RE: sreadtim and mreadtim < 1ms

> - I already understand why I'm getting such fast sreadtim and mreadtim
values (from OS caching). I'm just trying to figure out what is the best approach (in general) for setting the system stats in this scenario:

This doesn't necessarily help, but you're sure that the low values are due to OS caching? On AIX with 10.1 and all datafiles mounted CIO, I get:

MREADTIM	0.478
SREADTIM	0.962

I suppose if your DB is on a cooked FS, there's little choice but to cache.

I tried to see what a 10053 trace says for me, but that info doesn't appear to be available in the trace on 10.1. :( It could always be a reporting problem in the trace that's causing the truncated values -- there is precedence for this kind of issue...

Rich

--
http://www.freelists.org/webpage/oracle-l