Skip to content

Commit 0eb743e

Browse files
committed
bindata/alerts/slo: disregard health endpoints
Signed-off-by: Damien Grisonnet <[email protected]>
1 parent 2a0efa5 commit 0eb743e

File tree

2 files changed

+56
-56
lines changed

2 files changed

+56
-56
lines changed

bindata/assets/alerts/kube-apiserver-slos-basic.yaml

Lines changed: 32 additions & 32 deletions
Original file line numberDiff line numberDiff line change
@@ -43,23 +43,23 @@ spec:
4343
(
4444
(
4545
# too slow
46-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m]))
46+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz"}[5m]))
4747
-
4848
(
4949
(
50-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(.0)?"}[5m]))
50+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz",scope=~"resource|",le=~"1(.0)?"}[5m]))
5151
or
5252
vector(0)
5353
)
5454
+
55-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(.0)?"}[5m]))
55+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz",scope="namespace",le=~"5(.0)?"}[5m]))
5656
+
57-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(.0)?"}[5m]))
57+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz",scope="cluster",le=~"30(.0)?"}[5m]))
5858
)
5959
)
6060
+
6161
# errors
62-
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[5m]))
62+
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",subresource!~"/healthz|/livez|/readyz",code=~"5.."}[5m]))
6363
)
6464
/
6565
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m]))
@@ -70,23 +70,23 @@ spec:
7070
(
7171
(
7272
# too slow
73-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[30m]))
73+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz"}[30m]))
7474
-
7575
(
7676
(
77-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(.0)?"}[30m]))
77+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz",scope=~"resource|",le=~"1(.0)?"}[30m]))
7878
or
7979
vector(0)
8080
)
8181
+
82-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(.0)?"}[30m]))
82+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz",scope="namespace",le=~"5(.0)?"}[30m]))
8383
+
84-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(.0)?"}[30m]))
84+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz",scope="cluster",le=~"30(.0)?"}[30m]))
8585
)
8686
)
8787
+
8888
# errors
89-
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[30m]))
89+
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",subresource!~"/healthz|/livez|/readyz",code=~"5.."}[30m]))
9090
)
9191
/
9292
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[30m]))
@@ -97,23 +97,23 @@ spec:
9797
(
9898
(
9999
# too slow
100-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1h]))
100+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz"}[1h]))
101101
-
102102
(
103103
(
104-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(.0)?"}[1h]))
104+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz",scope=~"resource|",le=~"1(.0)?"}[1h]))
105105
or
106106
vector(0)
107107
)
108108
+
109-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(.0)?"}[1h]))
109+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz",scope="namespace",le=~"5(.0)?"}[1h]))
110110
+
111-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(.0)?"}[1h]))
111+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz",scope="cluster",le="30(.0)?"}[1h]))
112112
)
113113
)
114114
+
115115
# errors
116-
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1h]))
116+
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",subresource!~"/healthz|/livez|/readyz",code=~"5.."}[1h]))
117117
)
118118
/
119119
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1h]))
@@ -124,23 +124,23 @@ spec:
124124
(
125125
(
126126
# too slow
127-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[6h]))
127+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz"}[6h]))
128128
-
129129
(
130130
(
131-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le=~"1(.0)?"}[6h]))
131+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz",scope=~"resource|",le=~"1(.0)?"}[6h]))
132132
or
133133
vector(0)
134134
)
135135
+
136-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le=~"5(.0)?"}[6h]))
136+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz",scope="namespace",le=~"5(.0)?"}[6h]))
137137
+
138-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le=~"30(.0)?"}[6h]))
138+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz",scope="cluster",le=~"30(.0)?"}[6h]))
139139
)
140140
)
141141
+
142142
# errors
143-
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[6h]))
143+
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",subresource!~"/healthz|/livez|/readyz",code=~"5.."}[6h]))
144144
)
145145
/
146146
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[6h]))
@@ -151,12 +151,12 @@ spec:
151151
(
152152
(
153153
# too slow
154-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1h]))
154+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz"}[1h]))
155155
-
156-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(.0)?"}[1h]))
156+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz",le=~"1(.0)?"}[1h]))
157157
)
158158
+
159-
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1h]))
159+
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"/healthz|/livez|/readyz",code=~"5.."}[1h]))
160160
)
161161
/
162162
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h]))
@@ -167,12 +167,12 @@ spec:
167167
(
168168
(
169169
# too slow
170-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[30m]))
170+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz"}[30m]))
171171
-
172-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(.0)?"}[30m]))
172+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz",le=~"1(.0)?"}[30m]))
173173
)
174174
+
175-
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[30m]))
175+
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"/healthz|/livez|/readyz",code=~"5.."}[30m]))
176176
)
177177
/
178178
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m]))
@@ -183,12 +183,12 @@ spec:
183183
(
184184
(
185185
# too slow
186-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m]))
186+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz"}[5m]))
187187
-
188-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(.0)?"}[5m]))
188+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz",le=~"1(.0)?"}[5m]))
189189
)
190190
+
191-
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[5m]))
191+
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"/healthz|/livez|/readyz",code=~"5.."}[5m]))
192192
)
193193
/
194194
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
@@ -199,12 +199,12 @@ spec:
199199
(
200200
(
201201
# too slow
202-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[6h]))
202+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz"}[6h]))
203203
-
204-
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le=~"1(.0)?"}[6h]))
204+
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward|/healthz|/livez|/readyz",le=~"1(.0)?"}[6h]))
205205
)
206206
+
207-
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[6h]))
207+
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"/healthz|/livez|/readyz",code=~"5.."}[6h]))
208208
)
209209
/
210210
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h]))

0 commit comments

Comments
 (0)