3 - name: standard alerts
5 - alert: mailtest-check
7 time() - mailtest_check_last_usec > 60 * 12
11 description: '{{ $labels.instance }} mailtest-check'
12 summary: {{ $labels.instance }} mailtest-check
14 - alert: mailtest-check
16 # 42 mins: enough for a 30 min queue run plus 12
17 time() - mailtest_check_last_usec > 60 * 42
21 description: '{{ $labels.instance }} mailtest-check'
22 summary: {{ $labels.instance }} mailtest-check
26 # - alert: NodeFilesystemAlmostOutOfSpace
28 # description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has
29 # only {{ printf "%.2f" $value }}% available space left.
30 # summary: Filesystem has less than 5% space left.
33 # node_filesystem_avail_bytes{job="node",fstype!=""} / node_filesystem_size_bytes{job="node",fstype!=""} * 100 < 5
35 # node_filesystem_readonly{job="node",fstype!=""} == 0
40 # - alert: NodeFilesystemAlmostOutOfSpace
42 # description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has
43 # only {{ printf "%.2f" $value }}% available space left.
44 # summary: Filesystem has less than 3% space left.
47 # node_filesystem_avail_bytes{job="node",fstype!=""} / node_filesystem_size_bytes{job="node",fstype!=""} * 100 < 3
49 # node_filesystem_readonly{job="node",fstype!=""} == 0
54 # - alert: NodeFilesystemFilesFillingUp
56 # description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has
57 # only {{ printf "%.2f" $value }}% available inodes left and is filling up.
58 # summary: Filesystem is predicted to run out of inodes within the next 24 hours.
61 # node_filesystem_files_free{job="node",fstype!=""} / node_filesystem_files{job="node",fstype!=""} * 100 < 40
63 # predict_linear(node_filesystem_files_free{job="node",fstype!=""}[6h], 24*60*60) < 0
65 # node_filesystem_readonly{job="node",fstype!=""} == 0
70 # - alert: NodeFilesystemFilesFillingUp
72 # description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has
73 # only {{ printf "%.2f" $value }}% available inodes left and is filling up fast.
74 # summary: Filesystem is predicted to run out of inodes within the next 4 hours.
77 # node_filesystem_files_free{job="node",fstype!=""} / node_filesystem_files{job="node",fstype!=""} * 100 < 20
79 # predict_linear(node_filesystem_files_free{job="node",fstype!=""}[6h], 4*60*60) < 0
81 # node_filesystem_readonly{job="node",fstype!=""} == 0
86 # - alert: NodeFilesystemAlmostOutOfFiles
88 # description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has
89 # only {{ printf "%.2f" $value }}% available inodes left.
90 # summary: Filesystem has less than 5% inodes left.
93 # node_filesystem_files_free{job="node",fstype!=""} / node_filesystem_files{job="node",fstype!=""} * 100 < 5
95 # node_filesystem_readonly{job="node",fstype!=""} == 0
100 # - alert: NodeFilesystemAlmostOutOfFiles
102 # description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has
103 # only {{ printf "%.2f" $value }}% available inodes left.
104 # summary: Filesystem has less than 3% inodes left.
107 # node_filesystem_files_free{job="node",fstype!=""} / node_filesystem_files{job="node",fstype!=""} * 100 < 3
109 # node_filesystem_readonly{job="node",fstype!=""} == 0
114 # - alert: NodeNetworkReceiveErrs
116 # description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered
117 # {{ printf "%.0f" $value }} receive errors in the last two minutes.'
118 # summary: Network interface is reporting many receive errors.
120 # increase(node_network_receive_errs_total[2m]) > 10
124 # - alert: NodeNetworkTransmitErrs
126 # description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered
127 # {{ printf "%.0f" $value }} transmit errors in the last two minutes.'
128 # summary: Network interface is reporting many transmit errors.
130 # increase(node_network_transmit_errs_total[2m]) > 10
134 # - alert: NodeHighNumberConntrackEntriesUsed
136 # description: '{{ $value | humanizePercentage }} of conntrack entries are used'
137 # summary: Number of conntrack are getting close to the limit
139 # (node_nf_conntrack_entries / node_nf_conntrack_entries_limit) > 0.75
142 # - alert: NodeClockSkewDetected
144 # message: Clock on {{ $labels.instance }} is out of sync by more than 300s. Ensure
145 # NTP is configured correctly on this host.
146 # summary: Clock skew detected.
149 # node_timex_offset_seconds > 0.05
151 # deriv(node_timex_offset_seconds[5m]) >= 0
155 # node_timex_offset_seconds < -0.05
157 # deriv(node_timex_offset_seconds[5m]) <= 0
162 # - alert: NodeClockNotSynchronising
164 # message: Clock on {{ $labels.instance }} is not synchronising. Ensure NTP is configured
166 # summary: Clock not synchronising.
168 # min_over_time(node_timex_sync_status[5m]) == 0
173 # expr: node_systemd_version >= 300
177 # description: '{{ $labels.instance }} ianktest.'
178 # summary: Instance {{ $labels.instance }} - ianktest