Gentoo Websites Logo
Go to: Gentoo Home Documentation Forums Lists Bugs Planet Store Wiki Get Gentoo!
Bug 210747 - [2.6.24 regression] conservative governor doesn't increase frequency, just decrease. powernow-k7
Summary: [2.6.24 regression] conservative governor doesn't increase frequency, just de...
Status: RESOLVED OBSOLETE
Alias: None
Product: Gentoo Linux
Classification: Unclassified
Component: [OLD] Core system (show other bugs)
Hardware: x86 Linux
: High normal (vote)
Assignee: Gentoo Kernel Bug Wranglers and Kernel Maintainers
URL: http://bugzilla.kernel.org/show_bug.c...
Whiteboard: linux-2.6.24-regression
Keywords:
Depends on:
Blocks:
 
Reported: 2008-02-19 19:45 UTC by Erik Boritsch
Modified: 2011-06-28 09:34 UTC (History)
1 user (show)

See Also:
Package list:
Runtime testing required: ---


Attachments

Note You need to log in before you can comment on or make changes to this bug.
Description Erik Boritsch 2008-02-19 19:45:55 UTC
Tuxonice-sources-2.6.24-r2, conservative governor compiled in (doesn't matter whether module or not). If I set conservative as current governor (via cpufreq-utils, i don't use cpufreqd) the CPU frequency decreases slowly at low CPU load (good). But if I put the CPU on high load then,the frequency remains unchanged.Conservative is working on 2.6.23.*, ondemand works even on 2.6.24
CPU frequency module is powernow-k7.

Reproducible: Always

Steps to Reproduce:
1.compile kernel with conservative governor
2.set it as current governor
3.put CPU on high load
Comment 1 Krzysztof Pawlik (RETIRED) gentoo-dev 2008-02-19 22:02:42 UTC
Please test gentoo-sources and vanilla-sources, if the problem persists please file bug upstream.
Comment 2 Erik Boritsch 2008-02-20 19:41:27 UTC
The problem is there with both vanilla-sources-2.6.24.2 and gentoo-sources-2.6.24-r2. Filed a bug at kernel bugzilla http://bugzilla.kernel.org/show_bug.cgi?id=10055
Comment 3 Krzysztof Pawlik (RETIRED) gentoo-dev 2008-02-20 21:23:17 UTC
Confirmed with vanilla kernel, waiting for upstream.
Comment 4 Mike Pagano gentoo-dev 2008-02-24 21:41:32 UTC
Thanks, will track upstream bug
Comment 5 Arthur Hagen 2008-07-29 08:24:48 UTC
upstream is barking up the wrong tree.  There is a bug / design flaw with the scaling_min value that causes the frequency to rise very slowly, which upstreams mistakenly thought was the issue here too.  It isn't.

For the bug here, you can peg the CPU at 100% for an hour at the lowest possible scaling value, but the CPU frequency still will not climb a single notch.

The bug is still present in gentoo-sources-2.6.25-r7
2.6.23-r9 works fine.
Comment 6 Erik Boritsch 2008-08-17 15:39:43 UTC
Still there with 2.6.26. Reopening bug.
Comment 7 Mike Pagano gentoo-dev 2008-08-17 16:27:30 UTC
Test on the latest git kernel, if it still an issue, we will resolve this again as UPSTREAM and continue to track the upstream bug as written in our policy.

"If you had deduced in the previous steps that this issue is present in the latest release-candidate kernel, then we may close the bug, asking you to post a bug report at the upstream central kernel bugzilla. Don't be offended by this - we are interested in solving the problem, but its not always on our territory. However we do prefer to hear about issues users are having, and you will have fulfilled this by filing the bug with us first."[1]

http://dev.gentoo.org/~dsd/genpatches/bugs.htm