use specific charts labels instead of family in alarms (#14173)
Ilya Mashchenko committed
Dec 23, 2022 at 15:10 UTC
1a326fc1ce9ecbcce5ca4b4b72a3bea8f8da0f3b
6 files changed
+28
-26
collectors/proc.plugin/proc_spl_kstat_zfs.c
+2
@@ -285,6 +285,8 @@ int update_zfs_pool_state_chart(const DICTIONARY_ITEM *item, void *pool_p, void
285
pool->rd_offline = rrddim_add(pool->st, "offline", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE);
286
pool->rd_removed = rrddim_add(pool->st, "removed", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE);
287
pool->rd_unavail = rrddim_add(pool->st, "unavail", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE);
288
+
289
+ rrdlabels_add(pool->st->rrdlabels, "pool", name, RRDLABEL_SRC_AUTO);
290
}
291
292
rrddim_set_by_pointer(pool->st, pool->rd_online, pool->online);
health/health.d/cgroups.conf
+4
-4
@@ -51,7 +51,7 @@ component: Network
51
lookup: average -1m unaligned of received
52
units: packets
53
every: 10s
54
- info: average number of packets received by the network interface $family over the last minute
54
+ info: average number of packets received by the network interface $label:device over the last minute
55
56
template: cgroup_10s_received_packets_storm
57
on: cgroup.net_packets
@@ -66,7 +66,7 @@ component: Network
66
warn: $this > (($status >= $WARNING)?(200):(5000))
67
crit: $this > (($status == $CRITICAL)?(5000):(6000))
68
options: no-clear-notification
69
- info: ratio of average number of received packets for the network interface $family over the last 10 seconds, \
69
+ info: ratio of average number of received packets for the network interface $label:device over the last 10 seconds, \
70
compared to the rate over the last minute
71
to: sysadmin
72
@@ -121,7 +121,7 @@ component: Network
121
lookup: average -1m unaligned of received
122
units: packets
123
every: 10s
124
- info: average number of packets received by the network interface $family over the last minute
124
+ info: average number of packets received by the network interface $label:device over the last minute
125
126
template: k8s_cgroup_10s_received_packets_storm
127
on: k8s.cgroup.net_packets
@@ -136,6 +136,6 @@ component: Network
136
warn: $this > (($status >= $WARNING)?(200):(5000))
137
crit: $this > (($status == $CRITICAL)?(5000):(6000))
138
options: no-clear-notification
139
- info: ratio of average number of received packets for the network interface $family over the last 10 seconds, \
139
+ info: ratio of average number of received packets for the network interface $label:device over the last 10 seconds, \
140
compared to the rate over the last minute
141
to: sysadmin
health/health.d/disks.conf
+4
-4
@@ -23,7 +23,7 @@ component: Disk
23
warn: $this > (($status >= $WARNING ) ? (80) : (90))
24
crit: $this > (($status == $CRITICAL) ? (90) : (98))
25
delay: up 1m down 15m multiplier 1.5 max 1h
26
- info: disk $family space utilization
26
+ info: disk $label:mount_point space utilization
27
to: sysadmin
28
29
template: disk_inode_usage
@@ -40,7 +40,7 @@ component: Disk
40
warn: $this > (($status >= $WARNING) ? (80) : (90))
41
crit: $this > (($status == $CRITICAL) ? (90) : (98))
42
delay: up 1m down 15m multiplier 1.5 max 1h
43
- info: disk $family inode utilization
43
+ info: disk $label:mount_point inode utilization
44
to: sysadmin
45
46
@@ -147,7 +147,7 @@ component: Disk
147
every: 1m
148
warn: $this > 98 * (($status >= $WARNING) ? (0.7) : (1))
149
delay: down 15m multiplier 1.2 max 1h
150
- info: average percentage of time $family disk was busy over the last 10 minutes
150
+ info: average percentage of time $label:device disk was busy over the last 10 minutes
151
to: silent
152
153
@@ -169,5 +169,5 @@ component: Disk
169
every: 1m
170
warn: $this > 5000 * (($status >= $WARNING) ? (0.7) : (1))
171
delay: down 15m multiplier 1.2 max 1h
172
- info: average backlog size of the $family disk over the last 10 minutes
172
+ info: average backlog size of the $label:device disk over the last 10 minutes
173
to: silent
health/health.d/mdstat.conf
+2
-2
@@ -20,7 +20,7 @@ component: RAID
20
every: 10s
21
calc: $down
22
crit: $this > 0
23
- info: number of devices in the down state for the $family array. \
23
+ info: number of devices in the down state for the $label:device $label:raid_level array. \
24
Any number > 0 indicates that the array is degraded.
25
to: sysadmin
26
@@ -35,7 +35,7 @@ component: RAID
35
every: 60s
36
warn: $this > 1024
37
delay: up 30m
38
- info: number of unsynchronized blocks for the $family array
38
+ info: number of unsynchronized blocks for the $label:device $label:raid_level array
39
to: sysadmin
40
41
template: mdstat_nonredundant_last_collected
health/health.d/net.conf
+14
-14
@@ -15,7 +15,7 @@ component: Network
15
calc: ( $nic_speed_max > 0 ) ? ( $nic_speed_max) : ( nan )
16
units: Mbit
17
every: 10s
18
- info: network interface $family current speed
18
+ info: network interface $label:device current speed
19
20
template: 1m_received_traffic_overflow
21
on: net.net
@@ -31,7 +31,7 @@ component: Network
31
every: 10s
32
warn: $this > (($status >= $WARNING) ? (85) : (90))
33
delay: up 1m down 1m multiplier 1.5 max 1h
34
- info: average inbound utilization for the network interface $family over the last minute
34
+ info: average inbound utilization for the network interface $label:device over the last minute
35
to: sysadmin
36
37
template: 1m_sent_traffic_overflow
@@ -48,7 +48,7 @@ component: Network
48
every: 10s
49
warn: $this > (($status >= $WARNING) ? (85) : (90))
50
delay: up 1m down 1m multiplier 1.5 max 1h
51
- info: average outbound utilization for the network interface $family over the last minute
51
+ info: average outbound utilization for the network interface $label:device over the last minute
52
to: sysadmin
53
54
# -----------------------------------------------------------------------------
@@ -72,7 +72,7 @@ component: Network
72
lookup: sum -10m unaligned absolute of inbound
73
units: packets
74
every: 1m
75
- info: number of inbound dropped packets for the network interface $family in the last 10 minutes
75
+ info: number of inbound dropped packets for the network interface $label:device in the last 10 minutes
76
77
template: outbound_packets_dropped
78
on: net.drops
@@ -85,7 +85,7 @@ component: Network
85
lookup: sum -10m unaligned absolute of outbound
86
units: packets
87
every: 1m
88
- info: number of outbound dropped packets for the network interface $family in the last 10 minutes
88
+ info: number of outbound dropped packets for the network interface $label:device in the last 10 minutes
89
90
template: inbound_packets_dropped_ratio
91
on: net.packets
@@ -101,7 +101,7 @@ component: Network
101
every: 1m
102
warn: $this >= 2
103
delay: up 1m down 1h multiplier 1.5 max 2h
104
- info: ratio of inbound dropped packets for the network interface $family over the last 10 minutes
104
+ info: ratio of inbound dropped packets for the network interface $label:device over the last 10 minutes
105
to: sysadmin
106
107
template: outbound_packets_dropped_ratio
@@ -118,7 +118,7 @@ component: Network
118
every: 1m
119
warn: $this >= 2
120
delay: up 1m down 1h multiplier 1.5 max 2h
121
- info: ratio of outbound dropped packets for the network interface $family over the last 10 minutes
121
+ info: ratio of outbound dropped packets for the network interface $label:device over the last 10 minutes
122
to: sysadmin
123
124
template: wifi_inbound_packets_dropped_ratio
@@ -135,7 +135,7 @@ component: Network
135
every: 1m
136
warn: $this >= 10
137
delay: up 1m down 1h multiplier 1.5 max 2h
138
- info: ratio of inbound dropped packets for the network interface $family over the last 10 minutes
138
+ info: ratio of inbound dropped packets for the network interface $label:device over the last 10 minutes
139
to: sysadmin
140
141
template: wifi_outbound_packets_dropped_ratio
@@ -152,7 +152,7 @@ component: Network
152
every: 1m
153
warn: $this >= 10
154
delay: up 1m down 1h multiplier 1.5 max 2h
155
- info: ratio of outbound dropped packets for the network interface $family over the last 10 minutes
155
+ info: ratio of outbound dropped packets for the network interface $label:device over the last 10 minutes
156
to: sysadmin
157
158
# -----------------------------------------------------------------------------
@@ -171,7 +171,7 @@ component: Network
171
every: 1m
172
warn: $this >= 5
173
delay: down 1h multiplier 1.5 max 2h
174
- info: number of inbound errors for the network interface $family in the last 10 minutes
174
+ info: number of inbound errors for the network interface $label:device in the last 10 minutes
175
to: sysadmin
176
177
template: interface_outbound_errors
@@ -187,7 +187,7 @@ component: Network
187
every: 1m
188
warn: $this >= 5
189
delay: down 1h multiplier 1.5 max 2h
190
- info: number of outbound errors for the network interface $family in the last 10 minutes
190
+ info: number of outbound errors for the network interface $label:device in the last 10 minutes
191
to: sysadmin
192
193
# -----------------------------------------------------------------------------
@@ -211,7 +211,7 @@ component: Network
211
every: 1m
212
warn: $this > 0
213
delay: down 1h multiplier 1.5 max 2h
214
- info: number of FIFO errors for the network interface $family in the last 10 minutes
214
+ info: number of FIFO errors for the network interface $label:device in the last 10 minutes
215
to: sysadmin
216
217
# -----------------------------------------------------------------------------
@@ -234,7 +234,7 @@ component: Network
234
lookup: average -1m unaligned of received
235
units: packets
236
every: 10s
237
- info: average number of packets received by the network interface $family over the last minute
237
+ info: average number of packets received by the network interface $label:device over the last minute
238
239
template: 10s_received_packets_storm
240
on: net.packets
@@ -251,6 +251,6 @@ component: Network
251
warn: $this > (($status >= $WARNING)?(200):(5000))
252
crit: $this > (($status == $CRITICAL)?(5000):(6000))
253
options: no-clear-notification
254
- info: ratio of average number of received packets for the network interface $family over the last 10 seconds, \
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: sysadmin
health/health.d/zfs.conf
+2
-2
@@ -24,7 +24,7 @@ component: File system
24
every: 10s
25
warn: $this > 0
26
delay: down 1m multiplier 1.5 max 1h
27
- info: ZFS pool $family state is degraded
27
+ info: ZFS pool $label:pool state is degraded
28
to: sysadmin
29
30
template: zfs_pool_state_crit
@@ -37,5 +37,5 @@ component: File system
37
every: 10s
38
crit: $this > 0
39
delay: down 1m multiplier 1.5 max 1h
40
- info: ZFS pool $family state is faulted or unavail
40
+ info: ZFS pool $label:pool state is faulted or unavail
41
to: sysadmin