X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=t%2Fv2mirror.t;h=665a4d594f93e445f07cd96fa9a73595e2763ca2;hb=63d7b8ceee55a34cde983e8548d5ce61050d2891;hp=c31dcd5bf7cdc2ed6c8df36ab89656eb70f8d7d2;hpb=4bb34fb8f29530f6bda5f0d563a74f6289ac312d;p=public-inbox.git diff --git a/t/v2mirror.t b/t/v2mirror.t index c31dcd5b..665a4d59 100644 --- a/t/v2mirror.t +++ b/t/v2mirror.t @@ -1,34 +1,29 @@ -# Copyright (C) 2018 all contributors +# Copyright (C) 2018-2021 all contributors # License: AGPL-3.0+ use strict; -use warnings; -use Test::More; -require './t/common.perl'; +use v5.10.1; +use PublicInbox::TestCommon; +use File::Path qw(remove_tree make_path); +use Cwd qw(abs_path); require_git(2.6); +require_cmd('curl'); +local $ENV{HOME} = abs_path('t'); # Integration tests for HTTP cloning + mirroring -foreach my $mod (qw(Plack::Util Plack::Builder - HTTP::Date HTTP::Status Search::Xapian DBD::SQLite - IPC::Run)) { - eval "require $mod"; - plan skip_all => "$mod missing for v2mirror.t" if $@; -} -use File::Temp qw/tempdir/; -use IO::Socket; -use POSIX qw(dup2); +require_mods(qw(Plack::Util Plack::Builder + HTTP::Date HTTP::Status Search::Xapian DBD::SQLite)); use_ok 'PublicInbox::V2Writable'; use PublicInbox::InboxWritable; -use PublicInbox::MIME; +use PublicInbox::Eml; use PublicInbox::Config; # FIXME: too much setup -my $tmpdir = tempdir('pi-v2mirror-XXXXXX', TMPDIR => 1, CLEANUP => 1); -my $script = 'blib/script/public-inbox'; +my ($tmpdir, $for_destroy) = tmpdir(); my $pi_config = "$tmpdir/config"; { open my $fh, '>', $pi_config or die "open($pi_config): $!"; print $fh <<"" or die "print $pi_config: $!"; [publicinbox "v2"] - mainrepo = $tmpdir/in + inboxdir = $tmpdir/in address = test\@example.com close $fh or die "close($pi_config): $!"; @@ -39,10 +34,11 @@ my $cfg = PublicInbox::Config->new($pi_config); my $ibx = $cfg->lookup('test@example.com'); ok($ibx, 'inbox found'); $ibx->{version} = 2; +$ibx->{-no_fsync} = 1; my $v2w = PublicInbox::V2Writable->new($ibx, 1); ok $v2w, 'v2w loaded'; $v2w->{parallel} = 0; -my $mime = PublicInbox::MIME->new(<<''); +my $mime = PublicInbox::Eml->new(<<''); From: Me To: You Subject: a @@ -59,68 +55,63 @@ for my $i (1..9) { my $epoch_max = $v2w->{epoch_max}; ok($epoch_max > 0, "multiple epochs"); $v2w->done; +{ + my $smsg = $ibx->over->get_art(1); + like($smsg->{lines}, qr/\A[0-9]+\z/, 'lines is a digit'); + like($smsg->{bytes}, qr/\A[0-9]+\z/, 'bytes is a digit'); +} +$ibx->cleanup; -my %opts = ( - LocalAddr => '127.0.0.1', - ReuseAddr => 1, - Proto => 'tcp', - Listen => 1024, -); -my ($sock, $pid); -END { kill 'TERM', $pid if defined $pid }; - -$! = 0; -$sock = IO::Socket::INET->new(%opts); -ok($sock, 'sock created'); -my $cmd = [ "$script-httpd", "--stdout=$tmpdir/out", "--stderr=$tmpdir/err" ]; -ok(defined($pid = spawn_listener(undef, $cmd, [ $sock ])), - 'spawned httpd process successfully'); -my ($host, $port) = ($sock->sockhost, $sock->sockport); +my $sock = tcp_server(); +my @cmd = ('-httpd', '-W0', "--stdout=$tmpdir/out", "--stderr=$tmpdir/err"); +my $td = start_script(\@cmd, undef, { 3 => $sock }); +my ($host, $port) = tcp_host_port($sock); $sock = undef; -my @cmd; -foreach my $i (0..$epoch_max) { - my $sfx = $i == 0 ? '.git' : ''; - @cmd = (qw(git clone --mirror -q), - "http://$host:$port/v2/$i$sfx", - "$tmpdir/m/git/$i.git"); +@cmd = (qw(-clone -q), "http://$host:$port/v2/", "$tmpdir/m"); +run_script(\@cmd) or xbail '-clone'; - is(system(@cmd), 0, "cloned $i.git"); - ok(-d "$tmpdir/m/git/$i.git", "mirror $i OK"); +for my $i (0..$epoch_max) { + ok(-d "$tmpdir/m/git/$i.git", "epoch $i cloned"); } -@cmd = ("$script-init", '-V2', 'm', "$tmpdir/m", 'http://example.com/m', +@cmd = ("-init", '-j1', '-V2', 'm', "$tmpdir/m", 'http://example.com/m', 'alt@example.com'); -is(system(@cmd), 0, 'initialized public-inbox -V2'); -is(system("$script-index", "$tmpdir/m"), 0, 'indexed'); +ok(run_script(\@cmd), 'initialized public-inbox -V2'); +my @shards = glob("$tmpdir/m/xap*/?"); +is(scalar(@shards), 1, 'got a single shard on init'); -my $mibx = { mainrepo => "$tmpdir/m", address => 'alt@example.com' }; +ok(run_script([qw(-index -j0), "$tmpdir/m"]), 'indexed'); + +my $mibx = { inboxdir => "$tmpdir/m", address => 'alt@example.com' }; $mibx = PublicInbox::Inbox->new($mibx); is_deeply([$mibx->mm->minmax], [$ibx->mm->minmax], 'index synched minmax'); -$v2w->{rotate_bytes} = $old_rotate_bytes; for my $i (10..15) { $mime->header_set('Message-ID', "<$i\@example.com>"); $mime->header_set('Subject', "subject = $i"); ok($v2w->add($mime), "add msg $i OK"); } -$v2w->barrier; +$v2w->done; +$ibx->cleanup; -sub fetch_each_epoch { - foreach my $i (0..$epoch_max) { - my $dir = "$tmpdir/m/git/$i.git"; - is(system('git', "--git-dir=$dir", 'fetch', '-q'), 0, - 'fetch successful'); - } -} +my @new_epochs; +my $fetch_each_epoch = sub { + my %before = map { $_ => 1 } glob("$tmpdir/m/git/*"); + run_script([qw(-fetch --exit-code -q)], undef, {-C => "$tmpdir/m"}) or + xbail '-fetch fail'; + is($?, 0, '--exit-code 0 after fetch updated'); + my @after = grep { !$before{$_} } glob("$tmpdir/m/git/*"); + push @new_epochs, @after; +}; -fetch_each_epoch(); +$fetch_each_epoch->(); -my $mset = $mibx->search->reopen->query('m:15@example.com', {mset => 1}); +my $mset = $mibx->search->reopen->mset('m:15@example.com'); is(scalar($mset->items), 0, 'new message not found in mirror, yet'); -is(system("$script-index", "$tmpdir/m"), 0, 'index updated'); +ok(run_script([qw(-index -j0), "$tmpdir/m"]), 'index updated'); is_deeply([$mibx->mm->minmax], [$ibx->mm->minmax], 'index synched minmax'); -$mset = $mibx->search->reopen->query('m:15@example.com', {mset => 1}); +$mset = $mibx->search->reopen->mset('m:15@example.com'); is(scalar($mset->items), 1, 'found message in mirror'); # purge: @@ -136,28 +127,32 @@ $mime->header_set('Subject', 'subject = 10'); is_deeply(\@subj, ["# subject = 10"], "only rewrote one"); } -$v2w->barrier; +$v2w->done; -my $msgs = $mibx->search->{over_ro}->get_thread('10@example.com'); +my $msgs = $mibx->over->get_thread('10@example.com'); my $to_purge = $msgs->[0]->{blob}; like($to_purge, qr/\A[a-f0-9]{40,}\z/, 'read blob to be purged'); -$mset = $ibx->search->reopen->query('m:10@example.com', {mset => 1}); +$mset = $ibx->search->reopen->mset('m:10@example.com'); is(scalar($mset->items), 0, 'purged message gone from origin'); -fetch_each_epoch(); +$fetch_each_epoch->(); { - my $cmd = [ "$script-index", '--prune', "$tmpdir/m" ]; - my ($in, $out, $err) = ('', '', ''); - ok(IPC::Run::run($cmd, \$in, \$out, \$err), '-index --prune'); + $ibx->cleanup; + PublicInbox::InboxWritable::cleanup($mibx); + $v2w->done; + my $cmd = [ qw(-index --prune -j0), "$tmpdir/m" ]; + my ($out, $err) = ('', ''); + my $opt = { 1 => \$out, 2 => \$err }; + ok(run_script($cmd, undef, $opt), '-index --prune'); like($err, qr/discontiguous range/, 'warned about discontiguous range'); unlike($err, qr/fatal/, 'no scary fatal error shown'); } -$mset = $mibx->search->reopen->query('m:10@example.com', {mset => 1}); +$mset = $mibx->search->reopen->mset('m:10@example.com'); is(scalar($mset->items), 0, 'purged message not found in mirror'); is_deeply([$mibx->mm->minmax], [$ibx->mm->minmax], 'minmax still synced'); for my $i ((1..9),(11..15)) { - $mset = $mibx->search->query("m:$i\@example.com", {mset => 1}); + $mset = $mibx->search->mset("m:$i\@example.com"); is(scalar($mset->items), 1, "$i\@example.com remains visible"); } is($mibx->git->check($to_purge), undef, 'unindex+prune successful in mirror'); @@ -171,26 +166,104 @@ is($mibx->git->check($to_purge), undef, 'unindex+prune successful in mirror'); # deletes happen in a different fetch window { - $mset = $mibx->search->reopen->query('m:1@example.com', {mset => 1}); + $mset = $mibx->search->reopen->mset('m:1@example.com'); is(scalar($mset->items), 1, '1@example.com visible in mirror'); $mime->header_set('Message-ID', '<1@example.com>'); $mime->header_set('Subject', 'subject = 1'); ok($v2w->remove($mime), 'removed <1@example.com> from source'); $v2w->done; - fetch_each_epoch(); + $ibx->cleanup; + $fetch_each_epoch->(); + PublicInbox::InboxWritable::cleanup($mibx); - my ($in, $out, $err) = ('', '', ''); - my $cmd = [ "$script-index", "$tmpdir/m" ]; - ok(IPC::Run::run($cmd, \$in, \$out, \$err), 'index ran'); + my $cmd = [ qw(-index -j0), "$tmpdir/m" ]; + my ($out, $err) = ('', ''); + my $opt = { 1 => \$out, 2 => \$err }; + ok(run_script($cmd, undef, $opt), 'index ran'); is($err, '', 'no errors reported by index'); - $mset = $mibx->search->reopen->query('m:1@example.com', {mset => 1}); + $mset = $mibx->search->reopen->mset('m:1@example.com'); is(scalar($mset->items), 0, '1@example.com no longer visible in mirror'); } -ok(kill('TERM', $pid), 'killed httpd'); -$pid = undef; -waitpid(-1, 0); +if ('sequential-shard') { + $mset = $mibx->search->mset('m:15@example.com'); + is(scalar($mset->items), 1, 'large message not indexed'); + remove_tree(glob("$tmpdir/m/xap*"), glob("$tmpdir/m/msgmap.*")); + my $cmd = [ qw(-index -j9 --sequential-shard), "$tmpdir/m" ]; + ok(run_script($cmd), '--sequential-shard works'); + my @shards = glob("$tmpdir/m/xap*/?"); + is(scalar(@shards), 8, 'got expected shard count'); + PublicInbox::InboxWritable::cleanup($mibx); + $mset = $mibx->search->mset('m:15@example.com'); + is(scalar($mset->items), 1, 'search works after --sequential-shard'); +} + +if ('max size') { + $mime->header_set('Message-ID', '<2big@a>'); + my $max = '2k'; + $mime->body_str_set("z\n" x 1024); + ok($v2w->add($mime), "add big message"); + $v2w->done; + $ibx->cleanup; + $fetch_each_epoch->(); + PublicInbox::InboxWritable::cleanup($mibx); + my $cmd = [qw(-index -j0), "$tmpdir/m", "--max-size=$max" ]; + my $opt = { 2 => \(my $err) }; + ok(run_script($cmd, undef, $opt), 'indexed with --max-size'); + like($err, qr/skipping [a-f0-9]{40,}/, 'warned about skipping message'); + $mset = $mibx->search->reopen->mset('m:2big@a'); + is(scalar($mset->items), 0, 'large message not indexed'); + + { + open my $fh, '>>', $pi_config or die; + print $fh <search->reopen->mset('m:2big@a'); + is(scalar($mset->items), 0, 'large message not re-indexed'); +} +ok(scalar(@new_epochs), 'new epochs were created and fetched'); +for my $d (@new_epochs) { + is(xqx(['git', "--git-dir=$d", 'config', qw(include.path)]), + "../../all.git/config\n", + 'include.path set'); +} + +if ('test read-only epoch dirs') { + my @git = ('git', "--git-dir=$new_epochs[0]"); + my $get_objs = [@git, + qw(cat-file --buffer --batch-check --batch-all-objects)]; + my $before = [sort xqx($get_objs)]; + + remove_tree(map { "$new_epochs[0]/$_" } qw(objects refs/heads)); + chmod(0555, $new_epochs[0]) or xbail "chmod: $!"; + + # force a refetch + unlink("$tmpdir/m/manifest.js.gz") or xbail "unlink: $!"; + + run_script([qw(-fetch -q)], undef, {-C => "$tmpdir/m"}) or + xbail '-fetch failed'; + + ok(!-d "$new_epochs[0]/objects", 'no objects after fetch to R/O dir'); + + chmod(0755, $new_epochs[0]) or xbail "chmod: $!"; + mkdir("$new_epochs[0]/objects") or xbail "mkdir: $!"; + mkdir("$new_epochs[0]/refs/heads") or xbail "mkdir: $!"; + + my $err = ''; + run_script([qw(-fetch -q)], undef, {-C => "$tmpdir/m", 2 => \$err}) or + xbail '-fetch failed '.$err; + is_deeply([ sort xqx($get_objs) ], $before, + 'fetch restored objects once GIT_DIR became writable'); +} -done_testing(); +ok($td->kill, 'killed httpd'); +$td->join; -1; +done_testing;