in when it's about to schedule a new RT task.
Is this expected?
-- Steve
next prev parent reply other threads:[~2023-11-07 17:54 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-11-04 10:59 [PATCH v5 0/7] SCHED_DEADLINE server infrastructure Daniel Bristot de Oliveira
2023-11-04 10:59 ` [PATCH v5 1/7] sched: Unify runtime accounting across classes Daniel Bristot de Oliveira
2023-11-15 9:04 ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2023-11-04 10:59 ` [PATCH v5 2/7] sched/deadline: Collect sched_dl_entity initialization Daniel Bristot de Oliveira
2023-11-15 9:04 ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2023-11-04 10:59 ` [PATCH v5 3/7] sched/deadline: Move bandwidth accounting into {en,de}queue_dl_entity Daniel Bristot de Oliveira
2023-11-15 9:04 ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2023-11-04 10:59 ` [PATCH v5 4/7] sched/deadline: Introduce deadline servers Daniel Bristot de Oliveira
2023-11-15 9:04 ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2023-11-04 10:59 ` [PATCH v5 5/7] sched/fair: Add trivial fair server Daniel Bristot de Oliveira
2023-11-06 14:24 ` Peter Zijlstra
2023-11-06 14:26 ` Daniel Bristot de Oliveira
2023-11-04 10:59 ` [PATCH v5 6/7] sched/deadline: Deferrable dl server Daniel Bristot de Oliveira
2023-11-06 14:55 ` Peter Zijlstra
2023-11-06 17:05 ` Daniel Bristot de Oliveira
2023-11-06 19:32 ` Joel Fernandes
2023-11-06 21:32 ` Joel Fernandes
2023-11-06 21:37 ` Joel Fernandes
2023-11-07 11:58 ` Daniel Bristot de Oliveira
2023-11-08 2:42 ` Joel Fernandes
2023-11-07 16:47 ` Steven Rostedt
2023-11-07 17:35 ` Steven Rostedt
2023-11-07 17:46 ` Steven Rostedt
2023-11-07 17:54 ` Steven Rostedt [this message]
2023-11-07 19:32 ` Steven Rostedt
2023-11-07 20:07 ` Steven Rostedt
2023-11-07 17:37 ` Daniel Bristot de Oliveira
2023-11-07 18:50 ` Daniel Bristot de Oliveira
2023-11-08 3:20 ` Joel Fernandes
2023-11-08 8:01 ` Daniel Bristot de Oliveira
2023-11-08 18:25 ` Joel Fernandes
2023-11-08 12:44 ` Peter Zijlstra
2023-11-08 12:50 ` Peter Zijlstra
2023-11-08 14:52 ` Daniel Bristot de Oliveira
2023-11-08 13:46 ` Daniel Bristot de Oliveira
2023-11-08 13:58 ` Daniel Bristot de Oliveira
2023-11-08 15:14 ` Juri Lelli
2023-11-08 16:57 ` Peter Zijlstra
2023-11-08 2:37 ` Joel Fernandes
2023-11-07 7:30 ` Daniel Bristot de Oliveira
2023-11-07 16:37 ` Steven Rostedt
2023-11-13 15:05 ` kernel test robot
2024-03-20 0:03 ` Joel Fernandes
2024-03-20 19:24 ` Daniel Bristot de Oliveira
2024-03-21 16:15 ` Joel Fernandes
2024-03-23 14:37 ` Joel Fernandes
2024-04-05 14:35 ` Daniel Bristot de Oliveira
2024-04-08 17:11 ` Steven Rostedt
2023-11-04 10:59 ` [PATCH v5 7/7] sched/fair: Fair server interface Daniel Bristot de Oliveira
2023-11-04 15:18 ` kernel test robot
2023-11-05 0:55 ` kernel test robot
2023-11-06 15:40 ` Peter Zijlstra
2023-11-06 16:29 ` Daniel Bristot de Oliveira
2023-11-07 8:16 ` Peter Zijlstra
2023-11-07 14:06 ` Daniel Bristot de Oliveira
2023-11-07 14:44 ` Peter Zijlstra
2023-11-07 12:38 ` Peter Zijlstra
2023-11-07 13:24 ` Daniel Bristot de Oliveira
2024-01-19 1:49 ` Joel Fernandes
2024-01-19 1:55 ` Joel Fernandes
2024-01-22 14:14 ` Daniel Bristot de Oliveira
2024-01-23 15:39 ` Joel Fernandes
2024-01-23 15:44 ` Joel Fernandes
2024-02-13 2:13 ` Joel Fernandes
2024-02-13 2:21 ` Joel Fernandes
2024-02-14 14:23 ` Daniel Bristot de Oliveira
2024-02-15 13:57 ` Joel Fernandes
2024-02-15 17:27 ` Daniel Bristot de Oliveira
2024-02-15 17:41 ` Joel Fernandes
2024-04-04 17:43 ` Daniel Bristot de Oliveira
2023-12-08 21:47 ` [PATCH v5 0/7] SCHED_DEADLINE server infrastructure Joel Fernandes
2024-02-19 7:33 ` Huang, Ying
2024-02-19 10:23 ` Daniel Bristot de Oliveira
2024-02-20 3:28 ` Huang, Ying
2024-02-20 8:31 ` Daniel Bristot de Oliveira
2024-02-20 8:41 ` Huang, Ying
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=20231107125434.284c44da@gandalf.local.home \
--to=rostedt@goodmis.org \
--cc=bristot@kernel.org \
--cc=bristot@redhat.com \
--cc=bsegall@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=joel@joelfernandes.org \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luca.abeni@santannapisa.it \
--cc=mgorman@suse.de \
--cc=mingo@redhat.com \
--cc=pauld@redhat.com \
--cc=peterz@infradead.org \
--cc=skhan@linuxfoundation.org \
--cc=tglx@linutronix.de \
--cc=tommaso.cucinotta@santannapisa.it \
--cc=vincent.guittot@linaro.org \
--cc=vineeth@bitbyteword.org \
--cc=vschneid@redhat.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.