From: Alex Shi <alex.shi@intel.com>
To: tglx@linutronix.de, hpa@linux.intel.com, tim.c.chen@linux.intel.com
Cc: linux-kernel@vger.kernel.org, andi.kleen@intel.com,
a.p.zijlstra@chello.nl, mingo@elte.hu
Subject: [URGENT rfc patch 0/3] tsc clocksource bug fix
Date: Thu, 4 Jul 2013 13:34:13 +0800 [thread overview]
Message-ID: <1372916056-24301-1-git-send-email-alex.shi@intel.com> (raw)
We find some benchmarks drop a lot on tip/sched/core on many Intel boxes,
like oltp, tbench, hackbench etc. and bisected the commit 5d33b883ae
cause this regression. Due to this commit, the clocksource was changed
to hpet from tsc even tsc will be set CLOCK_SOURCE_VALID_FOR_HRES later
in clocksource_watchdog.
Tim Chen said the hpet reading cost much. That cause this regression.
This patchset fixed this bug by re-select clocksource after this flag set
on tsc.
BTW,
If the tsc is marked as constant and nonstop, could we set it as system
clocksource when do tsc register? w/o checking it on clocksource_watchdog?
regards!
Alex
next reply other threads:[~2013-07-04 5:36 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-07-04 5:34 Alex Shi [this message]
2013-07-04 5:34 ` [PATCH 1/3] clocksource: clean up clocksource_select Alex Shi
2013-07-04 9:57 ` Thomas Gleixner
2013-07-04 10:21 ` Alex Shi
2013-07-04 10:27 ` Thomas Gleixner
2013-07-05 1:22 ` Alex Shi
2013-07-04 5:34 ` [PATCH 2/3] clockesource: set override clocksource Alex Shi
2013-07-04 10:23 ` Thomas Gleixner
2013-07-04 5:34 ` [PATCH 3/3] clocksource: fix can not set tsc as clocksource bug Alex Shi
2013-07-04 10:55 ` Thomas Gleixner
2013-07-04 13:04 ` Thomas Gleixner
2013-07-04 20:46 ` [PATCH] clocksource: Reselect clocksource when watchdog validated Thomas Gleixner
2013-07-05 1:38 ` Alex Shi
2013-07-05 9:13 ` [tip:timers/core] clocksource: Reselect clocksource when watchdog validated high-res capability tip-bot for Thomas Gleixner
2013-07-05 2:48 ` [PATCH 3/3] clocksource: fix can not set tsc as clocksource bug Alex Shi
2013-07-05 5:41 ` Thomas Gleixner
2013-07-05 6:44 ` Alex Shi
2013-07-04 7:58 ` [URGENT rfc patch 0/3] tsc clocksource bug fix Peter Zijlstra
2013-07-04 8:13 ` Alex Shi
2013-07-05 14:23 ` Frederic Weisbecker
2013-07-05 14:38 ` Peter Zijlstra
2013-07-05 15:24 ` Thomas Gleixner
2013-07-05 21:22 ` Peter Zijlstra
2013-07-05 21:50 ` Thomas Gleixner
2013-07-05 21:58 ` Borislav Petkov
2013-07-05 22:17 ` Thomas Gleixner
2013-07-06 8:37 ` Borislav Petkov
2013-07-06 10:50 ` Peter Zijlstra
2013-07-04 11:00 ` Thomas Gleixner
2013-07-04 18:11 ` Davidlohr Bueso
2013-07-04 20:27 ` Thomas Gleixner
2013-07-05 1:12 ` Alex Shi
2013-07-05 5:58 ` Thomas Gleixner
2013-07-05 6:28 ` Alex Shi
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=1372916056-24301-1-git-send-email-alex.shi@intel.com \
--to=alex.shi@intel.com \
--cc=a.p.zijlstra@chello.nl \
--cc=andi.kleen@intel.com \
--cc=hpa@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=tglx@linutronix.de \
--cc=tim.c.chen@linux.intel.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 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).