| 1234567891011121314151617181920212223242526272829303132333435363738394041424344454647 |
- # you can disable an alarm notification by setting the 'to' line to: silent
- alarm: 1hour_ecc_memory_correctable
- on: mem.ecc_ce
- class: Errors
- type: System
- component: Memory
- os: linux
- hosts: *
- lookup: sum -10m unaligned
- units: errors
- every: 1m
- warn: $this > 0
- delay: down 1h multiplier 1.5 max 1h
- info: number of ECC correctable errors in the last 10 minutes
- to: sysadmin
- alarm: 1hour_ecc_memory_uncorrectable
- on: mem.ecc_ue
- class: Errors
- type: System
- component: Memory
- os: linux
- hosts: *
- lookup: sum -10m unaligned
- units: errors
- every: 1m
- crit: $this > 0
- delay: down 1h multiplier 1.5 max 1h
- info: number of ECC uncorrectable errors in the last 10 minutes
- to: sysadmin
- alarm: 1hour_memory_hw_corrupted
- on: mem.hwcorrupt
- class: Errors
- type: System
- component: Memory
- os: linux
- hosts: *
- calc: $HardwareCorrupted
- units: MB
- every: 10s
- warn: $this > 0
- delay: down 1h multiplier 1.5 max 1h
- info: amount of memory corrupted due to a hardware failure
- to: sysadmin
|
