Puppet Class: profile::reportupdater::jobs

Defined in:
modules/profile/manifests/reportupdater/jobs.pp

Overview

Class profile::reportupdater::jobs

Installs reportupdater jobs that run on Hadoop/Hive. This profile should only be included in a single role.

This requires that a Hadoop client is installed and the statistics compute role for the published_path.

Parameters:

  • ensure_jobs (Any) (defaults to: lookup('profile::reportupdater::jobs::ensure_jobs', { 'default_value' => 'present' })) 


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
 
# File 'modules/profile/manifests/reportupdater/jobs.pp', line 7

class profile::reportupdater::jobs(
    $ensure_jobs = lookup('profile::reportupdater::jobs::ensure_jobs', { 'default_value' => 'present' }),
) {

    require ::profile::analytics::cluster::packages::common
    require ::profile::analytics::cluster::client

    $base_path = '/srv/reportupdater'
    $log_path = "${base_path}/log"
    $user = 'analytics'

    # Set up reportupdater.
    # Reportupdater here launches Hadoop jobs, and
    # the 'analytics' user is the Analytics 'system' user that has
    # access to required files in Hadoop.
    class { 'reportupdater':
        user      => $user,
        base_path => $base_path,
        log_path  => $log_path,
    }

    # Setup timer for rsyncing logs to HDFS.
    $hdfs_log_path = '/tmp/reportupdater-logs'

    bigtop::hadoop::directory { $hdfs_log_path:
        owner => $user,
        group => $user,
        mode  => '0755',
    }

    kerberos::systemd_timer { 'analytics-reportupdater-logs-rsync':
        description => 'Rsync reportupdater logs to HDFS.',
        command     => "/usr/local/bin/hdfs-rsync -r -t --delete --perms file://${log_path} hdfs://${hdfs_log_path}",
        interval    => '*-*-* *:30:00',
        user        => $user,
        require     => Bigtop::Hadoop::Directory[$hdfs_log_path],
    }

    # And set up a link for periodic jobs to be included in published reports.
    # Because periodic is in published_path, files will be synced to
    # analytics.wikimedia.org/published/datasets/periodic/reports
    file { "${::statistics::compute::published_path}/datasets/periodic":
        ensure => 'directory',
        owner  => 'root',
        group  => 'wikidev',
        mode   => '0775',
    }
    file { "${::statistics::compute::published_path}/datasets/periodic/reports":
        ensure  => 'link',
        target  => "${base_path}/output",
        require => Class['reportupdater'],
    }

    # Set up a job to create browser reports on hive db.
    reportupdater::job { 'browser':
        ensure     => $ensure_jobs,
        output_dir => 'metrics/browser',
    }

    reportupdater::job { 'codemirror':
        # Force absenting jobs as per T357419
        # ensure     => $ensure_jobs,
        ensure     => 'absent',
        output_dir => 'metrics/codemirror',
    }

    reportupdater::job { 'interlanguage':
        # Force absenting jobs as per T357419
        # ensure     => $ensure_jobs,
        ensure     => 'absent',
        output_dir => 'metrics/interlanguage',
    }

    reportupdater::job { 'pingback':
        ensure     => $ensure_jobs,
        output_dir => 'metrics/pingback',
    }

    reportupdater::job { 'reference-previews':
        # Force absenting jobs as per T357419
        # ensure     => $ensure_jobs,
        ensure     => 'absent',
        output_dir => 'metrics/reference-previews',
    }

    reportupdater::job { 'templatedata':
        # Force absenting jobs as per T357419
        # ensure     => $ensure_jobs,
        ensure     => 'absent',
        output_dir => 'metrics/templatedata',
    }

    reportupdater::job { 'wmcs':
        ensure     => $ensure_jobs,
        output_dir => 'metrics/wmcs',
    }

    reportupdater::job { 'structured-data':
        # Force absenting jobs as per T357419
        # ensure     => $ensure_jobs,
        ensure     => 'absent',
        output_dir => 'metrics/structured-data',
    }

    reportupdater::job { 'visualeditor':
        # Force absenting jobs as per T357419
        # ensure     => $ensure_jobs,
        ensure     => 'absent',
        output_dir => 'metrics/visualeditor',
    }

    reportupdater::job { 'templatewizard':
        # Force absenting jobs as per T357419
        # ensure     => $ensure_jobs,
        ensure     => 'absent',
        output_dir => 'metrics/templatewizard',
    }

    # Set up various jobs to be executed by reportupdater
    # creating several reports on mysql research db.
    reportupdater::job { 'flow-beta-features':
        # Force absenting jobs as per T357419
        # ensure     => $ensure_jobs,
        ensure       => 'absent',
        output_dir   => 'metrics/beta-feature-enables',
        use_kerberos => false,
    }

    reportupdater::job { 'edit-beta-features':
        # Force absenting jobs as per T357419
        # ensure     => $ensure_jobs,
        ensure       => 'absent',
        output_dir   => 'metrics/beta-feature-enables',
        use_kerberos => false,
    }

    reportupdater::job { 'language':
        # Force absenting jobs as per T357419
        # ensure     => $ensure_jobs,
        ensure       => 'absent',
        output_dir   => 'metrics/beta-feature-enables',
        use_kerberos => false,
    }

    # Note:
    # The published_cx2_translations jobs were on stat1007 (hive based)
    # and on stat1006 (mysql based). They now have different job names,
    # but their output directory is the same on purpose, to allow rsync
    # jobs to properly collect and merge data downstream.
    reportupdater::job { 'published_cx2_translations':
        # Force absenting jobs as per T357419
        # ensure     => $ensure_jobs,
        ensure      => 'absent',
        config_file => "${base_path}/jobs/reportupdater-queries/published_cx2_translations/config-hive.yaml",
        output_dir  => 'metrics/published_cx2_translations',
    }
    reportupdater::job { 'published_cx2_translations_mysql':
        # Force absenting jobs as per T357419
        # ensure     => $ensure_jobs,
        ensure       => 'absent',
        config_file  => "${base_path}/jobs/reportupdater-queries/published_cx2_translations/config-mysql.yaml",
        output_dir   => 'metrics/published_cx2_translations',
        query_dir    => 'published_cx2_translations',
        interval     => '*-*-* *:30:00',
        use_kerberos => false,
    }

    reportupdater::job { 'mt_engines':
        # Force absenting jobs as per T357419
        # ensure     => $ensure_jobs,
        ensure       => 'absent',
        output_dir   => 'metrics/mt_engines',
        use_kerberos => false,
    }

    reportupdater::job { 'cx':
        ensure       => $ensure_jobs,
        output_dir   => 'metrics/cx',
        use_kerberos => false,
    }
}