12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364 |
- # you can disable an alarm notification by setting the 'to' line to: silent
- alarm: used_ram_to_ignore
- on: system.ram
- os: linux freebsd
- hosts: *
- calc: ($zfs.arc_size.arcsz = nan)?(0):($zfs.arc_size.arcsz)
- every: 10s
- info: the amount of memory that is reported as used, but it is actually capable for resizing itself based on the system needs (eg. ZFS ARC)
- alarm: ram_in_use
- on: system.ram
- os: linux
- hosts: *
- # calc: $used * 100 / ($used + $cached + $free)
- calc: ($used - $used_ram_to_ignore) * 100 / ($used - $used_ram_to_ignore + $cached + $free)
- units: %
- every: 1s
- warn: $this > 1
- crit: $this > 5
- delay: down 15m multiplier 1.5 max 1h
- info: system RAM used
- to: sysadmin #alarms
- repeat: warning 30s critical 60s
- alarm: ram_available
- on: mem.available
- os: linux
- hosts: *
- calc: ($avail + $used_ram_to_ignore) * 100 / ($system.ram.used + $system.ram.cached + $system.ram.free + $system.ram.buffers)
- units: %
- every: 10s
- warn: $this < (($status >= $WARNING) ? (15) : (10))
- crit: $this < (($status == $CRITICAL) ? (10) : ( 5))
- delay: down 15m multiplier 1.5 max 1h
- info: estimated amount of RAM available for userspace processes, without causing swapping
- to: sysadmin #alarms
- ## FreeBSD
- alarm: ram_in_use
- on: system.ram
- os: freebsd
- hosts: *
- calc: ($active + $wired + $laundry + $buffers - $used_ram_to_ignore) * 100 / ($active + $wired + $laundry + $buffers - $used_ram_to_ignore + $cache + $free + $inactive)
- units: %
- every: 10s
- warn: $this > (($status >= $WARNING) ? (80) : (90))
- crit: $this > (($status == $CRITICAL) ? (90) : (98))
- delay: down 15m multiplier 1.5 max 1h
- info: system RAM usage
- to: sysadmin #alarms
- alarm: ram_available
- on: system.ram
- os: freebsd
- hosts: *
- calc: ($free + $inactive + $used_ram_to_ignore) * 100 / ($free + $active + $inactive + $wired + $cache + $laundry + $buffers)
- units: %
- every: 10s
- warn: $this < (($status >= $WARNING) ? (15) : (10))
- crit: $this < (($status == $CRITICAL) ? (10) : ( 5))
- delay: down 15m multiplier 1.5 max 1h
- info: estimated amount of RAM available for userspace processes, without causing swapping
- to: sysadmin #alarms
|