Re: another query optimization question - Mailing list pgsql-performance

From Tom Lane
Subject Re: another query optimization question
Date
Msg-id 3875.1075563956@sss.pgh.pa.us
Whole thread Raw
In response to Re: another query optimization question  (David Teran <david.teran@cluster9.com>)
Responses Re: another query optimization question
List pgsql-performance
David Teran <david.teran@cluster9.com> writes:
> Apple provides a little tool that can enable / disable the l2 cache ...
> one CPU of a dual CPU system on the fly. When i start the testapp with
> two CPU's enabled i get this output here, when i turn off one CPU while
> the app is still running the messages disappear as long as one CPU is
> turned off. Reactivating the CPU again produces new error messages.

Ah-hah, so the gettimeofday bug *is* linked to multiple CPUs.  Marc,
were the machines you saw it on all multi-CPU?

> Do you remember where one can find a patch?

File a bug report with Apple.

> Do you know if this bug makes a system unusable with PostgresSQL?

Not at all.  The only bad effect we've noted is that EXPLAIN results
are sometimes wacky.  In theory you could sometimes see the result of
now() being off by a second or two, but no one's reported seeing that.

            regards, tom lane

pgsql-performance by date:

Previous
From: David Teran
Date:
Subject: Re: another query optimization question
Next
From: Bruce Momjian
Date:
Subject: Re: High Performance/High Reliability File system on SuSE64