tarrien/Mastodon
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix AccountsStatusesCleanupScheduler not spreading deletes across accounts correctly (#24607)

Browse Source
This commit is contained in:
Claire 2023-04-23 22:25:40 +02:00 committed by Tarrien
parent 841d58584e
commit c2b9764ba6
2 changed files with 49 additions and 103 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
app/workers/scheduler/accounts_statuses_cleanup_scheduler.rb
View File

@ -42,7 +42,7 @@ class Scheduler::AccountsStatusesCleanupScheduler
num_processed_accounts = 0
scope = AccountStatusesCleanupPolicy.where(enabled: true)
scope.where(Account.arel_table[:id].gt(first_policy_id)) if first_policy_id.present?
scope = scope.where(id: first_policy_id...) if first_policy_id.present?
scope.find_each(order: :asc) do |policy|
num_deleted = AccountStatusesCleanupService.new.call(policy, [budget, PER_ACCOUNT_BUDGET].min)
num_processed_accounts += 1 unless num_deleted.zero?
@ -77,14 +77,14 @@ class Scheduler::AccountsStatusesCleanupScheduler
end
def last_processed_id
redis.get('account_statuses_cleanup_scheduler:last_account_id')
redis.get('account_statuses_cleanup_scheduler:last_policy_id')
end
def save_last_processed_id(id)
if id.nil?
redis.del('account_statuses_cleanup_scheduler:last_account_id')
redis.del('account_statuses_cleanup_scheduler:last_policy_id')
else
redis.set('account_statuses_cleanup_scheduler:last_account_id', id, ex: 1.hour.seconds)
redis.set('account_statuses_cleanup_scheduler:last_policy_id', id, ex: 1.hour.seconds)
end
end
end

144
spec/workers/scheduler/accounts_statuses_cleanup_scheduler_spec.rb
View File

@ -1,16 +1,17 @@
# frozen_string_literal: true
require 'rails_helper'
describe Scheduler::AccountsStatusesCleanupScheduler do
subject { described_class.new }
let!(:account_alice) { Fabricate(:account, domain: nil, username: 'alice') }
let!(:account_bob) { Fabricate(:account, domain: nil, username: 'bob') }
let!(:account_chris) { Fabricate(:account, domain: nil, username: 'chris') }
let!(:account_dave) { Fabricate(:account, domain: nil, username: 'dave') }
let!(:account_erin) { Fabricate(:account, domain: nil, username: 'erin') }
let!(:remote) { Fabricate(:account) }
let!(:account1) { Fabricate(:account, domain: nil) }
let!(:account2) { Fabricate(:account, domain: nil) }
let!(:account3) { Fabricate(:account, domain: nil) }
let!(:account4) { Fabricate(:account, domain: nil) }
let!(:remote) { Fabricate(:account) }
let!(:policy1) { Fabricate(:account_statuses_cleanup_policy, account: account1) }
let!(:policy2) { Fabricate(:account_statuses_cleanup_policy, account: account3) }
let!(:policy3) { Fabricate(:account_statuses_cleanup_policy, account: account4, enabled: false) }
let(:queue_size) { 0 }
let(:queue_latency) { 0 }
@ -18,18 +19,38 @@ describe Scheduler::AccountsStatusesCleanupScheduler do
[
{
'concurrency' => 2,
'queues' => %w(push default),
'queues' => ['push', 'default'],
},
]
end
before do
queue_stub = instance_double(Sidekiq::Queue, size: queue_size, latency: queue_latency)
queue_stub = double
allow(queue_stub).to receive(:size).and_return(queue_size)
allow(queue_stub).to receive(:latency).and_return(queue_latency)
allow(Sidekiq::Queue).to receive(:new).and_return(queue_stub)
allow(Sidekiq::ProcessSet).to receive(:new).and_return(process_set_stub)
sidekiq_stats_stub = instance_double(Sidekiq::Stats)
sidekiq_stats_stub = double
allow(Sidekiq::Stats).to receive(:new).and_return(sidekiq_stats_stub)
# Create a bunch of old statuses
10.times do
Fabricate(:status, account: account1, created_at: 3.years.ago)
Fabricate(:status, account: account2, created_at: 3.years.ago)
Fabricate(:status, account: account3, created_at: 3.years.ago)
Fabricate(:status, account: account4, created_at: 3.years.ago)
Fabricate(:status, account: remote, created_at: 3.years.ago)
end
# Create a bunch of newer statuses
5.times do
Fabricate(:status, account: account1, created_at: 3.minutes.ago)
Fabricate(:status, account: account2, created_at: 3.minutes.ago)
Fabricate(:status, account: account3, created_at: 3.minutes.ago)
Fabricate(:status, account: account4, created_at: 3.minutes.ago)
Fabricate(:status, account: remote, created_at: 3.minutes.ago)
end
end
describe '#under_load?' do
@ -49,19 +70,19 @@ describe Scheduler::AccountsStatusesCleanupScheduler do
end
end
describe '#compute_budget' do
context 'with a single thread' do
let(:process_set_stub) { [{ 'concurrency' => 1, 'queues' => %w(push default) }] }
describe '#get_budget' do
context 'on a single thread' do
let(:process_set_stub) { [ { 'concurrency' => 1, 'queues' => ['push', 'default'] } ] }
it 'returns a low value' do
expect(subject.compute_budget).to be < 10
end
end
context 'with a lot of threads' do
context 'on a lot of threads' do
let(:process_set_stub) do
[
{ 'concurrency' => 2, 'queues' => %w(push default) },
{ 'concurrency' => 2, 'queues' => ['push', 'default'] },
{ 'concurrency' => 2, 'queues' => ['push'] },
{ 'concurrency' => 2, 'queues' => ['push'] },
{ 'concurrency' => 2, 'queues' => ['push'] },
@ -75,96 +96,21 @@ describe Scheduler::AccountsStatusesCleanupScheduler do
end
describe '#perform' do
around do |example|
Timeout.timeout(30) do
example.run
end
end
before do
# Policies for the accounts
Fabricate(:account_statuses_cleanup_policy, account: account_alice)
Fabricate(:account_statuses_cleanup_policy, account: account_chris)
Fabricate(:account_statuses_cleanup_policy, account: account_dave, enabled: false)
Fabricate(:account_statuses_cleanup_policy, account: account_erin)
# Create a bunch of old statuses
4.times do
Fabricate(:status, account: account_alice, created_at: 3.years.ago)
Fabricate(:status, account: account_bob, created_at: 3.years.ago)
Fabricate(:status, account: account_chris, created_at: 3.years.ago)
Fabricate(:status, account: account_dave, created_at: 3.years.ago)
Fabricate(:status, account: account_erin, created_at: 3.years.ago)
Fabricate(:status, account: remote, created_at: 3.years.ago)
end
# Create a bunch of newer statuses
Fabricate(:status, account: account_alice, created_at: 3.minutes.ago)
Fabricate(:status, account: account_bob, created_at: 3.minutes.ago)
Fabricate(:status, account: account_chris, created_at: 3.minutes.ago)
Fabricate(:status, account: account_dave, created_at: 3.minutes.ago)
Fabricate(:status, account: remote, created_at: 3.minutes.ago)
end
context 'when the budget is lower than the number of toots to delete' do
it 'deletes the appropriate statuses' do
expect(Status.count).to be > (subject.compute_budget) # Data check
expect { subject.perform }
.to change(Status, :count).by(-subject.compute_budget) # Cleanable statuses
.and (not_change { account_bob.statuses.count }) # No cleanup policy for account
.and(not_change { account_dave.statuses.count }) # Disabled cleanup policy
it 'deletes as many statuses as the given budget' do
expect { subject.perform }.to change { Status.count }.by(-subject.compute_budget)
end
it 'eventually deletes every deletable toot given enough runs' do
stub_const 'Scheduler::AccountsStatusesCleanupScheduler::MAX_BUDGET', 4
expect { 3.times { subject.perform } }.to change(Status, :count).by(-cleanable_statuses_count)
it 'does not delete from accounts with no cleanup policy' do
expect { subject.perform }.to_not change { account2.statuses.count }
end
it 'correctly round-trips between users across several runs' do
stub_const 'Scheduler::AccountsStatusesCleanupScheduler::MAX_BUDGET', 3
stub_const 'Scheduler::AccountsStatusesCleanupScheduler::PER_ACCOUNT_BUDGET', 2
expect { 3.times { subject.perform } }
.to change(Status, :count).by(-3 * 3)
.and change { account_alice.statuses.count }
.and change { account_chris.statuses.count }
.and(change { account_erin.statuses.count })
it 'does not delete from accounts with disabled cleanup policies' do
expect { subject.perform }.to_not change { account4.statuses.count }
end
context 'when given a big budget' do
let(:process_set_stub) { [{ 'concurrency' => 400, 'queues' => %w(push default) }] }
before do
stub_const 'Scheduler::AccountsStatusesCleanupScheduler::MAX_BUDGET', 400
end
it 'correctly handles looping in a single run' do
expect(subject.compute_budget).to eq(400)
expect { subject.perform }.to change(Status, :count).by(-cleanable_statuses_count)
end
end
context 'when there is no work to be done' do
let(:process_set_stub) { [{ 'concurrency' => 400, 'queues' => %w(push default) }] }
before do
stub_const 'Scheduler::AccountsStatusesCleanupScheduler::MAX_BUDGET', 400
subject.perform
end
it 'does not get stuck' do
expect(subject.compute_budget).to eq(400)
expect { subject.perform }.to_not change(Status, :count)
end
end
def cleanable_statuses_count
Status
.where(account_id: [account_alice, account_chris, account_erin]) # Accounts with enabled policies
.where('created_at < ?', 2.weeks.ago) # Policy defaults is 2.weeks
.count
it 'eventually deletes every deletable toot' do
expect { subject.perform; subject.perform; subject.perform; subject.perform }.to change { Status.count }.by(-20)
end
end
end