forked from pingcap/tidb-ansible
-
Notifications
You must be signed in to change notification settings - Fork 0
/
rolling_update_monitor.yml
447 lines (365 loc) · 14.1 KB
/
rolling_update_monitor.yml
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
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
---
# Copyright 2016 PingCAP, Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# See the License for the specific language governing permissions and
# limitations under the License.
# The rolling update playbook of TiDB
- name: check config locally
hosts: localhost
any_errors_fatal: true
tags:
- always
roles:
- check_config_static
- name: gather all facts, and check dest
hosts: all
any_errors_fatal: true
tags:
- always
roles:
- check_config_dynamic
- name: rolling update node_exporter
hosts: monitored_servers
any_errors_fatal: true
tags:
- node_exporter
pre_tasks:
- name: check node_exporter existed
stat:
path: "{{ deploy_dir }}/bin/node_exporter"
register: node_exporter_binary_file
- name: stop node_exporter by supervise
shell: cd {{ deploy_dir }}/scripts && ./stop_node_exporter.sh
when:
- process_supervision == 'supervise'
- node_exporter_binary_file.stat.exists == True
- name: stop node_exporter by systemd
systemd: name=node_exporter-{{ node_exporter_port }}.service state=stopped
become: true
when:
- process_supervision == 'systemd'
- node_exporter_binary_file.stat.exists == True
- name: wait for node_exporter down
wait_for: host={{ ansible_host }} port={{ node_exporter_port }} state=stopped
roles:
- node_exporter
post_tasks:
- name: start node_exporter by supervise
shell: cd {{ deploy_dir }}/scripts && ./start_node_exporter.sh
when: process_supervision == 'supervise'
- name: start node_exporter by systemd
systemd: name=node_exporter-{{ node_exporter_port }}.service state=started
become: true
when: process_supervision == 'systemd'
- name: wait for node_exporter up
wait_for: |
host={{ ansible_host }} port={{ node_exporter_port }} state=present
send='GET /metrics HTTP/1.0\r\n\r\n' search_regex='200 OK'
- name: rolling update blackbox_exporter
hosts: monitored_servers
any_errors_fatal: true
tags:
- blackbox_exporter
pre_tasks:
- name: check blackbox_exporter existed
stat:
path: "{{ deploy_dir }}/conf/blackbox.yml"
register: blackbox_exporter_configure_file
- name: stop blackbox_exporter by supervise
shell: cd {{ deploy_dir }}/scripts && ./stop_blackbox_exporter.sh
when:
- process_supervision == 'supervise'
- blackbox_exporter_configure_file.stat.exists == True
- name: stop blackbox_exporter by systemd
systemd: name=blackbox_exporter-{{ blackbox_exporter_port }}.service state=stopped
become: true
when:
- process_supervision == 'systemd'
- blackbox_exporter_configure_file.stat.exists == True
- name: wait for blackbox_exporter down
wait_for: host={{ ansible_host }} port={{ blackbox_exporter_port }} state=stopped
roles:
- blackbox_exporter
post_tasks:
- name: start blackbox_exporter by supervise
shell: cd {{ deploy_dir }}/scripts && ./start_blackbox_exporter.sh
when: process_supervision == 'supervise'
- name: start blackbox_exporter by systemd
systemd: name=blackbox_exporter-{{ blackbox_exporter_port }}.service state=started
become: true
when: process_supervision == 'systemd'
- name: wait for blackbox_exporter up
wait_for: |
host={{ ansible_host }} port={{ blackbox_exporter_port }} state=present
send='GET / HTTP/1.0\r\n\r\n' search_regex='200 OK'
- name: rolling update alertmanager
hosts: alertmanager_servers
any_errors_fatal: true
tags:
- alertmanager
pre_tasks:
- name: check alertmanager existed
stat:
path: "{{ deploy_dir }}/conf/alertmanager.yml"
register: alertmanager_configure_file
- name: stop alertmanager by supervise
shell: cd {{ deploy_dir }}/scripts && ./stop_alertmanager.sh
when:
- process_supervision == 'supervise'
- alertmanager_configure_file.stat.exists == True
- name: stop alertmanager by systemd
systemd: name=alertmanager-{{ alertmanager_port }}.service state=stopped
become: true
when:
- process_supervision == 'systemd'
- alertmanager_configure_file.stat.exists == True
- name: wait for alertmanager down
wait_for: host={{ ansible_host }} port={{ alertmanager_port }} state=stopped
roles:
- alertmanager
post_tasks:
- name: start alertmanager by supervise
shell: cd {{ deploy_dir }}/scripts && ./start_alertmanager.sh
when: process_supervision == 'supervise'
- name: start alertmanager by systemd
systemd: name=alertmanager-{{ alertmanager_port }}.service state=started
become: true
when: process_supervision == 'systemd'
- name: wait for alertmanager up
wait_for: |
host={{ ansible_host }} port={{ alertmanager_port }} state=present
- name: rolling update pushgateway
hosts: monitoring_servers
any_errors_fatal: true
tags:
- pushgateway
pre_tasks:
- name: stop pushgateway by supervise
shell: cd {{ deploy_dir }}/scripts && ./stop_{{ item }}.sh
with_items:
- pushgateway
when: process_supervision == 'supervise'
- name: stop pushgateway by systemd
systemd: name={{ item }} state=stopped
when: process_supervision == 'systemd'
become: true
with_items:
- pushgateway-{{ pushgateway_port }}.service
- name: wait for pushgateway down
wait_for: host={{ ansible_host }} port={{ pushgateway_port }} state=stopped
roles:
- pushgateway
post_tasks:
- name: start pushgateway by supervise
shell: cd {{ deploy_dir }}/scripts && ./start_{{ item }}.sh
when: process_supervision == 'supervise'
with_items:
- pushgateway
- name: start pushgateway by systemd
systemd: name={{ item }} state=started enabled=no
when: process_supervision == 'systemd'
become: true
with_items:
- pushgateway-{{ pushgateway_port }}.service
- name: wait for pushgateway up
wait_for: |
host={{ ansible_host }} port={{ pushgateway_port }} state=present
send='GET /metrics HTTP/1.0\r\n\r\n' search_regex='200 OK'
- name: rolling update prometheus
hosts: monitoring_servers
any_errors_fatal: true
tags:
- prometheus
pre_tasks:
- name: stop prometheus by supervise
shell: cd {{ deploy_dir }}/scripts && ./stop_{{ item }}.sh
with_items:
- prometheus
when: process_supervision == 'supervise'
- name: stop prometheus by systemd
systemd: name={{ item }} state=stopped
when: process_supervision == 'systemd'
become: true
with_items:
- prometheus-{{ prometheus_port }}.service
- name: wait for prometheus down
wait_for: host={{ ansible_host }} port={{ prometheus_port }} state=stopped
roles:
- prometheus
post_tasks:
- name: start prometheus by supervise
shell: cd {{ deploy_dir }}/scripts && ./start_{{ item }}.sh
when: process_supervision == 'supervise'
with_items:
- prometheus
- name: start prometheus by systemd
systemd: name={{ item }} state=started enabled=no
when: process_supervision == 'systemd'
become: true
with_items:
- prometheus-{{ prometheus_port }}.service
- name: wait for prometheus up
wait_for: |
host={{ ansible_host }} port={{ prometheus_port }} state=present
send='GET /metrics HTTP/1.0\r\n\r\n' search_regex='200 OK'
- name: rolling update grafana
hosts: grafana_servers
any_errors_fatal: true
tags:
- grafana
pre_tasks:
- name: stop grafana by supervise
shell: cd {{ deploy_dir }}/scripts && ./stop_{{ item }}.sh
when: process_supervision == 'supervise'
with_items:
- grafana
- name: stop grafana by systemd
systemd: name=grafana-{{ grafana_port }}.service state=stopped
become: true
when: process_supervision == 'systemd'
- name: wait for grafana down
wait_for: host={{ ansible_host }} port={{ grafana_port }} state=stopped
- name: check grafana_collector existed
stat:
path: "{{ deploy_dir }}/conf/grafana_collector.toml"
register: grafana_collector_config_file
- name: stop grafana_collector by supervise
shell: cd {{ deploy_dir }}/scripts && ./stop_{{ item }}.sh
when:
- process_supervision == 'supervise'
- grafana_collector_config_file.stat.exists == True
with_items:
- grafana_collector
- name: stop grafana_collector by systemd
systemd: name=grafana_collector-{{ grafana_collector_port }}.service state=stopped
become: true
when:
- process_supervision == 'systemd'
- grafana_collector_config_file.stat.exists == True
- name: wait for grafana_collector down
wait_for: host={{ ansible_host }} port={{ grafana_collector_port }} state=stopped
roles:
- grafana
- grafana_collector
post_tasks:
- name: start grafana by supervise
shell: cd {{ deploy_dir }}/scripts && ./start_{{ item }}.sh
when: process_supervision == 'supervise'
with_items:
- grafana
- name: start grafana by systemd
systemd: name=grafana-{{ grafana_port }}.service state=started enabled=no
when: process_supervision == 'systemd'
become: true
- name: wait for grafana up
wait_for: |
host={{ ansible_host }} port={{ grafana_port }} state=present
send='GET /login HTTP/1.0\r\n\r\n' search_regex='200 OK'
- name: start grafana_collector by supervise
shell: cd {{ deploy_dir }}/scripts && ./start_{{ item }}.sh
when: process_supervision == 'supervise'
with_items:
- grafana_collector
- name: start grafana_collector by systemd
systemd: name=grafana_collector-{{ grafana_collector_port }}.service state=started enabled=no
when: process_supervision == 'systemd'
become: true
- name: wait for grafana_collector up
wait_for: |
host={{ ansible_host }} port={{ grafana_collector_port }} state=present
- set_fact:
grafana_host: "{{ ansible_host }}"
- include_tasks: "common_tasks/create_grafana_api_keys.yml"
- name: import grafana data source
shell: >
chdir={{ grafana_data_dir }}
warn=no
curl -q -X POST -d @data_source.json --header 'Content-Type: application/json'
"http://{{ grafana_admin_user }}:{{ grafana_admin_password }}@127.0.0.1:{{ grafana_port }}/api/datasources"
- name: import grafana dashboards - prepare config
delegate_to: localhost
template: src=grafana.dest.json.j2 dest={{ playbook_dir }}/scripts/dests.json
vars:
- ansible_become: false
- ansible_connection: local
- grafana_dest_config:
name: "{{ cluster_name | title }}"
url: "http://{{ grafana_host }}:{{ grafana_port }}/"
report_url: "http://{{ grafana_host }}:{{ grafana_collector_port }}/"
user: "{{ grafana_admin_user }}"
password: "{{ grafana_admin_password }}"
apikey: "{{ lookup('file', grafana_api_keys_dir + '/grafana_apikey.key') }}"
datasource: "{{ cluster_name }}"
titles:
node: "{{ cluster_name | title }}-Node_exporter"
pd: "{{ cluster_name | title }}-PD"
tidb: "{{ cluster_name | title }}-TiDB"
tikv: "{{ cluster_name | title }}-TiKV"
tikv_instances: "{{ cluster_name | title }}-TiKV-Instances"
binlog: "{{ cluster_name | title }}-Binlog"
overview: "{{ cluster_name | title }}-Overview"
disk_performance: "{{ cluster_name | title }}-Disk-Performance"
blackbox_exporter: "{{ cluster_name | title }}-Blackbox_exporter"
kafka_overview: "{{ cluster_name | title }}-Kafka-Overview"
- name: import grafana dashboards - run import script
delegate_to: localhost
shell: >-
chdir={{ playbook_dir }}/scripts
./grafana-config-copy.py
vars:
- ansible_become: false
- ansible_connection: local
- name: rolling update kafka_exporter
hosts: kafka_exporter_servers
any_errors_fatal: true
tags:
- kafka_exporter
pre_tasks:
- name: check kafka_exporter existed
stat:
path: "{{ deploy_dir }}/bin/kafka_exporter"
register: kafka_exporter_binary_file
when: enable_binlog|default(false)
- name: stop kafka_exporter by supervise
shell: cd {{ deploy_dir }}/scripts && ./stop_kafka_exporter.sh
when:
- enable_binlog|default(false)
- process_supervision == 'supervise'
- kafka_exporter_binary_file.stat.exists == True
- name: stop kafka_exporter by systemd
become: true
systemd: name=kafka_exporter-{{ kafka_exporter_port }}.service state=stopped enabled=no
when:
- enable_binlog|default(false)
- process_supervision == 'systemd'
- kafka_exporter_binary_file.stat.exists == True
- name: wait for kafka_exporter down
wait_for: |
host={{ ansible_host }} port={{ kafka_exporter_port }} state=stopped
when: enable_binlog|default(false)
roles:
- { role: kafka_exporter, when: 'enable_binlog|default(false) and kafka_addrs|default("") != ""' }
post_tasks:
- name: start kafka_exporter by supervise
shell: cd {{ deploy_dir }}/scripts && ./start_kafka_exporter.sh
when:
- enable_binlog|default(false)
- process_supervision == 'supervise'
- name: start kafka_exporter by systemd
become: true
systemd: name=kafka_exporter-{{ kafka_exporter_port }}.service state=started enabled=no
when:
- enable_binlog|default(false)
- process_supervision == 'systemd'
- name: wait for kafka_exporter up
wait_for: |
host={{ ansible_host }} port={{ kafka_exporter_port }} state=present
when: enable_binlog|default(false)