analyzing high number of page faults
Hi,
On two of a customer's servers we see high number of page faults (~100/sec). The servers are 64 bit, running .net applications under 64 bit app pools. Both servers have enough available memory and the app pools are actually not consuming more than 2GB of RAM. Is there a way with Dynatrace to find or at least point to the area causing these page faults ?
Gil.
Page Faults are detected per host and not per process. So - the correlation between your monitored apps and the page faults is not given. Also - Page Faults can be caused by other applications running on your system that are not instrumented at all. Therefore its not possible to really detect the root cause.
The only thing you can try is to correlate these page faults with other events that you are capturing, e.g: Transaction Count, response Time, Garbage Collection. MAybe these Page Faults happen under high load or when your GC kicks in. i would build a dasboard that looks at the key performance metrics. Try to find any correlating metrics and take it from there
andi
Community Member of the Month
September 2018
Announcing Dynatrace's Community Member of the Month for September 2018, Muthu P.! Click here to read more! Employee Member of the Month
September 2018
Announcing Dynatrace's Employee Member of the Month for September 2018, Kris Z.! Click here to read more!