Re: pg_test_timing tool for EXPLAIN ANALYZE overhead

On 02/22/2012 12:25 PM, Marti Raudsepp wrote:
> On Wed, Feb 22, 2012 at 18:44, Greg Smith<greg(at)2ndquadrant(dot)com> wrote:
>> As far as I've been able to tell, there aren't any issues unique to Windows
>> there. Multiple cores can have their TSC results get out of sync on Windows
>> for the same reason they do on Linux systems, and there's also the same
>> frequency/temperature issues.
>
> Not on recent Linux kernel versions. Linux automatically detects when
> the TSC is unstable (due to power management or out-of-sync
> cores/sockets) and automatically falls back to the more expensive HPET
> or ACPI methods.

From the patch:

Newer operating systems may check for the known TSC problems and
switch to a slower, more stable clock source when they are seen.
If your system supports TSC time but doesn't default to that, it
may be disabled for a good reason.

I ran into a case like you're showing here in my longer exploration of
this at
http://archives.postgresql.org/message-id/4EDF1871.2010209@2ndQuadrant.com
I stopped just short of showing what the TSC error message looked
like. I hoped that with the above and some examples showing dmesg |
grep, that would be enough to lead enough people toward finding this on
their own.

--
Greg Smith 2ndQuadrant US greg(at)2ndQuadrant(dot)com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.com