|
| 1 | +# Copyright (c) 2025, PostgreSQL Global Development Group |
| 2 | +# |
| 3 | +# This test aims to validate that hard links are created as expected in the |
| 4 | +# output directory, when running pg_combinebackup with --link mode. |
| 5 | + |
| 6 | +use strict; |
| 7 | +use warnings FATAL => 'all'; |
| 8 | +use PostgreSQL::Test::Cluster; |
| 9 | +use PostgreSQL::Test::Utils; |
| 10 | +use Test::More; |
| 11 | + |
| 12 | +# Set up a new database instance. |
| 13 | +my $primary = PostgreSQL::Test::Cluster->new('primary'); |
| 14 | +$primary->init(has_archiving => 1, allows_streaming => 1); |
| 15 | +$primary->append_conf('postgresql.conf', 'summarize_wal = on'); |
| 16 | +# We disable autovacuum to prevent "something else" to modify our test tables. |
| 17 | +$primary->append_conf('postgresql.conf', 'autovacuum = off'); |
| 18 | +$primary->start; |
| 19 | + |
| 20 | +# Create a couple of tables (~264KB each). |
| 21 | +# Note: Cirrus CI runs some tests with a very small segment size, so, in that |
| 22 | +# environment, a single table of 264KB would have both a segment with a link |
| 23 | +# count of 1 and also one with a link count of 2. But in a normal installation, |
| 24 | +# segment size is 1GB. Therefore, we use 2 different tables here: for test_1, |
| 25 | +# all segments (or the only one) will have two hard links; for test_2, the |
| 26 | +# last segment (or the only one) will have 1 hard link, and any others will |
| 27 | +# have 2. |
| 28 | +my $query = <<'EOM'; |
| 29 | +CREATE TABLE test_%s AS |
| 30 | + SELECT x.id::bigint, |
| 31 | + repeat('a', 1600) AS value |
| 32 | + FROM generate_series(1, 100) AS x(id); |
| 33 | +EOM |
| 34 | + |
| 35 | +$primary->safe_psql('postgres', sprintf($query, '1')); |
| 36 | +$primary->safe_psql('postgres', sprintf($query, '2')); |
| 37 | + |
| 38 | +# Fetch information about the data files. |
| 39 | +$query = <<'EOM'; |
| 40 | +SELECT pg_relation_filepath(oid) |
| 41 | +FROM pg_class |
| 42 | +WHERE relname = 'test_%s'; |
| 43 | +EOM |
| 44 | + |
| 45 | +my $test_1_path = $primary->safe_psql('postgres', sprintf($query, '1')); |
| 46 | +note "test_1 path is $test_1_path"; |
| 47 | + |
| 48 | +my $test_2_path = $primary->safe_psql('postgres', sprintf($query, '2')); |
| 49 | +note "test_2 path is $test_2_path"; |
| 50 | + |
| 51 | +# Take a full backup. |
| 52 | +my $backup1path = $primary->backup_dir . '/backup1'; |
| 53 | +$primary->command_ok( |
| 54 | + [ |
| 55 | + 'pg_basebackup', |
| 56 | + '--pgdata' => $backup1path, |
| 57 | + '--no-sync', |
| 58 | + '--checkpoint' => 'fast', |
| 59 | + '--wal-method' => 'none' |
| 60 | + ], |
| 61 | + "full backup"); |
| 62 | + |
| 63 | +# Perform an insert that touches a page of the last segment of the data file of |
| 64 | +# table test_2. |
| 65 | +$primary->safe_psql('postgres', <<EOM); |
| 66 | +INSERT INTO test_2 (id, value) VALUES (101, repeat('a', 1600)); |
| 67 | +EOM |
| 68 | + |
| 69 | +# Take an incremental backup. |
| 70 | +my $backup2path = $primary->backup_dir . '/backup2'; |
| 71 | +$primary->command_ok( |
| 72 | + [ |
| 73 | + 'pg_basebackup', |
| 74 | + '--pgdata' => $backup2path, |
| 75 | + '--no-sync', |
| 76 | + '--checkpoint' => 'fast', |
| 77 | + '--wal-method' => 'none', |
| 78 | + '--incremental' => $backup1path . '/backup_manifest' |
| 79 | + ], |
| 80 | + "incremental backup"); |
| 81 | + |
| 82 | +# Restore the incremental backup and use it to create a new node. |
| 83 | +my $restore = PostgreSQL::Test::Cluster->new('restore'); |
| 84 | +$restore->init_from_backup( |
| 85 | + $primary, 'backup2', |
| 86 | + combine_with_prior => ['backup1'], |
| 87 | + combine_mode => '--link'); |
| 88 | + |
| 89 | +# Ensure files have the expected count of hard links. We expect all data files |
| 90 | +# from test_1 to contain 2 hard links, because they were not touched between the |
| 91 | +# full and incremental backups, and the last data file of table test_2 to |
| 92 | +# contain a single hard link because of changes in its last page. |
| 93 | +my $test_1_full_path = join('/', $restore->data_dir, $test_1_path); |
| 94 | +check_data_file($test_1_full_path, 2); |
| 95 | + |
| 96 | +my $test_2_full_path = join('/', $restore->data_dir, $test_2_path); |
| 97 | +check_data_file($test_2_full_path, 1); |
| 98 | + |
| 99 | +# OK, that's all. |
| 100 | +done_testing(); |
| 101 | + |
| 102 | + |
| 103 | +# Given the path to the first segment of a data file, inspect its parent |
| 104 | +# directory to find all the segments of that data file, and make sure all the |
| 105 | +# segments contain 2 hard links. The last one must have the given number of hard |
| 106 | +# links. |
| 107 | +# |
| 108 | +# Parameters: |
| 109 | +# * data_file: path to the first segment of a data file, as per the output of |
| 110 | +# pg_relation_filepath. |
| 111 | +# * last_segment_nlinks: the number of hard links expected in the last segment |
| 112 | +# of the given data file. |
| 113 | +sub check_data_file |
| 114 | +{ |
| 115 | + my ($data_file, $last_segment_nlinks) = @_; |
| 116 | + |
| 117 | + my @data_file_segments = ($data_file); |
| 118 | + |
| 119 | + # Start checking for additional segments |
| 120 | + my $segment_number = 1; |
| 121 | + |
| 122 | + while (1) |
| 123 | + { |
| 124 | + my $next_segment = $data_file . '.' . $segment_number; |
| 125 | + |
| 126 | + # If the file exists and is a regular file, add it to the list |
| 127 | + if (-f $next_segment) |
| 128 | + { |
| 129 | + push @data_file_segments, $next_segment; |
| 130 | + $segment_number++; |
| 131 | + } |
| 132 | + # Stop the loop if the file doesn't exist |
| 133 | + else |
| 134 | + { |
| 135 | + last; |
| 136 | + } |
| 137 | + } |
| 138 | + |
| 139 | + # All segments of the given data file should contain 2 hard links, except |
| 140 | + # for the last one, which should match the given number of links. |
| 141 | + my $last_segment = pop @data_file_segments; |
| 142 | + |
| 143 | + for my $segment (@data_file_segments) |
| 144 | + { |
| 145 | + # Get the file's stat information of each segment |
| 146 | + my $nlink_count = get_hard_link_count($segment); |
| 147 | + ok($nlink_count == 2, "File '$segment' has 2 hard links"); |
| 148 | + } |
| 149 | + |
| 150 | + # Get the file's stat information of the last segment |
| 151 | + my $nlink_count = get_hard_link_count($last_segment); |
| 152 | + ok($nlink_count == $last_segment_nlinks, |
| 153 | + "File '$last_segment' has $last_segment_nlinks hard link(s)"); |
| 154 | +} |
| 155 | + |
| 156 | + |
| 157 | +# Subroutine to get hard link count of a given file. |
| 158 | +# Receives the path to a file, and returns the number of hard links of |
| 159 | +# that file. |
| 160 | +sub get_hard_link_count |
| 161 | +{ |
| 162 | + my ($file) = @_; |
| 163 | + |
| 164 | + # Get file stats |
| 165 | + my @stats = stat($file); |
| 166 | + my $nlink = $stats[3]; # Number of hard links |
| 167 | + |
| 168 | + return $nlink; |
| 169 | +} |
0 commit comments