summaryrefslogtreecommitdiffstats
path: root/monitoring/ceph-mixin/tests_dashboards/features/radosgw_overview.feature
blob: 642e4397878287cd8a030cc44c1776b3a3009b26 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
Feature: RGW Overview Dashboard

Scenario: "Test Average GET Latencies"
  Given the following series:
    | metrics | values |
    | ceph_rgw_get_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 50 100 |
    | ceph_rgw_get_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 20 60 80 |
    | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
  When interval is `30s`
  Then Grafana panel `Average GET/PUT Latencies by RGW Instance` with legend `GET {{rgw_host}}` shows:
    | metrics | values |
    | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph", rgw_host="foo"} | 1.5 |

Scenario: "Test Average PUT Latencies"
  Given the following series:
    | metrics | values |
    | ceph_rgw_put_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 15 35 55 |
    | ceph_rgw_put_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 30 50 |
    | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
  When interval is `30s`
  Then Grafana panel `Average GET/PUT Latencies by RGW Instance` with legend `PUT {{rgw_host}}` shows:
    | metrics | values |
    | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph", rgw_host="foo"} | 1 |

Scenario: "Test Total Requests/sec by RGW Instance"
  Given the following series:
    | metrics | values |
    | ceph_rgw_req{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
    | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 |
  When interval is `30s`
  Then Grafana panel `Total Requests/sec by RGW Instance` with legend `{{rgw_host}}` shows:
    | metrics | values |
    | {rgw_host="1"} | 1.5 |

Scenario: "Test GET Latencies by RGW Instance"
  Given the following series:
    | metrics | values |
    | ceph_rgw_get_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 50 100 |
    | ceph_rgw_get_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 20 60 80 |
    | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
  When interval is `30s`
  Then Grafana panel `GET Latencies by RGW Instance` with legend `{{rgw_host}}` shows:
    | metrics | values |
    | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph", rgw_host="foo"} | 1.5 |

Scenario: "Test Bandwidth Consumed by Type- GET"
  Given the following series:
    | metrics | values |
    | ceph_rgw_get_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
  When evaluation time is `1m`
  And interval is `30s`
  Then Grafana panel `Bandwidth Consumed by Type` with legend `GETs` shows:
    | metrics | values |
    | {} | 1.5 |

Scenario: "Test Bandwidth Consumed by Type- PUT"
  Given the following series:
    | metrics | values |
    | ceph_rgw_put_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 5 20 50 |
  When evaluation time is `1m`
  And interval is `30s`
  Then Grafana panel `Bandwidth Consumed by Type` with legend `PUTs` shows:
    | metrics | values |
    | {} | 7.5E-01 |

Scenario: "Test Bandwidth by RGW Instance"
  Given the following series:
    | metrics | values |
    | ceph_rgw_get_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 |
    | ceph_rgw_put_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 5 20 50 |
    | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 |
  When evaluation time is `1m`
  And interval is `30s`
  Then Grafana panel `Bandwidth by RGW Instance` with legend `{{rgw_host}}` shows:
    | metrics | values |
    | {ceph_daemon="rgw.1", instance_id="92806566", rgw_host="1"} | 2.25 |

Scenario: "Test PUT Latencies by RGW Instance"
  Given the following series:
    | metrics | values |
    | ceph_rgw_put_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 15 35 55 |
    | ceph_rgw_put_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 30 50 |
    | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 |
  When evaluation time is `1m`
  And interval is `30s`
  Then Grafana panel `PUT Latencies by RGW Instance` with legend `{{rgw_host}}` shows:
    | metrics | values |
    | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph", rgw_host="foo"} | 1 |

Scenario: "Test Total backend responses by HTTP code"
  Given the following series:
    | metrics | values |
    | haproxy_backend_http_responses_total{job="haproxy",code="200",instance="ingress.rgw.1",proxy="backend"} | 10 100 |
    | haproxy_backend_http_responses_total{job="haproxy",code="404",instance="ingress.rgw.1",proxy="backend"} | 20 200 |
  When variable `ingress_service` is `ingress.rgw.1`
  When variable `code` is `200`
  Then Grafana panel `Total responses by HTTP code` with legend `Backend {{ code }}` shows:
    | metrics | values |
    | {code="200"} | 1.5 |

Scenario: "Test Total frontend responses by HTTP code"
  Given the following series:
    | metrics | values |
    | haproxy_frontend_http_responses_total{job="haproxy",code="200",instance="ingress.rgw.1",proxy="frontend"} | 10 100 |
    | haproxy_frontend_http_responses_total{job="haproxy",code="404",instance="ingress.rgw.1",proxy="frontend"} | 20 200 |
  When variable `ingress_service` is `ingress.rgw.1`
  When variable `code` is `200`
  Then Grafana panel `Total responses by HTTP code` with legend `Frontend {{ code }}` shows:
    | metrics | values |
    | {code="200"} | 1.5 |

Scenario: "Test Total http frontend requests by instance"
  Given the following series:
    | metrics | values |
    | haproxy_frontend_http_requests_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
    | haproxy_frontend_http_requests_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
  When variable `ingress_service` is `ingress.rgw.1`
  Then Grafana panel `Total requests / responses` with legend `Requests` shows:
    | metrics | values |
    | {instance="ingress.rgw.1"} | 3 |

Scenario: "Test Total backend response errors by instance"
  Given the following series:
    | metrics | values |
    | haproxy_backend_response_errors_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 |
    | haproxy_backend_response_errors_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 |
  When variable `ingress_service` is `ingress.rgw.1`
  Then Grafana panel `Total requests / responses` with legend `Response errors` shows:
    | metrics | values |
    | {instance="ingress.rgw.1"} | 3 |

Scenario: "Test Total frontend requests errors by instance"
  Given the following series:
    | metrics | values |
    | haproxy_frontend_request_errors_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
    | haproxy_frontend_request_errors_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
  When variable `ingress_service` is `ingress.rgw.1`
  Then Grafana panel `Total requests / responses` with legend `Requests errors` shows:
    | metrics | values |
    | {instance="ingress.rgw.1"} | 3 |

Scenario: "Test Total backend redispatch warnings by instance"
  Given the following series:
    | metrics | values |
    | haproxy_backend_redispatch_warnings_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 |
    | haproxy_backend_redispatch_warnings_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 |
  When variable `ingress_service` is `ingress.rgw.1`
  Then Grafana panel `Total requests / responses` with legend `Backend redispatch` shows:
    | metrics | values |
    | {instance="ingress.rgw.1"} | 3 |

Scenario: "Test Total backend retry warnings by instance"
  Given the following series:
    | metrics | values |
    | haproxy_backend_retry_warnings_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 |
    | haproxy_backend_retry_warnings_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 |
  When variable `ingress_service` is `ingress.rgw.1`
  Then Grafana panel `Total requests / responses` with legend `Backend retry` shows:
    | metrics | values |
    | {instance="ingress.rgw.1"} | 3 |

Scenario: "Test Total frontend requests denied by instance"
  Given the following series:
    | metrics | values |
    | haproxy_frontend_requests_denied_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
    | haproxy_frontend_requests_denied_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
  When variable `ingress_service` is `ingress.rgw.1`
  Then Grafana panel `Total requests / responses` with legend `Request denied` shows:
    | metrics | values |
    | {instance="ingress.rgw.1"} | 3 |

Scenario: "Test Total backend current queue by instance"
  Given the following series:
    | metrics | values |
    | haproxy_backend_current_queue{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 |
    | haproxy_backend_current_queue{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 |
  When variable `ingress_service` is `ingress.rgw.1`
  Then Grafana panel `Total requests / responses` with legend `Backend Queued` shows:
    | metrics | values |
    | {instance="ingress.rgw.1"} | 200 |

Scenario: "Test Total frontend connections by instance"
  Given the following series:
    | metrics | values |
    | haproxy_frontend_connections_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
    | haproxy_frontend_connections_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
  When variable `ingress_service` is `ingress.rgw.1`
  Then Grafana panel `Total number of connections` with legend `Front` shows:
    | metrics | values |
    | {instance="ingress.rgw.1"} | 3 |

Scenario: "Test Total backend connections attempts by instance"
  Given the following series:
    | metrics | values |
    | haproxy_backend_connection_attempts_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 |
    | haproxy_backend_connection_attempts_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 |
  When variable `ingress_service` is `ingress.rgw.1`
  Then Grafana panel `Total number of connections` with legend `Back` shows:
    | metrics | values |
    | {instance="ingress.rgw.1"} | 3 |

Scenario: "Test Total backend connections error by instance"
  Given the following series:
    | metrics | values |
    | haproxy_backend_connection_errors_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 |
    | haproxy_backend_connection_errors_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 |
  When variable `ingress_service` is `ingress.rgw.1`
  Then Grafana panel `Total number of connections` with legend `Back errors` shows:
    | metrics | values |
    | {instance="ingress.rgw.1"} | 3 |

Scenario: "Test Total frontend bytes incoming by instance"
  Given the following series:
    | metrics | values |
    | haproxy_frontend_bytes_in_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
    | haproxy_frontend_bytes_in_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
  When variable `ingress_service` is `ingress.rgw.1`
  Then Grafana panel `Current total of incoming / outgoing bytes` with legend `IN Front` shows:
    | metrics | values |
    | {instance="ingress.rgw.1"} | 24 |

Scenario: "Test Total frontend bytes outgoing by instance"
  Given the following series:
    | metrics | values |
    | haproxy_frontend_bytes_out_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 |
    | haproxy_frontend_bytes_out_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 |
  When variable `ingress_service` is `ingress.rgw.1`
  Then Grafana panel `Current total of incoming / outgoing bytes` with legend `OUT Front` shows:
    | metrics | values |
    | {instance="ingress.rgw.1"} | 24 |

Scenario: "Test Total backend bytes incoming by instance"
  Given the following series:
    | metrics | values |
    | haproxy_backend_bytes_in_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 |
    | haproxy_backend_bytes_in_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 |
  When variable `ingress_service` is `ingress.rgw.1`
  Then Grafana panel `Current total of incoming / outgoing bytes` with legend `IN Back` shows:
    | metrics | values |
    | {instance="ingress.rgw.1"} | 24 |

Scenario: "Test Total backend bytes outgoing by instance"
  Given the following series:
    | metrics | values |
    | haproxy_backend_bytes_out_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 |
    | haproxy_backend_bytes_out_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 |
  When variable `ingress_service` is `ingress.rgw.1`
  Then Grafana panel `Current total of incoming / outgoing bytes` with legend `OUT Back` shows:
    | metrics | values |
    | {instance="ingress.rgw.1"} | 24 |