From: Daniel Bristot de Oliveira <bristot@redhat.com>
To: John Stultz <john.stultz@linaro.org>,
lkml <linux-kernel@vger.kernel.org>
Cc: Prarit Bhargava <prarit@redhat.com>,
Richard Cochran <richardcochran@gmail.com>,
Jan Kara <jack@suse.cz>, Jiri Bohac <jbohac@suse.cz>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>,
Shuah Khan <shuahkh@osg.samsung.com>
Subject: Re: [RFC][PATCH 0/4] Fixes for leapsecond expiring early ABS_TIME CLOCK_REALTIME timers
Date: Mon, 01 Jun 2015 17:18:28 -0300 [thread overview]
Message-ID: <556CBE14.9070105@redhat.com> (raw)
In-Reply-To: <1432931068-4980-1-git-send-email-john.stultz@linaro.org>
Il 29/05/2015 17:24, John Stultz ha scritto:
> Thus this patch series tries to address this isssue, including
> extending the leap-a-day test to catch this problem, as well
> as other relevant fixups I found while working on the code.
>
> This series has only had limited testing, so I wanted to send
> it out for initial review and comment. Folks can grab this tree
> via git for testing here:
> https://git.linaro.org/people/john.stultz/linux.git dev/early-leap-timer
John,
I saw two failures while testing the patched kernel
using the patched leap-a-day.
On both cases the leap second was not inserted, and
then the timer fired at the second edge (as expected?).
Here is the output of both leap-a-day and dmesg for
both errors:
===== Error 1 =====
[root@vostro timers]# ./leap-a-day -s
[...many lines...]
Setting time to Wed Sep 9 20:59:50 2015
Scheduling leap second for Wed Sep 9 21:00:00 2015
Setting timer for Wed Sep 9 21:00:00 2015
Wed Sep 9 20:59:57 2015 + 147 us (0) TIME_INS
Wed Sep 9 20:59:57 2015 + 500352 us (0) TIME_INS
Wed Sep 9 20:59:58 2015 + 558 us (0) TIME_INS
Wed Sep 9 20:59:58 2015 + 500767 us (0) TIME_INS
Wed Sep 9 20:59:59 2015 + 975 us (0) TIME_INS
Wed Sep 9 20:59:59 2015 + 501181 us (0) TIME_INS
Wed Sep 9 20:59:59 2015 + 1442 us (1) TIME_OOP
Wed Sep 9 20:59:59 2015 + 501670 us (1) TIME_OOP
Wed Sep 9 21:00:00 2015 + 110 us (1) TIME_WAIT - TIMER FIRED
Wed Sep 9 21:00:00 2015 + 179 us (1) TIME_WAIT
Wed Sep 9 21:00:00 2015 + 500340 us (1) TIME_WAIT
Wed Sep 9 21:00:01 2015 + 548 us (1) TIME_WAIT
Wed Sep 9 21:00:01 2015 + 500768 us (1) TIME_WAIT
Wed Sep 9 21:00:02 2015 + 976 us (1) TIME_WAIT
Leap complete
Setting time to Thu Sep 10 20:59:50 2015
Scheduling leap second for Thu Sep 10 21:00:00 2015
Setting timer for Thu Sep 10 21:00:00 2015
Thu Sep 10 20:59:57 2015 + 209 us (1) TIME_DEL
Thu Sep 10 20:59:57 2015 + 500410 us (1) TIME_DEL
Thu Sep 10 20:59:58 2015 + 646 us (1) TIME_DEL
Thu Sep 10 20:59:58 2015 + 500881 us (1) TIME_DEL
Thu Sep 10 21:00:00 2015 + 1182 us (0) TIME_WAIT - TIMER FIRED
Thu Sep 10 21:00:00 2015 + 1283 us (0) TIME_WAIT
Thu Sep 10 21:00:00 2015 + 501475 us (0) TIME_WAIT
Thu Sep 10 21:00:01 2015 + 1654 us (0) TIME_WAIT
Thu Sep 10 21:00:01 2015 + 501856 us (0) TIME_WAIT
Thu Sep 10 21:00:02 2015 + 2032 us (0) TIME_WAIT
Leap complete
Setting time to Fri Sep 11 20:59:50 2015
Scheduling leap second for Fri Sep 11 21:00:00 2015
Setting timer for Fri Sep 11 21:00:00 2015
Fri Sep 11 20:59:57 2015 + 139 us (0) TIME_INS
Fri Sep 11 20:59:57 2015 + 500347 us (0) TIME_INS
Fri Sep 11 20:59:58 2015 + 527 us (0) TIME_INS
Fri Sep 11 20:59:58 2015 + 500751 us (0) TIME_INS
Fri Sep 11 20:59:59 2015 + 987 us (0) TIME_INS
Fri Sep 11 20:59:59 2015 + 501203 us (0) TIME_INS
Fri Sep 11 21:00:00 2015 + 100 us (0) TIME_INS - TIMER FIRED
Error: Incorrect NTP state?
Fri Sep 11 21:00:00 2015 + 173 us (0) TIME_INS
Fri Sep 11 21:00:00 2015 + 500353 us (0) TIME_OK
Fri Sep 11 21:00:01 2015 + 583 us (0) TIME_OK
Fri Sep 11 21:00:01 2015 + 500799 us (0) TIME_OK
Fri Sep 11 21:00:02 2015 + 1021 us (0) TIME_OK
Leap complete
Errors observed
[root@vostro timers]# dmesg | tail
[ 1451.279313] Clock: deleting leap second 23:59:59 UTC
[ 1464.296724] Clock: inserting leap second 23:59:60 UTC
[ 1477.312373] Clock: deleting leap second 23:59:59 UTC
[ 1490.329740] Clock: inserting leap second 23:59:60 UTC
[ 1503.345402] Clock: deleting leap second 23:59:59 UTC
[ 1516.362841] Clock: inserting leap second 23:59:60 UTC
[ 1529.378466] Clock: deleting leap second 23:59:59 UTC
[ 1542.395826] Clock: inserting leap second 23:59:60 UTC
[ 1555.411551] Clock: deleting leap second 23:59:59 UTC
[ 1697.998312] Adjusting tsc more than 11% (5677670 vs 7466007) <-- ???
---> did not insert the leap second <---
## did not insert the leap second
===== Error 2 =====
[root@vostro timers]# ./leap-a-day -s
[...many lines...]
Setting time to Wed Aug 19 20:59:50 2015
Scheduling leap second for Wed Aug 19 21:00:00 2015
Setting timer for Wed Aug 19 21:00:00 2015
Something cleared STA_INS/STA_DEL, setting it again.
Wed Aug 19 20:59:57 2015 + 181 us (0) TIME_OK
Wed Aug 19 20:59:57 2015 + 500357 us (0) TIME_INS
Wed Aug 19 20:59:58 2015 + 559 us (0) TIME_INS
Wed Aug 19 20:59:58 2015 + 500761 us (0) TIME_INS
Wed Aug 19 20:59:59 2015 + 967 us (0) TIME_INS
Wed Aug 19 20:59:59 2015 + 501177 us (0) TIME_INS
Wed Aug 19 20:59:59 2015 + 1318 us (1) TIME_OOP
Wed Aug 19 20:59:59 2015 + 501508 us (1) TIME_OOP
Wed Aug 19 21:00:00 2015 + 99 us (1) TIME_WAIT - TIMER FIRED
Wed Aug 19 21:00:00 2015 + 161 us (1) TIME_WAIT
Wed Aug 19 21:00:00 2015 + 500320 us (1) TIME_WAIT
Wed Aug 19 21:00:01 2015 + 523 us (1) TIME_WAIT
Wed Aug 19 21:00:01 2015 + 500735 us (1) TIME_WAIT
Wed Aug 19 21:00:02 2015 + 937 us (1) TIME_WAIT
Leap complete
Setting time to Thu Aug 20 20:59:50 2015
Scheduling leap second for Thu Aug 20 21:00:00 2015
Setting timer for Thu Aug 20 21:00:00 2015
Thu Aug 20 20:59:57 2015 + 144 us (1) TIME_DEL
Thu Aug 20 20:59:57 2015 + 500351 us (1) TIME_DEL
Thu Aug 20 20:59:58 2015 + 552 us (1) TIME_DEL
Thu Aug 20 20:59:58 2015 + 500752 us (1) TIME_DEL
Thu Aug 20 21:00:00 2015 + 1021 us (0) TIME_WAIT - TIMER FIRED
Thu Aug 20 21:00:00 2015 + 1096 us (0) TIME_WAIT
Thu Aug 20 21:00:00 2015 + 501267 us (0) TIME_WAIT
Thu Aug 20 21:00:01 2015 + 1470 us (0) TIME_WAIT
Thu Aug 20 21:00:01 2015 + 501677 us (0) TIME_WAIT
Thu Aug 20 21:00:02 2015 + 1886 us (0) TIME_WAIT
Leap complete
Setting time to Fri Aug 21 20:59:50 2015
Scheduling leap second for Fri Aug 21 21:00:00 2015
Setting timer for Fri Aug 21 21:00:00 2015
Fri Aug 21 20:59:57 2015 + 153 us (0) TIME_INS
Fri Aug 21 20:59:57 2015 + 500354 us (0) TIME_INS
Fri Aug 21 20:59:58 2015 + 562 us (0) TIME_INS
Fri Aug 21 20:59:58 2015 + 500815 us (0) TIME_INS
Fri Aug 21 20:59:59 2015 + 1000 us (0) TIME_INS
Fri Aug 21 20:59:59 2015 + 501207 us (0) TIME_INS
Fri Aug 21 21:00:00 2015 + 109 us (0) TIME_INS - TIMER FIRED
Error: Incorrect NTP state?
Fri Aug 21 21:00:00 2015 + 173 us (0) TIME_INS
Fri Aug 21 21:00:00 2015 + 500331 us (0) TIME_OK
Fri Aug 21 21:00:01 2015 + 540 us (0) TIME_OK
Fri Aug 21 21:00:01 2015 + 500791 us (0) TIME_OK
Fri Aug 21 21:00:02 2015 + 1046 us (0) TIME_OK
Leap complete
Errors observed
[root@vostro timers]# dmesg | tail
[ 1283.857902] Clock: inserting leap second 23:59:60 UTC
[ 1296.873600] Clock: deleting leap second 23:59:59 UTC
[ 1309.891049] Clock: inserting leap second 23:59:60 UTC
[ 1322.906709] Clock: deleting leap second 23:59:59 UTC
[ 1335.924154] Clock: inserting leap second 23:59:60 UTC
[ 1348.939824] Clock: deleting leap second 23:59:59 UTC
[ 1361.957267] Clock: inserting leap second 23:59:60 UTC
[ 1374.972919] Clock: deleting leap second 23:59:59 UTC
[ 1387.989238] Clock: inserting leap second 23:59:60 UTC
[ 1401.005877] Clock: deleting leap second 23:59:59 UTC
---> did not insert the leap second <---
Both cases occurred in the same physical machine.
AFAICS, it does not occur in the unpatched
kernel/leap-a-day in the same machine.
-- Daniel
next prev parent reply other threads:[~2015-06-01 20:18 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-05-29 20:24 [RFC][PATCH 0/4] Fixes for leapsecond expiring early ABS_TIME CLOCK_REALTIME timers John Stultz
2015-05-29 20:24 ` [RFC][PATCH 1/4] selftests: timers: Add leap-second timer edge testing to leap-a-day.c John Stultz
2015-05-29 20:24 ` [RFC][PATCH 2/4] timer_list: Add the base offset so remaining nsecs are accurate for non monotonic timers John Stultz
2015-05-29 20:24 ` [RFC][PATCH 3/4] ntp: Use printk_deferred in leapsecond path John Stultz
2015-06-02 10:31 ` Jiri Bohac
2015-06-02 10:43 ` Jiri Kosina
2015-06-02 16:14 ` John Stultz
2015-06-02 16:04 ` John Stultz
2015-05-29 20:24 ` [RFC][PATCH 4/4] time: Do leapsecond adjustment in gettime fastpaths John Stultz
2015-05-31 16:05 ` Richard Cochran
2015-06-02 9:01 ` Ingo Molnar
2015-06-02 9:21 ` Peter Zijlstra
2015-06-02 14:09 ` John Stultz
2015-06-02 15:52 ` John Stultz
2015-06-03 9:04 ` Ingo Molnar
2015-06-03 17:44 ` John Stultz
2015-06-04 6:48 ` Ingo Molnar
2015-06-05 0:08 ` John Stultz
2015-06-05 7:29 ` Peter Zijlstra
2015-06-05 9:04 ` Richard Cochran
2015-06-05 9:10 ` Peter Zijlstra
2015-06-05 14:12 ` Richard Cochran
2015-06-05 17:28 ` John Stultz
2015-06-06 9:44 ` Thomas Gleixner
2015-06-08 17:55 ` John Stultz
2015-06-08 19:05 ` Thomas Gleixner
2015-06-08 20:02 ` Thomas Gleixner
2015-06-05 11:37 ` Prarit Bhargava
2015-06-05 12:07 ` Thomas Gleixner
2015-06-05 14:22 ` Richard Cochran
2015-06-05 17:24 ` John Stultz
2015-05-31 13:55 ` [RFC][PATCH 0/4] Fixes for leapsecond expiring early ABS_TIME CLOCK_REALTIME timers Prarit Bhargava
2015-06-01 11:57 ` Prarit Bhargava
2015-06-01 17:02 ` John Stultz
2015-06-01 17:43 ` Prarit Bhargava
2015-06-01 20:18 ` Daniel Bristot de Oliveira [this message]
2015-06-01 20:32 ` John Stultz
2015-06-01 21:42 ` Prarit Bhargava
2015-06-01 22:29 ` Daniel Bristot de Oliveira
2015-06-02 6:19 ` John Stultz
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=556CBE14.9070105@redhat.com \
--to=bristot@redhat.com \
--cc=jack@suse.cz \
--cc=jbohac@suse.cz \
--cc=john.stultz@linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=prarit@redhat.com \
--cc=richardcochran@gmail.com \
--cc=shuahkh@osg.samsung.com \
--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).