summaryrefslogtreecommitdiff
path: root/object_lifetimes
blob: 2f7b164f866ffc5dd5cb0543fe0f0785a451505c (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
#!/usr/bin/env python2
# Copyright 2016  Lars Wirzenius
#
# 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, either version 3 of the License, or
# (at your option) any later version.
#
# 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, see <http://www.gnu.org/licenses/>.
#
# =*= License: GPL-3+ =*=


import re
import time

import cliapp


class ObjectLifetimes(cliapp.Application):

    def setup(self):
        self.objects = {}
        self.deleted = []

    def cleanup(self):
        self.report_max_by_class(self.deleted)

    def create(self, timestamp, obj_class, obj_id):
        if obj_id in self.objects:
            raise cliapp.AppException(
                'object %s has already been created' % obj_id)
        self.objects[obj_id] = (obj_class, timestamp)

    def delete(self, timestamp, obj_id, obj_size):
        obj_class, created = self.objects[obj_id]
        self.deleted.append((obj_class, int(obj_size), created, timestamp))
        del self.objects[obj_id]

    def process_input_line(self, filename, line):
        words = line.split()
        if re.match(r'^\d+-\d+-\d+ \d+:\d+:\d+ ', line):
            timestamp = self.parse_timestamp(words[0], words[1])
        if len(words) == 6 and words[3] == 'object_created:':
            self.create(timestamp, words[4], words[5])
        elif len(words) == 6 and words[3] == 'object_deleted:':
            self.delete(timestamp, words[4], words[5])

    def parse_timestamp(self, date, clock):
        y, m, d = map(int, date.split('-'))
        h, min, s = map(int, clock.split(':'))
        return time.mktime((y, m, d, h, min, s, 0, 0, -1))

    def report_max_by_class(self, lifetimes):
        factor = {
            'CREATE': +1,
            'DELETE': -1,
        }

        current = {}  # class to (object count, cumulative size)
        max_size = {}  # class to max size
        events = list(sorted(self.events(lifetimes)))
        for timestamp, event, obj_class, obj_size in events:
            count, total_size = current.get(obj_class, (0, 0))
            count += factor[event] * 1
            total_size += factor[event] * obj_size
            current[obj_class] = (count, total_size)

            old_max_size, old_count = max_size.get(obj_class, (0, 0))
            if total_size > old_max_size:
                max_size[obj_class] = (total_size, count)

        self.output.write('Max cumulative size at any one time:\n')
        for obj_class in sorted(max_size.keys()):
            size, count = max_size[obj_class]
            self.output.write('{} {} {}\n'.format(size, count, obj_class))

    def events(self, lifetimes):
        for obj_class, obj_size, created, deleted in lifetimes:
            yield created, 'CREATE', obj_class, obj_size
            yield deleted, 'DELETE', obj_class, obj_size

    def sort_by_creation(self, lifetimes):
        return sorted(lifetimes, key=lambda t: t[2])
        


ObjectLifetimes().run()