On 07:57 10 Feb 2003, David Busby <[EMAIL PROTECTED]> wrote: | I know I've seen questions to this before, but I couldn't find the | answer on the archive. I've got a Dual P3-550 + 1GB with 3 9G SCSI drives. | This box runs my PostgreSQL server. I was performing a data import with | `psql -f somefile -U post...`. | Well then I looked at top and saw that my loadavg was 1.9# 1.4 1.##. Anyhow | after reading that, I looked and saw CPU usage with ~5% Kernel, ~10-25% | User. `free` said I still had about 2/3rds of my physical ram free, none of | the swap was being used. So my question is, how can LoadAvg be 1.9 or | sometimes even >2 when CPU and Memory are well below any danger thresholds? | How could I check disk performance? Could that be the bottle neck? TIA
Processes blocked on short term disc waits (eg when PostgreSQL is hammering its tables for you) also contribute to the load average. Don't worry. Load average is a touchy-feely thing, so the PostgreSQL stuff is contributing even though it's not CPU bound). Cheers, -- Cameron Simpson, DoD#743 [EMAIL PROTECTED] http://www.zip.com.au/~cs/ This explains a lot about me. I thought it was the heavy drinking, the late hours, the barking mad women, the lying around in bed reading novels and eating Nescafe out of a jar with the spoon. But it's because of the Mac. - Tony Cunningham, <[EMAIL PROTECTED]> -- redhat-list mailing list unsubscribe mailto:[EMAIL PROTECTED]?subject=unsubscribe https://listman.redhat.com/mailman/listinfo/redhat-list
