X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FAdmin.pm;h=fb88e621b021b8b68e47c1524fd9227634abf81a;hb=256b3566e4d57a64bb349a7b896da10381a2a363;hp=5549b855bd65f66ed0766c36de8c177d011b6e28;hpb=a0eabc015e22e51cbf8f6060abafd5b53a0ae72f;p=public-inbox.git diff --git a/lib/PublicInbox/Admin.pm b/lib/PublicInbox/Admin.pm index 5549b855..fb88e621 100644 --- a/lib/PublicInbox/Admin.pm +++ b/lib/PublicInbox/Admin.pm @@ -1,16 +1,31 @@ -# Copyright (C) 2019 all contributors +# Copyright (C) 2019-2020 all contributors # License: AGPL-3.0+ # common stuff for administrative command-line tools # Unstable internal API package PublicInbox::Admin; use strict; -use warnings; -use Cwd 'abs_path'; -use base qw(Exporter); -our @EXPORT_OK = qw(resolve_repo_dir); -my $CFG; # all the admin stuff is a singleton -require PublicInbox::Config; +use parent qw(Exporter); +use Cwd qw(abs_path); +use POSIX (); +our @EXPORT_OK = qw(resolve_repo_dir setup_signals); +use PublicInbox::Config; +use PublicInbox::Inbox; +use PublicInbox::Spawn qw(popen_rd); + +sub setup_signals { + my ($cb, $arg) = @_; # optional + + # we call exit() here instead of _exit() so DESTROY methods + # get called (e.g. File::Temp::Dir and PublicInbox::Msgmap) + $SIG{INT} = $SIG{HUP} = $SIG{PIPE} = $SIG{TERM} = sub { + my ($sig) = @_; + # https://www.tldp.org/LDP/abs/html/exitcodes.html + eval { $cb->($sig, $arg) } if $cb; + $sig = 'SIG'.$sig; + exit(128 + POSIX->$sig); + }; +} sub resolve_repo_dir { my ($cd, $ver) = @_; @@ -19,41 +34,28 @@ sub resolve_repo_dir { $$ver = 2 if $ver; return abs_path($prefix); } - - my @cmd = qw(git rev-parse --git-dir); - my $cmd = join(' ', @cmd); - my $pid = open my $fh, '-|'; - defined $pid or die "forking $cmd failed: $!\n"; - if ($pid == 0) { - if (defined $cd) { - chdir $cd or die "chdir $cd failed: $!\n"; - } - exec @cmd; - die "Failed to exec $cmd: $!\n"; - } else { - my $dir = eval { - local $/; - <$fh>; - }; - close $fh or die "error in $cmd: $!\n"; - chomp $dir; - $$ver = 1 if $ver; - return abs_path($cd) if ($dir eq '.' && defined $cd); - abs_path($dir); - } + my $cmd = [ qw(git rev-parse --git-dir) ]; + my $fh = popen_rd($cmd, undef, {-C => $cd}); + my $dir = do { local $/; <$fh> }; + close $fh or die "error in ".join(' ', @$cmd)." (cwd:$cd): $!\n"; + chomp $dir; + $$ver = 1 if $ver; + return abs_path($cd) if ($dir eq '.' && defined $cd); + abs_path($dir); } # for unconfigured inboxes sub detect_indexlevel ($) { my ($ibx) = @_; - # brand new or never before indexed inboxes default to full - return 'full' unless $ibx->over; - delete $ibx->{over}; # don't leave open FD lying around + my $over = $ibx->over; + my $srch = $ibx->search; + delete @$ibx{qw(over search)}; # don't leave open FDs lying around + # brand new or never before indexed inboxes default to full + return 'full' unless $over; my $l = 'basic'; - my $srch = $ibx->search or return $l; - delete $ibx->{search}; # don't leave open FD lying around + return $l unless $srch; if (my $xdb = $srch->xdb) { $l = 'full'; my $m = $xdb->get_metadata('indexlevel'); @@ -61,9 +63,10 @@ sub detect_indexlevel ($) { $l = $m; } elsif ($m ne '') { warn <<""; -$ibx->{mainrepo} has unexpected indexlevel in Xapian: $m +$ibx->{inboxdir} has unexpected indexlevel in Xapian: $m } + $ibx->{-skip_docdata} = 1 if $xdb->get_metadata('skip_docdata'); } $l; } @@ -74,20 +77,17 @@ sub unconfigured_ibx ($$) { PublicInbox::Inbox->new({ name => $name, address => [ "$name\@example.com" ], - mainrepo => $dir, + inboxdir => $dir, # TODO: consumers may want to warn on this: #-unconfigured => 1, }); } -sub config () { $CFG //= eval { PublicInbox::Config->new } } - -sub resolve_inboxes ($;$) { - my ($argv, $opt) = @_; - require PublicInbox::Inbox; +sub resolve_inboxes ($;$$) { + my ($argv, $opt, $cfg) = @_; $opt ||= {}; - my $cfg = config(); + $cfg //= PublicInbox::Config->new; if ($opt->{all}) { my $cfgfile = PublicInbox::Config::default_file(); $cfg or die "--all specified, but $cfgfile not readable\n"; @@ -100,13 +100,19 @@ sub resolve_inboxes ($;$) { if ($cfg) { $cfg->each_inbox(sub { my ($ibx) = @_; - $ibx->{version} ||= 1; - $dir2ibx{abs_path($ibx->{mainrepo})} = $ibx; + my $path = abs_path($ibx->{inboxdir}); + if (defined($path)) { + $dir2ibx{$path} = $ibx; + } else { + warn <{name} $ibx->{inboxdir}: $! +EOF + } }); } if ($opt->{all}) { my @all = values %dir2ibx; - @all = grep { $_->{version} >= $min_ver } @all; + @all = grep { $_->version >= $min_ver } @all; push @ibxs, @all; } else { # directories specified on the command-line my $i = 0; @@ -125,14 +131,14 @@ sub resolve_inboxes ($;$) { } } if (@old) { - die "inboxes $min_ver inboxes not supported by $0\n\t", + die "-V$min_ver inboxes not supported by $0\n\t", join("\n\t", @old), "\n"; } @ibxs; } # TODO: make Devel::Peek optional, only used for daemon -my @base_mod = qw(Email::MIME Date::Parse Devel::Peek); +my @base_mod = qw(Devel::Peek); my @over_mod = qw(DBD::SQLite DBI); my %mod_groups = ( -index => [ @base_mod, @over_mod ], @@ -155,6 +161,10 @@ sub check_require { while (my $mod = shift @mods) { if (my $groups = $mod_groups{$mod}) { push @mods, @$groups; + } elsif ($mod eq 'Search::Xapian') { + require PublicInbox::Search; + PublicInbox::Search::load_xapian() or + $err->{'Search::Xapian || Xapian'} = $@; } else { eval "require $mod"; $err->{$mod} = $@ if $@; @@ -191,23 +201,32 @@ invalid indexlevel=$indexlevel (must be `basic', `medium', or `full') die missing_mod_msg($err) ." required for indexlevel=$indexlevel\n"; } +sub index_terminate { + my (undef, $ibx) = @_; # $_[0] = signal name + $ibx->git->cleanup; +} + sub index_inbox { - my ($ibx, $opt) = @_; + my ($ibx, $im, $opt) = @_; my $jobs = delete $opt->{jobs} if $opt; - if (ref($ibx) && ($ibx->{version} || 1) == 2) { + if (my $pr = $opt->{-progress}) { + $pr->("indexing $ibx->{inboxdir} ...\n"); + } + local %SIG = %SIG; + setup_signals(\&index_terminate, $ibx); + if (ref($ibx) && $ibx->version == 2) { eval { require PublicInbox::V2Writable }; die "v2 requirements not met: $@\n" if $@; - my $v2w = eval { $ibx->importer(0) } || eval { - PublicInbox::V2Writable->new($ibx, {nproc=>$jobs}); - }; + $ibx->{-creat_opt}->{nproc} = $jobs; + my $v2w = $im // $ibx->importer($opt->{reindex} // $jobs); if (defined $jobs) { if ($jobs == 0) { $v2w->{parallel} = 0; } else { - my $n = $v2w->{partitions}; - if ($jobs != ($n + 1)) { + my $n = $v2w->{shards}; + if ($jobs < ($n + 1) && !$opt->{reshard}) { warn -"Unable to respect --jobs=$jobs, inbox was created with $n shards\n"; +"Unable to respect --jobs=$jobs on index, inbox was created with $n shards\n"; } } } @@ -233,12 +252,58 @@ sub progress_prepare ($) { if ($opt->{quiet}) { open my $null, '>', '/dev/null' or die "failed to open /dev/null: $!\n"; - $opt->{1} = fileno($null); # suitable for spawn() redirect - $opt->{-dev_null} = $null; + $opt->{1} = $null; # suitable for spawn() redirect } else { $opt->{verbose} ||= 1; $opt->{-progress} = sub { print STDERR @_ }; } } +# same unit factors as git: +sub parse_unsigned ($) { + my ($val) = @_; + + $$val =~ /\A([0-9]+)([kmg])?\z/i or return; + my ($n, $unit_factor) = ($1, $2 // ''); + my %u = ( k => 1024, m => 1024**2, g => 1024**3 ); + $$val = $n * ($u{lc($unit_factor)} // 1); + 1; +} + +sub index_prepare ($$) { + my ($opt, $cfg) = @_; + my $env; + if ($opt->{compact}) { + require PublicInbox::Xapcmd; + PublicInbox::Xapcmd::check_compact(); + $opt->{compact_opt} = { -coarse_lock => 1, compact => 1 }; + if (defined(my $jobs = $opt->{jobs})) { + $opt->{compact_opt}->{jobs} = $jobs; + } + } + for my $k (qw(max_size batch_size)) { + my $git_key = "publicInbox.index".ucfirst($k); + $git_key =~ s/_([a-z])/\U$1/g; + defined(my $v = $opt->{$k} // $cfg->{lc($git_key)}) or next; + parse_unsigned(\$v) or die "`$git_key=$v' not parsed\n"; + $v > 0 or die "`$git_key=$v' must be positive\n"; + $opt->{$k} = $v; + } + + # out-of-the-box builds of Xapian 1.4.x are still limited to 32-bit + # https://getting-started-with-xapian.readthedocs.io/en/latest/concepts/indexing/limitations.html + $opt->{batch_size} and + $env = { XAPIAN_FLUSH_THRESHOLD => '4294967295' }; + + for my $k (qw(sequential_shard)) { + my $git_key = "publicInbox.index".ucfirst($k); + $git_key =~ s/_([a-z])/\U$1/g; + defined(my $s = $opt->{$k} // $cfg->{lc($git_key)}) or next; + defined(my $v = $cfg->git_bool($s)) + or die "`$git_key=$s' not boolean\n"; + $opt->{$k} = $v; + } + $env; +} + 1;