12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485 |
- # you can disable an alarm notification by setting the 'to' line to: silent
- 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
- summary: System corrupted memory
- info: Amount of memory corrupted due to a hardware failure
- to: sysadmin
- ## ECC Controller
- template: ecc_memory_mc_correctable
- on: mem.edac_mc
- class: Errors
- type: System
- component: Memory
- os: linux
- hosts: *
- lookup: sum -10m unaligned of correctable, correctable_noinfo
- units: errors
- every: 1m
- warn: $this > 0
- delay: down 1h multiplier 1.5 max 1h
- summary: System ECC memory ${label:controller} correctable errors
- info: Memory controller ${label:controller} ECC correctable errors in the last 10 minutes
- to: sysadmin
- template: ecc_memory_mc_uncorrectable
- on: mem.edac_mc
- class: Errors
- type: System
- component: Memory
- os: linux
- hosts: *
- lookup: sum -10m unaligned of uncorrectable,uncorrectable_noinfo
- units: errors
- every: 1m
- crit: $this > 0
- delay: down 1h multiplier 1.5 max 1h
- summary: System ECC memory ${label:controller} uncorrectable errors
- info: Memory controller ${label:controller} ECC uncorrectable errors in the last 10 minutes
- to: sysadmin
- ## ECC DIMM
- template: ecc_memory_dimm_correctable
- on: mem.edac_mc_dimm
- class: Errors
- type: System
- component: Memory
- os: linux
- hosts: *
- lookup: sum -10m unaligned of correctable
- units: errors
- every: 1m
- warn: $this > 0
- delay: down 1h multiplier 1.5 max 1h
- summary: System ECC memory DIMM ${label:dimm} correctable errors
- info: DIMM ${label:dimm} controller ${label:controller} (location ${label:dimm_location}) ECC correctable errors in the last 10 minutes
- to: sysadmin
- template: ecc_memory_dimm_uncorrectable
- on: mem.edac_mc_dimm
- class: Errors
- type: System
- component: Memory
- os: linux
- hosts: *
- lookup: sum -10m unaligned of uncorrectable
- units: errors
- every: 1m
- crit: $this > 0
- delay: down 1h multiplier 1.5 max 1h
- summary: System ECC memory DIMM ${label:dimm} uncorrectable errors
- info: DIMM ${label:dimm} controller ${label:controller} (location ${label:dimm_location}) ECC uncorrectable errors in the last 10 minutes
- to: sysadmin
|