From: | Achilleas Mantzios <achill(at)matrix(dot)gatewaynet(dot)com> |
---|---|
To: | pgsql-admin(at)postgresql(dot)org |
Subject: | Re: Postgresql 9.0.2 explain analyze very slow (10x), compared to actual query time |
Date: | 2011-01-13 10:17:52 |
Message-ID: | 201101131217.53575.achill@matrix.gatewaynet.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-admin |
Στις Wednesday 12 January 2011 21:17:00 ο/η Alex Hunsaker έγραψε:
> 2011/1/12 Achilleas Mantzios <achill(at)matrix(dot)gatewaynet(dot)com>:
>
> >
> > Changed that to smth like: micros_total = micros_total + (double) micros;
> > instead of the printf to beat any compiler optimization, and still linux runs at light speed:
> > FBSD_TEST : user 0.089s, sys 1.4s
> > FBSD_DEV : user 0.183s, sys 3.8s
> > LINUX_PROD : user 0.168s, sys 0s
> > (regarding that gettimeofday is a syscall in FreeBSD, and that sys time is 0 for linux, makes me think some optimization is being done)
>
> At least on x86_64, linux will use a vsyscall (v for virtual) for
> gettimeofday which does not actually need to enter/exit the kernel.
> That probably explains a large part of the speed difference here.
>
Thanx, thats the ARCH (x86_64) of our linux system.
--
Achilleas Mantzios
From | Date | Subject | |
---|---|---|---|
Next Message | Achilleas Mantzios | 2011-01-13 10:35:12 | Re: Postgresql 9.0.2 explain analyze very slow (10x), compared to actual query time |
Previous Message | Sivakatirswami | 2011-01-12 21:46:26 | Help with Restoring 8.01 databases to 9.0 |