Add summary to alerts configurations (#16129)
* add to web log alerts * add more * more adds * more adds * more * more * more * more * more * more * more * more * updates --------- Co-authored-by: ilyam8 <ilya@netdata.cloud>
Emmanuel Vasilakis committed
Oct 6, 2023 at 00:57 UTC
c317e4d380413109708a8b86b93e16514f8148bc
67 files changed
+339
-247
health/health.d/adaptec_raid.conf
+4
-2
@@ -11,7 +11,8 @@ component: RAID
11
every: 10s
12
crit: $this > 0
13
delay: down 5m multiplier 1.5 max 1h
14
- info: logical device status is failed or degraded
14
+ summary: Adaptec raid logical device status
15
+ info: Logical device status is failed or degraded
16
to: sysadmin
17
18
# physical device state check
@@ -26,5 +27,6 @@ component: RAID
27
every: 10s
28
crit: $this > 0
29
delay: down 5m multiplier 1.5 max 1h
29
- info: physical device state is not online
30
+ summary: Adaptec raid physical device state
31
+ info: Physical device state is not online
32
to: sysadmin
health/health.d/apcupsd.conf
+6
-3
@@ -12,7 +12,8 @@ component: UPS
12
every: 1m
13
warn: $this > (($status >= $WARNING) ? (70) : (80))
14
delay: down 10m multiplier 1.5 max 1h
15
- info: average UPS load over the last 10 minutes
15
+ summary: APC UPS load
16
+ info: APC UPS average load over the last 10 minutes
17
to: sitemgr
18
19
# Discussion in https://github.com/netdata/netdata/pull/3928:
@@ -30,7 +31,8 @@ component: UPS
31
warn: $this < 100
32
crit: $this < 40
33
delay: down 10m multiplier 1.5 max 1h
33
- info: average UPS charge over the last minute
34
+ summary: APC UPS battery charge
35
+ info: APC UPS average battery charge over the last minute
36
to: sitemgr
37
38
template: apcupsd_last_collected_secs
@@ -43,5 +45,6 @@ component: UPS device
45
units: seconds ago
46
warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
47
delay: down 5m multiplier 1.5 max 1h
46
- info: number of seconds since the last successful data collection
48
+ summary: APC UPS last collection
49
+ info: APC UPS number of seconds since the last successful data collection
50
to: sitemgr
health/health.d/bcache.conf
+4
-2
@@ -9,7 +9,8 @@ component: Disk
9
every: 1m
10
warn: $this > 0
11
delay: up 2m down 1h multiplier 1.5 max 2h
12
- info: number of times data was read from the cache, \
12
+ summary: Bcache cache read race errors
13
+ info: Number of times data was read from the cache, \
14
the bucket was reused and invalidated in the last 10 minutes \
15
(when this occurs the data is reread from the backing device)
16
to: silent
@@ -24,6 +25,7 @@ component: Disk
25
every: 1m
26
warn: $this > 75
27
delay: up 1m down 1h multiplier 1.5 max 2h
27
- info: percentage of cache space used for dirty data and metadata \
28
+ summary: Bcache cache used space
29
+ info: Percentage of cache space used for dirty data and metadata \
30
(this usually means your SSD cache is too small)
31
to: silent
health/health.d/beanstalkd.conf
+2
-1
@@ -10,7 +10,8 @@ component: Beanstalk
10
every: 10s
11
warn: $this > 3
12
delay: up 0 down 5m multiplier 1.2 max 1h
13
- info: number of buried jobs across all tubes. \
13
+ summary: Beanstalk buried jobs
14
+ info: Number of buried jobs across all tubes. \
15
You need to manually kick them so they can be processed. \
16
Presence of buried jobs in a tube does not affect new jobs.
17
to: sysadmin
health/health.d/bind_rndc.conf
+1
@@ -7,5 +7,6 @@ component: BIND
7
every: 60
8
calc: $stats_size
9
warn: $this > 512
10
+ summary: BIND statistics file size
11
info: BIND statistics-file size
12
to: sysadmin
health/health.d/boinc.conf
+8
-4
@@ -13,7 +13,8 @@ component: BOINC
13
every: 1m
14
warn: $this > 0
15
delay: up 1m down 5m multiplier 1.5 max 1h
16
- info: average number of compute errors over the last 10 minutes
16
+ summary: BOINC compute errors
17
+ info: Average number of compute errors over the last 10 minutes
18
to: sysadmin
19
20
# Warn on lots of upload errors
@@ -29,7 +30,8 @@ component: BOINC
30
every: 1m
31
warn: $this > 0
32
delay: up 1m down 5m multiplier 1.5 max 1h
32
- info: average number of failed uploads over the last 10 minutes
33
+ summary: BOINC failed uploads
34
+ info: Average number of failed uploads over the last 10 minutes
35
to: sysadmin
36
37
# Warn on the task queue being empty
@@ -45,7 +47,8 @@ component: BOINC
47
every: 1m
48
warn: $this < 1
49
delay: up 5m down 10m multiplier 1.5 max 1h
48
- info: average number of total tasks over the last 10 minutes
50
+ summary: BOINC total tasks
51
+ info: Average number of total tasks over the last 10 minutes
52
to: sysadmin
53
54
# Warn on no active tasks with a non-empty queue
@@ -62,5 +65,6 @@ component: BOINC
65
every: 1m
66
warn: $this < 1
67
delay: up 5m down 10m multiplier 1.5 max 1h
65
- info: average number of active tasks over the last 10 minutes
68
+ summary: BOINC active tasks
69
+ info: Average number of active tasks over the last 10 minutes
70
to: sysadmin
health/health.d/btrfs.conf
+2
-2
@@ -11,7 +11,7 @@ component: File system
11
every: 10s
12
warn: $this > (($status == $CRITICAL) ? (95) : (98))
13
delay: up 1m down 15m multiplier 1.5 max 1h
14
- summary: BTRFS space allocated
14
+ summary: BTRFS allocated space utilization
15
info: Percentage of allocated BTRFS physical disk space
16
to: silent
17
@@ -28,7 +28,7 @@ component: File system
28
warn: $this > (($status >= $WARNING) ? (90) : (95)) && $btrfs_allocated > 98
29
crit: $this > (($status == $CRITICAL) ? (95) : (98)) && $btrfs_allocated > 98
30
delay: up 1m down 15m multiplier 1.5 max 1h
31
- summary: BTRFS space utilization
31
+ summary: BTRFS data space utilization
32
info: Utilization of BTRFS data space
33
to: sysadmin
34
health/health.d/ceph.conf
+2
-1
@@ -11,5 +11,6 @@ component: Ceph
11
warn: $this > (($status >= $WARNING ) ? (85) : (90))
12
crit: $this > (($status == $CRITICAL) ? (90) : (98))
13
delay: down 5m multiplier 1.2 max 1h
14
- info: cluster disk space utilization
14
+ summary: Ceph cluster disk space utilization
15
+ info: Ceph cluster disk space utilization
16
to: sysadmin
health/health.d/cgroups.conf
+6
-79
@@ -13,8 +13,8 @@ component: CPU
13
every: 1m
14
warn: $this > (($status == $CRITICAL) ? (85) : (95))
15
delay: down 15m multiplier 1.5 max 1h
16
- summary: Cgroup CPU utilization
17
- info: Average cgroup CPU utilization over the last 10 minutes
16
+ summary: Cgroup ${label:cgroup_name} CPU utilization
17
+ info: Cgroup ${label:cgroup_name} average CPU utilization over the last 10 minutes
18
to: silent
19
20
template: cgroup_ram_in_use
@@ -30,47 +30,10 @@ component: Memory
30
warn: $this > (($status >= $WARNING) ? (80) : (90))
31
crit: $this > (($status == $CRITICAL) ? (90) : (98))
32
delay: down 15m multiplier 1.5 max 1h
33
- summary: Cgroup ram utilization
34
- info: Cgroup memory utilization
33
+ summary: Cgroup ${label:cgroup_name} memory utilization
34
+ info: Cgroup ${label:cgroup_name} memory utilization
35
to: silent
36
37
-# FIXME COMMENTED DUE TO A BUG IN NETDATA
38
-## -----------------------------------------------------------------------------
39
-## check for packet storms
40
-#
41
-## 1. calculate the rate packets are received in 1m: 1m_received_packets_rate
42
-## 2. do the same for the last 10s
43
-## 3. raise an alarm if the later is 10x or 20x the first
44
-## we assume the minimum packet storm should at least have
45
-## 10000 packets/s, average of the last 10 seconds
46
-#
47
-# template: cgroup_1m_received_packets_rate
48
-# on: cgroup.net_packets
49
-# class: Workload
50
-# type: Cgroups
51
-#component: Network
52
-# hosts: *
53
-# lookup: average -1m unaligned of received
54
-# units: packets
55
-# every: 10s
56
-# info: average number of packets received by the network interface ${label:device} over the last minute
57
-#
58
-# template: cgroup_10s_received_packets_storm
59
-# on: cgroup.net_packets
60
-# class: Workload
61
-# type: Cgroups
62
-#component: Network
63
-# hosts: *
64
-# lookup: average -10s unaligned of received
65
-# calc: $this * 100 / (($1m_received_packets_rate < 1000)?(1000):($1m_received_packets_rate))
66
-# every: 10s
67
-# units: %
68
-# warn: $this > (($status >= $WARNING)?(200):(5000))
69
-# options: no-clear-notification
70
-# info: ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, \
71
-# compared to the rate over the last minute
72
-# to: sysadmin
73
-#
37
# ---------------------------------K8s containers--------------------------------------------
38
39
template: k8s_cgroup_10min_cpu_usage
@@ -85,7 +48,7 @@ component: CPU
48
every: 1m
49
warn: $this > (($status >= $WARNING) ? (75) : (85))
50
delay: down 15m multiplier 1.5 max 1h
88
- summary: Container ${label:k8s_container_name} CPU utilization
51
+ summary: Container ${label:k8s_container_name} pod ${label:k8s_pod_name} CPU utilization
52
info: Container ${label:k8s_container_name} of pod ${label:k8s_pod_name} of namespace ${label:k8s_namespace}, \
53
average CPU utilization over the last 10 minutes
54
to: silent
@@ -103,43 +66,7 @@ component: Memory
66
warn: $this > (($status >= $WARNING) ? (80) : (90))
67
crit: $this > (($status == $CRITICAL) ? (90) : (98))
68
delay: down 15m multiplier 1.5 max 1h
106
- summary: Container ${label:k8s_container_name} ram utilization
69
+ summary: Container ${label:k8s_container_name} pod ${label:k8s_pod_name} memory utilization
70
info: container ${label:k8s_container_name} of pod ${label:k8s_pod_name} of namespace ${label:k8s_namespace}, \
71
memory utilization
72
to: silent
110
-
111
-# check for packet storms
112
-
113
-# FIXME COMMENTED DUE TO A BUG IN NETDATA
114
-## 1. calculate the rate packets are received in 1m: 1m_received_packets_rate
115
-## 2. do the same for the last 10s
116
-## 3. raise an alarm if the later is 10x or 20x the first
117
-## we assume the minimum packet storm should at least have
118
-## 10000 packets/s, average of the last 10 seconds
119
-#
120
-# template: k8s_cgroup_1m_received_packets_rate
121
-# on: k8s.cgroup.net_packets
122
-# class: Workload
123
-# type: Cgroups
124
-#component: Network
125
-# hosts: *
126
-# lookup: average -1m unaligned of received
127
-# units: packets
128
-# every: 10s
129
-# info: average number of packets received by the network interface ${label:device} over the last minute
130
-#
131
-# template: k8s_cgroup_10s_received_packets_storm
132
-# on: k8s.cgroup.net_packets
133
-# class: Workload
134
-# type: Cgroups
135
-#component: Network
136
-# hosts: *
137
-# lookup: average -10s unaligned of received
138
-# calc: $this * 100 / (($k8s_cgroup_10s_received_packets_storm < 1000)?(1000):($k8s_cgroup_10s_received_packets_storm))
139
-# every: 10s
140
-# units: %
141
-# warn: $this > (($status >= $WARNING)?(200):(5000))
142
-# options: no-clear-notification
143
-# info: ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, \
144
-# compared to the rate over the last minute
145
-# to: sysadmin
health/health.d/cockroachdb.conf
+10
-5
@@ -12,7 +12,8 @@ component: CockroachDB
12
warn: $this > (($status >= $WARNING) ? (80) : (85))
13
crit: $this > (($status == $CRITICAL) ? (85) : (95))
14
delay: down 15m multiplier 1.5 max 1h
15
- info: storage capacity utilization
15
+ summary: CockroachDB storage space utilization
16
+ info: Storage capacity utilization
17
to: dba
18
19
template: cockroachdb_used_usable_storage_capacity
@@ -26,7 +27,8 @@ component: CockroachDB
27
warn: $this > (($status >= $WARNING) ? (80) : (85))
28
crit: $this > (($status == $CRITICAL) ? (85) : (95))
29
delay: down 15m multiplier 1.5 max 1h
29
- info: storage usable space utilization
30
+ summary: CockroachDB usable storage space utilization
31
+ info: Storage usable space utilization
32
to: dba
33
34
# Replication
@@ -41,7 +43,8 @@ component: CockroachDB
43
every: 10s
44
warn: $this > 0
45
delay: down 15m multiplier 1.5 max 1h
44
- info: number of ranges with fewer live replicas than needed for quorum
46
+ summary: CockroachDB unavailable replication
47
+ info: Number of ranges with fewer live replicas than needed for quorum
48
to: dba
49
50
template: cockroachdb_underreplicated_ranges
@@ -54,7 +57,8 @@ component: CockroachDB
57
every: 10s
58
warn: $this > 0
59
delay: down 15m multiplier 1.5 max 1h
57
- info: number of ranges with fewer live replicas than the replication target
60
+ summary: CockroachDB under-replicated
61
+ info: Number of ranges with fewer live replicas than the replication target
62
to: dba
63
64
# FD
@@ -69,5 +73,6 @@ component: CockroachDB
73
every: 10s
74
warn: $this > 80
75
delay: down 15m multiplier 1.5 max 1h
72
- info: open file descriptors utilization (against softlimit)
76
+ summary: CockroachDB file descriptors utilization
77
+ info: Open file descriptors utilization (against softlimit)
78
to: dba
health/health.d/consul.conf
+22
-10
@@ -10,6 +10,7 @@ component: Consul
10
units: seconds
11
warn: $this < 14*24*60*60
12
crit: $this < 7*24*60*60
13
+ summary: Consul license expiration on ${label:node_name}
14
info: Consul Enterprise license expiration time on node ${label:node_name} datacenter ${label:datacenter}
15
to: sysadmin
16
@@ -23,7 +24,8 @@ component: Consul
24
units: status
25
warn: $this == 1
26
delay: down 5m multiplier 1.5 max 1h
26
- info: datacenter ${label:datacenter} cluster is unhealthy as reported by server ${label:node_name}
27
+ summary: Consul datacenter ${label:datacenter} health
28
+ info: Datacenter ${label:datacenter} cluster is unhealthy as reported by server ${label:node_name}
29
to: sysadmin
30
31
template: consul_autopilot_server_health_status
@@ -36,7 +38,8 @@ component: Consul
38
units: status
39
warn: $this == 1
40
delay: down 5m multiplier 1.5 max 1h
39
- info: server ${label:node_name} from datacenter ${label:datacenter} is unhealthy
41
+ summary: Consul server ${label:node_name} health
42
+ info: Server ${label:node_name} from datacenter ${label:datacenter} is unhealthy
43
to: sysadmin
44
45
template: consul_raft_leader_last_contact_time
@@ -50,7 +53,8 @@ component: Consul
53
warn: $this > (($status >= $WARNING) ? (150) : (200))
54
crit: $this > (($status == $CRITICAL) ? (200) : (500))
55
delay: down 5m multiplier 1.5 max 1h
53
- info: median time elapsed since leader server ${label:node_name} datacenter ${label:datacenter} was last able to contact the follower nodes
56
+ summary: Consul leader server ${label:node_name} last contact time
57
+ info: Median time elapsed since leader server ${label:node_name} datacenter ${label:datacenter} was last able to contact the follower nodes
58
to: sysadmin
59
60
template: consul_raft_leadership_transitions
@@ -63,7 +67,8 @@ component: Consul
67
units: transitions
68
warn: $this > 0
69
delay: down 5m multiplier 1.5 max 1h
66
- info: there has been a leadership change and server ${label:node_name} datacenter ${label:datacenter} has become the leader
70
+ summary: Consul server ${label:node_name} leadership transitions
71
+ info: There has been a leadership change and server ${label:node_name} datacenter ${label:datacenter} has become the leader
72
to: sysadmin
73
74
template: consul_raft_thread_main_saturation
@@ -76,7 +81,8 @@ component: Consul
81
units: percentage
82
warn: $this > (($status >= $WARNING) ? (40) : (50))
83
delay: down 5m multiplier 1.5 max 1h
79
- info: average saturation of the main Raft goroutine on server ${label:node_name} datacenter ${label:datacenter}
84
+ summary: Consul server ${label:node_name} main Raft saturation
85
+ info: Average saturation of the main Raft goroutine on server ${label:node_name} datacenter ${label:datacenter}
86
to: sysadmin
87
88
template: consul_raft_thread_fsm_saturation
@@ -89,7 +95,8 @@ component: Consul
95
units: milliseconds
96
warn: $this > (($status >= $WARNING) ? (40) : (50))
97
delay: down 5m multiplier 1.5 max 1h
92
- info: average saturation of the FSM Raft goroutine on server ${label:node_name} datacenter ${label:datacenter}
98
+ summary: Consul server ${label:node_name} FSM Raft saturation
99
+ info: Average saturation of the FSM Raft goroutine on server ${label:node_name} datacenter ${label:datacenter}
100
to: sysadmin
101
102
template: consul_client_rpc_requests_exceeded
@@ -102,7 +109,8 @@ component: Consul
109
units: requests
110
warn: $this > (($status >= $WARNING) ? (0) : (5))
111
delay: down 5m multiplier 1.5 max 1h
105
- info: number of rate-limited RPC requests made by server ${label:node_name} datacenter ${label:datacenter}
112
+ summary: Consul server ${label:node_name} RPC requests rate
113
+ info: Number of rate-limited RPC requests made by server ${label:node_name} datacenter ${label:datacenter}
114
to: sysadmin
115
116
template: consul_client_rpc_requests_failed
@@ -115,6 +123,7 @@ component: Consul
123
units: requests
124
warn: $this > (($status >= $WARNING) ? (0) : (5))
125
delay: down 5m multiplier 1.5 max 1h
126
+ summary: Consul server ${label:node_name} failed RPC requests
127
info: number of failed RPC requests made by server ${label:node_name} datacenter ${label:datacenter}
128
to: sysadmin
129
@@ -128,7 +137,8 @@ component: Consul
137
units: status
138
warn: $this != nan AND $this != 0
139
delay: down 5m multiplier 1.5 max 1h
131
- info: node health check ${label:check_name} has failed on server ${label:node_name} datacenter ${label:datacenter}
140
+ summary: Consul node health check ${label:check_name} on ${label:node_name}
141
+ info: Node health check ${label:check_name} has failed on server ${label:node_name} datacenter ${label:datacenter}
142
to: sysadmin
143
144
template: consul_service_health_check_status
@@ -141,7 +151,8 @@ component: Consul
151
units: status
152
warn: $this == 1
153
delay: down 5m multiplier 1.5 max 1h
144
- info: service health check ${label:check_name} for service ${label:service_name} has failed on server ${label:node_name} datacenter ${label:datacenter}
154
+ summary: Consul service health check ${label:check_name} service ${label:service_name} node ${label:node_name}
155
+ info: Service health check ${label:check_name} for service ${label:service_name} has failed on server ${label:node_name} datacenter ${label:datacenter}
156
to: sysadmin
157
158
template: consul_gc_pause_time
@@ -155,5 +166,6 @@ component: Consul
166
warn: $this > (($status >= $WARNING) ? (1) : (2))
167
crit: $this > (($status >= $WARNING) ? (2) : (5))
168
delay: down 5m multiplier 1.5 max 1h
158
- info: time spent in stop-the-world garbage collection pauses on server ${label:node_name} datacenter ${label:datacenter}
169
+ summary: Consul server ${label:node_name} garbage collection pauses
170
+ info: Time spent in stop-the-world garbage collection pauses on server ${label:node_name} datacenter ${label:datacenter}
171
to: sysadmin
health/health.d/cpu.conf
+4
-4
@@ -14,7 +14,7 @@ component: CPU
14
warn: $this > (($status >= $WARNING) ? (75) : (85))
15
crit: $this > (($status == $CRITICAL) ? (85) : (95))
16
delay: down 15m multiplier 1.5 max 1h
17
- summary: CPU utilization
17
+ summary: System CPU utilization
18
info: Average CPU utilization over the last 10 minutes (excluding iowait, nice and steal)
19
to: silent
20
@@ -30,7 +30,7 @@ component: CPU
30
every: 1m
31
warn: $this > (($status >= $WARNING) ? (20) : (40))
32
delay: up 30m down 30m multiplier 1.5 max 2h
33
- summary: CPU iowait time
33
+ summary: System CPU iowait time
34
info: Average CPU iowait time over the last 10 minutes
35
to: silent
36
@@ -46,7 +46,7 @@ component: CPU
46
every: 5m
47
warn: $this > (($status >= $WARNING) ? (5) : (10))
48
delay: down 1h multiplier 1.5 max 2h
49
- summary: CPU steal time
49
+ summary: System CPU steal time
50
info: Average CPU steal time over the last 20 minutes
51
to: silent
52
@@ -64,6 +64,6 @@ component: CPU
64
warn: $this > (($status >= $WARNING) ? (75) : (85))
65
crit: $this > (($status == $CRITICAL) ? (85) : (95))
66
delay: down 15m multiplier 1.5 max 1h
67
- summary: CPU utilization
67
+ summary: System CPU utilization
68
info: Average CPU utilization over the last 10 minutes (excluding nice)
69
to: silent
health/health.d/dbengine.conf
+7
-3
@@ -13,7 +13,8 @@ component: DB engine
13
every: 10s
14
crit: $this > 0
15
delay: down 15m multiplier 1.5 max 1h
16
- info: number of filesystem errors in the last 10 minutes (too many open files, wrong permissions, etc)
16
+ summary: Netdata DBengine filesystem errors
17
+ info: Number of filesystem errors in the last 10 minutes (too many open files, wrong permissions, etc)
18
to: sysadmin
19
20
alarm: 10min_dbengine_global_io_errors
@@ -28,7 +29,8 @@ component: DB engine
29
every: 10s
30
crit: $this > 0
31
delay: down 1h multiplier 1.5 max 3h
31
- info: number of IO errors in the last 10 minutes (CRC errors, out of space, bad disk, etc)
32
+ summary: Netdata DBengine IO errors
33
+ info: Number of IO errors in the last 10 minutes (CRC errors, out of space, bad disk, etc)
34
to: sysadmin
35
36
alarm: 10min_dbengine_global_flushing_warnings
@@ -43,6 +45,7 @@ component: DB engine
45
every: 10s
46
warn: $this > 0
47
delay: down 1h multiplier 1.5 max 3h
48
+ summary: Netdata DBengine global flushing warnings
49
info: number of times when dbengine dirty pages were over 50% of the instance's page cache in the last 10 minutes. \
50
Metric data are at risk of not being stored in the database. To remedy, reduce disk load or use faster disks.
51
to: sysadmin
@@ -59,6 +62,7 @@ component: DB engine
62
every: 10s
63
crit: $this != 0
64
delay: down 1h multiplier 1.5 max 3h
62
- info: number of pages deleted due to failure to flush data to disk in the last 10 minutes. \
65
+ summary: Netdata DBengine global flushing errors
66
+ info: Number of pages deleted due to failure to flush data to disk in the last 10 minutes. \
67
Metric data were lost to unblock data collection. To fix, reduce disk load or use faster disks.
68
to: sysadmin
health/health.d/disks.conf
+2
-2
@@ -81,7 +81,7 @@ template: out_of_disk_space_time
81
warn: $this > 0 and $this < (($status >= $WARNING) ? (48) : (8))
82
crit: $this > 0 and $this < (($status == $CRITICAL) ? (24) : (2))
83
delay: down 15m multiplier 1.2 max 1h
84
- summary: Out of disk space time for ${label:mount_point}
84
+ summary: Disk ${label:mount_point} estimation of lack of space
85
info: Estimated time the disk ${label:mount_point} will run out of space, if the system continues to add data with the rate of the last hour
86
to: silent
87
@@ -121,7 +121,7 @@ template: out_of_disk_inodes_time
121
warn: $this > 0 and $this < (($status >= $WARNING) ? (48) : (8))
122
crit: $this > 0 and $this < (($status == $CRITICAL) ? (24) : (2))
123
delay: down 15m multiplier 1.2 max 1h
124
- summary: Out of disk inodes time for ${label:mount_point}
124
+ summary: Disk ${label:mount_point} estimation of lack of inodes
125
info: Estimated time the disk ${label:mount_point} will run out of inodes, if the system continues to allocate inodes with the rate of the last hour
126
to: silent
127
health/health.d/dns_query.conf
+1
@@ -10,5 +10,6 @@ component: DNS
10
every: 10s
11
warn: $this != nan && $this != 1
12
delay: up 30s down 5m multiplier 1.5 max 1h
13
+ summary: DNS query unsuccessful requests to ${label:server}
14
info: DNS request type ${label:record_type} to server ${label:server} is unsuccessful
15
to: sysadmin
health/health.d/dnsmasq_dhcp.conf
+2
-1
@@ -10,5 +10,6 @@ component: Dnsmasq
10
calc: $used
11
warn: $this > ( ($status >= $WARNING ) ? ( 80 ) : ( 90 ) )
12
delay: down 5m
13
- info: DHCP range utilization
13
+ summary: Dnsmasq DHCP range ${label:dhcp_range} utilization
14
+ info: DHCP range ${label:dhcp_range} utilization
15
to: sysadmin
health/health.d/elasticsearch.conf
+10
-5
@@ -12,7 +12,8 @@ component: Elasticsearch
12
units: status
13
crit: $this == 1
14
delay: down 5m multiplier 1.5 max 1h
15
- info: cluster health status is red.
15
+ summary: Elasticsearch cluster ${label:cluster_name} status
16
+ info: Elasticsearch cluster ${label:cluster_name} health status is red.
17
to: sysadmin
18
19
# the idea of '-10m' is to handle yellow status after node restart,
@@ -27,7 +28,8 @@ component: Elasticsearch
28
units: status
29
warn: $this == 1
30
delay: down 5m multiplier 1.5 max 1h
30
- info: cluster health status is yellow.
31
+ summary: Elasticsearch cluster ${label:cluster_name} status
32
+ info: Elasticsearch cluster ${label:cluster_name} health status is yellow.
33
to: sysadmin
34
35
template: elasticsearch_node_index_health_red
@@ -40,7 +42,8 @@ component: Elasticsearch
42
units: status
43
warn: $this == 1
44
delay: down 5m multiplier 1.5 max 1h
43
- info: node index $label:index health status is red.
45
+ summary: Elasticsearch cluster ${label:cluster_name} index ${label:index} status
46
+ info: Elasticsearch cluster ${label:cluster_name} index ${label:index} health status is red.
47
to: sysadmin
48
49
# don't convert 'lookup' value to seconds in 'calc' due to UI showing seconds as hh:mm:ss (0 as now).
@@ -55,7 +58,8 @@ component: Elasticsearch
58
units: milliseconds
59
warn: $this > (($status >= $WARNING) ? (20 * 1000) : (30 * 1000))
60
delay: down 5m multiplier 1.5 max 1h
58
- info: search performance is degraded, queries run slowly.
61
+ summary: Elasticsearch cluster ${label:cluster_name} node ${label:node_name} query performance
62
+ info: Elasticsearch cluster ${label:cluster_name} node ${label:node_name} search performance is degraded, queries run slowly.
63
to: sysadmin
64
65
template: elasticsearch_node_indices_search_time_fetch
@@ -69,5 +73,6 @@ component: Elasticsearch
73
warn: $this > (($status >= $WARNING) ? (3 * 1000) : (5 * 1000))
74
crit: $this > (($status == $CRITICAL) ? (5 * 1000) : (30 * 1000))
75
delay: down 5m multiplier 1.5 max 1h
72
- info: search performance is degraded, fetches run slowly.
76
+ summary: Elasticsearch cluster ${label:cluster_name} node ${label:node_name} fetch performance
77
+ info: Elasticsearch cluster ${label:cluster_name} node ${label:node_name} search performance is degraded, fetches run slowly.
78
to: sysadmin
health/health.d/entropy.conf
+2
-1
@@ -15,5 +15,6 @@ component: Cryptography
15
every: 5m
16
warn: $this < (($status >= $WARNING) ? (200) : (100))
17
delay: down 1h multiplier 1.5 max 2h
18
- info: minimum number of entries in the random numbers pool in the last 5 minutes
18
+ summary: System entropy pool number of entries
19
+ info: Minimum number of entries in the random numbers pool in the last 5 minutes
20
to: silent
health/health.d/exporting.conf
+4
-2
@@ -10,7 +10,8 @@ component: Exporting engine
10
warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
11
crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
12
delay: down 5m multiplier 1.5 max 1h
13
- info: number of seconds since the last successful buffering of exporting data
13
+ summary: Netdata exporting data last successful buffering
14
+ info: Number of seconds since the last successful buffering of exporting data
15
to: dba
16
17
template: exporting_metrics_sent
@@ -23,5 +24,6 @@ component: Exporting engine
24
every: 10s
25
warn: $this != 100
26
delay: down 5m multiplier 1.5 max 1h
26
- info: percentage of metrics sent to the external database server
27
+ summary: Netdata exporting metrics sent
28
+ info: Percentage of metrics sent to the external database server
29
to: dba
health/health.d/file_descriptors.conf
+3
-3
@@ -11,12 +11,12 @@
11
every: 1m
12
crit: $this > 90
13
delay: down 15m multiplier 1.5 max 1h
14
- summary: System open files utilization
14
+ summary: System open file descriptors utilization
15
info: System-wide utilization of open files
16
to: sysadmin
17
18
template: apps_group_file_descriptors_utilization
19
- on: apps.fd_limit
19
+ on: app.fds_open_limit
20
class: Utilization
21
type: System
22
component: Process
@@ -28,6 +28,6 @@ component: Process
28
every: 10s
29
warn: $this > (($status >= $WARNING) ? (85) : (95))
30
delay: down 15m multiplier 1.5 max 1h
31
- summary: Group open files utilization
31
+ summary: App group ${label:app_group} file descriptors utilization
32
info: Open files percentage against the processes limits, among all PIDs in application group
33
to: sysadmin
health/health.d/gearman.conf
+2
-1
@@ -9,5 +9,6 @@ component: Gearman
9
every: 10s
10
warn: $this > 30000
11
delay: down 5m multiplier 1.5 max 1h
12
- info: average number of queued jobs over the last 10 minutes
12
+ summary: Gearman queued jobs
13
+ info: Average number of queued jobs over the last 10 minutes
14
to: sysadmin
health/health.d/go.d.plugin.conf
+2
-1
@@ -13,5 +13,6 @@ component: go.d.plugin
13
warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
14
crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
15
delay: down 5m multiplier 1.5 max 1h
16
- info: number of seconds since the last successful data collection
16
+ summary: Go.d plugin last collection
17
+ info: Number of seconds since the last successful data collection
18
to: webmaster
health/health.d/haproxy.conf
+4
-2
@@ -7,7 +7,8 @@ component: HAProxy
7
every: 10s
8
lookup: average -10s
9
crit: $this > 0
10
- info: average number of failed haproxy backend servers over the last 10 seconds
10
+ summary: HAProxy server status
11
+ info: Average number of failed haproxy backend servers over the last 10 seconds
12
to: sysadmin
13
14
template: haproxy_backend_status
@@ -19,5 +20,6 @@ component: HAProxy
20
every: 10s
21
lookup: average -10s
22
crit: $this > 0
22
- info: average number of failed haproxy backends over the last 10 seconds
23
+ summary: HAProxy backend status
24
+ info: Average number of failed haproxy backends over the last 10 seconds
25
to: sysadmin
health/health.d/hdfs.conf
+5
@@ -12,6 +12,7 @@ component: HDFS
12
warn: $this > (($status >= $WARNING) ? (70) : (80))
13
crit: $this > (($status == $CRITICAL) ? (80) : (98))
14
delay: down 15m multiplier 1.5 max 1h
15
+ summary: HDFS datanodes space utilization
16
info: summary datanodes space capacity utilization
17
to: sysadmin
18
@@ -28,6 +29,7 @@ component: HDFS
29
every: 10s
30
warn: $this > 0
31
delay: down 15m multiplier 1.5 max 1h
32
+ summary: HDFS missing blocks
33
info: number of missing blocks
34
to: sysadmin
35
@@ -42,6 +44,7 @@ component: HDFS
44
every: 10s
45
warn: $this > 0
46
delay: down 15m multiplier 1.5 max 1h
47
+ summary: HDFS stale datanodes
48
info: number of datanodes marked stale due to delayed heartbeat
49
to: sysadmin
50
@@ -56,6 +59,7 @@ component: HDFS
59
every: 10s
60
crit: $this > 0
61
delay: down 15m multiplier 1.5 max 1h
62
+ summary: HDFS dead datanodes
63
info: number of datanodes which are currently dead
64
to: sysadmin
65
@@ -72,5 +76,6 @@ component: HDFS
76
every: 10s
77
warn: $this > 0
78
delay: down 15m multiplier 1.5 max 1h
79
+ summary: HDFS failed volumes
80
info: number of failed volumes
81
to: sysadmin
health/health.d/httpcheck.conf
+1
-1
@@ -9,7 +9,7 @@ component: HTTP endpoint
9
calc: ($this < 75) ? (0) : ($this)
10
every: 5s
11
units: up/down
12
- info: HTTP endpoint ${label:url} liveness status
12
+ info: HTTP check endpoint ${label:url} liveness status
13
to: silent
14
15
template: httpcheck_web_service_bad_content
health/health.d/ioping.conf
+2
-1
@@ -9,5 +9,6 @@ component: Disk
9
green: 10000
10
warn: $this > $green
11
delay: down 30m multiplier 1.5 max 2h
12
- info: average I/O latency over the last 10 seconds
12
+ summary: IO ping latency
13
+ info: Average I/O latency over the last 10 seconds
14
to: silent
health/health.d/ipfs.conf
+1
@@ -10,5 +10,6 @@ component: IPFS
10
warn: $this > (($status >= $WARNING) ? (80) : (90))
11
crit: $this > (($status == $CRITICAL) ? (90) : (98))
12
delay: down 15m multiplier 1.5 max 1h
13
+ summary: IPFS datastore utilization
14
info: IPFS datastore utilization
15
to: sysadmin
health/health.d/ipmi.conf
+1
-1
@@ -23,6 +23,6 @@ component: IPMI
23
every: 10s
24
warn: $this > 0
25
delay: up 5m down 15m multiplier 1.5 max 1h
26
- summary: IPMI events
26
+ summary: IPMI entries in System Event Log
27
info: number of events in the IPMI System Event Log (SEL)
28
to: silent
health/health.d/kubelet.conf
+12
-6
@@ -14,7 +14,8 @@ component: Kubelet
14
every: 10s
15
warn: $this == 1
16
delay: down 1m multiplier 1.5 max 2h
17
- info: the node is experiencing a configuration-related error (0: false, 1: true)
17
+ summary: Kubelet node config error
18
+ info: The node is experiencing a configuration-related error (0: false, 1: true)
19
to: sysadmin
20
21
# Failed Token() requests to the alternate token source
@@ -29,7 +30,8 @@ component: Kubelet
30
every: 10s
31
warn: $this > 0
32
delay: down 1m multiplier 1.5 max 2h
32
- info: number of failed Token() requests to the alternate token source
33
+ summary: Kubelet failed token requests
34
+ info: Number of failed Token() requests to the alternate token source
35
to: sysadmin
36
37
# Docker and runtime operation errors
@@ -44,7 +46,8 @@ component: Kubelet
46
every: 10s
47
warn: $this > (($status >= $WARNING) ? (0) : (20))
48
delay: up 30s down 1m multiplier 1.5 max 2h
47
- info: number of Docker or runtime operation errors
49
+ summary: Kubelet runtime errors
50
+ info: Number of Docker or runtime operation errors
51
to: sysadmin
52
53
# -----------------------------------------------------------------------------
@@ -84,7 +87,8 @@ component: Kubelet
87
warn: $this > (($status >= $WARNING)?(100):(200))
88
crit: $this > (($status >= $WARNING)?(200):(400))
89
delay: down 1m multiplier 1.5 max 2h
87
- info: ratio of average Pod Lifecycle Event Generator relisting latency over the last 10 seconds, \
90
+ summary: Kubelet relisting latency (quantile 0.5)
91
+ info: Ratio of average Pod Lifecycle Event Generator relisting latency over the last 10 seconds, \
92
compared to the last minute (quantile 0.5)
93
to: sysadmin
94
@@ -112,7 +116,8 @@ component: Kubelet
116
warn: $this > (($status >= $WARNING)?(200):(400))
117
crit: $this > (($status >= $WARNING)?(400):(800))
118
delay: down 1m multiplier 1.5 max 2h
115
- info: ratio of average Pod Lifecycle Event Generator relisting latency over the last 10 seconds, \
119
+ summary: Kubelet relisting latency (quantile 0.9)
120
+ info: Ratio of average Pod Lifecycle Event Generator relisting latency over the last 10 seconds, \
121
compared to the last minute (quantile 0.9)
122
to: sysadmin
123
@@ -140,6 +145,7 @@ component: Kubelet
145
warn: $this > (($status >= $WARNING)?(400):(800))
146
crit: $this > (($status >= $WARNING)?(800):(1200))
147
delay: down 1m multiplier 1.5 max 2h
143
- info: ratio of average Pod Lifecycle Event Generator relisting latency over the last 10 seconds, \
148
+ summary: Kubelet relisting latency (quantile 0.99)
149
+ info: Ratio of average Pod Lifecycle Event Generator relisting latency over the last 10 seconds, \
150
compared to the last minute (quantile 0.99)
151
to: sysadmin
health/health.d/load.conf
+3
-3
@@ -33,7 +33,7 @@ component: Load
33
every: 1m
34
warn: ($this * 100 / $load_cpu_number) > (($status >= $WARNING) ? 175 : 200)
35
delay: down 15m multiplier 1.5 max 1h
36
- summary: Load average (15 minutes)
36
+ summary: Host load average (15 minutes)
37
info: System load average for the past 15 minutes
38
to: silent
39
@@ -50,7 +50,7 @@ component: Load
50
every: 1m
51
warn: ($this * 100 / $load_cpu_number) > (($status >= $WARNING) ? 350 : 400)
52
delay: down 15m multiplier 1.5 max 1h
53
- summary: Load average (5 minutes)
53
+ summary: System load average (5 minutes)
54
info: System load average for the past 5 minutes
55
to: silent
56
@@ -67,6 +67,6 @@ component: Load
67
every: 1m
68
warn: ($this * 100 / $load_cpu_number) > (($status >= $WARNING) ? 700 : 800)
69
delay: down 15m multiplier 1.5 max 1h
70
- summary: Load average (1 minute)
70
+ summary: System load average (1 minute)
71
info: System load average for the past 1 minute
72
to: silent
health/health.d/mdstat.conf
+3
-3
@@ -8,7 +8,7 @@ component: RAID
8
every: 10s
9
calc: $down
10
warn: $this > 0
11
- summary: Mdtat device ${label:device} down
11
+ summary: MD array device ${label:device} down
12
info: Number of devices in the down state for the ${label:device} ${label:raid_level} array. \
13
Any number > 0 indicates that the array is degraded.
14
to: sysadmin
@@ -24,7 +24,7 @@ chart labels: raid_level=!raid1 !raid10 *
24
every: 60s
25
warn: $this > 1024
26
delay: up 30m
27
- summary: Mdstat device ${label:device} unsynchronized blocks
27
+ summary: MD array device ${label:device} unsynchronized blocks
28
info: Number of unsynchronized blocks for the ${label:device} ${label:raid_level} array
29
to: silent
30
@@ -38,6 +38,6 @@ component: RAID
38
every: 10s
39
warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
40
crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
41
- summary: Mdstat last collected
41
+ summary: MD array last collected
42
info: Number of seconds since the last successful data collection
43
to: sysadmin
health/health.d/megacli.conf
+10
-5
@@ -11,7 +11,8 @@ component: RAID
11
every: 10s
12
crit: $this > 0
13
delay: down 5m multiplier 2 max 10m
14
- info: adapter is in the degraded state (0: false, 1: true)
14
+ summary: MegaCLI adapter state
15
+ info: Adapter is in the degraded state (0: false, 1: true)
16
to: sysadmin
17
18
## Physical Disks
@@ -26,7 +27,8 @@ component: RAID
27
every: 10s
28
warn: $this > 0
29
delay: up 1m down 5m multiplier 2 max 10m
29
- info: number of physical drive predictive failures
30
+ summary: MegaCLI physical drive predictive failures
31
+ info: Number of physical drive predictive failures
32
to: sysadmin
33
34
template: megacli_pd_media_errors
@@ -39,7 +41,8 @@ component: RAID
41
every: 10s
42
warn: $this > 0
43
delay: up 1m down 5m multiplier 2 max 10m
42
- info: number of physical drive media errors
44
+ summary: MegaCLI physical drive errors
45
+ info: Number of physical drive media errors
46
to: sysadmin
47
48
## Battery Backup Units (BBU)
@@ -54,7 +57,8 @@ component: RAID
57
every: 10s
58
warn: $this <= (($status >= $WARNING) ? (85) : (80))
59
crit: $this <= (($status == $CRITICAL) ? (50) : (40))
57
- info: average battery backup unit (BBU) relative state of charge over the last 10 seconds
60
+ summary: MegaCLI BBU charge state
61
+ info: Average battery backup unit (BBU) relative state of charge over the last 10 seconds
62
to: sysadmin
63
64
template: megacli_bbu_cycle_count
@@ -67,5 +71,6 @@ component: RAID
71
every: 10s
72
warn: $this >= 100
73
crit: $this >= 500
70
- info: average battery backup unit (BBU) charge cycles count over the last 10 seconds
74
+ summary: MegaCLI BBU cycles count
75
+ info: Average battery backup unit (BBU) charge cycles count over the last 10 seconds
76
to: sysadmin
health/health.d/memcached.conf
+5
-3
@@ -12,7 +12,8 @@ component: Memcached
12
warn: $this > (($status >= $WARNING) ? (70) : (80))
13
crit: $this > (($status == $CRITICAL) ? (80) : (90))
14
delay: up 0 down 15m multiplier 1.5 max 1h
15
- info: cache memory utilization
15
+ summary: Memcached memory utilization
16
+ info: Cache memory utilization
17
to: dba
18
19
@@ -27,7 +28,7 @@ component: Memcached
28
calc: ($this - $available) / (($now - $after) / 3600)
29
units: KB/hour
30
every: 1m
30
- info: average rate the cache fills up (positive), or frees up (negative) space over the last hour
31
+ info: Average rate the cache fills up (positive), or frees up (negative) space over the last hour
32
33
34
# find the hours remaining until memcached cache is full
@@ -43,6 +44,7 @@ component: Memcached
44
warn: $this > 0 and $this < (($status >= $WARNING) ? (48) : (8))
45
crit: $this > 0 and $this < (($status == $CRITICAL) ? (24) : (2))
46
delay: down 15m multiplier 1.5 max 1h
46
- info: estimated time the cache will run out of space \
47
+ summary: Memcached estimation of lack of cache space
48
+ info: Estimated time the cache will run out of space \
49
if the system continues to add data at the same rate as the past hour
50
to: dba
health/health.d/memory.conf
+8
-3
@@ -12,7 +12,8 @@ component: Memory
12
every: 10s
13
warn: $this > 0
14
delay: down 1h multiplier 1.5 max 1h
15
- info: amount of memory corrupted due to a hardware failure
15
+ summary: System corrupted memory
16
+ info: Amount of memory corrupted due to a hardware failure
17
to: sysadmin
18
19
## ECC Controller
@@ -29,7 +30,8 @@ component: Memory
30
every: 1m
31
warn: $this > 0
32
delay: down 1h multiplier 1.5 max 1h
32
- info: memory controller ${label:controller} ECC correctable errors in the last 10 minutes
33
+ summary: System ECC memory ${label:controller} correctable errors
34
+ info: Memory controller ${label:controller} ECC correctable errors in the last 10 minutes
35
to: sysadmin
36
37
template: ecc_memory_mc_uncorrectable
@@ -44,7 +46,8 @@ component: Memory
46
every: 1m
47
crit: $this > 0
48
delay: down 1h multiplier 1.5 max 1h
47
- info: memory controller ${label:controller} ECC uncorrectable errors in the last 10 minutes
49
+ summary: System ECC memory ${label:controller} uncorrectable errors
50
+ info: Memory controller ${label:controller} ECC uncorrectable errors in the last 10 minutes
51
to: sysadmin
52
53
## ECC DIMM
@@ -61,6 +64,7 @@ component: Memory
64
every: 1m
65
warn: $this > 0
66
delay: down 1h multiplier 1.5 max 1h
67
+ summary: System ECC memory DIMM ${label:dimm} correctable errors
68
info: DIMM ${label:dimm} controller ${label:controller} (location ${label:dimm_location}) ECC correctable errors in the last 10 minutes
69
to: sysadmin
70
@@ -76,5 +80,6 @@ component: Memory
80
every: 1m
81
crit: $this > 0
82
delay: down 1h multiplier 1.5 max 1h
83
+ summary: System ECC memory DIMM ${label:dimm} uncorrectable errors
84
info: DIMM ${label:dimm} controller ${label:controller} (location ${label:dimm_location}) ECC uncorrectable errors in the last 10 minutes
85
to: sysadmin
health/health.d/ml.conf
+2
-1
@@ -20,7 +20,8 @@ component: ML
20
units: %
21
every: 30s
22
warn: $this > 1
23
- info: rolling 1min node level anomaly rate
23
+ summary: ML node anomaly rate
24
+ info: Rolling 1min node level anomaly rate
25
to: silent
26
27
# alert per dimension example
health/health.d/mysql.conf
+22
-11
@@ -12,7 +12,8 @@ component: MySQL
12
warn: $this > (($status >= $WARNING) ? (5) : (10))
13
crit: $this > (($status == $CRITICAL) ? (10) : (20))
14
delay: down 5m multiplier 1.5 max 1h
15
- info: number of slow queries in the last 10 seconds
15
+ summary: MySQL slow queries
16
+ info: Number of slow queries in the last 10 seconds
17
to: dba
18
19
@@ -27,7 +28,8 @@ component: MySQL
28
lookup: sum -10s absolute of immediate
29
units: immediate locks
30
every: 10s
30
- info: number of table immediate locks in the last 10 seconds
31
+ summary: MySQL table immediate locks
32
+ info: Number of table immediate locks in the last 10 seconds
33
to: dba
34
35
template: mysql_10s_table_locks_waited
@@ -38,7 +40,8 @@ component: MySQL
40
lookup: sum -10s absolute of waited
41
units: waited locks
42
every: 10s
41
- info: number of table waited locks in the last 10 seconds
43
+ summary: MySQL table waited locks
44
+ info: Number of table waited locks in the last 10 seconds
45
to: dba
46
47
template: mysql_10s_waited_locks_ratio
@@ -52,7 +55,8 @@ component: MySQL
55
warn: $this > (($status >= $WARNING) ? (10) : (25))
56
crit: $this > (($status == $CRITICAL) ? (25) : (50))
57
delay: down 30m multiplier 1.5 max 1h
55
- info: ratio of waited table locks over the last 10 seconds
58
+ summary: MySQL waited table locks ratio
59
+ info: Ratio of waited table locks over the last 10 seconds
60
to: dba
61
62
@@ -70,7 +74,8 @@ component: MySQL
74
warn: $this > (($status >= $WARNING) ? (60) : (70))
75
crit: $this > (($status == $CRITICAL) ? (80) : (90))
76
delay: down 15m multiplier 1.5 max 1h
73
- info: client connections utilization
77
+ summary: MySQL connections utilization
78
+ info: Client connections utilization
79
to: dba
80
81
@@ -87,7 +92,8 @@ component: MySQL
92
every: 10s
93
crit: $this == 0
94
delay: down 5m multiplier 1.5 max 1h
90
- info: replication status (0: stopped, 1: working)
95
+ summary: MySQL replication status
96
+ info: Replication status (0: stopped, 1: working)
97
to: dba
98
99
template: mysql_replication_lag
@@ -101,7 +107,8 @@ component: MySQL
107
warn: $this > (($status >= $WARNING) ? (5) : (10))
108
crit: $this > (($status == $CRITICAL) ? (10) : (30))
109
delay: down 15m multiplier 1.5 max 1h
104
- info: difference between the timestamp of the latest transaction processed by the SQL thread and \
110
+ summary: MySQL replication lag
111
+ info: Difference between the timestamp of the latest transaction processed by the SQL thread and \
112
the timestamp of the same transaction when it was processed on the master
113
to: dba
114
@@ -131,7 +138,8 @@ component: MySQL
138
warn: $this > $mysql_galera_cluster_size_max_2m
139
crit: $this < $mysql_galera_cluster_size_max_2m
140
delay: up 20s down 5m multiplier 1.5 max 1h
134
- info: current galera cluster size, compared to the maximum size in the last 2 minutes
141
+ summary: MySQL galera cluster size
142
+ info: Current galera cluster size, compared to the maximum size in the last 2 minutes
143
to: dba
144
145
# galera node state
@@ -145,7 +153,8 @@ component: MySQL
153
every: 10s
154
warn: $this != nan AND $this != 0
155
delay: up 30s down 5m multiplier 1.5 max 1h
148
- info: galera node state is either Donor/Desynced or Joined.
156
+ summary: MySQL galera node state
157
+ info: Galera node state is either Donor/Desynced or Joined.
158
to: dba
159
160
template: mysql_galera_cluster_state_crit
@@ -157,7 +166,8 @@ component: MySQL
166
every: 10s
167
crit: $this != nan AND $this != 0
168
delay: up 30s down 5m multiplier 1.5 max 1h
160
- info: galera node state is either Undefined or Joining or Error.
169
+ summary: MySQL galera node state
170
+ info: Galera node state is either Undefined or Joining or Error.
171
to: dba
172
173
# galera node status
@@ -171,6 +181,7 @@ component: MySQL
181
every: 10s
182
crit: $this != nan AND $this != 1
183
delay: up 30s down 5m multiplier 1.5 max 1h
174
- info: galera node is part of a nonoperational component. \
184
+ summary: MySQL galera cluster status
185
+ info: Galera node is part of a nonoperational component. \
186
This occurs in cases of multiple membership changes that result in a loss of Quorum or in cases of split-brain situations.
187
to: dba
health/health.d/net.conf
+10
-10
@@ -29,7 +29,7 @@ component: Network
29
every: 10s
30
warn: $this > (($status >= $WARNING) ? (85) : (90))
31
delay: up 1m down 1m multiplier 1.5 max 1h
32
- summary: 1 minute received traffic overflow for ${label:device}
32
+ summary: System network interface ${label:device} inbound utilization
33
info: Average inbound utilization for the network interface ${label:device} over the last minute
34
to: silent
35
@@ -46,7 +46,7 @@ component: Network
46
every: 10s
47
warn: $this > (($status >= $WARNING) ? (85) : (90))
48
delay: up 1m down 1m multiplier 1.5 max 1h
49
- summary: 1 minute sent traffic overflow for ${label:device}
49
+ summary: System network interface ${label:device} outbound utilization
50
info: Average outbound utilization for the network interface ${label:device} over the last minute
51
to: silent
52
@@ -98,7 +98,7 @@ chart labels: device=!wl* *
98
every: 1m
99
warn: $this >= 2
100
delay: up 1m down 1h multiplier 1.5 max 2h
101
- summary: Inbound packets dropped ratio for ${label:device}
101
+ summary: System network interface ${label:device} inbound drops
102
info: Ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes
103
to: silent
104
@@ -116,7 +116,7 @@ chart labels: device=!wl* *
116
every: 1m
117
warn: $this >= 2
118
delay: up 1m down 1h multiplier 1.5 max 2h
119
- summary: Outbound packets dropped ratio for ${label:device}
119
+ summary: System network interface ${label:device} outbound drops
120
info: Ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes
121
to: silent
122
@@ -134,7 +134,7 @@ chart labels: device=wl*
134
every: 1m
135
warn: $this >= 10
136
delay: up 1m down 1h multiplier 1.5 max 2h
137
- summary: Inbound packets dropped ratio for ${label:device}
137
+ summary: System network interface ${label:device} inbound drops ratio
138
info: Ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes
139
to: silent
140
@@ -152,7 +152,7 @@ chart labels: device=wl*
152
every: 1m
153
warn: $this >= 10
154
delay: up 1m down 1h multiplier 1.5 max 2h
155
- summary: Outbound packets dropped ratio for ${label:device}
155
+ summary: System network interface ${label:device} outbound drops ratio
156
info: Ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes
157
to: silent
158
@@ -171,7 +171,7 @@ component: Network
171
every: 1m
172
warn: $this >= 5
173
delay: down 1h multiplier 1.5 max 2h
174
- summary: Inbound interface errors for ${label:device}
174
+ summary: System network interface ${label:device} inbound errors
175
info: Number of inbound errors for the network interface ${label:device} in the last 10 minutes
176
to: silent
177
@@ -187,7 +187,7 @@ component: Network
187
every: 1m
188
warn: $this >= 5
189
delay: down 1h multiplier 1.5 max 2h
190
- summary: Outbound interface errors for ${label:device}
190
+ summary: System network interface ${label:device} outbound errors
191
info: Number of outbound errors for the network interface ${label:device} in the last 10 minutes
192
to: silent
193
@@ -211,7 +211,7 @@ component: Network
211
every: 1m
212
warn: $this > 0
213
delay: down 1h multiplier 1.5 max 2h
214
- summary: Net FIFO errors for ${label:device}
214
+ summary: System network interface ${label:device} FIFO errors
215
info: Number of FIFO errors for the network interface ${label:device} in the last 10 minutes
216
to: silent
217
@@ -250,7 +250,7 @@ component: Network
250
warn: $this > (($status >= $WARNING)?(200):(5000))
251
crit: $this > (($status == $CRITICAL)?(5000):(6000))
252
options: no-clear-notification
253
- summary: Received packets storm for ${label:device}
253
+ summary: System network interface ${label:device} inbound packet storm
254
info: Ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, \
255
compared to the rate over the last minute
256
to: silent
health/health.d/netfilter.conf
+2
-1
@@ -15,5 +15,6 @@ component: Network
15
warn: $this > (($status >= $WARNING) ? (85) : (90))
16
crit: $this > (($status == $CRITICAL) ? (90) : (95))
17
delay: down 5m multiplier 1.5 max 1h
18
- info: netfilter connection tracker table size utilization
18
+ summary: System Netfilter connection tracker utilization
19
+ info: Netfilter connection tracker table size utilization
20
to: sysadmin
health/health.d/nut.conf
+4
-4
@@ -14,7 +14,7 @@ component: UPS
14
crit: $this > (($status == $CRITICAL) ? (85) : (95))
15
delay: down 10m multiplier 1.5 max 1h
16
summary: UPS load
17
- info: Average UPS load over the last 10 minutes
17
+ info: UPS average load over the last 10 minutes
18
to: sitemgr
19
20
template: nut_ups_charge
@@ -30,8 +30,8 @@ component: UPS
30
warn: $this < 75
31
crit: $this < 40
32
delay: down 10m multiplier 1.5 max 1h
33
- summary: UPS charge
34
- info: Average UPS charge over the last minute
33
+ summary: UPS battery charge
34
+ info: UPS average battery charge over the last minute
35
to: sitemgr
36
37
template: nut_last_collected_secs
@@ -46,5 +46,5 @@ component: UPS device
46
crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
47
delay: down 5m multiplier 1.5 max 1h
48
summary: NUT last collected
49
- info: number of seconds since the last successful data collection
49
+ info: Number of seconds since the last successful data collection
50
to: sitemgr
health/health.d/pihole.conf
+3
-1
@@ -11,6 +11,7 @@ component: Pi-hole
11
units: seconds
12
calc: $ago
13
warn: $this > 60 * 60 * 24 * 30
14
+ summary: Pi-hole blocklist last update
15
info: gravity.list (blocklist) file last update time
16
to: sysadmin
17
@@ -27,5 +28,6 @@ component: Pi-hole
28
calc: $disabled
29
warn: $this != nan AND $this == 1
30
delay: up 2m down 5m
30
- info: unwanted domains blocking is disabled
31
+ summary: Pi-hole domains blocking status
32
+ info: Unwanted domains blocking is disabled
33
to: sysadmin
health/health.d/plugin.conf
+1
@@ -7,5 +7,6 @@
7
every: 10s
8
warn: $this > (($status >= $WARNING) ? ($update_every) : (20 * $update_every))
9
delay: down 5m multiplier 1.5 max 1h
10
+ summary: Plugin ${label:_collect_plugin} availability status
11
info: the amount of time that ${label:_collect_plugin} did not report its availability status
12
to: sysadmin
health/health.d/portcheck.conf
+5
-2
@@ -9,6 +9,7 @@ component: TCP endpoint
9
calc: ($this < 75) ? (0) : ($this)
10
every: 5s
11
units: up/down
12
+ summary: Portcheck status for ${label:host}:${label:port}
13
info: TCP host ${label:host} port ${label:port} liveness status
14
to: silent
15
@@ -23,7 +24,8 @@ component: TCP endpoint
24
warn: $this >= 10 AND $this < 40
25
crit: $this >= 40
26
delay: down 5m multiplier 1.5 max 1h
26
- info: percentage of timed-out TCP connections to host ${label:host} port ${label:port} in the last 5 minutes
27
+ summary: Portcheck timeouts for ${label:host}:${label:port}
28
+ info: Percentage of timed-out TCP connections to host ${label:host} port ${label:port} in the last 5 minutes
29
to: sysadmin
30
31
template: portcheck_connection_fails
@@ -37,5 +39,6 @@ component: TCP endpoint
39
warn: $this >= 10 AND $this < 40
40
crit: $this >= 40
41
delay: down 5m multiplier 1.5 max 1h
40
- info: percentage of failed TCP connections to host ${label:host} port ${label:port} in the last 5 minutes
42
+ summary: Portcheck fails for ${label:host}:${label:port}
43
+ info: Percentage of failed TCP connections to host ${label:host} port ${label:port} in the last 5 minutes
44
to: sysadmin
health/health.d/postgres.conf
+8
-8
@@ -110,7 +110,7 @@ component: PostgreSQL
110
warn: $this < (($status >= $WARNING) ? (70) : (60))
111
crit: $this < (($status == $CRITICAL) ? (60) : (50))
112
delay: down 15m multiplier 1.5 max 1h
113
- summary: PostgreSQL table ${label:table} cache hit ratio
113
+ summary: PostgreSQL table ${label:table} db ${label:database} cache hit ratio
114
info: Average cache hit ratio in db ${label:database} table ${label:table} over the last minute
115
to: dba
116
@@ -127,7 +127,7 @@ component: PostgreSQL
127
warn: $this < (($status >= $WARNING) ? (70) : (60))
128
crit: $this < (($status == $CRITICAL) ? (60) : (50))
129
delay: down 15m multiplier 1.5 max 1h
130
- summary: PostgreSQL table ${label:table} index cache hit ratio
130
+ summary: PostgreSQL table ${label:table} db ${label:database} index cache hit ratio
131
info: Average index cache hit ratio in db ${label:database} table ${label:table} over the last minute
132
to: dba
133
@@ -144,7 +144,7 @@ component: PostgreSQL
144
warn: $this < (($status >= $WARNING) ? (70) : (60))
145
crit: $this < (($status == $CRITICAL) ? (60) : (50))
146
delay: down 15m multiplier 1.5 max 1h
147
- summary: PostgreSQL table ${label:table} toast cache hit ratio
147
+ summary: PostgreSQL table ${label:table} db ${label:database} toast cache hit ratio
148
info: Average TOAST hit ratio in db ${label:database} table ${label:table} over the last minute
149
to: dba
150
@@ -161,7 +161,7 @@ component: PostgreSQL
161
warn: $this < (($status >= $WARNING) ? (70) : (60))
162
crit: $this < (($status == $CRITICAL) ? (60) : (50))
163
delay: down 15m multiplier 1.5 max 1h
164
- summary: PostgreSQL table ${label:table} index toast hit ratio
164
+ summary: PostgreSQL table ${label:table} db ${label:database} index toast hit ratio
165
info: average index TOAST hit ratio in db ${label:database} table ${label:table} over the last minute
166
to: dba
167
@@ -177,7 +177,7 @@ component: PostgreSQL
177
warn: $this > (($status >= $WARNING) ? (60) : (70))
178
crit: $this > (($status == $CRITICAL) ? (70) : (80))
179
delay: down 15m multiplier 1.5 max 1h
180
- summary: PostgreSQL table ${label:table} bloat size
180
+ summary: PostgreSQL table ${label:table} db ${label:database} bloat size
181
info: Bloat size percentage in db ${label:database} table ${label:table}
182
to: dba
183
@@ -191,7 +191,7 @@ component: PostgreSQL
191
units: seconds
192
every: 1m
193
warn: $this != nan AND $this > (60 * 60 * 24 * 7)
194
- summary: PostgreSQL table ${label:table} last autovacuum
194
+ summary: PostgreSQL table ${label:table} db ${label:database} last autovacuum
195
info: Time elapsed since db ${label:database} table ${label:table} was vacuumed by the autovacuum daemon
196
to: dba
197
@@ -205,7 +205,7 @@ component: PostgreSQL
205
units: seconds
206
every: 1m
207
warn: $this != nan AND $this > (60 * 60 * 24 * 7)
208
- summary: PostgreSQL table ${label:table} last autoanalyze
208
+ summary: PostgreSQL table ${label:table} db ${label:database} last autoanalyze
209
info: Time elapsed since db ${label:database} table ${label:table} was analyzed by the autovacuum daemon
210
to: dba
211
@@ -223,6 +223,6 @@ component: PostgreSQL
223
warn: $this > (($status >= $WARNING) ? (60) : (70))
224
crit: $this > (($status == $CRITICAL) ? (70) : (80))
225
delay: down 15m multiplier 1.5 max 1h
226
- summary: PostgreSQL table ${label:table} index bloat size
226
+ summary: PostgreSQL table ${label:table} db ${label:database} index bloat size
227
info: Bloat size percentage in db ${label:database} table ${label:table} index ${label:index}
228
to: dba
health/health.d/processes.conf
+2
-1
@@ -12,5 +12,6 @@ component: Processes
12
warn: $this > (($status >= $WARNING) ? (85) : (90))
13
crit: $this > (($status == $CRITICAL) ? (90) : (95))
14
delay: down 5m multiplier 1.5 max 1h
15
- info: system process IDs (PID) space utilization
15
+ summary: System PIDs utilization
16
+ info: System process IDs (PID) space utilization
17
to: sysadmin
health/health.d/python.d.plugin.conf
+2
-1
@@ -13,5 +13,6 @@ component: python.d.plugin
13
warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
14
crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
15
delay: down 5m multiplier 1.5 max 1h
16
- info: number of seconds since the last successful data collection
16
+ summary: Python.d plugin last collection
17
+ info: Number of seconds since the last successful data collection
18
to: webmaster
health/health.d/ram.conf
+5
-5
@@ -14,7 +14,7 @@ component: Memory
14
warn: $this > (($status >= $WARNING) ? (80) : (90))
15
crit: $this > (($status == $CRITICAL) ? (90) : (98))
16
delay: down 15m multiplier 1.5 max 1h
17
- summary: Ram utilization
17
+ summary: System memory utilization
18
info: System memory utilization
19
to: sysadmin
20
@@ -30,7 +30,7 @@ component: Memory
30
every: 10s
31
warn: $this < (($status >= $WARNING) ? (15) : (10))
32
delay: down 15m multiplier 1.5 max 1h
33
- summary: Available Ram
33
+ summary: System available memory
34
info: Percentage of estimated amount of RAM available for userspace processes, without causing swapping
35
to: silent
36
@@ -43,7 +43,7 @@ component: Memory
43
every: 5m
44
warn: $this > 0
45
delay: down 10m
46
- summary: OOM kills
46
+ summary: System OOM kills
47
info: Number of out of memory kills in the last 30 minutes
48
to: silent
49
@@ -61,7 +61,7 @@ component: Memory
61
warn: $this > (($status >= $WARNING) ? (80) : (90))
62
crit: $this > (($status == $CRITICAL) ? (90) : (98))
63
delay: down 15m multiplier 1.5 max 1h
64
- summary: Ram utilization
64
+ summary: System memory utilization
65
info: System memory utilization
66
to: sysadmin
67
@@ -77,6 +77,6 @@ component: Memory
77
every: 10s
78
warn: $this < (($status >= $WARNING) ? (15) : (10))
79
delay: down 15m multiplier 1.5 max 1h
80
- summary: Available Ram
80
+ summary: System available memory
81
info: Percentage of estimated amount of RAM available for userspace processes, without causing swapping
82
to: silent
health/health.d/retroshare.conf
+2
-1
@@ -12,5 +12,6 @@ component: Retroshare
12
warn: $this < (($status >= $WARNING) ? (120) : (100))
13
crit: $this < (($status == $CRITICAL) ? (10) : (1))
14
delay: up 0 down 15m multiplier 1.5 max 1h
15
- info: number of DHT peers
15
+ summary: Retroshare DHT peers
16
+ info: Number of DHT peers
17
to: sysadmin
health/health.d/riakkv.conf
+10
-5
@@ -9,7 +9,8 @@ component: Riak KV
9
units: state machines
10
every: 10s
11
warn: $list_fsm_active > 0
12
- info: number of currently running list keys finite state machines
12
+ summary: Riak KV active list keys
13
+ info: Number of currently running list keys finite state machines
14
to: dba
15
16
@@ -38,7 +39,8 @@ component: Riak KV
39
every: 10s
40
warn: ($this > ($riakkv_1h_kv_get_mean_latency * 2) )
41
crit: ($this > ($riakkv_1h_kv_get_mean_latency * 3) )
41
- info: average time between reception of client GET request and \
42
+ summary: Riak KV GET latency
43
+ info: Average time between reception of client GET request and \
44
subsequent response to the client over the last 3 minutes, \
45
compared to the average over the last hour
46
delay: down 5m multiplier 1.5 max 1h
@@ -54,7 +56,8 @@ component: Riak KV
56
lookup: average -1h unaligned of time
57
every: 30s
58
units: ms
57
- info: average time between reception of client PUT request and \
59
+ summary: Riak KV PUT mean latency
60
+ info: Average time between reception of client PUT request and \
61
subsequent response to the client over the last hour
62
63
template: riakkv_kv_put_slow
@@ -68,7 +71,8 @@ component: Riak KV
71
every: 10s
72
warn: ($this > ($riakkv_1h_kv_put_mean_latency * 2) )
73
crit: ($this > ($riakkv_1h_kv_put_mean_latency * 3) )
71
- info: average time between reception of client PUT request and \
74
+ summary: Riak KV PUT latency
75
+ info: Average time between reception of client PUT request and \
76
subsequent response to the client over the last 3 minutes, \
77
compared to the average over the last hour
78
delay: down 5m multiplier 1.5 max 1h
@@ -89,5 +93,6 @@ component: Riak KV
93
every: 10s
94
warn: $this > 10000
95
crit: $this > 100000
92
- info: number of processes running in the Erlang VM
96
+ summary: Riak KV number of processes
97
+ info: Number of processes running in the Erlang VM
98
to: dba
health/health.d/scaleio.conf
+3
-1
@@ -12,7 +12,8 @@ component: ScaleIO
12
warn: $this > (($status >= $WARNING) ? (80) : (85))
13
crit: $this > (($status == $CRITICAL) ? (85) : (90))
14
delay: down 15m multiplier 1.5 max 1h
15
- info: storage pool capacity utilization
15
+ summary: ScaleIO storage pool capacity utilization
16
+ info: Storage pool capacity utilization
17
to: sysadmin
18
19
@@ -27,5 +28,6 @@ component: ScaleIO
28
every: 10s
29
warn: $this != 1
30
delay: up 30s down 5m multiplier 1.5 max 1h
31
+ summary: ScaleIO SDC-MDM connection state
32
info: Data Client (SDC) to Metadata Manager (MDM) connection state (0: disconnected, 1: connected)
33
to: sysadmin
health/health.d/softnet.conf
+6
-3
@@ -15,7 +15,8 @@ component: Network
15
every: 10s
16
warn: $this > (($status >= $WARNING) ? (0) : (10))
17
delay: down 1h multiplier 1.5 max 2h
18
- info: average number of dropped packets in the last minute \
18
+ summary: System netdev dropped packets
19
+ info: Average number of dropped packets in the last minute \
20
due to exceeded net.core.netdev_max_backlog
21
to: silent
22
@@ -31,7 +32,8 @@ component: Network
32
every: 10s
33
warn: $this > (($status >= $WARNING) ? (0) : (10))
34
delay: down 1h multiplier 1.5 max 2h
34
- info: average number of times ksoftirq ran out of sysctl net.core.netdev_budget or \
35
+ summary: System netdev budget run outs
36
+ info: Average number of times ksoftirq ran out of sysctl net.core.netdev_budget or \
37
net.core.netdev_budget_usecs with work remaining over the last minute \
38
(this can be a cause for dropped packets)
39
to: silent
@@ -48,7 +50,8 @@ component: Network
50
every: 10s
51
warn: $this > (($status >= $WARNING) ? (0) : (10))
52
delay: down 1h multiplier 1.5 max 2h
51
- info: average number of drops in the last minute \
53
+ summary: System netisr drops
54
+ info: Average number of drops in the last minute \
55
due to exceeded sysctl net.route.netisr_maxqlen \
56
(this can be a cause for dropped packets)
57
to: silent
health/health.d/swap.conf
+2
-2
@@ -15,7 +15,7 @@ component: Memory
15
every: 1m
16
warn: $this > (($status >= $WARNING) ? (20) : (30))
17
delay: down 15m multiplier 1.5 max 1h
18
- summary: Ram swapped out
18
+ summary: System memory swapped out
19
info: Percentage of the system RAM swapped in the last 30 minutes
20
to: silent
21
@@ -32,6 +32,6 @@ component: Memory
32
warn: $this > (($status >= $WARNING) ? (80) : (90))
33
crit: $this > (($status == $CRITICAL) ? (90) : (98))
34
delay: up 30s down 15m multiplier 1.5 max 1h
35
- summary: Swap utilization
35
+ summary: System swap memory utilization
36
info: Swap memory utilization
37
to: sysadmin
health/health.d/synchronization.conf
+2
-1
@@ -6,7 +6,8 @@
6
every: 1m
7
warn: $this > 6
8
delay: up 1m down 10m multiplier 1.5 max 1h
9
- info: number of sync() system calls. \
9
+ summary: Sync system call frequency
10
+ info: Number of sync() system calls. \
11
Every call causes all pending modifications to filesystem metadata and \
12
cached file data to be written to the underlying filesystems.
13
to: silent
health/health.d/systemdunits.conf
+10
@@ -12,6 +12,7 @@ component: Systemd units
12
every: 10s
13
warn: $this != nan AND $this == 1
14
delay: down 5m multiplier 1.5 max 1h
15
+ summary: systemd unit ${label:unit_name} state
16
info: systemd service unit in the failed state
17
to: sysadmin
18
@@ -27,6 +28,7 @@ component: Systemd units
28
every: 10s
29
warn: $this != nan AND $this == 1
30
delay: down 5m multiplier 1.5 max 1h
31
+ summary: systemd unit ${label:unit_name} state
32
info: systemd socket unit in the failed state
33
to: sysadmin
34
@@ -42,6 +44,7 @@ component: Systemd units
44
every: 10s
45
warn: $this != nan AND $this == 1
46
delay: down 5m multiplier 1.5 max 1h
47
+ summary: systemd unit ${label:unit_name} state
48
info: systemd target unit in the failed state
49
to: sysadmin
50
@@ -57,6 +60,7 @@ component: Systemd units
60
every: 10s
61
warn: $this != nan AND $this == 1
62
delay: down 5m multiplier 1.5 max 1h
63
+ summary: systemd unit ${label:unit_name} state
64
info: systemd path unit in the failed state
65
to: sysadmin
66
@@ -72,6 +76,7 @@ component: Systemd units
76
every: 10s
77
warn: $this != nan AND $this == 1
78
delay: down 5m multiplier 1.5 max 1h
79
+ summary: systemd unit ${label:unit_name} state
80
info: systemd device unit in the failed state
81
to: sysadmin
82
@@ -87,6 +92,7 @@ component: Systemd units
92
every: 10s
93
warn: $this != nan AND $this == 1
94
delay: down 5m multiplier 1.5 max 1h
95
+ summary: systemd unit ${label:unit_name} state
96
info: systemd mount units in the failed state
97
to: sysadmin
98
@@ -102,6 +108,7 @@ component: Systemd units
108
every: 10s
109
warn: $this != nan AND $this == 1
110
delay: down 5m multiplier 1.5 max 1h
111
+ summary: systemd unit ${label:unit_name} state
112
info: systemd automount unit in the failed state
113
to: sysadmin
114
@@ -117,6 +124,7 @@ component: Systemd units
124
every: 10s
125
warn: $this != nan AND $this == 1
126
delay: down 5m multiplier 1.5 max 1h
127
+ summary: systemd unit ${label:unit_name} state
128
info: systemd swap units in the failed state
129
to: sysadmin
130
@@ -132,6 +140,7 @@ component: Systemd units
140
every: 10s
141
warn: $this != nan AND $this == 1
142
delay: down 5m multiplier 1.5 max 1h
143
+ summary: systemd unit ${label:unit_name} state
144
info: systemd scope units in the failed state
145
to: sysadmin
146
@@ -147,5 +156,6 @@ component: Systemd units
156
every: 10s
157
warn: $this != nan AND $this == 1
158
delay: down 5m multiplier 1.5 max 1h
159
+ summary: systemd unit ${label:unit_name} state
160
info: systemd slice units in the failed state
161
to: sysadmin
health/health.d/tcp_conn.conf
+1
@@ -18,5 +18,6 @@ component: Network
18
warn: $this > (($status >= $WARNING ) ? ( 60 ) : ( 80 ))
19
crit: $this > (($status == $CRITICAL) ? ( 80 ) : ( 90 ))
20
delay: up 0 down 5m multiplier 1.5 max 1h
21
+ summary: System TCP connections utilization
22
info: IPv4 TCP connections utilization
23
to: sysadmin
health/health.d/tcp_listen.conf
+8
-4
@@ -31,7 +31,8 @@ component: Network
31
warn: $this > 1
32
crit: $this > (($status == $CRITICAL) ? (1) : (5))
33
delay: up 0 down 5m multiplier 1.5 max 1h
34
- info: average number of overflows in the TCP accept queue over the last minute
34
+ summary: System TCP accept queue overflows
35
+ info: Average number of overflows in the TCP accept queue over the last minute
36
to: silent
37
38
# THIS IS TOO GENERIC
@@ -49,7 +50,8 @@ component: Network
50
warn: $this > 1
51
crit: $this > (($status == $CRITICAL) ? (1) : (5))
52
delay: up 0 down 5m multiplier 1.5 max 1h
52
- info: average number of dropped packets in the TCP accept queue over the last minute
53
+ summary: System TCP accept queue dropped packets
54
+ info: Average number of dropped packets in the TCP accept queue over the last minute
55
to: silent
56
57
@@ -74,7 +76,8 @@ component: Network
76
warn: $this > 1
77
crit: $this > (($status == $CRITICAL) ? (0) : (5))
78
delay: up 10 down 5m multiplier 1.5 max 1h
77
- info: average number of SYN requests was dropped due to the full TCP SYN queue over the last minute \
79
+ summary: System TCP SYN queue drops
80
+ info: Average number of SYN requests was dropped due to the full TCP SYN queue over the last minute \
81
(SYN cookies were not enabled)
82
to: silent
83
@@ -91,6 +94,7 @@ component: Network
94
warn: $this > 1
95
crit: $this > (($status == $CRITICAL) ? (0) : (5))
96
delay: up 10 down 5m multiplier 1.5 max 1h
94
- info: average number of sent SYN cookies due to the full TCP SYN queue over the last minute
97
+ summary: System TCP SYN queue cookies
98
+ info: Average number of sent SYN cookies due to the full TCP SYN queue over the last minute
99
to: silent
100
health/health.d/tcp_mem.conf
+1
-1
@@ -19,6 +19,6 @@ component: Network
19
warn: ${mem} > (($status >= $WARNING ) ? ( ${tcp_mem_pressure} * 0.8 ) : ( ${tcp_mem_pressure} ))
20
crit: ${mem} > (($status == $CRITICAL ) ? ( ${tcp_mem_pressure} ) : ( ${tcp_mem_high} * 0.9 ))
21
delay: up 0 down 5m multiplier 1.5 max 1h
22
- summary: TCP memory utilization
22
+ summary: System TCP memory utilization
23
info: TCP memory utilization
24
to: silent
health/health.d/tcp_orphans.conf
+2
-1
@@ -20,5 +20,6 @@ component: Network
20
warn: $this > (($status >= $WARNING ) ? ( 20 ) : ( 25 ))
21
crit: $this > (($status == $CRITICAL) ? ( 25 ) : ( 50 ))
22
delay: up 0 down 5m multiplier 1.5 max 1h
23
- info: orphan IPv4 TCP sockets utilization
23
+ summary: System TCP orphan sockets utilization
24
+ info: Orphan IPv4 TCP sockets utilization
25
to: silent
health/health.d/tcp_resets.conf
+3
-1
@@ -29,7 +29,8 @@ component: Network
29
warn: $netdata.uptime.uptime > (1 * 60) AND $this > ((($1m_ip_tcp_resets_sent < 5)?(5):($1m_ip_tcp_resets_sent)) * (($status >= $WARNING) ? (1) : (10)))
30
delay: up 20s down 60m multiplier 1.2 max 2h
31
options: no-clear-notification
32
- info: average number of sent TCP RESETS over the last 10 seconds. \
32
+ summary: System TCP outbound resets
33
+ info: Average number of sent TCP RESETS over the last 10 seconds. \
34
This can indicate a port scan, \
35
or that a service running on this host has crashed. \
36
Netdata will not send a clear notification for this alarm.
@@ -63,6 +64,7 @@ component: Network
64
warn: $netdata.uptime.uptime > (1 * 60) AND $this > ((($1m_ip_tcp_resets_received < 5)?(5):($1m_ip_tcp_resets_received)) * (($status >= $WARNING) ? (1) : (10)))
65
delay: up 20s down 60m multiplier 1.2 max 2h
66
options: no-clear-notification
67
+ summary: System TCP inbound resets
68
info: average number of received TCP RESETS over the last 10 seconds. \
69
This can be an indication that a service this host needs has crashed. \
70
Netdata will not send a clear notification for this alarm.
health/health.d/udp_errors.conf
+4
-2
@@ -15,7 +15,8 @@ component: Network
15
units: errors
16
every: 10s
17
warn: $this > (($status >= $WARNING) ? (0) : (10))
18
- info: average number of UDP receive buffer errors over the last minute
18
+ summary: System UDP receive buffer errors
19
+ info: Average number of UDP receive buffer errors over the last minute
20
delay: up 1m down 60m multiplier 1.2 max 2h
21
to: silent
22
@@ -33,6 +34,7 @@ component: Network
34
units: errors
35
every: 10s
36
warn: $this > (($status >= $WARNING) ? (0) : (10))
36
- info: average number of UDP send buffer errors over the last minute
37
+ summary: System UDP send buffer errors
38
+ info: Average number of UDP send buffer errors over the last minute
39
delay: up 1m down 60m multiplier 1.2 max 2h
40
to: silent
health/health.d/unbound.conf
+4
-2
@@ -11,7 +11,8 @@ component: Unbound
11
every: 10s
12
warn: $this > 5
13
delay: up 10 down 5m multiplier 1.5 max 1h
14
- info: number of overwritten queries in the request-list
14
+ summary: Unbound overwritten queries
15
+ info: Number of overwritten queries in the request-list
16
to: sysadmin
17
18
template: unbound_request_list_dropped
@@ -24,5 +25,6 @@ component: Unbound
25
every: 10s
26
warn: $this > 0
27
delay: up 10 down 5m multiplier 1.5 max 1h
27
- info: number of dropped queries in the request-list
28
+ summary: Unbound dropped queries
29
+ info: Number of dropped queries in the request-list
30
to: sysadmin
health/health.d/vcsa.conf
+15
@@ -16,6 +16,7 @@ component: VMware vCenter
16
every: 10s
17
warn: $this == 1
18
delay: down 1m multiplier 1.5 max 1h
19
+ summary: VCSA system status
20
info: VCSA overall system status is orange. One or more components are degraded.
21
to: sysadmin
22
@@ -29,6 +30,7 @@ component: VMware vCenter
30
every: 10s
31
crit: $this == 1
32
delay: down 1m multiplier 1.5 max 1h
33
+ summary: VCSA system status
34
info: VCSA overall system status is red. One or more components are unavailable or will stop functioning soon.
35
to: sysadmin
36
@@ -49,6 +51,7 @@ component: VMware vCenter
51
every: 10s
52
warn: $this == 1
53
delay: down 1m multiplier 1.5 max 1h
54
+ summary: VCSA ApplMgmt service status
55
info: VCSA ApplMgmt component status is orange. It is degraded, and may have serious problems.
56
to: silent
57
@@ -62,6 +65,7 @@ component: VMware vCenter
65
every: 10s
66
warn: $this == 1
67
delay: down 1m multiplier 1.5 max 1h
68
+ summary: VCSA ApplMgmt service status
69
info: VCSA ApplMgmt component status is red. It is unavailable, or will stop functioning soon.
70
to: sysadmin
71
@@ -75,6 +79,7 @@ component: VMware vCenter
79
every: 10s
80
warn: $this == 1
81
delay: down 1m multiplier 1.5 max 1h
82
+ summary: VCSA Load status
83
info: VCSA Load component status is orange. It is degraded, and may have serious problems.
84
to: silent
85
@@ -88,6 +93,7 @@ component: VMware vCenter
93
every: 10s
94
warn: $this == 1
95
delay: down 1m multiplier 1.5 max 1h
96
+ summary: VCSA Load status
97
info: VCSA Load component status is red. It is unavailable, or will stop functioning soon.
98
to: sysadmin
99
@@ -101,6 +107,7 @@ component: VMware vCenter
107
every: 10s
108
warn: $this == 1
109
delay: down 1m multiplier 1.5 max 1h
110
+ summary: VCSA Memory status
111
info: VCSA Memory component status is orange. It is degraded, and may have serious problems.
112
to: silent
113
@@ -114,6 +121,7 @@ component: VMware vCenter
121
every: 10s
122
warn: $this == 1
123
delay: down 1m multiplier 1.5 max 1h
124
+ summary: VCSA Memory status
125
info: VCSA Memory component status is red. It is unavailable, or will stop functioning soon.
126
to: sysadmin
127
@@ -127,6 +135,7 @@ component: VMware vCenter
135
every: 10s
136
warn: $this == 1
137
delay: down 1m multiplier 1.5 max 1h
138
+ summary: VCSA Swap status
139
info: VCSA Swap component status is orange. It is degraded, and may have serious problems.
140
to: silent
141
@@ -140,6 +149,7 @@ component: VMware vCenter
149
every: 10s
150
warn: $this == 1
151
delay: down 1m multiplier 1.5 max 1h
152
+ summary: VCSA Swap status
153
info: VCSA Swap component status is red. It is unavailable, or will stop functioning soon.
154
to: sysadmin
155
@@ -153,6 +163,7 @@ component: VMware vCenter
163
every: 10s
164
warn: $this == 1
165
delay: down 1m multiplier 1.5 max 1h
166
+ summary: VCSA Database status
167
info: VCSA Database Storage component status is orange. It is degraded, and may have serious problems.
168
to: silent
169
@@ -166,6 +177,7 @@ component: VMware vCenter
177
every: 10s
178
warn: $this == 1
179
delay: down 1m multiplier 1.5 max 1h
180
+ summary: VCSA Database status
181
info: VCSA Database Storage component status is red. It is unavailable, or will stop functioning soon.
182
to: sysadmin
183
@@ -179,6 +191,7 @@ component: VMware vCenter
191
every: 10s
192
warn: $this == 1
193
delay: down 1m multiplier 1.5 max 1h
194
+ summary: VCSA Storage status
195
info: VCSA Storage component status is orange. It is degraded, and may have serious problems.
196
to: silent
197
@@ -192,6 +205,7 @@ component: VMware vCenter
205
every: 10s
206
warn: $this == 1
207
delay: down 1m multiplier 1.5 max 1h
208
+ summary: VCSA Storage status
209
info: VCSA Storage component status is red. It is unavailable, or will stop functioning soon.
210
to: sysadmin
211
@@ -211,5 +225,6 @@ component: VMware vCenter
225
every: 10s
226
warn: $this == 1
227
delay: down 1m multiplier 1.5 max 1h
228
+ summary: VCSA software status
229
info: VCSA software packages security updates are available.
230
to: silent
health/health.d/vsphere.conf
+4
@@ -15,6 +15,7 @@ component: CPU
15
warn: $this > (($status >= $WARNING) ? (75) : (85))
16
crit: $this > (($status == $CRITICAL) ? (85) : (95))
17
delay: down 15m multiplier 1.5 max 1h
18
+ summary: vSphere CPU utilization for VM ${label:vm}
19
info: CPU utilization VM ${label:vm} host ${label:host} cluster ${label:cluster} datacenter ${label:datacenter}
20
to: silent
21
@@ -30,6 +31,7 @@ component: Memory
31
warn: $this > (($status >= $WARNING) ? (80) : (90))
32
crit: $this > (($status == $CRITICAL) ? (90) : (98))
33
delay: down 15m multiplier 1.5 max 1h
34
+ summary: vSphere memory utilization for VM ${label:vm}
35
info: Memory utilization VM ${label:vm} host ${label:host} cluster ${label:cluster} datacenter ${label:datacenter}
36
to: silent
37
@@ -47,6 +49,7 @@ component: CPU
49
warn: $this > (($status >= $WARNING) ? (75) : (85))
50
crit: $this > (($status == $CRITICAL) ? (85) : (95))
51
delay: down 15m multiplier 1.5 max 1h
52
+ summary: vSphere ESXi CPU utilization for host ${label:host}
53
info: CPU utilization ESXi host ${label:host} cluster ${label:cluster} datacenter ${label:datacenter}
54
to: sysadmin
55
@@ -62,5 +65,6 @@ component: Memory
65
warn: $this > (($status >= $WARNING) ? (80) : (90))
66
crit: $this > (($status == $CRITICAL) ? (90) : (98))
67
delay: down 15m multiplier 1.5 max 1h
68
+ summary: vSphere ESXi Ram utilization for host ${label:host}
69
info: Memory utilization ESXi host ${label:host} cluster ${label:cluster} datacenter ${label:datacenter}
70
to: sysadmin
health/health.d/web_log.conf
+14
-7
@@ -30,7 +30,8 @@ component: Web log
30
every: 10s
31
warn: ($web_log_1m_total_requests > 120) ? ($this > 1) : ( 0 )
32
delay: up 1m down 5m multiplier 1.5 max 1h
33
- info: percentage of unparsed log lines over the last minute
33
+ summary: Web log unparsed
34
+ info: Percentage of unparsed log lines over the last minute
35
to: webmaster
36
37
# -----------------------------------------------------------------------------
@@ -66,7 +67,8 @@ component: Web log
67
warn: ($web_log_1m_requests > 120) ? ($this < (($status >= $WARNING ) ? ( 95 ) : ( 85 )) ) : ( 0 )
68
crit: ($web_log_1m_requests > 120) ? ($this < (($status == $CRITICAL) ? ( 85 ) : ( 75 )) ) : ( 0 )
69
delay: up 2m down 15m multiplier 1.5 max 1h
69
- info: ratio of successful HTTP requests over the last minute (1xx, 2xx, 304, 401)
70
+ summary: Web log successful
71
+ info: Ratio of successful HTTP requests over the last minute (1xx, 2xx, 304, 401)
72
to: webmaster
73
74
template: web_log_1m_redirects
@@ -80,7 +82,8 @@ component: Web log
82
every: 10s
83
warn: ($web_log_1m_requests > 120) ? ($this > (($status >= $WARNING ) ? ( 1 ) : ( 20 )) ) : ( 0 )
84
delay: up 2m down 15m multiplier 1.5 max 1h
83
- info: ratio of redirection HTTP requests over the last minute (3xx except 304)
85
+ summary: Web log redirects
86
+ info: Ratio of redirection HTTP requests over the last minute (3xx except 304)
87
to: webmaster
88
89
template: web_log_1m_bad_requests
@@ -94,7 +97,8 @@ component: Web log
97
every: 10s
98
warn: ($web_log_1m_requests > 120) ? ($this > (($status >= $WARNING) ? ( 10 ) : ( 30 )) ) : ( 0 )
99
delay: up 2m down 15m multiplier 1.5 max 1h
97
- info: ratio of client error HTTP requests over the last minute (4xx except 401)
100
+ summary: Web log bad requests
101
+ info: Ratio of client error HTTP requests over the last minute (4xx except 401)
102
to: webmaster
103
104
template: web_log_1m_internal_errors
@@ -109,7 +113,8 @@ component: Web log
113
warn: ($web_log_1m_requests > 120) ? ($this > (($status >= $WARNING) ? ( 1 ) : ( 2 )) ) : ( 0 )
114
crit: ($web_log_1m_requests > 120) ? ($this > (($status == $CRITICAL) ? ( 2 ) : ( 5 )) ) : ( 0 )
115
delay: up 2m down 15m multiplier 1.5 max 1h
112
- info: ratio of server error HTTP requests over the last minute (5xx)
116
+ summary: Web log server errors
117
+ info: Ratio of server error HTTP requests over the last minute (5xx)
118
to: webmaster
119
120
# -----------------------------------------------------------------------------
@@ -145,7 +150,8 @@ component: Web log
150
warn: ($web_log_1m_requests > 120) ? ($this > $green && $this > ($web_log_10m_response_time * 2) ) : ( 0 )
151
crit: ($web_log_1m_requests > 120) ? ($this > $red && $this > ($web_log_10m_response_time * 4) ) : ( 0 )
152
delay: down 15m multiplier 1.5 max 1h
148
- info: average HTTP response time over the last 1 minute
153
+ summary: Web log processing time
154
+ info: Average HTTP response time over the last 1 minute
155
options: no-clear-notification
156
to: webmaster
157
@@ -192,7 +198,8 @@ component: Web log
198
crit: ($web_log_5m_successful_old > 120) ? ($this > 400 OR $this < 25) : (0)
199
delay: down 15m multiplier 1.5 max 1h
200
options: no-clear-notification
195
- info: ratio of successful HTTP requests over over the last 5 minutes, \
201
+ summary: Web log 5 minutes requests ratio
202
+ info: Ratio of successful HTTP requests over over the last 5 minutes, \
203
compared with the previous 5 minutes \
204
(clear notification for this alarm will not be sent)
205
to: webmaster
health/health.d/whoisquery.conf
+2
-1
@@ -9,5 +9,6 @@ component: WHOIS
9
every: 60s
10
warn: $this < $days_until_expiration_warning*24*60*60
11
crit: $this < $days_until_expiration_critical*24*60*60
12
- info: time until the domain name registration expires
12
+ summary: Whois expiration time for domain ${label:domain}
13
+ info: Time until the domain name registration for ${label:domain} expires
14
to: webmaster
health/health.d/windows.conf
+14
-7
@@ -14,7 +14,8 @@ component: CPU
14
warn: $this > (($status >= $WARNING) ? (75) : (85))
15
crit: $this > (($status == $CRITICAL) ? (85) : (95))
16
delay: down 15m multiplier 1.5 max 1h
17
- info: average CPU utilization over the last 10 minutes
17
+ summary: CPU utilization
18
+ info: Average CPU utilization over the last 10 minutes
19
to: silent
20
21
@@ -33,7 +34,8 @@ component: Memory
34
warn: $this > (($status >= $WARNING) ? (80) : (90))
35
crit: $this > (($status == $CRITICAL) ? (90) : (98))
36
delay: down 15m multiplier 1.5 max 1h
36
- info: memory utilization
37
+ summary: Ram utilization
38
+ info: Memory utilization
39
to: sysadmin
40
41
@@ -51,7 +53,8 @@ component: Network
53
every: 1m
54
warn: $this >= 5
55
delay: down 1h multiplier 1.5 max 2h
54
- info: number of inbound discarded packets for the network interface in the last 10 minutes
56
+ summary: Inbound network packets discarded
57
+ info: Number of inbound discarded packets for the network interface in the last 10 minutes
58
to: silent
59
60
template: windows_outbound_packets_discarded
@@ -66,7 +69,8 @@ component: Network
69
every: 1m
70
warn: $this >= 5
71
delay: down 1h multiplier 1.5 max 2h
69
- info: number of outbound discarded packets for the network interface in the last 10 minutes
72
+ summary: Outbound network packets discarded
73
+ info: Number of outbound discarded packets for the network interface in the last 10 minutes
74
to: silent
75
76
template: windows_inbound_packets_errors
@@ -81,7 +85,8 @@ component: Network
85
every: 1m
86
warn: $this >= 5
87
delay: down 1h multiplier 1.5 max 2h
84
- info: number of inbound errors for the network interface in the last 10 minutes
88
+ summary: Inbound network errors
89
+ info: Number of inbound errors for the network interface in the last 10 minutes
90
to: silent
91
92
template: windows_outbound_packets_errors
@@ -96,7 +101,8 @@ component: Network
101
every: 1m
102
warn: $this >= 5
103
delay: down 1h multiplier 1.5 max 2h
99
- info: number of outbound errors for the network interface in the last 10 minutes
104
+ summary: Outbound network errors
105
+ info: Number of outbound errors for the network interface in the last 10 minutes
106
to: silent
107
108
@@ -115,5 +121,6 @@ component: Disk
121
warn: $this > (($status >= $WARNING) ? (80) : (90))
122
crit: $this > (($status == $CRITICAL) ? (90) : (98))
123
delay: down 15m multiplier 1.5 max 1h
118
- info: disk space utilization
124
+ summary: Disk space usage
125
+ info: Disk space utilization
126
to: sysadmin
health/health.d/x509check.conf
+4
-2
@@ -9,7 +9,8 @@ component: x509 certificates
9
every: 60s
10
warn: $this < $days_until_expiration_warning*24*60*60
11
crit: $this < $days_until_expiration_critical*24*60*60
12
- info: time until x509 certificate expires
12
+ summary: x509 certificate expiration for ${label:source}
13
+ info: Time until x509 certificate expires for ${label:source}
14
to: webmaster
15
16
template: x509check_revocation_status
@@ -20,5 +21,6 @@ component: x509 certificates
21
calc: $revoked
22
every: 60s
23
crit: $this != nan AND $this != 0
23
- info: x509 certificate revocation status (0: revoked, 1: valid)
24
+ summary: x509 certificate revocation status for ${label:source}
25
+ info: x509 certificate revocation status (0: revoked, 1: valid) for ${label:source}
26
to: webmaster
health/health.d/zfs.conf
+1
-1
@@ -9,7 +9,7 @@ component: File system
9
every: 1m
10
warn: $this > 0
11
delay: down 1h multiplier 1.5 max 2h
12
- summary: ZFS memory throttle
12
+ summary: ZFS ARC growth throttling
13
info: number of times ZFS had to limit the ARC growth in the last 10 minutes
14
to: silent
15