Skip to content

Commit 8803337

Browse files
authored
Merge pull request #111 from TicketPing/feature/monitoring
[feature #110] 모니터링 알람 추가
2 parents 0ec5adc + 240376f commit 8803337

File tree

1 file changed

+134
-7
lines changed

1 file changed

+134
-7
lines changed

monitoring/grafana/provisioning/alerting/alert-rule.yml

Lines changed: 134 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -1,12 +1,12 @@
11
apiVersion: 1
22
groups:
33
- orgId: 1
4-
name: TicketPing
4+
name: TicketPing-CPU
55
folder: TicketPing
66
interval: 1m
77
rules:
88
- uid: de31h1522x1j4c
9-
title: Gateway CPU Usage Over 50%
9+
title: CPU Usage Over 80%
1010
condition: C
1111
data:
1212
- refId: A
@@ -36,7 +36,7 @@ groups:
3636
conditions:
3737
- evaluator:
3838
params:
39-
- 0.5
39+
- 0.8
4040
type: gt
4141
operator:
4242
type: and
@@ -57,16 +57,143 @@ groups:
5757
type: threshold
5858
dashboardUid: ""
5959
panelId: 0
60-
noDataState: Alerting
60+
noDataState: OK
6161
execErrState: Alerting
62-
for: 1m
62+
for: 0s
6363
annotations: {}
6464
labels: {}
6565
isPaused: false
6666
notification_settings:
6767
receiver: TicketPing-Discord
6868
- orgId: 1
69-
name: CircuitBreaker Open or Half_Open for 5m
69+
name: TicketPing-CPU
70+
folder: TicketPing
71+
interval: 1m
72+
rules:
73+
- uid: ee8sedq6voge8c
74+
title: CPU Usage Over 50% in 1m
75+
condition: C
76+
data:
77+
- refId: A
78+
relativeTimeRange:
79+
from: 300
80+
to: 0
81+
datasourceUid: PBFA97CFB590B2093
82+
model:
83+
disableTextWrap: false
84+
editorMode: builder
85+
expr: avg_over_time(system_cpu_usage{instance="host.docker.internal:10001"}[1m])
86+
fullMetaSearch: false
87+
includeNullMetadata: true
88+
instant: true
89+
intervalMs: 1000
90+
legendFormat: __auto
91+
maxDataPoints: 43200
92+
range: false
93+
refId: A
94+
useBackend: false
95+
- refId: C
96+
relativeTimeRange:
97+
from: 300
98+
to: 0
99+
datasourceUid: __expr__
100+
model:
101+
conditions:
102+
- evaluator:
103+
params:
104+
- 0.5
105+
type: gt
106+
operator:
107+
type: and
108+
query:
109+
params:
110+
- C
111+
reducer:
112+
params: [ ]
113+
type: last
114+
type: query
115+
datasource:
116+
type: __expr__
117+
uid: __expr__
118+
expression: A
119+
intervalMs: 1000
120+
maxDataPoints: 43200
121+
refId: C
122+
type: threshold
123+
noDataState: OK
124+
execErrState: Error
125+
for: 1m
126+
annotations: { }
127+
labels: { }
128+
isPaused: false
129+
notification_settings:
130+
receiver: TicketPing-Discord
131+
- orgId: 1
132+
name: CircuitBreaker
133+
folder: TicketPing
134+
interval: 1m
135+
rules:
136+
- uid: ae8shaqrswcn4a
137+
title: CircuitBreaker Open
138+
condition: C
139+
data:
140+
- refId: A
141+
relativeTimeRange:
142+
from: 600
143+
to: 0
144+
datasourceUid: PBFA97CFB590B2093
145+
model:
146+
disableTextWrap: false
147+
editorMode: builder
148+
expr: sum by(name) (resilience4j_circuitbreaker_state{state=~"open|half_open"})
149+
fullMetaSearch: false
150+
includeNullMetadata: true
151+
instant: true
152+
intervalMs: 1000
153+
legendFormat: __auto
154+
maxDataPoints: 43200
155+
range: false
156+
refId: A
157+
useBackend: false
158+
- refId: C
159+
relativeTimeRange:
160+
from: 600
161+
to: 0
162+
datasourceUid: __expr__
163+
model:
164+
conditions:
165+
- evaluator:
166+
params:
167+
- 0.99
168+
type: gt
169+
operator:
170+
type: and
171+
query:
172+
params:
173+
- C
174+
reducer:
175+
params: [ ]
176+
type: last
177+
type: query
178+
datasource:
179+
type: __expr__
180+
uid: __expr__
181+
expression: A
182+
intervalMs: 1000
183+
maxDataPoints: 43200
184+
refId: C
185+
type: threshold
186+
noDataState: OK
187+
execErrState: Error
188+
for: 0s
189+
annotations:
190+
description: CircuitBreaker ''{{ $labels.name }}'' has change from CLOSED to OPEN.
191+
labels: { }
192+
isPaused: false
193+
notification_settings:
194+
receiver: TicketPing-Discord
195+
- orgId: 1
196+
name: CircuitBreaker
70197
folder: TicketPing
71198
interval: 1m
72199
rules:
@@ -125,7 +252,7 @@ groups:
125252
execErrState: Error
126253
for: 1m
127254
annotations:
128-
description: '"CircuitBreaker ''{{ $labels.name }}'' has been in an OPEN or HALF_OPEN state for 5 minutes."'
255+
description: 'CircuitBreaker ''{{ $labels.name }}'' has been in an OPEN or HALF_OPEN state for 5 minutes.'
129256
labels: {}
130257
isPaused: false
131258
notification_settings:

0 commit comments

Comments
 (0)