Re: Vacuum time degrading

On 3/2/05 12:16 PM, "Tom Lane" <tgl(at)sss(dot)pgh(dot)pa(dot)us> wrote:

> Would you post the complete VACUUM VERBOSE log? The CPU/elapsed time lines
> would help us identify where the time is going.

Mailed.

I do see stats like:

CPU 518.88s/25.17u sec elapsed 10825.33 sec.
CPU 884.96s/64.35u sec elapsed 13793.13 sec.
CPU 132.46s/6.66u sec elapsed 2435.42 sec.
CPU 49.25s/4.15u sec elapsed 414.71 sec.

This is a dual CPU hyperthreaded (which probably makes little difference
here) 2.4Ghz RedHat 3.0. The database is on an 8-disk SCSI hardware RAID 5
with 10k rpm disks. Pg_xlog is on a separate volume.

I thought it was a 2.6 kernel, but it looks like it is 2.4.20. I need to
monitor the system when the vacuum is running to see if sar/top show
anything. I wonder if it's hitting the kswapd thrashing problem?

Wes