X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=lib%2FPublicInbox%2FV2Writable.pm;h=479e2b5daafbd25c0868a0a762fea6edee65a794;hp=46bfebbd3c92fe5369a18ac31ecf91c25a0ce601;hb=87425172fb480214c3f72e0174f4f8f15f48d92d;hpb=54590383027a67d11953690cbb6390347757730b

diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 46bfebbd..479e2b5d 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -7,13 +7,15 @@ use strict;
 use warnings;
 use base qw(PublicInbox::Lock);
 use PublicInbox::SearchIdxPart;
-use PublicInbox::SearchIdxSkeleton;
 use PublicInbox::MIME;
 use PublicInbox::Git;
 use PublicInbox::Import;
 use PublicInbox::MID qw(mids);
 use PublicInbox::ContentId qw(content_id content_digest);
 use PublicInbox::Inbox;
+use PublicInbox::OverIdxFork;
+use PublicInbox::Msgmap;
+use IO::Handle;
 
 # an estimate of the post-packed size to the raw uncompressed size
 my $PACKING_FACTOR = 0.4;
@@ -50,14 +52,14 @@ sub new {
 	}
 	$nparts = nproc() if ($nparts == 0);
 
+	$v2ibx = PublicInbox::InboxWritable->new($v2ibx);
 	my $self = {
 		-inbox => $v2ibx,
 		im => undef, #  PublicInbox::Import
-		xap_rw => undef, # PublicInbox::V2SearchIdx
-		xap_ro => undef,
 		partitions => $nparts,
 		parallel => 1,
 		transact_bytes => 0,
+		over => PublicInbox::OverIdxFork->new("$xpfx/over.sqlite3"),
 		lock_path => "$dir/inbox.lock",
 		# limit each repo to 1GB or so
 		rotate_bytes => int((1024 * 1024 * 1024) / $PACKING_FACTOR),
@@ -69,7 +71,9 @@ sub init_inbox {
 	my ($self, $parallel) = @_;
 	$self->{parallel} = $parallel;
 	$self->idx_init;
-	$self->git_init(0);
+	my $max_git = -1;
+	git_dir_latest($self, \$max_git);
+	$self->git_init($max_git >= 0 ? $max_git : 0);
 	$self->done;
 }
 
@@ -116,7 +120,7 @@ sub num_for {
 	my $mids = mids($mime->header_obj);
 	if (@$mids) {
 		my $mid = $mids->[0];
-		my $num = $self->{skel}->{mm}->mid_insert($mid);
+		my $num = $self->{mm}->mid_insert($mid);
 		if (defined $num) { # common case
 			$$mid0 = $mid;
 			return $num;
@@ -137,9 +141,9 @@ sub num_for {
 		warn "<$mid> reused for mismatched content\n";
 
 		# try the rest of the mids
-		foreach my $i (1..$#$mids) {
+		for(my $i = $#$mids; $i >= 1; $i--) {
 			my $m = $mids->[$i];
-			$num = $self->{skel}->{mm}->mid_insert($m);
+			$num = $self->{mm}->mid_insert($m);
 			if (defined $num) {
 				warn "alternative <$m> for <$mid> found\n";
 				$$mid0 = $m;
@@ -157,24 +161,23 @@ sub num_for_harder {
 	my $hdr = $mime->header_obj;
 	my $dig = content_digest($mime);
 	$$mid0 = PublicInbox::Import::digest2mid($dig);
-	my $num = $self->{skel}->{mm}->mid_insert($$mid0);
+	my $num = $self->{mm}->mid_insert($$mid0);
 	unless (defined $num) {
 		# it's hard to spoof the last Received: header
 		my @recvd = $hdr->header_raw('Received');
 		$dig->add("Received: $_") foreach (@recvd);
 		$$mid0 = PublicInbox::Import::digest2mid($dig);
-		$num = $self->{skel}->{mm}->mid_insert($$mid0);
+		$num = $self->{mm}->mid_insert($$mid0);
 
 		# fall back to a random Message-ID and give up determinism:
 		until (defined($num)) {
 			$dig->add(rand);
 			$$mid0 = PublicInbox::Import::digest2mid($dig);
 			warn "using random Message-ID <$$mid0> as fallback\n";
-			$num = $self->{skel}->{mm}->mid_insert($$mid0);
+			$num = $self->{mm}->mid_insert($$mid0);
 		}
 	}
-	my @cur = $hdr->header_raw('Message-Id');
-	$hdr->header_set('Message-Id', "<$$mid0>", @cur);
+	PublicInbox::Import::append_mid($hdr, $$mid0);
 	$num;
 }
 
@@ -194,35 +197,58 @@ sub idx_init {
 	# frequently activated.
 	delete $ibx->{$_} foreach (qw(git mm search));
 
-	$self->lock_acquire;
+	my $over = $self->{over};
+	$ibx->umask_prepare;
+	$ibx->with_umask(sub {
+		$self->lock_acquire;
+		$over->create($self);
 
-	# first time initialization, first we create the skeleton pipe:
-	my $skel = $self->{skel} = PublicInbox::SearchIdxSkeleton->new($self);
+		# need to create all parts before initializing msgmap FD
+		my $max = $self->{partitions} - 1;
 
-	# need to create all parts before initializing msgmap FD
-	my $max = $self->{partitions} - 1;
-	my $idx = $self->{idx_parts} = [];
-	for my $i (0..$max) {
-		push @$idx, PublicInbox::SearchIdxPart->new($self, $i, $skel);
-	}
+		# idx_parts must be visible to all forked processes
+		my $idx = $self->{idx_parts} = [];
+		for my $i (0..$max) {
+			push @$idx, PublicInbox::SearchIdxPart->new($self, $i);
+		}
 
-	# Now that all subprocesses are up, we can open the FD for SQLite:
-	$skel->_msgmap_init->{dbh}->begin_work;
+		# 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);
+		$mm->{dbh}->begin_work;
+	});
 }
 
-sub remove {
-	my ($self, $mime, $cmt_msg) = @_;
+sub purge_oids {
+	my ($self, $purge) = @_; # $purge = { $object_id => 1, ... }
+	$self->done;
+	my $pfx = "$self->{-inbox}->{mainrepo}/git";
+	foreach my $i (0..$self->{max_git}) {
+		my $git = PublicInbox::Git->new("$pfx/$i.git");
+		my $im = $self->import_init($git, 0);
+		$im->purge_oids($purge);
+	}
+}
+
+sub remove_internal {
+	my ($self, $mime, $cmt_msg, $purge) = @_;
 	$self->barrier;
 	$self->idx_init;
-	my $im = $self->importer;
+	my $im = $self->importer unless $purge;
 	my $ibx = $self->{-inbox};
 	my $srch = $ibx->search;
 	my $cid = content_id($mime);
-	my $skel = $self->{skel};
 	my $parts = $self->{idx_parts};
-	my $mm = $skel->{mm};
+	my $mm = $self->{mm};
 	my $removed;
 	my $mids = mids($mime->header_obj);
+
+	# We avoid introducing new blobs into git since the raw content
+	# can be slightly different, so we do not need the user-supplied
+	# message now that we have the mids and content_id
+	$mime = undef;
+
 	foreach my $mid (@$mids) {
 		$srch->reopen->each_smsg_by_mid($mid, sub {
 			my ($smsg) = @_;
@@ -240,86 +266,97 @@ sub remove {
 				# no bugs in our deduplication code:
 				$removed = $smsg;
 				$removed->{mime} = $cur;
-				$im->remove(\$orig, $cmt_msg);
+				my $oid = $smsg->{blob};
+				if ($purge) {
+					$purge->{$oid} = 1;
+				} else {
+					$im->remove(\$orig, $cmt_msg);
+				}
 				$orig = undef;
 				$removed->num; # memoize this for callers
 
-				my $oid = $smsg->{blob};
-				foreach my $idx (@$parts, $skel) {
+				foreach my $idx (@$parts) {
 					$idx->remote_remove($oid, $mid);
 				}
+				$self->{over}->remove_oid($oid, $mid);
 			}
 			1; # continue
 		});
 		$self->barrier;
 	}
+	if ($purge && scalar keys %$purge) {
+		purge_oids($self, $purge);
+	}
 	$removed;
 }
 
+sub remove {
+	my ($self, $mime, $cmt_msg) = @_;
+	remove_internal($self, $mime, $cmt_msg);
+}
+
+sub purge {
+	my ($self, $mime) = @_;
+	remove_internal($self, $mime, undef, {});
+}
+
+
 sub done {
 	my ($self) = @_;
-	my $locked = defined $self->{idx_parts};
 	my $im = delete $self->{im};
 	$im->done if $im; # PublicInbox::Import::done
-	$self->searchidx_checkpoint(0);
-	$self->lock_release if $locked;
+
+	if (my $mm = delete $self->{mm}) {
+		$mm->{dbh}->commit;
+	}
+
+	# order matters, we can only close {over} after all partitions
+	# are done because the partitions also write to {over}
+	my $parts = delete $self->{idx_parts};
+	if ($parts) {
+		$_->remote_commit for @$parts;
+		$_->remote_close for @$parts;
+	}
+
+	my $over = $self->{over};
+	$over->remote_commit;
+	$over->remote_close;
+	$self->{transact_bytes} = 0;
+	$self->lock_release if $parts;
 }
 
 sub checkpoint {
 	my ($self) = @_;
 	my $im = $self->{im};
 	$im->checkpoint if $im; # PublicInbox::Import::checkpoint
-	$self->searchidx_checkpoint(1);
+	$self->barrier(1);
 }
 
 # issue a write barrier to ensure all data is visible to other processes
 # and read-only ops.  Order of data importance is: git > SQLite > Xapian
 sub barrier {
-	my ($self) = @_;
+	my ($self, $fsync) = @_;
 
 	if (my $im = $self->{im}) {
 		$im->barrier;
 	}
-	my $skel = $self->{skel};
 	my $parts = $self->{idx_parts};
-	if ($parts && $skel) {
-		my $dbh = $skel->{mm}->{dbh};
-		$dbh->commit; # SQLite data is second in importance
+	if ($parts) {
+		my $dbh = $self->{mm}->{dbh};
+		$dbh->commit; # SQLite msgmap data is second in importance
 
-		# Now deal with Xapian
-		$skel->barrier_init(scalar(@$parts));
-		# each partition needs to issue a barrier command to skel:
-		$_->remote_barrier foreach @$parts;
+		my $over = $self->{over};
 
-		$skel->barrier_wait; # wait for each Xapian partition
+		# Now deal with Xapian and overview DB
+		$over->barrier_init(scalar(@$parts));
 
-		$dbh->begin_work;
-	}
-	$self->{transact_bytes} = 0;
-}
-
-sub searchidx_checkpoint {
-	my ($self, $more) = @_;
+		# each partition needs to issue a barrier command to over
+		$_->remote_barrier foreach @$parts;
 
-	# order matters, we can only close {skel} after all partitions
-	# are done because the partitions also write to {skel}
-	if (my $parts = $self->{idx_parts}) {
-		foreach my $idx (@$parts) {
-			$idx->remote_commit; # propagates commit to skel
-			$idx->remote_close unless $more;
-		}
-		delete $self->{idx_parts} unless $more;
-	}
+		$over->barrier_wait; # wait for each Xapian partition
+		$over->commit_fsync if $fsync;
 
-	if (my $skel = $self->{skel}) {
-		my $dbh = $skel->{mm}->{dbh};
-		$dbh->commit;
-		if ($more) {
-			$dbh->begin_work;
-		} else {
-			$skel->remote_close;
-			delete $self->{skel};
-		}
+		$dbh->begin_work;
 	}
 	$self->{transact_bytes} = 0;
 }
@@ -328,7 +365,6 @@ sub git_init {
 	my ($self, $new) = @_;
 	my $pfx = "$self->{-inbox}->{mainrepo}/git";
 	my $git_dir = "$pfx/$new.git";
-	die "$git_dir exists\n" if -e $git_dir;
 	my @cmd = (qw(git init --bare -q), $git_dir);
 	PublicInbox::Import::run_die(\@cmd);
 
@@ -359,6 +395,23 @@ sub git_init {
 	$git_dir
 }
 
+sub git_dir_latest {
+	my ($self, $max) = @_;
+	$$max = -1;
+	my $pfx = "$self->{-inbox}->{mainrepo}/git";
+	return unless -d $pfx;
+	my $latest;
+	opendir my $dh, $pfx or die "opendir $pfx: $!\n";
+	while (defined(my $git_dir = readdir($dh))) {
+		$git_dir =~ m!\A(\d+)\.git\z! or next;
+		if ($1 > $$max) {
+			$$max = $1;
+			$latest = "$pfx/$git_dir";
+		}
+	}
+	$latest;
+}
+
 sub importer {
 	my ($self) = @_;
 	my $im = $self->{im};
@@ -368,27 +421,16 @@ sub importer {
 		} else {
 			$self->{im} = undef;
 			$im->done;
-			$self->searchidx_checkpoint(1);
+			$self->barrier(1);
 			$im = undef;
 			my $git_dir = $self->git_init(++$self->{max_git});
 			my $git = PublicInbox::Git->new($git_dir);
 			return $self->import_init($git, 0);
 		}
 	}
-	my $latest;
-	my $max = -1;
 	my $new = 0;
-	my $pfx = "$self->{-inbox}->{mainrepo}/git";
-	if (-d $pfx) {
-		foreach my $git_dir (glob("$pfx/*.git")) {
-			$git_dir =~ m!/(\d+)\.git\z! or next;
-			my $n = $1;
-			if ($n > $max) {
-				$max = $n;
-				$latest = $git_dir;
-			}
-		}
-	}
+	my $max;
+	my $latest = git_dir_latest($self, \$max);
 	if (defined $latest) {
 		my $git = PublicInbox::Git->new($latest);
 		my $packed_bytes = $git->packed_bytes;
@@ -420,10 +462,11 @@ sub diff ($$$) {
 	use File::Temp qw(tempfile);
 	use PublicInbox::Spawn qw(spawn);
 
-	my ($ah, $an) = tempfile('email-cur-XXXXXXXX');
+	my ($ah, $an) = tempfile('email-cur-XXXXXXXX', TMPDIR => 1);
 	print $ah $cur->as_string or die "print: $!";
 	close $ah or die "close: $!";
-	my ($bh, $bn) = tempfile('email-new-XXXXXXXX');
+	my ($bh, $bn) = tempfile('email-new-XXXXXXXX', TMPDIR => 1);
+	PublicInbox::Import::drop_unwanted_headers($new);
 	print $bh $new->as_string or die "print: $!";
 	close $bh or die "close: $!";
 	my $cmd = [ qw(diff -u), $an, $bn ];
@@ -466,12 +509,189 @@ sub lookup_content {
 
 sub atfork_child {
 	my ($self) = @_;
+	my $fh = delete $self->{reindex_pipe};
+	close $fh if $fh;
 	if (my $parts = $self->{idx_parts}) {
 		$_->atfork_child foreach @$parts;
 	}
 	if (my $im = $self->{im}) {
 		$im->atfork_child;
 	}
+	die "unexpected mm" if $self->{mm};
+}
+
+sub mark_deleted {
+	my ($self, $D, $git, $oid) = @_;
+	my $msgref = $git->cat_file($oid);
+	my $mime = PublicInbox::MIME->new($$msgref);
+	my $mids = mids($mime->header_obj);
+	my $cid = content_id($mime);
+	foreach my $mid (@$mids) {
+		$D->{"$mid\0$cid"} = 1;
+	}
+}
+
+sub reindex_oid {
+	my ($self, $mm_tmp, $D, $git, $oid, $regen) = @_;
+	my $len;
+	my $msgref = $git->cat_file($oid, \$len);
+	my $mime = PublicInbox::MIME->new($$msgref);
+	my $mids = mids($mime->header_obj);
+	my $cid = content_id($mime);
+
+	# get the NNTP article number we used before, highest number wins
+	# and gets deleted from mm_tmp;
+	my $mid0;
+	my $num = -1;
+	my $del = 0;
+	foreach my $mid (@$mids) {
+		$del += (delete $D->{"$mid\0$cid"} || 0);
+		my $n = $mm_tmp->num_for($mid);
+		if (defined $n && $n > $num) {
+			$mid0 = $mid;
+			$num = $n;
+		}
+	}
+	if (!defined($mid0) && $regen && !$del) {
+		$num = $$regen--;
+		die "BUG: ran out of article numbers\n" if $num <= 0;
+		my $mm = $self->{mm};
+		foreach my $mid (reverse @$mids) {
+			if ($mm->mid_set($num, $mid) == 1) {
+				$mid0 = $mid;
+				last;
+			}
+		}
+		if (!defined($mid0)) {
+			my $id = '<' . join('> <', @$mids) . '>';
+			warn "Message-ID $id unusable for $num\n";
+			foreach my $mid (@$mids) {
+				defined(my $n = $mm->num_for($mid)) or next;
+				warn "#$n previously mapped for <$mid>\n";
+			}
+		}
+	}
+
+	if (!defined($mid0) || $del) {
+		if (!defined($mid0) && $del) { # expected for deletes
+			$$regen--;
+			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";
+		}
+		return;
+
+	}
+	$mm_tmp->mid_delete($mid0) or
+		die "failed to delete <$mid0> for article #$num\n";
+
+	my $nparts = $self->{partitions};
+	my $part = $num % $nparts;
+	my $idx = $self->idx_part($part);
+	$idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime);
+	my $n = $self->{transact_bytes} += $len;
+	if ($n > (PublicInbox::SearchIdx::BATCH_BYTES * $nparts)) {
+		$git->cleanup;
+		$mm_tmp->atfork_prepare;
+		$self->done; # release lock
+		# allow -watch or -mda to write...
+		$self->idx_init; # reacquire lock
+		$mm_tmp->atfork_parent;
+	}
+}
+
+sub reindex {
+	my ($self, $regen) = @_;
+	my $ibx = $self->{-inbox};
+	my $pfx = "$ibx->{mainrepo}/git";
+	my $max_git;
+	my $latest = git_dir_latest($self, \$max_git);
+	return unless defined $latest;
+	my $head = $ibx->{ref_head} || 'refs/heads/master';
+	$self->idx_init; # acquire lock
+	my $x40 = qr/[a-f0-9]{40}/;
+	my $mm_tmp = $self->{mm}->tmp_clone;
+	if (!$regen) {
+		my (undef, $max) = $mm_tmp->minmax;
+		unless (defined $max) {
+			$regen = 1;
+			warn
+"empty msgmap.sqlite3, regenerating article numbers\n";
+		}
+	}
+	my $tip; # latest commit out of all git repos
+	if ($regen) {
+		my $regen_max = 0;
+		for (my $cur = $max_git; $cur >= 0; $cur--) {
+			die "already reindexing!\n" if $self->{reindex_pipe};
+			my $git = PublicInbox::Git->new("$pfx/$cur.git");
+			-d $git->{git_dir} or next; # missing parts are fine
+			chomp($tip = $git->qx('rev-parse', $head)) unless $tip;
+			my $h = $cur == $max_git ? $tip : $head;
+
+			# can't use 'rev-list --count' if we use --diff-filter
+			my $fh = $git->popen(qw(log --pretty=tformat:%h
+					--no-notes --no-color --no-renames
+					--diff-filter=AM), $h, '--', 'm');
+			++$regen_max while <$fh>;
+		}
+		die "No messages found in $pfx/*.git, bug?\n" unless $regen_max;
+		$regen = \$regen_max;
+	}
+	my $D = {};
+	my @cmd = qw(log --raw -r --pretty=tformat:%h
+			--no-notes --no-color --no-abbrev --no-renames);
+
+	# if we are regenerating, we must not use a newer tip commit than what
+	# the regeneration counter used:
+	$tip ||= $head;
+
+	# work backwards through history
+	for (my $cur = $max_git; $cur >= 0; $cur--) {
+		die "already reindexing!\n" if delete $self->{reindex_pipe};
+		my $cmt;
+		my $git_dir = "$pfx/$cur.git";
+		-d $git_dir or next; # missing parts are fine
+		my $git = PublicInbox::Git->new($git_dir);
+		my $h = $cur == $max_git ? $tip : $head;
+		my $fh = $self->{reindex_pipe} = $git->popen(@cmd, $h);
+		while (<$fh>) {
+			if (/\A$x40$/o) {
+				chomp($cmt = $_);
+			} elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\tm$/o) {
+				$self->reindex_oid($mm_tmp, $D, $git, $1,
+						$regen);
+			} elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\td$/o) {
+				$self->mark_deleted($D, $git, $1);
+			}
+		}
+		delete $self->{reindex_pipe};
+	}
+	my $gaps;
+	if ($regen && $$regen != 0) {
+		warn "W: leftover article number ($$regen)\n";
+		$gaps = 1;
+	}
+	my ($min, $max) = $mm_tmp->minmax;
+	if (defined $max) {
+		warn "W: leftover article numbers at $min..$max\n";
+		$gaps = 1;
+	}
+	warn "W: were old git partitions deleted?\n" if $gaps;
+	my @d = sort keys %$D;
+	if (@d) {
+		warn "BUG: ", scalar(@d)," unseen deleted messages marked\n";
+		foreach (@d) {
+			my ($mid, undef) = split(/\0/, $_, 2);
+			warn "<$mid>\n";
+		}
+	}
 }
 
 1;