From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net X-Spam-Level: X-Spam-ASN: X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,BAYES_00 shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2 Received: from localhost (dcvr.yhbt.net [127.0.0.1]) by dcvr.yhbt.net (Postfix) with ESMTP id 963B91F934; Fri, 24 Sep 2021 10:56:45 +0000 (UTC) From: Eric Wong To: meta@public-inbox.org Cc: Luis Chamberlain Subject: [PATCH 1/5] clone|--mirror: support --epoch=RANGE for partial clones Date: Fri, 24 Sep 2021 10:56:41 +0000 Message-Id: <20210924105645.8627-2-e@80x24.org> In-Reply-To: <20210924105645.8627-1-e@80x24.org> References: <20210924105645.8627-1-e@80x24.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit List-Id: Partial (v2) clones should be useful addition for users wanting to conserve storage while having fast access to recent messages. Continuing work started in 876e74283ff3 (fetch: ignore non-writable epoch dirs, 2021-09-17), this creates bare, read-only epoch git repos. These git repos have the remotes pre-configured, but does not fetch any objects. The goal is to allow users to set the writable bit on a previously-skipped epoch and start fetching it. Shell completion support may not be necessary given how short the epoch ranges are, here. Cc: Luis Chamberlain Link: https://public-inbox.org/meta/20210917002204.GA13112@dcvr/T/#u --- Documentation/lei-add-external.pod | 15 ++++ Documentation/public-inbox-clone.pod | 15 ++++ lib/PublicInbox/LEI.pm | 2 +- lib/PublicInbox/LeiMirror.pm | 101 +++++++++++++++++++++++---- script/public-inbox-clone | 3 +- t/lei-mirror.t | 8 +++ t/v2mirror.t | 25 +++++++ 7 files changed, 155 insertions(+), 14 deletions(-) diff --git a/Documentation/lei-add-external.pod b/Documentation/lei-add-external.pod index 9c8bde0f..1ab65a16 100644 --- a/Documentation/lei-add-external.pod +++ b/Documentation/lei-add-external.pod @@ -30,6 +30,21 @@ Default: 0 Create C by mirroring the public-inbox at C. +=item --epoch=RANGE + +Restrict clones of L inboxes to the +given range of epochs. The range may be a single non-negative +integer or a (possibly open-ended) C range of +non-negative integers. C<~> may be prefixed to either (or both) +integer values to represent the offset from the maximum possible +value. + +For example, C<--epoch=~0> alone clones only the latest epoch, +C<--epoch=~2..> clones the three latest epochs. + +Default: C<0..~0> or C<0..> or C<..~0> +(all epochs, all three examples are equivalent) + =item -v =item --verbose diff --git a/Documentation/public-inbox-clone.pod b/Documentation/public-inbox-clone.pod index fdb57663..efee01ee 100644 --- a/Documentation/public-inbox-clone.pod +++ b/Documentation/public-inbox-clone.pod @@ -31,6 +31,21 @@ file to speed up subsequent L. =over +=item --epoch=RANGE + +Restrict clones of L inboxes to the +given range of epochs. The range may be a single non-negative +integer or a (possibly open-ended) C range of +non-negative integers. C<~> may be prefixed to either (or both) +integer values to represent the offset from the maximum possible +value. + +For example, C<--epoch=~0> alone clones only the latest epoch, +C<--epoch=~2..> clones the three latest epochs. + +Default: C<0..~0> or C<0..> or C<..~0> +(all epochs, all three examples are equivalent) + =item -q =item --quiet diff --git a/lib/PublicInbox/LEI.pm b/lib/PublicInbox/LEI.pm index 96f63805..9d5a5a46 100644 --- a/lib/PublicInbox/LEI.pm +++ b/lib/PublicInbox/LEI.pm @@ -206,7 +206,7 @@ our %CMD = ( # sorted in order of importance/use: 'add-external' => [ 'LOCATION', 'add/set priority of a publicinbox|extindex for extra matches', - qw(boost=i mirror=s inbox-version=i verbose|v+), + qw(boost=i mirror=s inbox-version=i epoch=s verbose|v+), @c_opt, index_opt(), @net_opt ], 'ls-external' => [ '[FILTER]', 'list publicinbox|extindex locations', qw(format|f=s z|0 globoff|g invert-match|v local remote), @c_opt ], diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm index 6bfa4b6f..53f7dd31 100644 --- a/lib/PublicInbox/LeiMirror.pm +++ b/lib/PublicInbox/LeiMirror.pm @@ -49,8 +49,11 @@ sub try_scrape { # since this is for old instances w/o manifest.js.gz, try v1 first return clone_v1($self) if grep(m!\A\Q$url\E/*\z!, @urls); if (my @v2_urls = grep(m!\A\Q$url\E/[0-9]+\z!, @urls)) { - my %v2_uris = map { $_ => URI->new($_) } @v2_urls; # uniq - return clone_v2($self, [ values %v2_uris ]); + my %v2_epochs = map { + my ($n) = (m!/([0-9]+)\z!); + $n => URI->new($_) + } @v2_urls; # uniq + return clone_v2($self, \%v2_epochs); } # filter out common URLs served by WWW (e.g /$MSGID/T/) @@ -189,6 +192,8 @@ sub clone_v1 { my $lei = $self->{lei}; my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return; my $uri = URI->new($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; my $cmd = [ @$pfx, clone_cmd($lei, my $opt = {}), $uri->as_string, $self->{dst} ]; @@ -199,22 +204,89 @@ sub clone_v1 { index_cloned_inbox($self, 1); } -sub clone_v2 { - my ($self, $v2_uris) = @_; +sub parse_epochs ($$) { + my ($opt_epochs, $v2_epochs) = @_; # $epcohs "LOW..HIGH" + $opt_epochs // return; # undef => all epochs + my ($lo, $dotdot, $hi, @extra) = split(/(\.\.)/, $opt_epochs); + undef($lo) if ($lo // '') eq ''; + my $re = qr/\A~?[0-9]+\z/; + if (@extra || (($lo // '0') !~ $re) || + (($hi // '0') !~ $re) || + !(grep(defined, $lo, $hi))) { + die < $b } keys %$v2_epochs; + for (grep(defined, $lo, $hi)) { + if (/\A[0-9]+\z/) { + $_ > $n[-1] and die +"`$_' exceeds maximum available epoch ($n[-1])\n"; + $_ < $n[0] and die +"`$_' is lower than minimum available epoch ($n[0])\n"; + } elsif (/\A~([0-9]+)/) { + my $off = -$1 - 1; + $n[$off] // die "`$_' is out of range\n"; + $_ = $n[$off]; + } else { die "`$_' not understood\n" } + } + defined($lo) && defined($hi) && $lo > $hi and die +"low value (`$lo') exceeds high (`$hi')\n"; + $lo //= $n[0] if $dotdot; + $hi //= $n[-1] if $dotdot; + $hi //= $lo; + my $want = {}; + for ($lo..$hi) { + if (defined $v2_epochs->{$_}) { + $want->{$_} = 1; + } else { + warn +"# epoch $_ is not available (non-fatal, $lo..$hi)\n"; + } + } + $want +} + +sub init_placeholder ($$) { + my ($src, $edst) = @_; + PublicInbox::Import::init_bare($edst); + my $f = "$edst/config"; + open my $fh, '>>', $f or die "open($f): $!"; + print $fh <{lei}; my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return; - my $pfx //= $curl->torsocks($lei, $v2_uris->[0]) or return; + my $pfx = $curl->torsocks($lei, (values %$v2_epochs)[0]) or return; my $dst = $self->{dst}; - my @src_edst; - for my $uri (@$v2_uris) { + my $want = parse_epochs($lei->{opt}->{epoch}, $v2_epochs); + my (@src_edst, @read_only); + for my $nr (sort { $a <=> $b } keys %$v2_epochs) { + my $uri = $v2_epochs->{$nr}; my $src = $uri->as_string; my $edst = $dst; $src =~ m!/([0-9]+)(?:\.git)?\z! or die <<""; failed to extract epoch number from $src - my $nr = $1 + 0; + $1 + 0 == $nr or die "BUG: <$uri> miskeyed $1 != $nr"; $edst .= "/git/$nr.git"; - push @src_edst, $src, $edst; + if (!$want || $want->{$nr}) { + push @src_edst, $src, $edst; + } else { # create a placeholder so users only need to chmod +w + init_placeholder($src, $edst); + push @read_only, $edst; + } } my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock'; _try_config($self); @@ -229,6 +301,10 @@ failed to extract epoch number from $src my $mg = PublicInbox::MultiGit->new($dst, 'all.git', 'git'); $mg->fill_alternates; for my $i ($mg->git_epochs) { $mg->epoch_cfg_set($i) } + for my $edst (@read_only) { + my @st = stat($edst) or die "stat($edst): $!"; + chmod($st[2] & 0555, $edst) or die "chmod(a-w, $edst): $!"; + } write_makefile($self->{dst}, 2); undef $on_destroy; # unlock index_cloned_inbox($self, 2); @@ -291,11 +367,12 @@ sub try_manifest { # @v2_epochs # ignoring $v1_path (use --inbox-version=1 to force v1 instead) EOM - @v2_epochs = map { + my %v2_epochs = map { $uri->path($path_pfx.$_); - $uri->clone + my ($n) = ("$uri" =~ m!/([0-9]+)\.git\z!); + $n => $uri->clone } @v2_epochs; - clone_v2($self, \@v2_epochs); + clone_v2($self, \%v2_epochs); } elsif (defined $v1_path) { clone_v1($self); } else { diff --git a/script/public-inbox-clone b/script/public-inbox-clone index 0efde1a8..54059d03 100755 --- a/script/public-inbox-clone +++ b/script/public-inbox-clone @@ -13,6 +13,7 @@ usage: public-inbox-clone INBOX_URL [DESTINATION] options: + --epoch=RANGE range of v2 epochs to clone (e.g `2..5', `~0', `~1..') --torsocks VAL whether or not to wrap git and curl commands with torsocks (default: `auto') Must be one of: `auto', `no' or `yes' @@ -21,7 +22,7 @@ options: -C DIR chdir to specified directory EOF GetOptions($opt, qw(help|h quiet|q verbose|v+ C=s@ c=s@ - no-torsocks torsocks=s)) or die $help; + no-torsocks torsocks=s epoch=s)) or die $help; if ($opt->{help}) { print $help; exit }; require PublicInbox::Admin; # loads Config PublicInbox::Admin::do_chdir(delete $opt->{C}); diff --git a/t/lei-mirror.t b/t/lei-mirror.t index 7dd03b26..de5246b6 100644 --- a/t/lei-mirror.t +++ b/t/lei-mirror.t @@ -65,6 +65,14 @@ test_lei({ tmpdir => $tmpdir }, sub { lei_ok('ls-external'); unlike($lei_out, qr!\Q$d\E!s, 'not added to ls-external'); + $d = "$home/bad-epoch"; + ok(!lei(qw(add-external -q --epoch=0.. --mirror), "$http/t1/", $d), + 'v1 fails on --epoch'); + ok(!-d $d, 'destination not created on unacceptable --epoch'); + ok(!lei(qw(add-external -q --epoch=1 --mirror), "$http/t2/", $d), + 'v2 fails on bad epoch range'); + ok(!-d $d, 'destination not created on bad epoch'); + my %phail = ( HTTPS => 'https://public-inbox.org/' . 'phail', ONION => diff --git a/t/v2mirror.t b/t/v2mirror.t index 665a4d59..20a8daaa 100644 --- a/t/v2mirror.t +++ b/t/v2mirror.t @@ -263,6 +263,31 @@ if ('test read-only epoch dirs') { 'fetch restored objects once GIT_DIR became writable'); } +{ + my $dst = "$tmpdir/partial"; + run_script([qw(-clone -q --epoch=~0), "http://$host:$port/v2/", $dst]); + is($?, 0, 'no error from partial clone'); + my @g = glob("$dst/git/*.git"); + my @w = grep { -w $_ } @g; + my @r = grep { ! -w $_ } @g; + is(scalar(@w), 1, 'one writable directory'); + my ($w) = ($w[0] =~ m!/([0-9]+)\.git\z!); + is((grep { + m!/([0-9]+)\.git\z! or xbail "no digit in $_"; + $w > ($1 + 0) + } @r), scalar(@r), 'writable epoch # exceeds read-only ones'); + run_script([qw(-fetch -q)], undef, { -C => $dst }); + is($?, 0, 'no error from partial fetch'); + remove_tree($dst); + + run_script([qw(-clone -q --epoch=~1..), + "http://$host:$port/v2/", $dst]); + my @g2 = glob("$dst/git/*.git") ; + is_deeply(\@g2, \@g, 'cloned again'); + is(scalar(grep { -w $_ } @g2), scalar(@w) + 1, + 'got one more cloned epoch'); +} + ok($td->kill, 'killed httpd'); $td->join;