fix(alerting): removing some of criticals (#15124)
Mateusz Bularz committed
Jul 6, 2023 at 11:43 UTC
94ec32356117cf09ef6e4f79329dc00c911b8015
21 files changed
+12
-54
health/health.d/apcupsd.conf
+1
-3
@@ -11,7 +11,6 @@ component: UPS
11
units: %
12
every: 1m
13
warn: $this > (($status >= $WARNING) ? (70) : (80))
14
- crit: $this > (($status == $CRITICAL) ? (85) : (95))
14
delay: down 10m multiplier 1.5 max 1h
15
info: average UPS load over the last 10 minutes
16
to: sitemgr
@@ -29,7 +28,7 @@ component: UPS
28
units: %
29
every: 60s
30
warn: $this < 100
32
- crit: $this < (($status == $CRITICAL) ? (60) : (50))
31
+ crit: $this < 40
32
delay: down 10m multiplier 1.5 max 1h
33
info: average UPS charge over the last minute
34
to: sitemgr
@@ -43,7 +42,6 @@ component: UPS device
42
every: 10s
43
units: seconds ago
44
warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
46
- crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
45
delay: down 5m multiplier 1.5 max 1h
46
info: number of seconds since the last successful data collection
47
to: sitemgr
health/health.d/bcache.conf
+1
-2
@@ -22,8 +22,7 @@ component: Disk
22
calc: $dirty + $metadata + $undefined
23
units: %
24
every: 1m
25
- warn: $this > ( ($status >= $WARNING ) ? ( 70 ) : ( 90 ) )
26
- crit: $this > ( ($status == $CRITICAL) ? ( 90 ) : ( 95 ) )
25
+ warn: $this > 75
26
delay: up 1m down 1h multiplier 1.5 max 2h
27
info: percentage of cache space used for dirty data and metadata \
28
(this usually means your SSD cache is too small)
health/health.d/beanstalkd.conf
+1
-2
@@ -8,8 +8,7 @@ component: Beanstalk
8
calc: $buried
9
units: jobs
10
every: 10s
11
- warn: $this > 0
12
- crit: $this > 10
11
+ warn: $this > 3
12
delay: up 0 down 5m multiplier 1.2 max 1h
13
info: number of buried jobs across all tubes. \
14
You need to manually kick them so they can be processed. \
health/health.d/bind_rndc.conf
-1
@@ -7,6 +7,5 @@ component: BIND
7
every: 60
8
calc: $stats_size
9
warn: $this > 512
10
- crit: $this > 1024
10
info: BIND statistics-file size
11
to: sysadmin
health/health.d/boinc.conf
-4
@@ -12,7 +12,6 @@ component: BOINC
12
units: tasks
13
every: 1m
14
warn: $this > 0
15
- crit: $this > 1
15
delay: up 1m down 5m multiplier 1.5 max 1h
16
info: average number of compute errors over the last 10 minutes
17
to: sysadmin
@@ -29,7 +28,6 @@ component: BOINC
28
units: tasks
29
every: 1m
30
warn: $this > 0
32
- crit: $this > 1
31
delay: up 1m down 5m multiplier 1.5 max 1h
32
info: average number of failed uploads over the last 10 minutes
33
to: sysadmin
@@ -46,7 +44,6 @@ component: BOINC
44
units: tasks
45
every: 1m
46
warn: $this < 1
49
- crit: $this < 0.1
47
delay: up 5m down 10m multiplier 1.5 max 1h
48
info: average number of total tasks over the last 10 minutes
49
to: sysadmin
@@ -64,7 +61,6 @@ component: BOINC
61
units: tasks
62
every: 1m
63
warn: $this < 1
67
- crit: $this < 0.1
64
delay: up 5m down 10m multiplier 1.5 max 1h
65
info: average number of active tasks over the last 10 minutes
66
to: sysadmin
health/health.d/cgroups.conf
-3
@@ -64,7 +64,6 @@ component: Network
64
every: 10s
65
units: %
66
warn: $this > (($status >= $WARNING)?(200):(5000))
67
- crit: $this > (($status == $CRITICAL)?(5000):(6000))
67
options: no-clear-notification
68
info: ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, \
69
compared to the rate over the last minute
@@ -83,7 +82,6 @@ component: CPU
82
units: %
83
every: 1m
84
warn: $this > (($status >= $WARNING) ? (75) : (85))
86
- crit: $this > (($status == $CRITICAL) ? (85) : (95))
85
delay: down 15m multiplier 1.5 max 1h
86
info: average cgroup CPU utilization over the last 10 minutes
87
to: sysadmin
@@ -134,7 +132,6 @@ component: Network
132
every: 10s
133
units: %
134
warn: $this > (($status >= $WARNING)?(200):(5000))
137
- crit: $this > (($status == $CRITICAL)?(5000):(6000))
135
options: no-clear-notification
136
info: ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, \
137
compared to the rate over the last minute
health/health.d/cpu.conf
-2
@@ -28,7 +28,6 @@ component: CPU
28
units: %
29
every: 1m
30
warn: $this > (($status >= $WARNING) ? (20) : (40))
31
- crit: $this > (($status == $CRITICAL) ? (40) : (50))
31
delay: down 15m multiplier 1.5 max 1h
32
info: average CPU iowait time over the last 10 minutes
33
to: sysadmin
@@ -44,7 +43,6 @@ component: CPU
43
units: %
44
every: 5m
45
warn: $this > (($status >= $WARNING) ? (5) : (10))
47
- crit: $this > (($status == $CRITICAL) ? (20) : (30))
46
delay: down 1h multiplier 1.5 max 2h
47
info: average CPU steal time over the last 20 minutes
48
to: sysadmin
health/health.d/dnsmasq_dhcp.conf
-1
@@ -9,7 +9,6 @@ component: Dnsmasq
9
units: %
10
calc: $used
11
warn: $this > ( ($status >= $WARNING ) ? ( 80 ) : ( 90 ) )
12
- crit: $this > ( ($status == $CRITICAL) ? ( 90 ) : ( 95 ) )
12
delay: down 5m
13
info: DHCP range utilization
14
to: sysadmin
health/health.d/docker.conf
+1
-1
@@ -6,6 +6,6 @@ component: Docker
6
units: status
7
every: 10s
8
lookup: average -10s of unhealthy
9
- crit: $this > 0
9
+ warn: $this > 0
10
info: ${label:container_name} docker container health status is unhealthy
11
to: sysadmin
health/health.d/elasticsearch.conf
+1
-1
@@ -10,7 +10,7 @@ component: Elasticsearch
10
lookup: average -5s unaligned of *ed
11
every: 10s
12
units: status
13
- warn: $this == 1
13
+ crit: $this == 1
14
delay: down 5m multiplier 1.5 max 1h
15
info: cluster health status is red.
16
to: sysadmin
health/health.d/gearman.conf
-1
@@ -8,7 +8,6 @@ component: Gearman
8
units: workers
9
every: 10s
10
warn: $this > 30000
11
- crit: $this > 100000
11
delay: down 5m multiplier 1.5 max 1h
12
info: average number of queued jobs over the last 10 minutes
13
to: sysadmin
health/health.d/geth.conf
-1
@@ -8,5 +8,4 @@ component: geth
8
calc: $chain_head_block - $chain_head_header
9
units: blocks
10
warn: $this != 0
11
- crit: $this > 5
11
delay: down 1m multiplier 1.5 max 1h
health/health.d/ioping.conf
+1
-3
@@ -6,10 +6,8 @@ component: Disk
6
lookup: average -10s unaligned of latency
7
units: microseconds
8
every: 10s
9
- green: 5000
10
- red: 10000
9
+ green: 10000
10
warn: $this > $green
12
- crit: $this > $red
11
delay: down 30m multiplier 1.5 max 2h
12
info: average I/O latency over the last 10 seconds
13
to: sysadmin
health/health.d/ipc.conf
-2
@@ -12,7 +12,6 @@ component: IPC
12
units: %
13
every: 10s
14
warn: $this > (($status >= $WARNING) ? (70) : (80))
15
- crit: $this > (($status == $CRITICAL) ? (70) : (90))
15
delay: down 5m multiplier 1.5 max 1h
16
info: IPC semaphore utilization
17
to: sysadmin
@@ -28,7 +27,6 @@ component: IPC
27
units: %
28
every: 10s
29
warn: $this > (($status >= $WARNING) ? (70) : (80))
31
- crit: $this > (($status == $CRITICAL) ? (70) : (90))
30
delay: down 5m multiplier 1.5 max 1h
31
info: IPC semaphore arrays utilization
32
to: sysadmin
health/health.d/linux_power_supply.conf
-1
@@ -9,7 +9,6 @@ component: Battery
9
units: %
10
every: 10s
11
warn: $this < 10
12
- crit: $this < 5
12
delay: up 30s down 5m multiplier 1.2 max 1h
13
info: percentage of remaining power supply capacity
14
to: sysadmin
health/health.d/nut.conf
+2
-2
@@ -26,8 +26,8 @@ component: UPS
26
lookup: average -60s unaligned of battery_charge
27
units: %
28
every: 60s
29
- warn: $this < 100
30
- crit: $this < (($status == $CRITICAL) ? (60) : (50))
29
+ warn: $this < 75
30
+ crit: $this < 40
31
delay: down 10m multiplier 1.5 max 1h
32
info: average UPS charge over the last minute
33
to: sitemgr
health/health.d/pihole.conf
+1
-2
@@ -10,8 +10,7 @@ component: Pi-hole
10
every: 10s
11
units: seconds
12
calc: $ago
13
- warn: $this > 60 * 60 * 24 * 8
14
- crit: $this > 60 * 60 * 24 * 8 * 2
13
+ warn: $this > 60 * 60 * 24 * 30
14
info: gravity.list (blocklist) file last update time
15
to: sysadmin
16
health/health.d/ram.conf
-2
@@ -28,7 +28,6 @@ component: Memory
28
units: %
29
every: 10s
30
warn: $this < (($status >= $WARNING) ? (15) : (10))
31
- crit: $this < (($status == $CRITICAL) ? (10) : ( 5))
31
delay: down 15m multiplier 1.5 max 1h
32
info: percentage of estimated amount of RAM available for userspace processes, without causing swapping
33
to: sysadmin
@@ -74,7 +73,6 @@ component: Memory
73
units: %
74
every: 10s
75
warn: $this < (($status >= $WARNING) ? (15) : (10))
77
- crit: $this < (($status == $CRITICAL) ? (10) : ( 5))
76
delay: down 15m multiplier 1.5 max 1h
77
info: percentage of estimated amount of RAM available for userspace processes, without causing swapping
78
to: sysadmin
health/health.d/scaleio.conf
+2
-2
@@ -9,8 +9,8 @@ component: ScaleIO
9
calc: $used
10
units: %
11
every: 10s
12
- warn: $this > (($status >= $WARNING) ? (80) : (90))
13
- crit: $this > (($status == $CRITICAL) ? (90) : (98))
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
16
to: sysadmin
health/health.d/vcsa.conf
+1
-2
@@ -133,8 +133,7 @@ component: VMware vCenter
133
lookup: max -10s unaligned of software_packages
134
units: status
135
every: 10s
136
- warn: $this == 4
137
- crit: $this == 3
136
+ warn: ($this == 3) || ($this == 4)
137
delay: down 1m multiplier 1.5 max 1h
138
info: software updates availability status \
139
(-1: unknown, 0: green, 2: orange, 3: red, 4: grey)
health/health.d/windows.conf
-16
@@ -36,22 +36,6 @@ component: Memory
36
info: memory utilization
37
to: sysadmin
38
39
- template: windows_swap_in_use
40
- on: windows.memory_swap_utilization
41
- class: Utilization
42
- type: Windows
43
-component: Memory
44
- os: linux
45
- hosts: *
46
- calc: ($used) * 100 / ($used + $available)
47
- units: %
48
- every: 10s
49
- warn: $this > (($status >= $WARNING) ? (80) : (90))
50
- crit: $this > (($status == $CRITICAL) ? (90) : (98))
51
- delay: down 15m multiplier 1.5 max 1h
52
- info: swap memory utilization
53
- to: sysadmin
54
-
39
40
## Network
41