health: add collector prefix to the external collectors alarms/templates (#10830)
Ilya Mashchenko committed
Mar 22, 2021 at 17:30 UTC
48e0dc53a25354f459294fd60b63307174b19aa2
14 files changed
+66
-67
collectors/python.d.plugin/adaptec_raid/adaptec_raid.chart.py
+4
-4
@@ -24,21 +24,21 @@ ORDER = [
24
CHARTS = {
25
'ld_status': {
26
'options': [None, 'Status of logical devices (1: Failed or Degraded)', 'bool', 'logical devices',
27
- 'adapter_raid.ld_status', 'line'],
27
+ 'adaptec_raid.ld_status', 'line'],
28
'lines': []
29
},
30
'pd_state': {
31
'options': [None, 'State of physical devices (1: not Online)', 'bool', 'physical devices',
32
- 'adapter_raid.pd_state', 'line'],
32
+ 'adaptec_raid.pd_state', 'line'],
33
'lines': []
34
},
35
'pd_smart_warnings': {
36
'options': [None, 'S.M.A.R.T warnings', 'count', 'physical devices',
37
- 'adapter_raid.smart_warnings', 'line'],
37
+ 'adaptec_raid.smart_warnings', 'line'],
38
'lines': []
39
},
40
'pd_temperature': {
41
- 'options': [None, 'Temperature', 'celsius', 'physical devices', 'adapter_raid.temperature', 'line'],
41
+ 'options': [None, 'Temperature', 'celsius', 'physical devices', 'adaptec_raid.temperature', 'line'],
42
'lines': []
43
},
44
}
health/health.d/adaptec_raid.conf
+4
-4
@@ -1,8 +1,8 @@
1
2
# logical device status check
3
4
-template: adapter_raid_ld_status
5
- on: adapter_raid.ld_status
4
+template: adaptec_raid_ld_status
5
+ on: adaptec_raid.ld_status
6
lookup: max -10s foreach *
7
units: bool
8
every: 10s
@@ -13,8 +13,8 @@ template: adapter_raid_ld_status
13
14
# physical device state check
15
16
-template: adapter_raid_pd_state
17
- on: adapter_raid.pd_state
16
+template: adaptec_raid_pd_state
17
+ on: adaptec_raid.pd_state
18
lookup: max -10s foreach *
19
units: bool
20
every: 10s
health/health.d/anomalies.conf
+2
-2
@@ -1,6 +1,6 @@
1
# raise a warning alarm if an anomaly probability is consistently above 50%
2
3
-template: anomaly_probabilities
3
+template: anomalies_anomaly_probabilities
4
on: anomalies.probability
5
lookup: average -2m foreach *
6
every: 1m
@@ -9,7 +9,7 @@ template: anomaly_probabilities
9
10
# raise a warning alarm if an anomaly flag is consistently firing
11
12
-template: anomaly_flags
12
+template: anomalies_anomaly_flags
13
on: anomalies.anomaly
14
lookup: sum -2m foreach *
15
every: 1m
health/health.d/apcupsd.conf
+2
-2
@@ -1,6 +1,6 @@
1
# you can disable an alarm notification by setting the 'to' line to: silent
2
3
-template: 10min_ups_load
3
+template: apcupsd_10min_ups_load
4
on: apcupsd.load
5
os: *
6
hosts: *
@@ -15,7 +15,7 @@ template: 10min_ups_load
15
16
# Discussion in https://github.com/netdata/netdata/pull/3928:
17
# Fire the alarm as soon as it's going on battery (99% charge) and clear only when full.
18
-template: ups_charge
18
+template: apcupsd_ups_charge
19
on: apcupsd.charge
20
os: *
21
hosts: *
health/health.d/beanstalkd.conf
+3
-3
@@ -1,6 +1,6 @@
1
# get the number of buried jobs in all queues
2
3
-template: server_buried_jobs
3
+template: beanstalk_server_buried_jobs
4
on: beanstalk.current_jobs
5
calc: $buried
6
units: jobs
@@ -13,7 +13,7 @@ template: server_buried_jobs
13
14
# get the number of buried jobs per queue
15
16
-#template: tube_buried_jobs
16
+#template: beanstalk_tube_buried_jobs
17
# on: beanstalk.jobs
18
# calc: $buried
19
# units: jobs
@@ -26,7 +26,7 @@ template: server_buried_jobs
26
27
# get the current number of tubes
28
29
-#template: number_of_tubes
29
+#template: beanstalk_number_of_tubes
30
# on: beanstalk.current_tubes
31
# calc: $tubes
32
# every: 10s
health/health.d/ceph.conf
+1
-1
@@ -1,6 +1,6 @@
1
# low ceph disk available
2
3
-template: cluster_space_usage
3
+template: ceph_cluster_space_usage
4
on: ceph.general_usage
5
calc: $used * 100 / ($used + $avail)
6
units: %
health/health.d/fping.conf
+3
-4
@@ -11,7 +11,7 @@ families: *
11
info: number of seconds since the last successful data collection
12
to: sysadmin
13
14
-template: host_reachable
14
+template: fping_host_reachable
15
families: *
16
on: fping.latency
17
calc: $average != nan
@@ -22,7 +22,7 @@ families: *
22
delay: down 30m multiplier 1.5 max 2h
23
to: sysadmin
24
25
-template: host_latency
25
+template: fping_host_latency
26
families: *
27
on: fping.latency
28
lookup: average -10s unaligned of average
@@ -36,7 +36,7 @@ families: *
36
delay: down 30m multiplier 1.5 max 2h
37
to: sysadmin
38
39
-template: packet_loss
39
+template: fping_packet_loss
40
families: *
41
on: fping.quality
42
lookup: average -10m unaligned of returned
@@ -50,4 +50,3 @@ families: *
50
info: packet loss percentage
51
delay: down 30m multiplier 1.5 max 2h
52
to: sysadmin
53
-
health/health.d/httpcheck.conf
+13
-13
@@ -11,7 +11,7 @@ families: *
11
to: sysadmin
12
13
# This is a fast-reacting no-notification alarm ideal for custom dashboards or badges
14
-template: web_service_up
14
+template: httpcheck_web_service_up
15
families: *
16
on: httpcheck.status
17
lookup: average -1m unaligned percentage of success
@@ -21,7 +21,7 @@ families: *
21
info: at least 75% verified responses during last 60 seconds, ideal for badges
22
to: silent
23
24
-template: web_service_bad_content
24
+template: httpcheck_web_service_bad_content
25
families: *
26
on: httpcheck.status
27
lookup: average -5m unaligned percentage of bad_content
@@ -34,7 +34,7 @@ families: *
34
options: no-clear-notification
35
to: webmaster
36
37
-template: web_service_bad_status
37
+template: httpcheck_web_service_bad_status
38
families: *
39
on: httpcheck.status
40
lookup: average -5m unaligned percentage of bad_status
@@ -47,7 +47,7 @@ families: *
47
options: no-clear-notification
48
to: webmaster
49
50
-template: web_service_timeouts
50
+template: httpcheck_web_service_timeouts
51
families: *
52
on: httpcheck.status
53
lookup: average -5m unaligned percentage of timeout
@@ -55,7 +55,7 @@ families: *
55
units: %
56
info: average of timeouts during the last 5 minutes
57
58
-template: no_web_service_connections
58
+template: httpcheck_no_web_service_connections
59
families: *
60
on: httpcheck.status
61
lookup: average -5m unaligned percentage of no_connection
@@ -64,20 +64,20 @@ families: *
64
info: average of failed requests during the last 5 minutes
65
66
# combined timeout & no connection alarm
67
-template: web_service_unreachable
67
+template: httpcheck_web_service_unreachable
68
families: *
69
on: httpcheck.status
70
- calc: ($no_web_service_connections >= $web_service_timeouts) ? ($no_web_service_connections) : ($web_service_timeouts)
70
+ calc: ($httpcheck_no_web_service_connections >= $httpcheck_web_service_timeouts) ? ($httpcheck_no_web_service_connections) : ($httpcheck_web_service_timeouts)
71
units: %
72
every: 10s
73
- warn: ($no_web_service_connections >= 10 OR $web_service_timeouts >= 10) AND ($no_web_service_connections < 40 OR $web_service_timeouts < 40)
74
- crit: $no_web_service_connections >= 40 OR $web_service_timeouts >= 40
73
+ warn: ($httpcheck_no_web_service_connections >= 10 OR $httpcheck_web_service_timeouts >= 10) AND ($httpcheck_no_web_service_connections < 40 OR $httpcheck_web_service_timeouts < 40)
74
+ crit: $httpcheck_no_web_service_connections >= 40 OR $httpcheck_web_service_timeouts >= 40
75
delay: down 5m multiplier 1.5 max 1h
76
info: average of failed requests either due to timeouts or no connection during the last 5 minutes
77
options: no-clear-notification
78
to: webmaster
79
80
-template: 1h_web_service_response_time
80
+template: httpcheck_1h_web_service_response_time
81
families: *
82
on: httpcheck.responsetime
83
lookup: average -1h unaligned of time
@@ -85,14 +85,14 @@ families: *
85
units: ms
86
info: average response time over the last hour
87
88
-template: web_service_slow
88
+template: httpcheck_web_service_slow
89
families: *
90
on: httpcheck.responsetime
91
lookup: average -3m unaligned of time
92
units: ms
93
every: 10s
94
- warn: ($this > ($1h_web_service_response_time * 2) )
95
- crit: ($this > ($1h_web_service_response_time * 3) )
94
+ warn: ($this > ($httpcheck_1h_web_service_response_time * 2) )
95
+ crit: ($this > ($httpcheck_1h_web_service_response_time * 3) )
96
info: average response time over the last 3 minutes, compared to the average over the last hour
97
delay: down 5m multiplier 1.5 max 1h
98
options: no-clear-notification
health/health.d/ioping.conf
+1
-1
@@ -1,4 +1,4 @@
1
-template: disk_latency
1
+template: ioping_disk_latency
2
families: *
3
on: ioping.latency
4
lookup: average -10s unaligned of average
health/health.d/kubelet.conf
+11
-11
@@ -4,7 +4,7 @@
4
5
# True (1) if the node is experiencing a configuration-related error, false (0) otherwise.
6
7
- template: node_config_error
7
+ template: kubelet_node_config_error
8
on: k8s_kubelet.kubelet_node_config_error
9
calc: $kubelet_node_config_error
10
units: bool
@@ -16,7 +16,7 @@
16
17
# Failed Token() requests to the alternate token source
18
19
- template: token_requests
19
+ template: kubelet_token_requests
20
lookup: sum -10s of token_fail_count
21
on: k8s_kubelet.kubelet_token_requests
22
units: failed requests
@@ -53,17 +53,17 @@
53
54
# quantile 0.5
55
56
-template: 1m_kubelet_pleg_relist_latency_quantile_05
56
+template: kubelet_1m_pleg_relist_latency_quantile_05
57
on: k8s_kubelet.kubelet_pleg_relist_latency_microseconds
58
lookup: average -1m unaligned of kubelet_pleg_relist_latency_05
59
units: microseconds
60
every: 10s
61
info: the average value of pleg relisting latency during the last minute (quantile 0.5)
62
63
-template: 10s_kubelet_pleg_relist_latency_quantile_05
63
+template: kubelet_10s_pleg_relist_latency_quantile_05
64
on: k8s_kubelet.kubelet_pleg_relist_latency_microseconds
65
lookup: average -10s unaligned of kubelet_pleg_relist_latency_05
66
- calc: $this * 100 / (($1m_kubelet_pleg_relist_latency_quantile_05 < 1000)?(1000):($1m_kubelet_pleg_relist_latency_quantile_05))
66
+ calc: $this * 100 / (($kubelet_1m_pleg_relist_latency_quantile_05 < 1000)?(1000):($kubelet_1m_pleg_relist_latency_quantile_05))
67
every: 10s
68
units: %
69
warn: $this > (($status >= $WARNING)?(100):(200))
@@ -74,17 +74,17 @@ template: 10s_kubelet_pleg_relist_latency_quantile_05
74
75
# quantile 0.9
76
77
-template: 1m_kubelet_pleg_relist_latency_quantile_09
77
+template: kubelet_1m_pleg_relist_latency_quantile_09
78
on: k8s_kubelet.kubelet_pleg_relist_latency_microseconds
79
lookup: average -1m unaligned of kubelet_pleg_relist_latency_09
80
units: microseconds
81
every: 10s
82
info: the average value of pleg relisting latency during the last minute (quantile 0.9)
83
84
-template: 10s_kubelet_pleg_relist_latency_quantile_09
84
+template: kubelet_10s_pleg_relist_latency_quantile_09
85
on: k8s_kubelet.kubelet_pleg_relist_latency_microseconds
86
lookup: average -10s unaligned of kubelet_pleg_relist_latency_09
87
- calc: $this * 100 / (($1m_kubelet_pleg_relist_latency_quantile_09 < 1000)?(1000):($1m_kubelet_pleg_relist_latency_quantile_09))
87
+ calc: $this * 100 / (($kubelet_1m_pleg_relist_latency_quantile_09 < 1000)?(1000):($kubelet_1m_pleg_relist_latency_quantile_09))
88
every: 10s
89
units: %
90
warn: $this > (($status >= $WARNING)?(200):(400))
@@ -95,17 +95,17 @@ template: 10s_kubelet_pleg_relist_latency_quantile_09
95
96
# quantile 0.99
97
98
-template: 1m_kubelet_pleg_relist_latency_quantile_099
98
+template: kubelet_1m_pleg_relist_latency_quantile_099
99
on: k8s_kubelet.kubelet_pleg_relist_latency_microseconds
100
lookup: average -1m unaligned of kubelet_pleg_relist_latency_099
101
units: microseconds
102
every: 10s
103
info: the average value of pleg relisting latency during the last minute (quantile 0.99)
104
105
-template: 10s_kubelet_pleg_relist_latency_quantile_099
105
+template: kubelet_10s_pleg_relist_latency_quantile_099
106
on: k8s_kubelet.kubelet_pleg_relist_latency_microseconds
107
lookup: average -10s unaligned of kubelet_pleg_relist_latency_099
108
- calc: $this * 100 / (($1m_kubelet_pleg_relist_latency_quantile_099 < 1000)?(1000):($1m_kubelet_pleg_relist_latency_quantile_099))
108
+ calc: $this * 100 / (($kubelet_1m_pleg_relist_latency_quantile_099 < 1000)?(1000):($kubelet_1m_pleg_relist_latency_quantile_099))
109
every: 10s
110
units: %
111
warn: $this > (($status >= $WARNING)?(400):(800))
health/health.d/megacli.conf
+5
-5
@@ -1,4 +1,4 @@
1
-template: adapter_state
1
+template: megacli_adapter_state
2
on: megacli.adapter_degraded
3
units: is degraded
4
lookup: sum -10s
@@ -7,7 +7,7 @@ template: adapter_state
7
info: adapter state
8
to: sysadmin
9
10
-template: bbu_relative_charge
10
+template: megacli_bbu_relative_charge
11
on: megacli.bbu_relative_charge
12
units: percent
13
lookup: average -10s
@@ -17,7 +17,7 @@ template: bbu_relative_charge
17
info: BBU relative state of charge
18
to: sysadmin
19
20
-template: bbu_cycle_count
20
+template: megacli_bbu_cycle_count
21
on: megacli.bbu_cycle_count
22
units: cycle count
23
lookup: average -10s
@@ -27,7 +27,7 @@ template: bbu_cycle_count
27
info: BBU cycle count
28
to: sysadmin
29
30
-template: pd_media_errors
30
+template: megacli_pd_media_errors
31
on: megacli.pd_media_error
32
units: media errors
33
lookup: sum -10s
@@ -37,7 +37,7 @@ template: pd_media_errors
37
info: physical drive media errors
38
to: sysadmin
39
40
-template: pd_predictive_failures
40
+template: megacli_pd_predictive_failures
41
on: megacli.pd_predictive_failure
42
units: predictive failures
43
lookup: sum -10s
health/health.d/memcached.conf
+3
-3
@@ -29,7 +29,7 @@ template: memcached_cache_memory_usage
29
30
# find the rate memcached cache is filling
31
32
-template: cache_fill_rate
32
+template: memcached_cache_fill_rate
33
on: memcached.cache
34
lookup: min -10m at -50m unaligned of available
35
calc: ($this - $available) / (($now - $after) / 3600)
@@ -40,9 +40,9 @@ template: cache_fill_rate
40
41
# find the hours remaining until memcached cache is full
42
43
-template: out_of_cache_space_time
43
+template: memcached_out_of_cache_space_time
44
on: memcached.cache
45
- calc: ($cache_fill_rate > 0) ? ($available / $cache_fill_rate) : (inf)
45
+ calc: ($memcached_cache_fill_rate > 0) ? ($available / $memcached_cache_fill_rate) : (inf)
46
units: hours
47
every: 10s
48
warn: $this > 0 and $this < (($status >= $WARNING) ? (48) : (8))
health/health.d/portcheck.conf
+3
-3
@@ -11,7 +11,7 @@ families: *
11
to: sysadmin
12
13
# This is a fast-reacting no-notification alarm ideal for custom dashboards or badges
14
-template: service_reachable
14
+template: portcheck_service_reachable
15
families: *
16
on: portcheck.status
17
lookup: average -1m unaligned percentage of success
@@ -21,7 +21,7 @@ families: *
21
info: at least 75% successful connections during last 60 seconds, ideal for badges
22
to: silent
23
24
-template: connection_timeouts
24
+template: portcheck_connection_timeouts
25
families: *
26
on: portcheck.status
27
lookup: average -5m unaligned percentage of timeout
@@ -33,7 +33,7 @@ families: *
33
info: average of timeouts during the last 5 minutes
34
to: sysadmin
35
36
-template: connection_fails
36
+template: portcheck_connection_fails
37
families: *
38
on: portcheck.status
39
lookup: average -5m unaligned percentage of no_connection,failed
health/health.d/riakkv.conf
+11
-11
@@ -1,5 +1,5 @@
1
# Ensure that Riak is running. template: riak_last_collected_secs
2
-template: riak_last_collected_secs
2
+template: riakkv_last_collected_secs
3
on: riak.kv.throughput
4
calc: $now - $last_collected_t
5
units: seconds ago
@@ -11,7 +11,7 @@ template: riak_last_collected_secs
11
to: dba
12
13
# Warn if a list keys operation is running.
14
-template: riak_list_keys_active
14
+template: riakkv_list_keys_active
15
on: riak.core.fsm_active
16
calc: $list_fsm_active
17
units: state machines
@@ -23,7 +23,7 @@ template: riak_list_keys_active
23
24
## Timing healthchecks
25
# KV GET
26
-template: 1h_kv_get_mean_latency
26
+template: riakkv_1h_kv_get_mean_latency
27
on: riak.kv.latency.get
28
calc: $node_get_fsm_time_mean
29
lookup: average -1h unaligned of time
@@ -31,20 +31,20 @@ template: 1h_kv_get_mean_latency
31
units: ms
32
info: mean average KV GET latency over the last hour
33
34
-template: riak_kv_get_slow
34
+template: riakkv_kv_get_slow
35
on: riak.kv.latency.get
36
calc: $mean
37
lookup: average -3m unaligned of time
38
units: ms
39
every: 10s
40
- warn: ($this > ($1h_kv_get_mean_latency * 2) )
41
- crit: ($this > ($1h_kv_get_mean_latency * 3) )
40
+ warn: ($this > ($riakkv_1h_kv_get_mean_latency * 2) )
41
+ crit: ($this > ($riakkv_1h_kv_get_mean_latency * 3) )
42
info: average KV GET time over the last 3 minutes, compared to the average over the last hour
43
delay: down 5m multiplier 1.5 max 1h
44
to: dba
45
46
# KV PUT
47
-template: 1h_kv_put_mean_latency
47
+template: riakkv_1h_kv_put_mean_latency
48
on: riak.kv.latency.put
49
calc: $node_put_fsm_time_mean
50
lookup: average -1h unaligned of time
@@ -52,14 +52,14 @@ template: 1h_kv_put_mean_latency
52
units: ms
53
info: mean average KV PUT latency over the last hour
54
55
-template: riak_kv_put_slow
55
+template: riakkv_kv_put_slow
56
on: riak.kv.latency.put
57
calc: $mean
58
lookup: average -3m unaligned of time
59
units: ms
60
every: 10s
61
- warn: ($this > ($1h_kv_put_mean_latency * 2) )
62
- crit: ($this > ($1h_kv_put_mean_latency * 3) )
61
+ warn: ($this > ($riakkv_1h_kv_put_mean_latency * 2) )
62
+ crit: ($this > ($riakkv_1h_kv_put_mean_latency * 3) )
63
info: average KV PUT time over the last 3 minutes, compared to the average over the last hour
64
delay: down 5m multiplier 1.5 max 1h
65
to: dba
@@ -69,7 +69,7 @@ template: riak_kv_put_slow
69
70
# Default Erlang VM process limit: 262144
71
# On systems observed, this is < 2000, but may grow depending on load.
72
-template: riak_vm_high_process_count
72
+template: riakkv_vm_high_process_count
73
on: riak.vm
74
calc: $sys_process_count
75
units: processes