I'll assume you're not running NTP for the obvious reason that it
negates the timer patch benefit, but we've seen some relationship to
frequency of disk I/O and network I/O to how bad the timekeeping
becomes. I haven't been able to pin it down either.

The short cut fix is to enable NTP. The longer term fix is to determine
what's stalling the clock during I/O.

-- db

David Boyes
Sine Nomine Associates


> -----Original Message-----
> From: Linux on 390 Port [mailto:[EMAIL PROTECTED]]On Behalf Of
> p43cibmgs-Arden
> Sent: Thursday, January 02, 2003 4:29 PM
> To: [EMAIL PROTECTED]
> Subject: Linux time/date getting skewed
>
>
> I was wondering is anyone else has seen this.
>
> We are running zVM 4.3.0 on a 9672 R66, Linux is mostly SuSE
> 2.4.17 with the
> timer patch. All developerworks patches through 8/16 I think.
>
> We have been noticing for some time that the clocks on our
> Linux systems display
> times that seem to slowly fall further and further out of
> sync with real time.
> At 1/2/03, 2:30PM CST, we have several systems that display
> the correct time,
> but also systems that display the current time as 1/2/03
> 13:17 and 13:35, 1/1/03
> 13:35, 12/31/02 08:55 and on and on.
>
> It doesn't seem to have any relation to how long the systems
> have been up. For
> example, we have four systems that were last booted on
> 11/26/02. One still has
> the correct time, one is an hour behind, one is 25 hours
> behind and one is 53
> hours, 40 minutes behind.
>
> It also doesn't seem to have anything to do with workload. Or
> lack of workload
> either, we thought maybe that idling systems that spent most
> of their time
> swapped out by VM might be the ones that fell the furthest
> behind, but some
> examples of those were were still absolutely current, while
> the system we work
> with the most fell an hour behind in less than a week.
>
> We just haven't found a common thread as to why some systems
> are falling behind,
> nor why some are falling behind faster than others.
>
> If anyone has any ideas....
>
> Thanks,
>
> Steve Arden
>
> [EMAIL PROTECTED]
> IBM-Global Services @ Lucent
> (630)979-7124
>

Reply via email to