summaryrefslogtreecommitdiff
path: root/lorry-controller-remove-old-jobs
blob: d6dca381a77eb917cc41e7e4d437f4c41f933e2c (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
#!/usr/bin/env python3
#
# Copyright (C) 2014-2019  Codethink Limited
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; version 2 of the License.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License along
# with this program; if not, write to the Free Software Foundation, Inc.,
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.


import json
import logging
import time
import urllib.request, urllib.error, urllib.parse

import cliapp


class JobInfo(object):

    def __init__(self, job_id, exit_code, exit_timestamp, start_timestamp):
        self.job_id = job_id
        self.exit_code = exit_code
        self.exit_timestamp = exit_timestamp
        self.start_timestamp = start_timestamp

    def __repr__(self):
        return 'JobInfo(%s,%s,%s,%s)' % (
            self.job_id, self.exit_code, self.exit_timestamp,
            self.start_timestamp)


class OldJobRemover(cliapp.Application):

    def add_settings(self):
        self.settings.string(
            ['webapp-host'],
            'address of WEBAPP',
            default='localhost')

        self.settings.integer(
            ['webapp-port'],
            'port of WEBAPP',
            default=12765)

        ONE_MINUTE = 60
        ONE_HOUR = 60 * ONE_MINUTE
        ONE_DAY = 24 * ONE_HOUR

        self.settings.integer(
            ['max-age-in-seconds', 'max-age'],
            'maximum age of a finished job in seconds',
            metavar='SECONDS',
            default=3 * ONE_DAY)

        self.settings.integer(
            ['debug-now'],
            'for tests and debugging, '
            'set current time to SECONDS since the epoch '
            '(set to 0 to use real time',
            metavar='SECONDS')

    def process_args(self, args):
        logging.info('Removing old jobs from Lorry Controller STATEDB')

        for job_id in sorted(self.list_jobs()):
            try:
                job_info = self.get_job_info(job_id)
            except urllib.error.HTTPError as e:
                logging.warning(
                    'Trouble getting job info for job %s: %s' %
                    (job_id, str(e)))
                continue

            # If the start time of this job is less than max-age ago,
            # then the finish time of this job, and every job with a
            # higher ID, must be less than max-age ago.  So we can
            # stop now.
            if self.was_started_too_recently(job_info):
                break

            if self.is_old(job_info):
                self.remove_job(job_info.job_id)

    def list_jobs(self):
        data = self.get('/1.0/list-jobs')
        obj = json.loads(data.decode('utf-8'))
        return obj['job_ids']

    def get(self, path):
        url = self.make_url(path)
        with urllib.request.urlopen(url) as f:
            return f.read()

    def make_url(self, path):
        scheme = 'http'
        netloc = '%s:%s' % (
            self.settings['webapp-host'], self.settings['webapp-port'])
        query = None
        fragment = None
        parts = (scheme, netloc, path, query, fragment)
        return urllib.parse.urlunsplit(parts)

    def get_job_info(self, job_id):
        data = self.get('/1.0/job/%s' % job_id)
        obj = json.loads(data.decode('utf-8'))
        exit_code = obj['exit']
        if obj['job_ended']:
            exit_timestamp = self.parse_timestamp(obj['job_ended'])
        else:
            exit_timestamp = None
        start_timestamp = self.parse_timestamp(obj['job_started'])
        return JobInfo(job_id, exit_code, exit_timestamp, start_timestamp)

    def parse_timestamp(self, timestamp):
        return time.mktime(time.strptime(timestamp, '%Y-%m-%d %H:%M:%S UTC'))

    def is_old(self, job_info):
        if job_info.exit_timestamp is None:
            return False
        current_time = self.get_current_time()
        age_in_seconds = current_time - job_info.exit_timestamp
        return age_in_seconds >= self.settings['max-age-in-seconds']

    def was_started_too_recently(self, job_info):
        current_time = self.get_current_time()
        age_in_seconds = current_time - job_info.start_timestamp
        return age_in_seconds < self.settings['max-age-in-seconds']

    def get_current_time(self):
        if self.settings['debug-now']:
            return self.settings['debug-now']
        return time.time()

    def remove_job(self, job_id):
        logging.info('Removing job %s', job_id)
        self.post('/1.0/remove-job', 'job_id=%s' % job_id)

    def post(self, path, data):
        url = self.make_url(path)
        with urllib.request.urlopen(url, data.encode('utf-8')) as f:
            f.read()


OldJobRemover().run()