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
|
::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::
: Copyright (c) 2019 Mirantis Inc., Enea AB and others.
:
: All rights reserved. This program and the accompanying materials
: are made available under the terms of the Apache License, Version 2.0
: which accompanies this distribution, and is available at
: http://www.apache.org/licenses/LICENSE-2.0
::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::
From: Alexandru Avadanii <Alexandru.Avadanii@enea.com>
Date: Sun, 23 Sep 2018 03:57:27 +0200
Subject: [PATCH] Extend wait_for maas.py, wait_for_* attempts arg
1. maas.py: Extend wait_for states with timeout param
Extend the wait_for states with a timeout parameter.
The timeout value is taken from reclass pillar data if
defined. Oterwise, the states use the default value.
Based on Ting's PR [1], slightly refactored.
2. maas.py: Extend `req_status` support to multiple values
Previously, req_status could be one of the MaaS status strings, e.g.
'Ready'. Extend matching to '|'-separated statuses (e.g.
'Ready|Deployed') to allow idempotency in MaaS machine commissioning
and deployment cycles.
Also provide a `maas.machines.wait_for_ready_or_deployed` sls.
3. maas.py: wait_for_*: Add attempts arg
Introduce a new parameter that allows a maximum number of automatic
recovery attempts for the common failures w/ machine operations.
If not present in pillar data, it defaults to 0 (OFF).
Common error states, possible cause and automatic recovery pattern:
* New
- usually indicates issues with BMC connectivity (no network route,
but on rare occassions it happens due to MaaS API being flaky);
- fix: delete the machine, (re)process machine definitions;
* Failed commissioning
- various causes, usually a simple retry works;
- fix: delete the machine, (re)process machine definitions;
* Failed testing
- incompatible hardware, missing drivers etc.
- usually consistent and board-specific;
- fix: override failed testing
* Allocated
- on rare ocassions nodes get stuck in this state instead 'Deploy';
- fix: mark-broken, mark-fixed, if it failed at least once before
perform a fio test (fixes another unrelated spurious issue with
encrypted disks from previous deployments), (re)deploy machines;
* Failed deployment
- various causes, usually a simple retry works;
- fix: same as for nodes stuck in 'Allocated';
[1] https://github.com/salt-formulas/salt-formula-maas/pull/34
Change-Id: Ifb7dd9f8fcfbbed557e47d8fdffb1f963604fb15
Signed-off-by: ting wu <ting.wu@enea.com>
Signed-off-by: Alexandru Avadanii <Alexandru.Avadanii@enea.com>
---
README.rst | 9 +++-
_modules/maas.py | 52 +++++++++++++++++---
maas/machines/wait_for_deployed.sls | 2 +
maas/machines/wait_for_ready.sls | 3 ++
maas/machines/wait_for_ready_or_deployed.sls | 15 ++++++
maas/map.jinja | 4 ++
tests/pillar/maas_region.sls | 4 ++
7 files changed, 81 insertions(+), 8 deletions(-)
create mode 100644 maas/machines/wait_for_ready_or_deployed.sls
diff --git a/README.rst b/README.rst
index 20da43e..78d8aef 100644
--- a/README.rst
+++ b/README.rst
@@ -622,12 +622,16 @@ Wait for status of selected machine's:
machines:
- kvm01
- kvm02
- timeout: 1200 # in seconds
+ timeout: {{ region.timeout.ready }}
+ attempts: {{ region.timeout.attempts }}
req_status: "Ready"
- require:
- cmd: maas_login_admin
...
+The timeout setting is taken from the reclass pillar data.
+If the pillar data is not defined, it will use the default value.
+
If module run w/\o any extra paremeters,
``wait_for_machines_ready`` will wait for defined in salt
machines. In this case, it is usefull to skip some machines:
@@ -642,7 +646,8 @@ machines. In this case, it is usefull to skip some machines:
module.run:
- name: maas.wait_for_machine_status
- kwargs:
- timeout: 1200 # in seconds
+ timeout: {{ region.timeout.deployed }}
+ attempts: {{ region.timeout.attempts }}
req_status: "Deployed"
ignore_machines:
- kvm01 # in case it's broken or whatever
diff --git a/_modules/maas.py b/_modules/maas.py
index c02f104..bb70576 100644
--- a/_modules/maas.py
+++ b/_modules/maas.py
@@ -670,7 +670,7 @@ class DeployMachines(MaasObject):
if machine['status'] == self.DEPLOYED:
return
if machine['status'] != self.READY:
- raise Exception('Not in ready state')
+ return
data = {
'system_id': machine['system_id'],
}
@@ -921,6 +921,7 @@ class MachinesStatus(MaasObject):
req_status: string; Polling status
machines: list; machine names
ignore_machines: list; machine names
+ attempts: max number of automatic hard retries
:ret: True
Exception - if something fail/timeout reached
"""
@@ -929,6 +930,8 @@ class MachinesStatus(MaasObject):
req_status = kwargs.get("req_status", "Ready")
to_discover = kwargs.get("machines", None)
ignore_machines = kwargs.get("ignore_machines", None)
+ attempts = kwargs.get("attempts", 0)
+ failed_attempts = {}
if not to_discover:
try:
to_discover = __salt__['config.get']('maas')['region'][
@@ -943,11 +946,46 @@ class MachinesStatus(MaasObject):
while len(total) <= len(to_discover):
for m in to_discover:
for discovered in MachinesStatus.execute()['machines']:
- if m == discovered['hostname'] and \
- discovered['status'].lower() == req_status.lower():
- if m in total:
+ if m == discovered['hostname'] and m in total:
+ req_status_list = req_status.lower().split('|')
+ if discovered['status'].lower() in req_status_list:
total.remove(m)
-
+ elif attempts > 0 and (m not in failed_attempts or
+ failed_attempts[m] < attempts):
+ status = discovered['status']
+ sid = discovered['system_id']
+ cls._maas = _create_maas_client()
+ if status in ['Failed commissioning', 'New']:
+ LOG.info('Machine {0} deleted'.format(sid))
+ cls._maas.delete(u'api/2.0/machines/{0}/'
+ .format(sid))
+ Machine().process()
+ elif status in ['Failed testing']:
+ data = {}
+ LOG.info('Machine {0} overriden'.format(sid))
+ action = 'override_failed_testing'
+ cls._maas.post(u'api/2.0/machines/{0}/'
+ .format(sid), action, **data)
+ elif status in ['Failed deployment', 'Allocated']:
+ data = {}
+ LOG.info('Machine {0} mark broken'.format(sid))
+ cls._maas.post(u'api/2.0/machines/{0}/'
+ .format(sid), 'mark_broken', **data)
+ time.sleep(poll_time)
+ LOG.info('Machine {0} mark fixed'.format(sid))
+ cls._maas.post(u'api/2.0/machines/{0}/'
+ .format(sid), 'mark_fixed', **data)
+ if m in failed_attempts and failed_attempts[m]:
+ LOG.info('Machine {0} fio test'.format(sid))
+ data['testing_scripts'] = 'fio'
+ cls._maas.post(u'api/2.0/machines/{0}/'
+ .format(sid), 'commission', **data)
+ DeployMachines().process()
+ else:
+ continue
+ if m not in failed_attempts:
+ failed_attempts[m] = 0
+ failed_attempts[m] = failed_attempts[m] + 1
if len(total) <= 0:
LOG.debug(
"Machines:{} are:{}".format(to_discover, req_status))
@@ -959,7 +997,9 @@ class MachinesStatus(MaasObject):
"Waiting status:{} "
"for machines:{}"
"\nsleep for:{}s "
- "Timeout:{}s".format(req_status, total, poll_time, timeout))
+ "Timeout:{}s ({}s left)"
+ .format(req_status, total, poll_time, timeout,
+ timeout - (time.time() - started_at)))
time.sleep(poll_time)
diff --git a/maas/machines/wait_for_deployed.sls b/maas/machines/wait_for_deployed.sls
index ebeedac..a646fdb 100644
--- a/maas/machines/wait_for_deployed.sls
+++ b/maas/machines/wait_for_deployed.sls
@@ -9,5 +9,7 @@ wait_for_machines_deployed:
- name: maas.wait_for_machine_status
- kwargs:
req_status: "Deployed"
+ timeout: {{ region.timeout.deployed }}
+ attempts: {{ region.timeout.attempts }}
- require:
- cmd: maas_login_admin
diff --git a/maas/machines/wait_for_ready.sls b/maas/machines/wait_for_ready.sls
index c5d3c28..d8a2963 100644
--- a/maas/machines/wait_for_ready.sls
+++ b/maas/machines/wait_for_ready.sls
@@ -7,5 +7,8 @@ maas_login_admin:
wait_for_machines_ready:
module.run:
- name: maas.wait_for_machine_status
+ - kwargs:
+ timeout: {{ region.timeout.ready }}
+ attempts: {{ region.timeout.attempts }}
- require:
- cmd: maas_login_admin
diff --git a/maas/machines/wait_for_ready_or_deployed.sls b/maas/machines/wait_for_ready_or_deployed.sls
new file mode 100644
index 0000000..db3dcc4
--- /dev/null
+++ b/maas/machines/wait_for_ready_or_deployed.sls
@@ -0,0 +1,15 @@
+{%- from "maas/map.jinja" import region with context %}
+
+maas_login_admin:
+ cmd.run:
+ - name: "maas-region apikey --username {{ region.admin.username }} > /var/lib/maas/.maas_credentials"
+
+wait_for_machines_ready_or_deployed:
+ module.run:
+ - name: maas.wait_for_machine_status
+ - kwargs:
+ req_status: "Ready|Deployed"
+ timeout: {{ region.timeout.ready }}
+ attempts: {{ region.timeout.attempts }}
+ - require:
+ - cmd: maas_login_admin
diff --git a/maas/map.jinja b/maas/map.jinja
index 0671435..1e6ac07 100644
--- a/maas/map.jinja
+++ b/maas/map.jinja
@@ -22,6 +22,10 @@ Debian:
bind:
host: 0.0.0.0
port: 80
+ timeout:
+ ready: 1200
+ deployed: 7200
+ attempts: 0
{%- endload %}
{%- set region = salt['grains.filter_by'](region_defaults, merge=salt['pillar.get']('maas:region', {})) %}
diff --git a/tests/pillar/maas_region.sls b/tests/pillar/maas_region.sls
index d3325eb..d710216 100644
--- a/tests/pillar/maas_region.sls
+++ b/tests/pillar/maas_region.sls
@@ -34,3 +34,7 @@ maas:
password: password
username: maas
salt_master_ip: 127.0.0.1
+ timeout:
+ deployed: 900
+ ready: 900
+ attempts: 2
|
