Quote:
Originally Posted by konsolebox
Do you mean the time the data gets updated, or the time the script takes another loop?.. For the former I think it depends on how the kernel was configured for the time it should update the data in /proc.
|
I meant my monitoring script sleep 2 seconds before taking another loop.
And sometimes the data is /proc/pid/status was updated fast, because some data got by the script are only in several seconds.
for example:
ElapsedTime VmSize VmRSS
14:08:14:487053684 31643556 3456272
14:08:28:750838950 31643556 3456272
14:08:44:595622851 31643556 3456272
14:09:00:068480514 31643556 3456272
14:09:15:089910302 31643556 3456272
14:09:31:990478795 31643556 3456272
14:09:48:008821734 31643556 3456272
14:10:02:410624899 31643556 3456272
This is the data I got this afternoon. The results were all like this , in the beginning, the period between two records are small, but it got larger when the stress of the system became very high.