Bug 604239 - Memtest86+ clock runs fast.
Summary: Memtest86+ clock runs fast.
Alias: None
Product: Fedora
Classification: Fedora
Component: memtest86   
(Show other bugs)
Version: 13
Hardware: All
OS: Linux
Target Milestone: ---
Assignee: Warren Togami
QA Contact:
Depends On:
TreeView+ depends on / blocked
Reported: 2010-06-15 16:57 UTC by Maciej Żenczykowski
Modified: 2011-06-27 18:18 UTC (History)
0 users

Fixed In Version:
Doc Type: Bug Fix
Doc Text:
Story Points: ---
Clone Of:
Last Closed: 2011-06-27 18:18:39 UTC
Type: ---
Regression: ---
Mount Type: ---
Documentation: ---
Verified Versions:
Category: ---
oVirt Team: ---
RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: ---

Attachments (Terms of Use)

Description Maciej Żenczykowski 2010-06-15 16:57:12 UTC
I've noticed that on my computer the memtest walltime clock runs fast.

The problem is *probably* that it's using the TSC to measure time.

I have a 3 GHz Intel CPU which is BIOS configured to start at 2 GHz.
This is an EIST configuration (ie. multiplier = 6 instead of the default/max 9).
However because of 'constant_tsc cpu flag' the TSC continues to cycle at 3 GHz (even though the cpu only executes at 2 GHz).
So Memtest probably sees a 2 GHz CPU and uses TSC for the walltime, but the TSC is cycling at 3GHz instead of 2 (ie. 150%).  This is inline with the observed behaviour of the wall clock taking 40 seconds to measure off a minute (ie. speedup of 150%).

My guess is this may also be a problem on newer cpu's (i7's) which have turboboost and other dynamic accelerations (IDA), since [I believe] their TSC cycle frequency is actually the maximum turbo boost frequency (and not the 'normal' frequency of the cpu).  Although the difference should be much smaller than the 150% I'm seeing.

You can get some information about EIST out of MSRs 0x198 and 0x199.  So you might be able to detect the scaling factor...

At a very rough first approximation, the scaling factor is bits 45-40 of MSR 0x198 divided by bits 13-8 of MSR 0x199 (with bits 46 and 14 increasing the relevant number by 0.5).  Unfortunately this is definitely nowhere near a full solution (it fails to handle non-zero bits 47 and 15 for example, not sure if it even deals with i7 turboboost or IDA - it should handle your basic garden variety Intel EIST without super-low-power laptop mode).

Comment 1 Bug Zapper 2011-06-02 10:43:52 UTC
This message is a reminder that Fedora 13 is nearing its end of life.
Approximately 30 (thirty) days from now Fedora will stop maintaining
and issuing updates for Fedora 13.  It is Fedora's policy to close all
bug reports from releases that are no longer maintained.  At that time
this bug will be closed as WONTFIX if it remains open with a Fedora 
'version' of '13'.

Package Maintainer: If you wish for this bug to remain open because you
plan to fix it in a currently maintained version, simply change the 'version' 
to a later Fedora version prior to Fedora 13's end of life.

Bug Reporter: Thank you for reporting this issue and we are sorry that 
we may not be able to fix it before Fedora 13 is end of life.  If you 
would still like to see this bug fixed and are able to reproduce it 
against a later version of Fedora please change the 'version' of this 
bug to the applicable version.  If you are unable to change the version, 
please add a comment here and someone will do it for you.

Although we aim to fix as many bugs as possible during every release's 
lifetime, sometimes those efforts are overtaken by events.  Often a 
more recent Fedora release includes newer upstream software that fixes 
bugs or makes them obsolete.

The process we are following is described here: 

Comment 2 Bug Zapper 2011-06-27 18:18:39 UTC
Fedora 13 changed to end-of-life (EOL) status on 2011-06-25. Fedora 13 is 
no longer maintained, which means that it will not receive any further 
security or bug fix updates. As a result we are closing this bug.

If you can reproduce this bug against a currently maintained version of 
Fedora please feel free to reopen this bug against that version.

Thank you for reporting this bug and we are sorry it could not be fixed.

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