X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiMirror.pm;h=1138a82d04f7c03d92de5134358650d8bd09b317;hb=550d283867c0f8a39207f368c49b5d7496045320;hp=b0e6fa53c3bcb45aae8229be9dd7e6e1e5f4c94c;hpb=e6208a4d8c67e9eccd72d17b85aed7d5a4ad8e31;p=public-inbox.git diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm index b0e6fa53..1138a82d 100644 --- a/lib/PublicInbox/LeiMirror.pm +++ b/lib/PublicInbox/LeiMirror.pm @@ -18,8 +18,10 @@ use PublicInbox::Config; use PublicInbox::Inbox; use PublicInbox::LeiCurl; use PublicInbox::OnDestroy; +use Digest::SHA qw(sha256_hex); our $LIVE; # pid => callback +my $update_ref_stdin = $ENV{GIT_CAN_UPDATE_REF_STDIN} // 1; sub _wq_done_wait { # dwaitpid callback (via wq_eof) my ($arg, $pid) = @_; @@ -31,9 +33,9 @@ sub _wq_done_wait { # dwaitpid callback (via wq_eof) warn("unlink($f): $!\n") unless $!{ENOENT}; } else { if (!$mrr->{dry_run} && $lei->{cmd} ne 'public-inbox-clone') { - # calls _finish_add_external - $lei->lazy_cb('add-external', '_finish_' - )->($lei, $mrr->{dst}); + require PublicInbox::LeiAddExternal; + PublicInbox::LeiAddExternal::_finish_add_external( + $lei, $mrr->{dst}); } $lei->qerr("# mirrored $mrr->{src} => $mrr->{dst}"); } @@ -111,9 +113,9 @@ sub clone_cmd { @cmd; } -sub ft_rename ($$$) { - my ($ft, $dst, $open_mode) = @_; - my @st = stat($dst); +sub ft_rename ($$$;$) { + my ($ft, $dst, $open_mode, $fh) = @_; + my @st = stat($fh // $dst); my $mode = @st ? ($st[2] & 07777) : ($open_mode & ~umask); chmod($mode, $ft) or croak "E: chmod($ft): $!"; require File::Copy; @@ -121,6 +123,21 @@ sub ft_rename ($$$) { $ft->unlink_on_destroy(0); } +sub do_reap ($;$) { + my ($self, $jobs) = @_; + $jobs //= $self->{-jobs} //= $self->{lei}->{opt}->{jobs} // 1; + $jobs = 1 if $jobs < 1; + while (keys(%$LIVE) >= $jobs) { + my $pid = waitpid(-1, 0) // die "waitpid(-1): $!"; + if (my $x = delete $LIVE->{$pid}) { + my $cb = shift @$x; + $cb->(@$x) if $cb; + } else { + warn "reaped unknown PID=$pid ($?)\n"; + } + } +} + sub _get_txt_start { # non-fatal my ($self, $endpoint, $fini) = @_; my $uri = URI->new($self->{cur_src} // $self->{src}); @@ -133,8 +150,7 @@ sub _get_txt_start { # non-fatal my $opt = { 0 => $lei->{0}, 1 => $lei->{1}, 2 => $lei->{2} }; my $cmd = $self->{curl}->for_uri($lei, $uri, qw(-f --compressed -R -o), $ft->filename); - my $jobs = $lei->{opt}->{jobs} // 1; - reap_live() while keys(%$LIVE) >= $jobs; + do_reap($self); $lei->qerr("# @$cmd"); return if $self->{dry_run}; $self->{"-get_txt.$endpoint"} = [ $ft, $cmd, $uri ]; @@ -202,8 +218,6 @@ sub set_description ($) { sub index_cloned_inbox { my ($self, $iv) = @_; my $lei = $self->{lei}; - eval { set_description($self) }; - warn $@ if $@; # n.b. public-inbox-clone works w/o (SQLite || Xapian) # lei is useless without Xapian + SQLite @@ -245,11 +259,181 @@ sub run_reap { sub start_clone { my ($self, $cmd, $opt, $fini) = @_; - my $jobs = $self->{lei}->{opt}->{jobs} // 1; - reap_live() while keys(%$LIVE) >= $jobs; + do_reap($self); $self->{lei}->qerr("# @$cmd"); return if $self->{dry_run}; - $LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_clone, $self, $cmd, $fini ] + $LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_cmd, $self, $cmd, $fini ] +} + +sub fetch_args ($$) { + my ($lei, $opt) = @_; + my @cmd; # (git --git-dir=...) to be added by caller + $opt->{$_} = $lei->{$_} for (0..2); + # we support "-c $key=$val" for arbitrary git config options + # e.g.: git -c http.proxy=socks5h://127.0.0.1:9050 + push(@cmd, '-c', $_) for @{$lei->{opt}->{c} // []}; + push @cmd, 'fetch'; + push @cmd, '-q' if $lei->{opt}->{quiet} || + ($lei->{opt}->{jobs} // 1) > 1; + push @cmd, '-v' if $lei->{opt}->{verbose}; + @cmd; +} + +sub fgrp_update_old ($) { # for git <1.8.5 + my ($fgrp) = @_; + my $cmd = [ @{$fgrp->{-torsocks}}, 'git', "--git-dir=$fgrp->{cur_dst}", + fetch_args($fgrp->{lei}, my $opt = {}) ]; + $fgrp->{lei}->qerr("# @$cmd"); + do_reap($fgrp); + $LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_cmd, $fgrp, $cmd ]; +} + +sub upr { # feed `git update-ref --stdin -z' verbosely + my ($lei, $w, $op, $ref, $oid) = @_; + $lei->qerr("# $op $ref $oid") if $lei->{opt}->{verbose}; + print $w "$op $ref\0$oid\0" or die "print(w): $!"; +} + +sub fgrp_update { + my ($fgrp) = @_; + my $srcfh = delete $fgrp->{srcfh} or return; + my $dstfh = delete $fgrp->{dstfh} or return; + seek($srcfh, SEEK_SET, 0) or die "seek(src): $!"; + seek($dstfh, SEEK_SET, 0) or die "seek(dst): $!"; + my %src = map { chomp; split(/\0/) } (<$srcfh>); + close $srcfh; + my %dst = map { chomp; split(/\0/) } (<$dstfh>); + close $dstfh; + pipe(my ($r, $w)) or die "pipe: $!"; + my $cmd = [ 'git', "--git-dir=$fgrp->{cur_dst}", + qw(update-ref --stdin -z) ]; + my $lei = $fgrp->{lei}; + $lei->qerr("# @$cmd"); + my $opt = { 0 => $r, 1 => $lei->{1}, 2 => $lei->{2} }; + my $pid = spawn($cmd, undef, $opt); + close $r or die "close(r): $!"; + for my $ref (keys %dst) { + my $new = delete $src{$ref}; + my $old = $dst{$ref}; + if (defined $new) { + upr($lei, $w, 'update', $ref, $new) if $new ne $old; + } else { + upr($lei, $w, 'delete', $ref, $old); + } + } + while (my ($ref, $oid) = each %src) { + upr($lei, $w, 'create', $ref, $oid); + } + if (close($w)) { # git >= 1.8.5 + $LIVE->{$pid} = [ \&reap_cmd, $fgrp, $cmd ]; + do_reap($fgrp); + } else { # git <1.8.5 w/o update-ref --stdin + warn "E: close(update-ref --stdin): $!\n"; + $update_ref_stdin = 0; + waitpid($pid, 0) // die "waitpid(update-ref --stdin): $!"; + fgrp_update_old($fgrp); + } +} + +sub pack_refs { + my ($self, $git_dir) = @_; + do_reap($self); + my $cmd = [ 'git', "--git-dir=$git_dir", qw(pack-refs --all --prune) ]; + $self->{lei}->qerr("# @$cmd"); + my $opt = { 1 => $self->{lei}->{1}, 2 => $self->{lei}->{2} }; + $LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_cmd, $self, $cmd ]; +} + +sub fgrp_fetched { + my ($fgrp) = @_; + return if $fgrp->{dry_run} || !$LIVE; + my $rn = $fgrp->{-remote}; + my %opt = map { $_ => $fgrp->{lei}->{$_} } (0..2); + pack_refs($fgrp, $fgrp->{-osdir}); # objstore refs always packed + + $update_ref_stdin or return fgrp_update_old($fgrp); + + my $update_ref = PublicInbox::OnDestroy->new($$, \&fgrp_update, $fgrp); + + my $src = [ 'git', "--git-dir=$fgrp->{-osdir}", 'for-each-ref', + "--format=refs/%(refname:lstrip=3)%00%(objectname)", + "refs/remotes/$rn/" ]; + do_reap($fgrp); + open($fgrp->{srcfh}, '+>', undef) or die "open(src): $!"; + $fgrp->{lei}->qerr("# @$src >SRC"); + my $pid = spawn($src, undef, { %opt, 1 => $fgrp->{srcfh} }); + $LIVE->{$pid} = [ \&reap_cmd, $fgrp, $src, $update_ref ]; + + my $dst = [ 'git', "--git-dir=$fgrp->{cur_dst}", 'for-each-ref', + '--format=%(refname)%00%(objectname)' ]; + do_reap($fgrp); + open($fgrp->{dstfh}, '+>', undef) or die "open(dst): $!"; + $fgrp->{lei}->qerr("# @$dst >DST"); + $pid = spawn($dst, undef, { %opt, 1 => $fgrp->{dstfh} }); + $LIVE->{$pid} = [ \&reap_cmd, $fgrp, $dst, $update_ref ]; +} + +sub fgrp_fetch { + my ($fgrp, $fini) = @_; + my $cmd = [ @{$fgrp->{-torsocks}}, 'git', "--git-dir=$fgrp->{-osdir}", + fetch_args($fgrp->{lei}, my $opt = {}), '--no-tags', + $fgrp->{-remote} ]; + $fgrp->{-fini} = $fini; + do_reap($fgrp); + $fgrp->{lei}->qerr("# @$cmd"); + return if $fgrp->{dry_run}; + my $fgrp_fini = PublicInbox::OnDestroy->new($$, \&fgrp_fetched, $fgrp); + my $pid = spawn($cmd, undef, $opt); + $LIVE->{$pid} = [ \&reap_cmd, $fgrp, $cmd, $fgrp_fini ]; +} + +# keep this idempotent for future use by public-inbox-fetch +sub forkgroup_prep { + my ($self, $uri) = @_; + $self->{-ent} // return; + my $os = $self->{-objstore} // return; + my $fg = $self->{-ent}->{forkgroup} // return; + my $dir = "$os/$fg.git"; + my @cmd = ('git', "--git-dir=$dir", 'config'); + my $opt = +{ map { $_ => $self->{lei}->{$_} } (0..2) }; + if (!-d $dir) { + PublicInbox::Import::init_bare($dir); + for ('repack.useDeltaIslands=true', + 'pack.island=refs/remotes/([^/]+)/') { + run_die([@cmd, split(/=/, $_, 2)], undef, $opt); + } + } + my $key = $self->{-key} // die 'BUG: no -key'; + my ($bn) = ($key =~ m{/([a-z0-9_,;=!\+\{\}\|][^/]*)(?:\.git)?\z}i); + my $rn = "$bn-".substr(sha256_hex($key), 0, 16); + # --no-tags is required to avoid conflicts + for ("url=$uri", "fetch=+refs/*:refs/remotes/$rn/*", + 'tagopt=--no-tags') { + my @kv = split(/=/, $_, 2); + $kv[0] = "remote.$rn.$kv[0]"; + run_die([@cmd, @kv], undef, $opt); + } + $self->{-do_pack_refs} = 1; # likely coderepo + if (!-d $self->{cur_dst}) { + my $alt = File::Spec->rel2abs("$dir/objects"); + PublicInbox::Import::init_bare($self->{cur_dst}); + my $o = "$self->{cur_dst}/objects"; + my $f = "$o/info/alternates"; + my $l = File::Spec->abs2rel($alt, File::Spec->rel2abs($o)); + open my $fh, '+>>', $f or die "open($f): $!"; + seek($fh, SEEK_SET, 0) or die "seek($f): $!"; + chomp(my @cur = <$fh>); + if (!grep(/\A\Q$l\E\z/, @cur)) { + say $fh $l or die "say($f): $!"; + } + close $fh or die "close($f): $!"; + @cmd = ('git', "--git-dir=$self->{cur_dst}", + qw(remote add --mirror=fetch origin), "$uri"); + my $pid = spawn(\@cmd, undef, $opt); + waitpid($pid, 0) // die "waitpid(@cmd): $!"; + die "E: @cmd: \$?=$?" if ($? && ($? >> 8) != 3); + } + bless { %$self, -osdir => $dir, -remote => $rn }, __PACKAGE__; } sub clone_v1 { @@ -259,14 +443,20 @@ sub clone_v1 { my $uri = URI->new($self->{cur_src} // $self->{src}); defined($lei->{opt}->{epoch}) and die "$uri is a v1 inbox, --epoch is not supported\n"; - my $pfx = $curl->torsocks($lei, $uri) or return; + $self->{-torsocks} //= $curl->torsocks($lei, $uri) or return; my $dst = $self->{cur_dst} // $self->{dst}; my $fini = PublicInbox::OnDestroy->new($$, \&v1_done, $self); - my $cmd = [ @$pfx, clone_cmd($lei, my $opt = {}), "$uri", $dst ]; - my $ref = $self->{-ent} ? $self->{-ent}->{reference} : undef; - defined($ref) && -e "$self->{dst}$ref" and - push @$cmd, '--reference', "$self->{dst}$ref"; - start_clone($self, $cmd, $opt, $fini); + my $cmd = [ @{$self->{-torsocks}}, clone_cmd($lei, my $opt = {}), + "$uri", $dst ]; + my $fgrp = forkgroup_prep($self, $uri); + if (!defined($fgrp) && defined($self->{-ent})) { + if (defined(my $ref = $self->{-ent}->{reference})) { + -e "$self->{dst}$ref" and + push @$cmd, '--reference', "$self->{dst}$ref"; + } + } + $fgrp ? fgrp_fetch($fgrp, $fini) : + start_clone($self, $cmd, $opt, $fini); if (!$self->{-is_epoch} && $lei->{opt}->{'inbox-config'} =~ /\A(?:always|v1)\z/s) { @@ -278,7 +468,7 @@ sub clone_v1 { (!defined($d) && !$nohang) and _get_txt_start($self, 'description', $fini); - reap_live() until ($nohang || !keys(%$LIVE)); # for non-manifest clone + $nohang or do_reap($self, 1); # for non-manifest clone } sub parse_epochs ($$) { @@ -357,7 +547,7 @@ EOM } } -sub reap_clone { # async, called via SIGCHLD +sub reap_cmd { # async, called via SIGCHLD my ($self, $cmd) = @_; my $cerr = $?; $? = 0; # don't let it influence normal exit @@ -376,16 +566,25 @@ sub v1_done { # called via OnDestroy run_die([qw(git config -f), "$dst/config", 'gitweb.owner', $o]); } my $o = "$dst/objects"; - if (open(my $fh, '<', "$o/info/alternates")) { - chomp(my @l = <$fh>); - for (@l) { $_ = File::Spec->abs2rel($_, $o)."\n" } - my $f = File::Temp->new(TEMPLATE => '.XXXX', DIR => "$o/info"); - print $f @l; - $f->flush or die "flush($f): $!"; - rename($f->filename, "$o/info/alternates") or - die "rename($f, $o/info/alternates): $!"; - $f->unlink_on_destroy(0); + if (open(my $fh, '<', my $fn = "$o/info/alternates")) {; + my $base = File::Spec->rel2abs($o); + my @l = <$fh>; + my $ft; + for (@l) { + next unless m!\A/!; + $_ = File::Spec->abs2rel($_, $base); + $ft //= File::Temp->new(TEMPLATE => '.XXXX', + DIR => "$o/info"); + } + if ($ft) { + print $ft @l or die "print($ft): $!"; + $ft->flush or die "flush($ft): $!"; + ft_rename($ft, $fn, 0666, $fh); + } } + pack_refs($self, $dst) if delete $self->{-do_pack_refs}; + eval { set_description($self) }; + warn $@ if $@; return if ($self->{-is_epoch} || $self->{lei}->{opt}->{'inbox-config'} ne 'always'); write_makefile($dst, 1); @@ -410,30 +609,23 @@ sub v2_done { # called via OnDestroy } write_makefile($dst, 2); undef $lck; # unlock + eval { set_description($self) }; + warn $@ if $@; index_cloned_inbox($self, 2); } -sub reap_live { - my $pid = waitpid(-1, 0) // die "waitpid(-1): $!"; - if (my $x = delete $LIVE->{$pid}) { - my $cb = shift @$x; - $cb->(@$x); - } else { - warn "reaped unknown PID=$pid ($?)\n"; - } -} - sub clone_v2_prep ($$;$) { my ($self, $v2_epochs, $m) = @_; # $m => manifest.js.gz hashref my $lei = $self->{lei}; my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return; my $first_uri = (map { $_->[0] } values %$v2_epochs)[0]; - my $pfx = $curl->torsocks($lei, $first_uri) or return; + $self->{-torsocks} //= $curl->torsocks($lei, $first_uri) or return; my $dst = $self->{cur_dst} // $self->{dst}; my $want = parse_epochs($lei->{opt}->{epoch}, $v2_epochs); my $task = $m ? bless { %$self }, __PACKAGE__ : $self; delete $task->{todo}; # $self->{todo} still exists - my (@src_edst, @skip, $desc, @entv); + my (@skip, $desc); + my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task); for my $nr (sort { $a <=> $b } keys %$v2_epochs) { my ($uri, $key) = @{$v2_epochs->{$nr}}; my $src = $uri->as_string; @@ -453,8 +645,13 @@ failed to extract epoch number from $src } } if (!$want || $want->{$nr}) { - push @src_edst, $src, $edst; - push @entv, $edst, $ent; + my $etask = bless { %$task, -key => $key }, __PACKAGE__; + $etask->{-ent} = $ent; # may have {reference} + $etask->{cur_src} = $src; + $etask->{cur_dst} = $edst; + $etask->{-is_epoch} = $fini; + my $ref = $ent->{reference} // ''; + push @{$self->{todo}->{$ref}}, $etask; $self->{any_want}->{$key} = 1; } else { # create a placeholder so users only need to chmod +w init_placeholder($src, $edst, $ent); @@ -467,24 +664,11 @@ failed to extract epoch number from $src (!$self->{dry_run} && !-d $dst) and File::Path::mkpath($dst); - my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task); - $lei->{opt}->{'inbox-config'} =~ /\A(?:always|v2)\z/s and _get_txt_start($task, '_/text/config/raw', $fini); defined($desc) ? ($task->{'txt.description'} = $desc) : _get_txt_start($task, 'description', $fini); - while (@entv) { - my ($edst, $ent) = splice(@entv, 0, 2); - my $etask = bless { %$task }, __PACKAGE__; - $etask->{-ent} = $ent; # may have {reference} - $etask->{cur_src} = shift @src_edst // die 'BUG: no cur_src'; - $etask->{cur_dst} = shift @src_edst // die 'BUG: no cur_dst'; - $etask->{cur_dst} eq $edst or - die "BUG: `$etask->{cur_dst}' != `$edst'"; - $etask->{-is_epoch} = $fini; - push @{$self->{todo}->{($ent->{reference} // '')}}, $etask; - } } sub decode_manifest ($$$) { @@ -592,7 +776,21 @@ EOM last; # restart %$todo iteration } } - reap_live() while keys(%$LIVE); + do_reap($self, 1); +} + +sub dump_manifest ($$) { + my ($m, $ft) = @_; + # write the smaller manifest if epochs were skipped so + # users won't have to delete manifest if they +w an + # epoch they no longer want to skip + my $json = PublicInbox::Config->json->encode($m); + my $mtime = (stat($ft))[9]; + seek($ft, SEEK_SET, 0) or die "seek($ft): $!"; + truncate($ft, 0) or die "truncate($ft): $!"; + gzip(\$json => $ft) or die "gzip($ft): $GzipError"; + $ft->flush or die "flush($ft): $!"; + utime($mtime, $mtime, "$ft") or die "utime(..., $ft): $!"; } # FIXME: this gets confused by single inbox instance w/ global manifest.js.gz @@ -657,6 +855,7 @@ EOM die("BUG: no `$name' in manifest"); $task->{cur_src} = "$uri"; $task->{cur_dst} = $task->{dst}; + $task->{-key} = $name; if ($n > 1) { $task->{cur_dst} .= $name; $task->{cur_src} .= $name; @@ -675,18 +874,7 @@ EOM return if $self->{lei}->{child_error} || $self->{dry_run}; # set by clone_v2_prep/-I/--exclude - if (delete $self->{-culled_manifest}) { - # write the smaller manifest if epochs were skipped so - # users won't have to delete manifest if they +w an - # epoch they no longer want to skip - my $json = PublicInbox::Config->json->encode($m); - my $mtime = (stat($ft))[9]; - seek($ft, SEEK_SET, 0) or die "seek($ft): $!"; - truncate($ft, 0) or die "truncate($ft): $!"; - gzip(\$json => $ft) or die "gzip($ft): $GzipError"; - $ft->flush or die "flush($ft): $!"; - utime($mtime, $mtime, "$ft") or die "utime(..., $ft): $!"; - } + dump_manifest($m => $ft) if delete $self->{-culled_manifest}; ft_rename($ft, "$self->{dst}/manifest.js.gz", 0666); open my $x, '>', "$self->{dst}/mirror.done"; # for _wq_done_wait } @@ -706,6 +894,11 @@ sub do_mirror { # via wq_io_do or public-inbox-clone $ic =~ /\A(?:v1|v2|always|never)\z/s or die <<""; --inbox-config must be one of `always', `v2', `v1', or `never' + if (defined(my $os = $lei->{opt}->{objstore})) { + $os = 'objstore' if $os eq ''; # --objstore w/o args + $os = "$self->{dst}/$os" if $os !~ m!\A/!; + $self->{-objstore} = $os; + } local $LIVE; my $iv = $lei->{opt}->{'inbox-version'} // return start_clone_url($self);