hi all,
i'm trying to monitor a smallish group of debian servers, with a web/postgresql app.
we're trying to figure out why users of the app feel it's sluggish.
cpu load and utilization is very low all the time, across all servers.
using htop, it seems that the way the app is written, we're saturating some cores on some machines for a few seconds at a time, and that it may be those seconds that make users feel the app is sluggish. (even though there are always quite a few cores doing nothing)
what would be the best way to show this in zabbix ?
i guess that a graph for each server with cores separate would be better than what i have so far, but what i really need to know is how often cores are staying at 100% a few seconds at a time.
many thanks for your help,
itsme
i'm trying to monitor a smallish group of debian servers, with a web/postgresql app.
we're trying to figure out why users of the app feel it's sluggish.
cpu load and utilization is very low all the time, across all servers.
using htop, it seems that the way the app is written, we're saturating some cores on some machines for a few seconds at a time, and that it may be those seconds that make users feel the app is sluggish. (even though there are always quite a few cores doing nothing)
what would be the best way to show this in zabbix ?
i guess that a graph for each server with cores separate would be better than what i have so far, but what i really need to know is how often cores are staying at 100% a few seconds at a time.
many thanks for your help,
itsme