Fault monitoring: can we share ideas?

[mgiammarco]

Hello,
I would like to monitor all my proxmox/ceph installations:
- check that backups start;
- check errors after backup run;
- check if ceph osd is down;
- check if some ha vm is in error state

I plan to use influxdb with telegraf or opendistro for elasticsearch or others.
I started with influxdb with telegraf:
- there is a proxmox plugin for telegraf;
- there is official support by ceph for influxdb and telegraf for sending metrics

After one day:
- ceph support is very undocumented/buggy/error prone
- proxmox and ceph metrics are not useful at all to quickly check for problems above

I now plan to send logs to elasticsearch then parse logs to get alerts.
Can we share some ideas/help/tricks to reach this goal?
Thanks,
Mario

 

[UdoB]

Hello,

currently I am using plain Zabbix for monitoring. (https://www.zabbix.com/)

On my Todo list is to switch to the Template discussed here: https://forum.proxmox.com/threads/zabbix-template.76058

Best regards