So, I'm following up my own question. The current answer that solves the current problem is to set swappiness to 0. Basically, in this environment, if any of Oracle's data space gets swapped out in preference to filesystem cache, there is a positive feedback with the application that causes everything to melt down.
Unfortunately, the DBAs are highly resistant to trying things like Huge Pages or ASM, so the fixes need to happen on the OS side. -- Matt It's not what I know that counts. It's what I can remember in time to use. _______________________________________________ Tech mailing list [email protected] http://lopsa.org/cgi-bin/mailman/listinfo/tech This list provided by the League of Professional System Administrators http://lopsa.org/
