-# Copyright (C) 2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2019 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# This interface wraps and mimics PublicInbox::Import
use PublicInbox::Msgmap;
use PublicInbox::Spawn qw(spawn);
use PublicInbox::SearchIdx;
-use IO::Handle;
+use IO::Handle; # ->autoflush
+use File::Temp qw(tempfile);
# an estimate of the post-packed size to the raw uncompressed size
my $PACKING_FACTOR = 0.4;
# SATA storage lags behind what CPUs are capable of, so relying on
-# nproc(1) can be misleading and having extra Xapian partions is a
+# nproc(1) can be misleading and having extra Xapian shards is a
# waste of FDs and space. It can also lead to excessive IO latency
# and slow things down. Users on NVME or other fast storage can
# use the NPROC env or switches in our script/public-inbox-* programs
my $n = 0;
my $xpfx = $self->{xpfx};
- # always load existing partitions in case core count changes:
+ # always load existing shards in case core count changes:
# Also, shard count may change while -watch is running
# due to "xcpdb --reshard"
if (-d $xpfx) {
+ require PublicInbox::Search;
+ PublicInbox::Search::load_xapian();
+ my $XapianDatabase = $PublicInbox::Search::X{Database};
foreach my $shard (<$xpfx/*>) {
-d $shard && $shard =~ m!/[0-9]+\z! or next;
eval {
- Search::Xapian::Database->new($shard)->close;
+ $XapianDatabase->new($shard)->close;
$n++;
};
}
# $creat may be any true value, or 0/undef. A hashref is true,
# and $creat->{nproc} may be set to an integer
my ($class, $v2ibx, $creat) = @_;
- my $dir = $v2ibx->{mainrepo} or die "no mainrepo in inbox\n";
+ $v2ibx = PublicInbox::InboxWritable->new($v2ibx);
+ my $dir = $v2ibx->assert_usable_dir;
unless (-d $dir) {
if ($creat) {
require File::Path;
die "$dir does not exist\n";
}
}
-
- $v2ibx = PublicInbox::InboxWritable->new($v2ibx);
$v2ibx->umask_prepare;
my $xpfx = "$dir/xap" . PublicInbox::Search::SCHEMA_VERSION;
# leaking FDs to it...
$self->idx_init;
- my $mid0;
- my $num = num_for($self, $mime, \$mid0);
+ my ($num, $mid0) = v2_num_for($self, $mime);
defined $num or return; # duplicate
defined $mid0 or die "BUG: $mid0 undefined\n";
my $im = $self->importer;
$cmt;
}
-sub num_for {
- my ($self, $mime, $mid0) = @_;
+sub v2_num_for {
+ my ($self, $mime) = @_;
my $mids = mids($mime->header_obj);
if (@$mids) {
my $mid = $mids->[0];
my $num = $self->{mm}->mid_insert($mid);
if (defined $num) { # common case
- $$mid0 = $mid;
- return $num;
- };
+ return ($num, $mid);
+ }
# crap, Message-ID is already known, hope somebody just resent:
foreach my $m (@$mids) {
# easy, don't store duplicates
# note: do not add more diagnostic info here since
# it gets noisy on public-inbox-watch restarts
- return if $existing;
+ return () if $existing;
}
# AltId may pre-populate article numbers (e.g. X-Mail-Count
my $num = $self->{mm}->num_for($mid);
if (defined $num && !$self->{over}->get_art($num)) {
- $$mid0 = $mid;
- return $num;
+ return ($num, $mid);
}
}
$num = $self->{mm}->mid_insert($m);
if (defined $num) {
warn "alternative <$m> for <$mid> found\n";
- $$mid0 = $m;
- return $num;
+ return ($num, $m);
}
}
}
# none of the existing Message-IDs are good, generate a new one:
- num_for_harder($self, $mime, $mid0);
+ v2_num_for_harder($self, $mime);
}
-sub num_for_harder {
- my ($self, $mime, $mid0) = @_;
+sub v2_num_for_harder {
+ my ($self, $mime) = @_;
my $hdr = $mime->header_obj;
my $dig = content_digest($mime);
- $$mid0 = PublicInbox::Import::digest2mid($dig, $hdr);
- my $num = $self->{mm}->mid_insert($$mid0);
+ my $mid0 = PublicInbox::Import::digest2mid($dig, $hdr);
+ my $num = $self->{mm}->mid_insert($mid0);
unless (defined $num) {
# it's hard to spoof the last Received: header
my @recvd = $hdr->header_raw('Received');
$dig->add("Received: $_") foreach (@recvd);
- $$mid0 = PublicInbox::Import::digest2mid($dig, $hdr);
- $num = $self->{mm}->mid_insert($$mid0);
+ $mid0 = PublicInbox::Import::digest2mid($dig, $hdr);
+ $num = $self->{mm}->mid_insert($mid0);
# fall back to a random Message-ID and give up determinism:
until (defined($num)) {
$dig->add(rand);
- $$mid0 = PublicInbox::Import::digest2mid($dig, $hdr);
- warn "using random Message-ID <$$mid0> as fallback\n";
- $num = $self->{mm}->mid_insert($$mid0);
+ $mid0 = PublicInbox::Import::digest2mid($dig, $hdr);
+ warn "using random Message-ID <$mid0> as fallback\n";
+ $num = $self->{mm}->mid_insert($mid0);
}
}
- PublicInbox::Import::append_mid($hdr, $$mid0);
- $num;
+ PublicInbox::Import::append_mid($hdr, $mid0);
+ ($num, $mid0);
}
sub idx_shard {
$self->{shards} = $nshards;
}
- # need to create all parts before initializing msgmap FD
+ # need to create all shards before initializing msgmap FD
my $max = $self->{shards} - 1;
# idx_shards must be visible to all forked processes
# Now that all subprocesses are up, we can open the FDs
# for SQLite:
my $mm = $self->{mm} = PublicInbox::Msgmap->new_file(
- "$self->{-inbox}->{mainrepo}/msgmap.sqlite3", 1);
+ "$self->{-inbox}->{inboxdir}/msgmap.sqlite3", 1);
$mm->{dbh}->begin_work;
});
}
sub _replace_oids ($$$) {
my ($self, $mime, $replace_map) = @_;
$self->done;
- my $pfx = "$self->{-inbox}->{mainrepo}/git";
+ my $pfx = "$self->{-inbox}->{inboxdir}/git";
my $rewrites = []; # epoch => commit
my $max = $self->{epoch_max};
my ($r, $w);
pipe($r, $w) or die "failed to create pipe: $!";
- my $rdr = { 0 => fileno($tmp_fh), 1 => fileno($w) };
+ my $rdr = { 0 => $tmp_fh, 1 => $w };
my $git_dir = $self->{-inbox}->git->{git_dir};
my $cmd = ['git', "--git-dir=$git_dir", qw(hash-object --stdin)];
my $pid = spawn($cmd, undef, $rdr);
$rewritten->{rewrites};
}
-sub last_commit_part ($$;$) {
+sub last_epoch_commit ($$;$) {
my ($self, $i, $cmt) = @_;
my $v = PublicInbox::Search::SCHEMA_VERSION();
$self->{mm}->last_commit_xap($v, $i, $cmt);
foreach my $i (0..$epoch_max) {
defined(my $cmt = $last_commit->[$i]) or next;
$last_commit->[$i] = undef;
- last_commit_part($self, $i, $cmt);
+ last_epoch_commit($self, $i, $cmt);
}
}
if ($wait) {
my $barrier = $self->barrier_init(scalar @$shards);
- # each partition needs to issue a barrier command
+ # each shard needs to issue a barrier command
$_->remote_barrier for @$shards;
- # wait for each Xapian partition
+ # wait for each Xapian shard
$self->barrier_wait($barrier);
} else {
$_->remote_commit for @$shards;
}
# last_commit is special, don't commit these until
- # remote partitions are done:
+ # remote shards are done:
$dbh->begin_work;
set_last_commits($self);
$dbh->commit;
sub fill_alternates ($$) {
my ($self, $epoch) = @_;
- my $pfx = "$self->{-inbox}->{mainrepo}/git";
- my $all = "$self->{-inbox}->{mainrepo}/all.git";
- my @cmd;
+ my $pfx = "$self->{-inbox}->{inboxdir}/git";
+ my $all = "$self->{-inbox}->{inboxdir}/all.git";
+
unless (-d $all) {
PublicInbox::Import::init_bare($all);
}
- @cmd = (qw/git config/, "--file=$pfx/$epoch.git/config",
- 'include.path', '../../all.git/config');
- PublicInbox::Import::run_die(\@cmd);
-
my $alt = "$all/objects/info/alternates";
my %alts;
my @add;
sub git_init {
my ($self, $epoch) = @_;
- my $git_dir = "$self->{-inbox}->{mainrepo}/git/$epoch.git";
+ my $git_dir = "$self->{-inbox}->{inboxdir}/git/$epoch.git";
my @cmd = (qw(git init --bare -q), $git_dir);
PublicInbox::Import::run_die(\@cmd);
+ @cmd = (qw/git config/, "--file=$git_dir/config",
+ 'include.path', '../../all.git/config');
+ PublicInbox::Import::run_die(\@cmd);
fill_alternates($self, $epoch);
$git_dir
}
sub git_dir_latest {
my ($self, $max) = @_;
$$max = -1;
- my $pfx = "$self->{-inbox}->{mainrepo}/git";
+ my $pfx = "$self->{-inbox}->{inboxdir}/git";
return unless -d $pfx;
my $latest;
opendir my $dh, $pfx or die "opendir $pfx: $!\n";
# XXX experimental
sub diff ($$$) {
my ($mid, $cur, $new) = @_;
- use File::Temp qw(tempfile);
my ($ah, $an) = tempfile('email-cur-XXXXXXXX', TMPDIR => 1);
print $ah $cur->as_string or die "print: $!";
}
}
-sub reindex_oid ($$$$) {
- my ($self, $sync, $git, $oid) = @_;
- my $len;
+sub reindex_checkpoint ($$$) {
+ my ($self, $sync, $git) = @_;
+
+ $git->cleanup;
+ $sync->{mm_tmp}->atfork_prepare;
+ $self->done; # release lock
+
+ if (my $pr = $sync->{-opt}->{-progress}) {
+ my ($bn) = (split('/', $git->{git_dir}))[-1];
+ $pr->("$bn ".sprintf($sync->{-regen_fmt}, $sync->{nr}));
+ }
+
+ # allow -watch or -mda to write...
+ $self->idx_init; # reacquire lock
+ $sync->{mm_tmp}->atfork_parent;
+}
+
+# only for a few odd messages with multiple Message-IDs
+sub reindex_oid_m ($$$$;$) {
+ my ($self, $sync, $git, $oid, $regen_num) = @_;
+ $self->{current_info} = "multi_mid $oid";
+ my ($num, $mid0, $len);
my $msgref = $git->cat_file($oid, \$len);
my $mime = PublicInbox::MIME->new($$msgref);
my $mids = mids($mime->header_obj);
my $cid = content_id($mime);
+ die "BUG: reindex_oid_m called for <=1 mids" if scalar(@$mids) <= 1;
- # get the NNTP article number we used before, highest number wins
- # and gets deleted from sync->{mm_tmp};
- my $mid0;
- my $num = -1;
- my $del = 0;
- foreach my $mid (@$mids) {
- $del += delete($sync->{D}->{"$mid\0$cid"}) ? 1 : 0;
- my $n = $sync->{mm_tmp}->num_for($mid);
- if (defined $n && $n > $num) {
- $mid0 = $mid;
- $num = $n;
- $self->{mm}->mid_set($num, $mid0);
+ for my $mid (reverse @$mids) {
+ delete($sync->{D}->{"$mid\0$cid"}) and
+ die "BUG: reindex_oid should handle <$mid> delete";
+ }
+ my $over = $self->{over};
+ for my $mid (reverse @$mids) {
+ ($num, $mid0) = $over->num_mid0_for_oid($oid, $mid);
+ next unless defined $num;
+ if (defined($regen_num) && $regen_num != $num) {
+ die "BUG: regen(#$regen_num) != over(#$num)";
}
}
- if (!defined($mid0) && !$del) {
- $num = $sync->{regen}--;
- die "BUG: ran out of article numbers\n" if $num <= 0;
- my $mm = $self->{mm};
- foreach my $mid (reverse @$mids) {
- if ($mm->mid_set($num, $mid) == 1) {
- $mid0 = $mid;
- last;
- }
+ unless (defined($num)) {
+ for my $mid (reverse @$mids) {
+ # is this a number we got before?
+ my $n = $sync->{mm_tmp}->num_for($mid);
+ next unless defined $n;
+ next if defined($regen_num) && $regen_num != $n;
+ ($num, $mid0) = ($n, $mid);
+ last;
+ }
+ }
+ if (defined($num)) {
+ $sync->{mm_tmp}->num_delete($num);
+ } elsif (defined $regen_num) {
+ $num = $regen_num;
+ for my $mid (reverse @$mids) {
+ $self->{mm}->mid_set($num, $mid) == 1 or next;
+ $mid0 = $mid;
+ last;
}
- if (!defined($mid0)) {
- my $id = '<' . join('> <', @$mids) . '>';
- warn "Message-ID $id unusable for $num\n";
- foreach my $mid (@$mids) {
- defined(my $n = $mm->num_for($mid)) or next;
- warn "#$n previously mapped for <$mid>\n";
+ unless (defined $mid0) {
+ warn "E: cannot regen #$num\n";
+ return;
+ }
+ } else { # fixup bugs in old mirrors on reindex
+ for my $mid (reverse @$mids) {
+ $num = $self->{mm}->mid_insert($mid);
+ next unless defined $num;
+ $mid0 = $mid;
+ last;
+ }
+ if (defined $mid0) {
+ if ($sync->{reindex}) {
+ warn "reindex added #$num <$mid0>\n";
}
+ } else {
+ warn "E: cannot find article #\n";
+ return;
}
}
+ $sync->{nr}++;
+ if (do_idx($self, $msgref, $mime, $len, $num, $oid, $mid0)) {
+ reindex_checkpoint($self, $sync, $git);
+ }
+}
- if (!defined($mid0) || $del) {
- if (!defined($mid0) && $del) { # expected for deletes
- $num = $sync->{regen}--;
- $self->{mm}->num_highwater($num) if !$sync->{reindex};
- return
+sub check_unindexed ($$$) {
+ my ($self, $num, $mid0) = @_;
+ my $unindexed = $self->{unindexed} // {};
+ my $n = delete($unindexed->{$mid0});
+ defined $n or return;
+ if ($n != $num) {
+ die "BUG: unindexed $n != $num <$mid0>\n";
+ } else {
+ $self->{mm}->mid_set($num, $mid0);
+ }
+}
+
+# reuse Msgmap to store num => oid mapping (rather than num => mid)
+sub multi_mid_q_new () {
+ my ($fh, $fn) = tempfile('multi_mid-XXXXXXX', EXLOCK => 0, TMPDIR => 1);
+ my $multi_mid = PublicInbox::Msgmap->new_file($fn, 1);
+ $multi_mid->{dbh}->do('PRAGMA synchronous = OFF');
+ # for Msgmap->DESTROY:
+ $multi_mid->{tmp_name} = $fn;
+ $multi_mid->{pid} = $$;
+ close $fh or die "failed to close $fn: $!";
+ $multi_mid
+}
+
+sub multi_mid_q_push ($$) {
+ my ($sync, $oid) = @_;
+ my $multi_mid = $sync->{multi_mid} //= multi_mid_q_new();
+ if ($sync->{reindex}) { # no regen on reindex
+ $multi_mid->mid_insert($oid);
+ } else {
+ my $num = $sync->{regen}--;
+ die "BUG: ran out of article numbers" if $num <= 0;
+ $multi_mid->mid_set($num, $oid);
+ }
+}
+
+sub reindex_oid ($$$$) {
+ my ($self, $sync, $git, $oid) = @_;
+ my ($num, $mid0, $len);
+ my $msgref = $git->cat_file($oid, \$len);
+ return if $len == 0; # purged
+ my $mime = PublicInbox::MIME->new($$msgref);
+ my $mids = mids($mime->header_obj);
+ my $cid = content_id($mime);
+
+ if (scalar(@$mids) == 0) {
+ warn "E: $oid has no Message-ID, skipping\n";
+ return;
+ } elsif (scalar(@$mids) == 1) {
+ my $mid = $mids->[0];
+
+ # was the file previously marked as deleted?, skip if so
+ if (delete($sync->{D}->{"$mid\0$cid"})) {
+ if (!$sync->{reindex}) {
+ $num = $sync->{regen}--;
+ $self->{mm}->num_highwater($num);
+ }
+ return;
}
- my $id = '<' . join('> <', @$mids) . '>';
- defined($mid0) or
- warn "Skipping $id, no article number found\n";
- if ($del && defined($mid0)) {
- warn "$id was deleted $del " .
- "time(s) but mapped to article #$num\n";
+ # is this a number we got before?
+ $num = $sync->{mm_tmp}->num_for($mid);
+ if (defined $num) {
+ $mid0 = $mid;
+ check_unindexed($self, $num, $mid0);
+ } else {
+ $num = $sync->{regen}--;
+ die "BUG: ran out of article numbers" if $num <= 0;
+ if ($self->{mm}->mid_set($num, $mid) != 1) {
+ warn "E: unable to assign $num => <$mid>\n";
+ return;
+ }
+ $mid0 = $mid;
+ }
+ } else { # multiple MIDs are a weird case:
+ my $del = 0;
+ for (@$mids) {
+ $del += delete($sync->{D}->{"$_\0$cid"}) // 0;
+ }
+ if ($del) {
+ unindex_oid_remote($self, $oid, $_) for @$mids;
+ # do not delete from {mm_tmp}, since another
+ # single-MID message may use it.
+ } else { # handle them at the end:
+ multi_mid_q_push($sync, $oid);
}
return;
-
}
$sync->{mm_tmp}->mid_delete($mid0) or
die "failed to delete <$mid0> for article #$num\n";
$sync->{nr}++;
if (do_idx($self, $msgref, $mime, $len, $num, $oid, $mid0)) {
- $git->cleanup;
- $sync->{mm_tmp}->atfork_prepare;
- $self->done; # release lock
-
- if (my $pr = $sync->{-opt}->{-progress}) {
- my ($bn) = (split('/', $git->{git_dir}))[-1];
- $pr->("$bn ".sprintf($sync->{-regen_fmt}, $sync->{nr}));
- }
-
- # allow -watch or -mda to write...
- $self->idx_init; # reacquire lock
- $sync->{mm_tmp}->atfork_parent;
+ reindex_checkpoint($self, $sync, $git);
}
}
# only update last_commit for $i on reindex iff newer than current
sub update_last_commit ($$$$) {
my ($self, $git, $i, $cmt) = @_;
- my $last = last_commit_part($self, $i);
+ my $last = last_epoch_commit($self, $i);
if (defined $last && is_ancestor($git, $last, $cmt)) {
my @cmd = (qw(rev-list --count), "$last..$cmt");
chomp(my $n = $git->qx(@cmd));
return if $n ne '' && $n == 0;
}
- last_commit_part($self, $i, $cmt);
+ last_epoch_commit($self, $i, $cmt);
}
-sub git_dir_n ($$) { "$_[0]->{-inbox}->{mainrepo}/git/$_[1].git" }
+sub git_dir_n ($$) { "$_[0]->{-inbox}->{inboxdir}/git/$_[1].git" }
sub last_commits ($$) {
my ($self, $epoch_max) = @_;
my $heads = [];
for (my $i = $epoch_max; $i >= 0; $i--) {
- $heads->[$i] = last_commit_part($self, $i);
+ $heads->[$i] = last_epoch_commit($self, $i);
}
$heads;
}
for (my $i = $epoch_max; $i >= 0; $i--) {
die 'BUG: already indexing!' if $self->{reindex_pipe};
my $git_dir = git_dir_n($self, $i);
- -d $git_dir or next; # missing parts are fine
+ -d $git_dir or next; # missing epochs are fine
my $git = PublicInbox::Git->new($git_dir);
if ($reindex_heads) {
$head = $reindex_heads->[$i] or next;
--no-notes --no-color --no-renames
--diff-filter=AM), $range, '--', 'm');
++$n while <$fh>;
+ close $fh or die "git log failed: \$?=$?";
$pr->("$n\n") if $pr;
$regen_max += $n;
}
$self->{over}->remove_oid($oid, $mid);
}
-sub unindex_oid ($$$) {
- my ($self, $git, $oid) = @_;
+sub unindex_oid ($$$;$) {
+ my ($self, $git, $oid, $unindexed) = @_;
+ my $mm = $self->{mm};
my $msgref = $git->cat_file($oid);
my $mime = PublicInbox::MIME->new($msgref);
my $mids = mids($mime->header_obj);
join(',',sort keys %gone), "\n";
}
foreach my $num (keys %gone) {
- $self->{unindexed}->{$_}++;
- $self->{mm}->num_delete($num);
+ if ($unindexed) {
+ my $mid0 = $mm->mid_for($num);
+ $unindexed->{$mid0} = $num;
+ }
+ $mm->num_delete($num);
}
unindex_oid_remote($self, $oid, $mid);
}
my $x40 = qr/[a-f0-9]{40}/;
sub unindex ($$$$) {
my ($self, $sync, $git, $unindex_range) = @_;
- my $un = $self->{unindexed} ||= {}; # num => removal count
- my $before = scalar keys %$un;
+ my $unindexed = $self->{unindexed} ||= {}; # $mid0 => $num
+ my $before = scalar keys %$unindexed;
+ # order does not matter, here:
my @cmd = qw(log --raw -r
--no-notes --no-color --no-abbrev --no-renames);
my $fh = $self->{reindex_pipe} = $git->popen(@cmd, $unindex_range);
while (<$fh>) {
/\A:\d{6} 100644 $x40 ($x40) [AM]\tm$/o or next;
- unindex_oid($self, $git, $1);
+ unindex_oid($self, $git, $1, $unindexed);
}
delete $self->{reindex_pipe};
- $fh = undef;
+ close $fh or die "git log failed: \$?=$?";
return unless $sync->{-opt}->{prune};
- my $after = scalar keys %$un;
+ my $after = scalar keys %$unindexed;
return if $before == $after;
# ensure any blob can not longer be accessed via dumb HTTP
PublicInbox::Import::run_die(['git', "--git-dir=$git->{git_dir}",
- qw(-c gc.reflogExpire=now gc --prune=all)]);
+ qw(-c gc.reflogExpire=now gc --prune=all --quiet)]);
}
sub sync_ranges ($$$) {
my $git_dir = git_dir_n($self, $i);
die 'BUG: already reindexing!' if $self->{reindex_pipe};
- -d $git_dir or return; # missing parts are fine
+ -d $git_dir or return; # missing epochs are fine
fill_alternates($self, $i);
my $git = PublicInbox::Git->new($git_dir);
if (my $unindex_range = delete $sync->{unindex_range}->{$i}) {
mark_deleted($self, $sync, $git, $1);
}
}
- $fh = undef;
+ close $fh or die "git log failed: \$?=$?";
delete $self->{reindex_pipe};
update_last_commit($self, $git, $i, $cmt) if defined $cmt;
}
# unindex is required for leftovers if "deletes" affect messages
# in a previous fetch+index window:
+ my $git;
if (my @leftovers = values %{delete $sync->{D}}) {
- my $git = $self->{-inbox}->git;
- unindex_oid($self, $git, $_) for @leftovers;
- $git->cleanup;
+ $git = $self->{-inbox}->git;
+ for my $oid (@leftovers) {
+ $self->{current_info} = "leftover $oid";
+ unindex_oid($self, $git, $oid);
+ }
+ }
+ if (my $multi_mid = delete $sync->{multi_mid}) {
+ $git //= $self->{-inbox}->git;
+ my ($min, $max) = $multi_mid->minmax;
+ if ($sync->{reindex}) {
+ # we may need to create new Message-IDs if mirrors
+ # were initially indexed with old versions
+ for (my $i = $max; $i >= $min; $i--) {
+ my $oid = $multi_mid->mid_for($i);
+ next unless defined $oid;
+ reindex_oid_m($self, $sync, $git, $oid);
+ }
+ } else { # regen on initial index
+ for my $num ($min..$max) {
+ my $oid = $multi_mid->mid_for($num);
+ next unless defined $oid;
+ reindex_oid_m($self, $sync, $git, $oid, $num);
+ }
+ }
}
+ $git->cleanup if $git;
$self->done;
if (my $nr = $sync->{nr}) {