summaryrefslogtreecommitdiffstats
path: root/qa/suites/upgrade/reef-x/stress-split/1-start.yaml
blob: 4cd05432d5fc67bb7f71d8df038bce4e72e689f4 (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
tasks:
- install:
    branch: reef
    exclude_packages:
      - ceph-volume

- cephadm:
    image: quay.ceph.io/ceph-ci/ceph:reef
    compiled_cephadm_branch: reef
    conf:
      osd:
        #set config option for which cls modules are allowed to be loaded / used
        osd_class_load_list: "*"
        osd_class_default_list: "*"

- cephadm.shell:
    mon.a:
      - ceph fs volume create foo
      - ceph config set mon mon_warn_on_insecure_global_id_reclaim false --force
      - ceph config set mon mon_warn_on_insecure_global_id_reclaim_allowed false --force

- ceph.healthy:

- print: "**** upgrading first half of cluster, with stress ****"
- parallel:
    - first-half-tasks
    - first-half-sequence
- print: "**** done upgrading first half of cluster ****"

- ceph.healthy:

- print: "**** applying stress + thrashing to mixed-version cluster ****"

- parallel:
    - stress-tasks

- ceph.healthy:

- print: "**** finishing upgrade ****"
- parallel:
    - second-half-tasks
    - second-half-sequence

- ceph.healthy:


#################

first-half-sequence:
- cephadm.shell:
    env: [sha1]
    mon.a:
      - ceph config set mgr mgr/cephadm/daemon_cache_timeout 60
      - ceph config set global log_to_journald false --force

      - echo wait for mgr daemons to upgrade
      # upgrade the mgr daemons first
      - ceph orch upgrade start --image quay.ceph.io/ceph-ci/ceph:$sha1 --daemon-types mgr
      - while ceph orch upgrade status | jq '.in_progress' | grep true && ! ceph orch upgrade status | jq '.message' | grep Error ; do ceph orch ps ; ceph versions ; ceph orch upgrade status ; sleep 30 ; done

      - echo wait for minority of mons to upgrade
      # upgrade 1 of 3 mon daemons, then wait 60 seconds
      - ceph orch upgrade start --image quay.ceph.io/ceph-ci/ceph:$sha1 --daemon-types mon --limit 1
      - while ceph orch upgrade status | jq '.in_progress' | grep true && ! ceph orch upgrade status | jq '.message' | grep Error ; do ceph orch ps ; ceph versions ; ceph orch upgrade status ; sleep 30 ; done
      - sleep 60

      - echo wait for majority of mons to upgrade
      # upgrade one more mon daemon (to get us to 2/3 upgraded) and wait 60 seconds
      - ceph orch upgrade start --image quay.ceph.io/ceph-ci/ceph:$sha1 --daemon-types mon --limit 1
      - while ceph orch upgrade status | jq '.in_progress' | grep true && ! ceph orch upgrade status | jq '.message' | grep Error ; do ceph orch ps ; ceph versions ; ceph orch upgrade status ; sleep 30 ; done
      - sleep 60

      - echo wait for all mons to upgrade
      # upgrade final mon daemon and wait 60 seconds
      - ceph orch upgrade start --image quay.ceph.io/ceph-ci/ceph:$sha1 --daemon-types mon
      - while ceph orch upgrade status | jq '.in_progress' | grep true && ! ceph orch upgrade status | jq '.message' | grep Error ; do ceph orch ps ; ceph versions ; ceph orch upgrade status ; sleep 30 ; done
      - sleep 60

      - echo wait for half of osds to upgrade
      # upgrade 4 of the 8 OSDs
      - ceph orch upgrade start --image quay.ceph.io/ceph-ci/ceph:$sha1 --daemon-types osd --limit 4
      - while ceph orch upgrade status | jq '.in_progress' | grep true && ! ceph orch upgrade status | jq '.message' | grep Error ; do ceph orch ps ; ceph versions ; ceph orch upgrade status ; sleep 30 ; done


#################

stress-tasks:
- thrashosds:
    timeout: 1200
    chance_pgnum_grow: 1
    chance_pgpnum_fix: 1
    chance_thrash_cluster_full: 0
    chance_thrash_pg_upmap: 0
    chance_thrash_pg_upmap_items: 0
    disable_objectstore_tool_tests: true
    chance_force_recovery: 0
    aggressive_pg_num_changes: false


#################

second-half-sequence:
  sequential:
    - cephadm.shell:
        env: [sha1]
        mon.a:
          - sleep 60

          - echo wait for upgrade to complete
          # upgrade whatever is left
          - ceph orch upgrade start --image quay.ceph.io/ceph-ci/ceph:$sha1
          - while ceph orch upgrade status | jq '.in_progress' | grep true && ! ceph orch upgrade status | jq '.message' | grep Error ; do ceph orch ps ; ceph versions ; ceph orch upgrade status ; sleep 30 ; done

          - echo upgrade complete
          - ceph orch ps
          - ceph versions
          - ceph versions | jq -e '.overall | length == 1'
          - ceph versions | jq -e '.overall | keys' | grep $sha1