Re: 8.3 / 8.2.6 restore comparison

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

On Thu, 7 Feb 2008 18:40:37 -0800
"Joshua D. Drake" <jd(at)commandprompt(dot)com> wrote:

> On Thu, 7 Feb 2008 18:32:41 -0800
> "Joshua D. Drake" <jd(at)commandprompt(dot)com> wrote:
>
> >
> > Do you want counts or actual output?
>
> % time seconds usecs/call calls errors syscall
> ------ ----------- ----------- --------- --------- ----------------
> 58.22 1.597638 33 47795 write
> 31.86 0.874104 23 38024 recvfrom
> 4.43 0.121559 92 1319 munmap
> 4.17 0.114445 3 37906 lseek
> 0.70 0.019341 13 1440 brk
> 0.56 0.015402 12 1316 mmap
> 0.04 0.000991 26 38 open
> 0.01 0.000298 8 38 close
> 0.01 0.000156 4 38 time
> 0.00 0.000008 8 1 semop
> ------ ----------- ----------- --------- --------- ----------------
> 100.00 2.743942 127915 total
>

Were their any thoughts on this? I am also finding that backing up this
database is rudely slow with the same type of odd metrics (almost zero
(or zero) iowait). We can saturate a CPU but the CPU is certainly not
pushing the data to disk as fast as it could.

Joshua D. Drake

- --
The PostgreSQL Company since 1997: http://www.commandprompt.com/
PostgreSQL Community Conference: http://www.postgresqlconference.org/
Donate to the PostgreSQL Project: http://www.postgresql.org/about/donate
PostgreSQL SPI Liaison | SPI Director | PostgreSQL political pundit

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.6 (GNU/Linux)

iD8DBQFHu0hqATb/zqfZUUQRAm77AJ41yWT4f6UNiMwyHtcq9GASK51uDgCgpKzf
lu14eCbSDl2v2Rsq40zww8E=
=DshT
-----END PGP SIGNATURE-----