Bug 163397 - cpuspeed doesn't handle hyperthreaded cpu's effectively
Summary: cpuspeed doesn't handle hyperthreaded cpu's effectively
Alias: None
Product: Red Hat Enterprise Linux 4
Classification: Red Hat
Component: kernel-utils
Version: 4.0
Hardware: All
OS: Linux
Target Milestone: ---
: ---
Assignee: Jarod Wilson
QA Contact: Brian Brock
Depends On:
TreeView+ depends on / blocked
Reported: 2005-07-15 20:17 UTC by Eric Jones
Modified: 2007-11-30 22:07 UTC (History)
2 users (show)

Clone Of:
Last Closed: 2007-06-04 21:37:19 UTC

Attachments (Terms of Use)

Description Eric Jones 2005-07-15 20:17:53 UTC
From Bugzilla Helper:
User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.7.8) Gecko/20050512 Red Hat/1.0.4-1.4.1 Firefox/1.0.4

Description of problem:
When using a HyperThreaded Pentium 4 CPU, the cpuspeed daemon doens't use an effective algorithm for determining the current CPU utilizization.  Since a single CPU intensive process only runs on one "virtual" CPU, the other CPU appears 100% idle, giving a net system usage of 50%.  cpuspeed sees this and lowers the clock speed, slowing down the otherwise CPU intensive application.  When running on a hyperthreaded system, cpuspeed should use the most active "virtual" processor as its gauge for current system activity.

Version-Release number of selected component (if applicable):

How reproducible:

Steps to Reproduce:
1. start cpuspeed
2. run an intense cpu benchmark on one "virtual" processor
3. cat /proc/cpuinfo and watch the processor get slowed to its lowest state (2.8 GHz on my 3.6 GHz box)

Actual Results:  The cpu was frequency scaled down to its lowest state.

Expected Results:  The cpu should have run at the maximum clock speed since the benchmark was utilizing 100% of one of the "virtual" processors.

Additional info:

Comment 1 Jarod Wilson 2007-01-24 14:53:32 UTC
Is this still an issue with the latest RHEL4 kernel and kernel-utils packages?
I'm taking over all cpu frequency scaling bugs, and trying to work my way
through them...

Comment 2 Jarod Wilson 2007-06-04 21:37:19 UTC
4+ months of no activity, 1.5+ years since hearing from the original poster,
closing out bug.

Note You need to log in before you can comment on or make changes to this bug.