master
conf 76 lines 2.25 KB
Raw
1 # you can disable an alarm notification by setting the 'to' line to: silent
2
3 alarm: 1hour_memory_hw_corrupted
4 on: mem.hwcorrupt
5 class: Errors
6 type: System
7 component: Memory
8 host labels: _os=linux
9 calc: $HardwareCorrupted
10 units: MB
11 every: 10s
12 warn: $this > 0
13 delay: down 1h multiplier 1.5 max 1h
14 summary: System corrupted memory
15 info: Amount of memory corrupted due to a hardware failure
16 to: sysadmin
17
18 ## ECC Controller
19
20 template: ecc_memory_mc_correctable
21 on: mem.edac_mc_errors
22 class: Errors
23 type: System
24 component: Memory
25 host labels: _os=linux
26 calc: $correctable + $correctable_noinfo
27 units: errors
28 every: 1m
29 warn: $this > 0
30 summary: System ECC memory ${label:controller} correctable errors
31 info: Memory controller ${label:controller} ECC correctable errors
32 to: sysadmin
33
34 template: ecc_memory_mc_uncorrectable
35 on: mem.edac_mc_errors
36 class: Errors
37 type: System
38 component: Memory
39 host labels: _os=linux
40 calc: $uncorrectable + $uncorrectable_noinfo
41 units: errors
42 every: 1m
43 crit: $this > 0
44 summary: System ECC memory ${label:controller} uncorrectable errors
45 info: Memory controller ${label:controller} ECC uncorrectable errors
46 to: sysadmin
47
48 ## ECC DIMM
49
50 template: ecc_memory_dimm_correctable
51 on: mem.edac_mc_dimm_errors
52 class: Errors
53 type: System
54 component: Memory
55 host labels: _os=linux
56 calc: $correctable
57 units: errors
58 every: 1m
59 warn: $this > 0
60 summary: System ECC memory DIMM ${label:dimm} correctable errors
61 info: DIMM ${label:dimm} controller ${label:controller} (location ${label:dimm_location}) ECC correctable errors
62 to: sysadmin
63
64 template: ecc_memory_dimm_uncorrectable
65 on: mem.edac_mc_dimm_errors
66 class: Errors
67 type: System
68 component: Memory
69 host labels: _os=linux
70 calc: $uncorrectable
71 units: errors
72 every: 1m
73 crit: $this > 0
74 summary: System ECC memory DIMM ${label:dimm} uncorrectable errors
75 info: DIMM ${label:dimm} controller ${label:controller} (location ${label:dimm_location}) ECC uncorrectable errors
76 to: sysadmin