master
yaml 182 lines 6.9 KB
Raw
1 plugin_name: go.d.plugin
2 modules:
3 - meta:
4 id: collector-go.d.plugin-megacli
5 plugin_name: go.d.plugin
6 module_name: megacli
7 monitored_instance:
8 name: MegaCLI MegaRAID
9 link: "https://wikitech.wikimedia.org/wiki/MegaCli"
10 icon_filename: "hard-drive.svg"
11 categories:
12 - data-collection.storage
13 keywords:
14 - storage
15 - raid-controller
16 - manage-disks
17 related_resources:
18 integrations:
19 list: []
20 info_provided_to_referring_integrations:
21 description: ""
22 overview:
23 data_collection:
24 metrics_description: |
25 Monitors the health of MegaCLI Hardware RAID by tracking the status of RAID adapters, physical drives, and backup batteries in your storage system.
26 It relies on the `megacli` CLI tool but avoids directly executing the binary.
27 Instead, it utilizes `ndsudo`, a Netdata helper specifically designed to run privileged commands securely within the Netdata environment.
28 This approach eliminates the need to use `sudo`, improving security and potentially simplifying permission management.
29
30 Executed commands:
31 - `megacli -LDPDInfo -aAll -NoLog`
32 - `megacli -AdpBbuCmd -aAll -NoLog`
33 method_description: ""
34 supported_platforms:
35 include: [Linux, BSD]
36 exclude: []
37 multi_instance: false
38 additional_permissions:
39 description: ""
40 default_behavior:
41 auto_detection:
42 description: ""
43 limits:
44 description: ""
45 performance_impact:
46 description: ""
47 setup:
48 prerequisites:
49 list: []
50 configuration:
51 file:
52 name: go.d/megacli.conf
53 options:
54 description: |
55 The following options can be defined globally: update_every.
56 folding:
57 title: Config options
58 enabled: true
59 list:
60 - name: update_every
61 description: Data collection frequency.
62 default_value: 10
63 required: false
64 - name: timeout
65 description: megacli binary execution timeout.
66 default_value: 2
67 required: false
68 examples:
69 folding:
70 title: Config
71 enabled: true
72 list:
73 - name: Custom update_every
74 description: Allows you to override the default data collection interval.
75 config: |
76 jobs:
77 - name: megacli
78 update_every: 5 # Collect MegaCli Hardware RAID statistics every 5 seconds
79 troubleshooting:
80 problems:
81 list: []
82 alerts:
83 - name: megacli_adapter_health_state
84 metric: megacli.adapter_health_state
85 info: MegaCLI adapter ${label:adapter_number} is in the degraded state
86 link: https://github.com/netdata/netdata/blob/master/src/health/health.d/megacli.conf
87 - name: megacli_phys_drive_media_errors
88 metric: megacli.phys_drive_media_errors
89 info: MegaCLI physical drive adapter ${label:adapter_number} slot ${label:slot_number} media errors
90 link: https://github.com/netdata/netdata/blob/master/src/health/health.d/megacli.conf
91 - name: megacli_phys_drive_predictive_failures
92 metric: megacli.phys_drive_predictive_failures
93 info: MegaCLI physical drive (adapter ${label:adapter_number} slot ${label:slot_number}) predictive failures
94 link: https://github.com/netdata/netdata/blob/master/src/health/health.d/megacli.conf
95 - name: megacli_bbu_charge
96 metric: megacli.bbu_charge
97 info: MegaCLI Backup Battery Unit (adapter ${label:adapter_number}) average charge over the last minute
98 link: https://github.com/netdata/netdata/blob/master/src/health/health.d/megacli.conf
99 - name: megacli_bbu_recharge_cycles
100 metric: megacli.bbu_recharge_cycles
101 info: MegaCLI Backup Battery Unit (adapter ${label:adapter_number}) average charge over the last minute
102 link: https://github.com/netdata/netdata/blob/master/src/health/health.d/megacli.conf
103 metrics:
104 folding:
105 title: Metrics
106 enabled: false
107 description: ""
108 availability: []
109 scopes:
110 - name: adapter
111 description: These metrics refer to the MegaCLI Adapter.
112 labels:
113 - name: adapter_number
114 description: Adapter number
115 metrics:
116 - name: megacli.adapter_health_state
117 description: Adapter health state
118 unit: state
119 chart_type: line
120 dimensions:
121 - name: optimal
122 - name: degraded
123 - name: partially_degraded
124 - name: failed
125 - name: physical drive
126 description: These metrics refer to the MegaCLI Physical Drive.
127 labels:
128 - name: adapter_number
129 description: Adapter number
130 - name: wwn
131 description: World Wide Name
132 - name: slot_number
133 description: Slot number
134 - name: drive_position
135 description: "Position (e.g. DiskGroup: 0, Span: 0, Arm: 2)"
136 - name: drive_type
137 description: Type (e.g. SATA)
138 metrics:
139 - name: megacli.phys_drive_media_errors_rate
140 description: Physical Drive media errors rate
141 unit: errors/s
142 chart_type: line
143 dimensions:
144 - name: media_errors
145 - name: megacli.phys_drive_predictive_failures_rate
146 description: Physical Drive predictive failures rate
147 unit: failures/s
148 chart_type: line
149 dimensions:
150 - name: predictive_failures
151 - name: backup battery unit
152 description: These metrics refer to the MegaCLI Backup Battery Unit.
153 labels:
154 - name: adapter_number
155 description: Adapter number
156 - name: battery_type
157 description: Battery type (e.g. BBU)
158 metrics:
159 - name: megacli.bbu_charge
160 description: BBU relative charge
161 unit: percentage
162 chart_type: area
163 dimensions:
164 - name: charge
165 - name: megacli.bbu_recharge_cycles
166 description: BBU relative charge
167 unit: cycles
168 chart_type: line
169 dimensions:
170 - name: recharge
171 - name: megacli.bbu_capacity_degradation
172 description: BBU capacity degradation
173 unit: percent
174 chart_type: area
175 dimensions:
176 - name: cap_degradation
177 - name: megacli.bbu_temperature
178 description: BBU bbu_temperature
179 unit: Celsius
180 chart_type: line
181 dimensions:
182 - name: temperature