|
| 1 | +# Patchwork - automated patch tracking system |
| 2 | +# SPDX-License-Identifier: GPL-2.0-or-later |
| 3 | + |
| 4 | +import datetime |
| 5 | +import random |
| 6 | +import re |
| 7 | + |
| 8 | +from django.conf import settings |
| 9 | +from django.core.management.base import BaseCommand |
| 10 | +from django.core.management.base import CommandError |
| 11 | +from django.db import reset_queries |
| 12 | +from django.db import transaction |
| 13 | + |
| 14 | +from patchwork.hasher import hash_diff |
| 15 | +from patchwork.models import Patch |
| 16 | +from patchwork.models import PatchComment |
| 17 | +from patchwork.models import Person |
| 18 | +from patchwork.models import Project |
| 19 | +from patchwork.models import Series |
| 20 | +from patchwork.models import State |
| 21 | + |
| 22 | + |
| 23 | +DIFF = '''diff --git a/example.txt b/example.txt |
| 24 | +--- a/example.txt |
| 25 | ++++ b/example.txt |
| 26 | +@@ -1 +1 @@ |
| 27 | +-before |
| 28 | ++after |
| 29 | +''' |
| 30 | + |
| 31 | + |
| 32 | +class Command(BaseCommand): |
| 33 | + help = 'Generate synthetic projects and patches for performance testing' |
| 34 | + |
| 35 | + def add_arguments(self, parser): |
| 36 | + parser.add_argument('--projects', type=int, default=12) |
| 37 | + parser.add_argument('--patches-per-project', type=int, default=100000) |
| 38 | + parser.add_argument('--batch-size', type=int, default=1000) |
| 39 | + parser.add_argument('--max-series-size', type=int, default=10) |
| 40 | + parser.add_argument('--open-series-percent', type=int, default=20) |
| 41 | + parser.add_argument('--archived-percent', type=int, default=10) |
| 42 | + parser.add_argument('--seed', type=int, default=42) |
| 43 | + parser.add_argument('--prefix', default='perf') |
| 44 | + |
| 45 | + def handle(self, *args, **options): |
| 46 | + for option in ( |
| 47 | + 'projects', |
| 48 | + 'patches_per_project', |
| 49 | + 'batch_size', |
| 50 | + 'max_series_size', |
| 51 | + ): |
| 52 | + if options[option] < 1: |
| 53 | + raise CommandError(f'{option.replace("_", "-")} must be > 0') |
| 54 | + if options['max_series_size'] > 32767: |
| 55 | + raise CommandError('max-series-size must be <= 32767') |
| 56 | + for option in ('open_series_percent', 'archived_percent'): |
| 57 | + if not 0 <= options[option] <= 100: |
| 58 | + raise CommandError( |
| 59 | + f'{option.replace("_", "-")} must be between 0 and 100' |
| 60 | + ) |
| 61 | + prefix = options['prefix'] |
| 62 | + if not re.fullmatch(r'[a-zA-Z0-9_-]{1,64}', prefix): |
| 63 | + raise CommandError('prefix must be a slug of 1 to 64 characters') |
| 64 | + |
| 65 | + names = [f'{prefix}-{i + 1}' for i in range(options['projects'])] |
| 66 | + emails = [f'{prefix}-{i + 1}@example.invalid' for i in range(100)] |
| 67 | + if Project.objects.filter(linkname__in=names).exists() or ( |
| 68 | + Project.objects.filter(name__in=names).exists() |
| 69 | + ): |
| 70 | + raise CommandError( |
| 71 | + 'Generated projects already exist; use a new prefix' |
| 72 | + ) |
| 73 | + if Person.objects.filter(email__in=emails).exists(): |
| 74 | + raise CommandError( |
| 75 | + 'Generated people already exist; use a new prefix' |
| 76 | + ) |
| 77 | + open_state = State.objects.filter(action_required=True).first() |
| 78 | + closed_state = State.objects.filter(action_required=False).first() |
| 79 | + if not open_state or not closed_state: |
| 80 | + raise CommandError( |
| 81 | + 'An actionable and a non-actionable state are required. ' |
| 82 | + 'Load default_states first.' |
| 83 | + ) |
| 84 | + |
| 85 | + rng = random.Random(options['seed']) # noqa: S311 |
| 86 | + Person.objects.bulk_create( |
| 87 | + [ |
| 88 | + Person(email=email, name=f'Test submitter {i + 1}') |
| 89 | + for i, email in enumerate(emails) |
| 90 | + ] |
| 91 | + ) |
| 92 | + # Query IDs explicitly: not every backend returns them on bulk insert. |
| 93 | + people = list( |
| 94 | + Person.objects.filter(email__in=emails).order_by('email') |
| 95 | + ) |
| 96 | + total_series = 0 |
| 97 | + total_replies = 0 |
| 98 | + for name in names: |
| 99 | + project = Project.objects.create( |
| 100 | + linkname=name, |
| 101 | + name=name, |
| 102 | + listid=f'{name}.example.invalid', |
| 103 | + listemail=f'{name}@example.invalid', |
| 104 | + use_tags=False, |
| 105 | + ) |
| 106 | + count, replies = self.generate_project( |
| 107 | + project, people, open_state, closed_state, rng, options |
| 108 | + ) |
| 109 | + total_series += count |
| 110 | + total_replies += replies |
| 111 | + self.stdout.write( |
| 112 | + self.style.SUCCESS( |
| 113 | + f'Created {len(names)} projects, {total_series} series, ' |
| 114 | + f'{len(names) * options["patches_per_project"]} patches and ' |
| 115 | + f'{total_replies} replies.' |
| 116 | + ) |
| 117 | + ) |
| 118 | + |
| 119 | + def generate_project( |
| 120 | + self, project, people, open_state, closed_state, rng, options |
| 121 | + ): |
| 122 | + remaining = options['patches_per_project'] |
| 123 | + series_count = 0 |
| 124 | + patch_count = 0 |
| 125 | + reply_count = 0 |
| 126 | + diff_hash = hash_diff(DIFF) |
| 127 | + # A fixed anchor makes dates reproducible as well as relationships. |
| 128 | + anchor = datetime.datetime(2025, 1, 1) |
| 129 | + if settings.USE_TZ: |
| 130 | + anchor = anchor.replace(tzinfo=datetime.timezone.utc) |
| 131 | + while remaining: |
| 132 | + series_batch = [] |
| 133 | + patches = [] |
| 134 | + while remaining and len(patches) < options['batch_size']: |
| 135 | + size = min( |
| 136 | + rng.randint(1, options['max_series_size']), |
| 137 | + remaining, |
| 138 | + options['batch_size'] - len(patches), |
| 139 | + ) |
| 140 | + series_count += 1 |
| 141 | + date = anchor - datetime.timedelta( |
| 142 | + seconds=rng.randrange(365 * 24 * 60 * 60) |
| 143 | + ) |
| 144 | + series = Series( |
| 145 | + project=project, |
| 146 | + name=f'Synthetic series {series_count}', |
| 147 | + date=date, |
| 148 | + submitter=rng.choice(people), |
| 149 | + total=size, |
| 150 | + ) |
| 151 | + series_batch.append(series) |
| 152 | + is_open = rng.randrange(100) < options['open_series_percent'] |
| 153 | + # Guarantee one match for open series, at a varied position. |
| 154 | + actionable = rng.randint(1, size) if is_open else None |
| 155 | + for number in range(1, size + 1): |
| 156 | + archived = rng.randrange(100) < options['archived_percent'] |
| 157 | + state = rng.choice((open_state, closed_state)) |
| 158 | + if number == actionable: |
| 159 | + archived, state = False, open_state |
| 160 | + elif not is_open and not archived: |
| 161 | + state = closed_state |
| 162 | + patch_count += 1 |
| 163 | + patches.append( |
| 164 | + Patch( |
| 165 | + project=project, |
| 166 | + series=series, |
| 167 | + number=number, |
| 168 | + name=f'[PATCH {number}/{size}] {series.name}', |
| 169 | + msgid=f'<{project.linkname}-{patch_count}@example.invalid>', |
| 170 | + date=date, |
| 171 | + submitter=series.submitter, |
| 172 | + state=state, |
| 173 | + archived=archived, |
| 174 | + content='Synthetic performance test patch.\n', |
| 175 | + diff=DIFF, |
| 176 | + hash=diff_hash, |
| 177 | + ) |
| 178 | + ) |
| 179 | + remaining -= size |
| 180 | + |
| 181 | + # Bulk inserts intentionally bypass save hooks, tags and events. |
| 182 | + with transaction.atomic(): |
| 183 | + Series.objects.bulk_create(series_batch) |
| 184 | + saved_series = { |
| 185 | + series.name: series |
| 186 | + for series in Series.objects.filter( |
| 187 | + project=project, |
| 188 | + name__in=[series.name for series in series_batch], |
| 189 | + ) |
| 190 | + } |
| 191 | + for patch in patches: |
| 192 | + patch.series = saved_series[patch.series.name] |
| 193 | + Patch.objects.bulk_create(patches) |
| 194 | + # As with series, query IDs for backends that don't return |
| 195 | + # primary keys after bulk inserts. |
| 196 | + patch_ids = dict( |
| 197 | + Patch.objects.filter( |
| 198 | + project=project, |
| 199 | + msgid__in=[patch.msgid for patch in patches], |
| 200 | + ).values_list('msgid', 'pk') |
| 201 | + ) |
| 202 | + replies = [] |
| 203 | + for patch in patches: |
| 204 | + date = patch.date |
| 205 | + for number in range(1, rng.randint(1, 10) + 1): |
| 206 | + date += datetime.timedelta( |
| 207 | + minutes=rng.randint(1, 24 * 60) |
| 208 | + ) |
| 209 | + replies.append( |
| 210 | + PatchComment( |
| 211 | + patch_id=patch_ids[patch.msgid], |
| 212 | + msgid=f'<reply-{number}-{patch.msgid[1:]}', |
| 213 | + date=date, |
| 214 | + submitter=rng.choice(people), |
| 215 | + headers=( |
| 216 | + f'In-Reply-To: {patch.msgid}\n' |
| 217 | + f'References: {patch.msgid}\n' |
| 218 | + ), |
| 219 | + content='Synthetic performance test reply.\n', |
| 220 | + ) |
| 221 | + ) |
| 222 | + reply_count += 1 |
| 223 | + if len(replies) >= options['batch_size']: |
| 224 | + PatchComment.objects.bulk_create(replies) |
| 225 | + replies = [] |
| 226 | + if replies: |
| 227 | + PatchComment.objects.bulk_create(replies) |
| 228 | + # Development settings enable DEBUG; don't retain millions of SQL |
| 229 | + # queries in memory while generating a large dataset. |
| 230 | + reset_queries() |
| 231 | + if options['verbosity']: |
| 232 | + self.stdout.write( |
| 233 | + f'{project.linkname}: {patch_count}/' |
| 234 | + f'{options["patches_per_project"]} patches' |
| 235 | + ) |
| 236 | + return series_count, reply_count |
0 commit comments