X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=lib%2FPublicInbox%2FV2Writable.pm;h=33c0038d18ebac631c2b2a9c84f55222d5d3d5ac;hp=db905f924879e78e61e8bf1c4d06405cd09d19bd;hb=96a8b8832d791d53e05f235b5bc2492daab5f60a;hpb=f7651f3fea8cea0ee1f6567cc53f93a57a652a47

diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index db905f92..33c0038d 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -1,4 +1,4 @@
-# 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
@@ -7,7 +7,7 @@ package PublicInbox::V2Writable;
 use strict;
 use warnings;
 use base qw(PublicInbox::Lock);
-use PublicInbox::SearchIdxPart;
+use PublicInbox::SearchIdxShard;
 use PublicInbox::MIME;
 use PublicInbox::Git;
 use PublicInbox::Import;
@@ -24,14 +24,14 @@ use IO::Handle;
 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
-# to increase Xapian partitions.
+# to increase Xapian shards
 our $NPROC_MAX_DEFAULT = 4;
 
-sub nproc_parts ($) {
+sub nproc_shards ($) {
 	my ($creat_opt) = @_;
 	if (ref($creat_opt) eq 'HASH') {
 		if (defined(my $n = $creat_opt->{nproc})) {
@@ -52,31 +52,31 @@ sub nproc_parts ($) {
 	$n < 1 ? 1 : $n;
 }
 
-sub count_partitions ($) {
+sub count_shards ($) {
 	my ($self) = @_;
-	my $nparts = 0;
+	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) {
-		foreach my $part (<$xpfx/*>) {
-			-d $part && $part =~ m!/[0-9]+\z! or next;
+		foreach my $shard (<$xpfx/*>) {
+			-d $shard && $shard =~ m!/[0-9]+\z! or next;
 			eval {
-				Search::Xapian::Database->new($part)->close;
-				$nparts++;
+				Search::Xapian::Database->new($shard)->close;
+				$n++;
 			};
 		}
 	}
-	$nparts;
+	$n;
 }
 
 sub new {
 	# $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";
+	my $dir = $v2ibx->{inboxdir} or die "no inboxdir in inbox\n";
 	unless (-d $dir) {
 		if ($creat) {
 			require File::Path;
@@ -103,7 +103,7 @@ sub new {
 		rotate_bytes => int((1024 * 1024 * 1024) / $PACKING_FACTOR),
 		last_commit => [], # git repo -> commit
 	};
-	$self->{partitions} = count_partitions($self) || nproc_parts($creat);
+	$self->{shards} = count_shards($self) || nproc_shards($creat);
 	bless $self, $class;
 }
 
@@ -134,12 +134,10 @@ sub add {
 sub do_idx ($$$$$$$) {
 	my ($self, $msgref, $mime, $len, $num, $oid, $mid0) = @_;
 	$self->{over}->add_overview($mime, $len, $num, $oid, $mid0);
-	my $npart = $self->{partitions};
-	my $part = $num % $npart;
-	my $idx = idx_part($self, $part);
+	my $idx = idx_shard($self, $num % $self->{shards});
 	$idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime);
 	my $n = $self->{transact_bytes} += $len;
-	$n >= (PublicInbox::SearchIdx::BATCH_BYTES * $npart);
+	$n >= (PublicInbox::SearchIdx::BATCH_BYTES * $self->{shards});
 }
 
 sub _add {
@@ -157,8 +155,7 @@ sub _add {
 	# 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;
@@ -174,16 +171,15 @@ sub _add {
 	$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) {
@@ -192,7 +188,7 @@ sub num_for {
 			# 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
@@ -203,8 +199,7 @@ sub num_for {
 			my $num = $self->{mm}->num_for($mid);
 
 			if (defined $num && !$self->{over}->get_art($num)) {
-				$$mid0 = $mid;
-				return $num;
+				return ($num, $mid);
 			}
 		}
 
@@ -217,50 +212,49 @@ sub num_for {
 			$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_part {
-	my ($self, $part) = @_;
-	$self->{idx_parts}->[$part];
+sub idx_shard {
+	my ($self, $shard_i) = @_;
+	$self->{idx_shards}->[$shard_i];
 }
 
 # idempotent
 sub idx_init {
 	my ($self, $opt) = @_;
-	return if $self->{idx_parts};
+	return if $self->{idx_shards};
 	my $ibx = $self->{-inbox};
 
 	# do not leak read-only FDs to child processes, we only have these
@@ -289,24 +283,24 @@ sub idx_init {
 		$over->create;
 
 		# xcpdb can change shard count while -watch is idle
-		my $nparts = count_partitions($self);
-		if ($nparts && $nparts != $self->{partitions}) {
-			$self->{partitions} = $nparts;
+		my $nshards = count_shards($self);
+		if ($nshards && $nshards != $self->{shards}) {
+			$self->{shards} = $nshards;
 		}
 
-		# need to create all parts before initializing msgmap FD
-		my $max = $self->{partitions} - 1;
+		# need to create all shards before initializing msgmap FD
+		my $max = $self->{shards} - 1;
 
-		# idx_parts must be visible to all forked processes
-		my $idx = $self->{idx_parts} = [];
+		# idx_shards must be visible to all forked processes
+		my $idx = $self->{idx_shards} = [];
 		for my $i (0..$max) {
-			push @$idx, PublicInbox::SearchIdxPart->new($self, $i);
+			push @$idx, PublicInbox::SearchIdxShard->new($self, $i);
 		}
 
 		# 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;
 	});
 }
@@ -317,7 +311,7 @@ sub idx_init {
 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};
 
@@ -370,7 +364,6 @@ sub rewrite_internal ($$;$$$) {
 	}
 	my $over = $self->{over};
 	my $cids = content_ids($old_mime);
-	my $parts = $self->{idx_parts};
 	my $removed;
 	my $mids = mids($old_mime->header_obj);
 
@@ -559,7 +552,7 @@ W: $list
 	$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, $cmt);
@@ -572,7 +565,7 @@ sub set_last_commits ($) {
 	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);
 	}
 }
 
@@ -590,7 +583,7 @@ sub barrier_wait {
 	while (scalar keys %$barrier) {
 		defined(my $l = $r->getline) or die "EOF on barrier_wait: $!";
 		$l =~ /\Abarrier (\d+)/ or die "bad line on barrier_wait: $l";
-		delete $barrier->{$1} or die "bad part[$1] on barrier wait";
+		delete $barrier->{$1} or die "bad shard[$1] on barrier wait";
 	}
 }
 
@@ -605,8 +598,8 @@ sub checkpoint ($;$) {
 			$im->checkpoint;
 		}
 	}
-	my $parts = $self->{idx_parts};
-	if ($parts) {
+	my $shards = $self->{idx_shards};
+	if ($shards) {
 		my $dbh = $self->{mm}->{dbh};
 
 		# SQLite msgmap data is second in importance
@@ -617,19 +610,19 @@ sub checkpoint ($;$) {
 
 		# Now deal with Xapian
 		if ($wait) {
-			my $barrier = $self->barrier_init(scalar @$parts);
+			my $barrier = $self->barrier_init(scalar @$shards);
 
-			# each partition needs to issue a barrier command
-			$_->remote_barrier for @$parts;
+			# 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 {
-			$_->remote_commit for @$parts;
+			$_->remote_commit for @$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);
 		$dbh->commit;
@@ -652,30 +645,26 @@ sub done {
 	checkpoint($self);
 	my $mm = delete $self->{mm};
 	$mm->{dbh}->commit if $mm;
-	my $parts = delete $self->{idx_parts};
-	if ($parts) {
-		$_->remote_close for @$parts;
+	my $shards = delete $self->{idx_shards};
+	if ($shards) {
+		$_->remote_close for @$shards;
 	}
 	$self->{over}->disconnect;
 	delete $self->{bnote};
 	$self->{transact_bytes} = 0;
-	$self->lock_release if $parts;
+	$self->lock_release if $shards;
 	$self->{-inbox}->git->cleanup;
 }
 
 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;
@@ -697,9 +686,12 @@ sub fill_alternates ($$) {
 
 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);
 	$git_dir
 }
@@ -707,7 +699,7 @@ sub git_init {
 sub git_dir_latest {
 	my ($self, $max) = @_;
 	$$max = -1;
-	my $pfx = "$self->{-inbox}->{mainrepo}/git";
+	my $pfx = "$self->{-inbox}->{inboxdir}/git";
 	return unless -d $pfx;
 	my $latest;
 	opendir my $dh, $pfx or die "opendir $pfx: $!\n";
@@ -827,8 +819,8 @@ sub atfork_child {
 	my ($self) = @_;
 	my $fh = delete $self->{reindex_pipe};
 	close $fh if $fh;
-	if (my $parts = $self->{idx_parts}) {
-		$_->atfork_child foreach @$parts;
+	if (my $shards = $self->{idx_shards}) {
+		$_->atfork_child foreach @$shards;
 	}
 	if (my $im = $self->{im}) {
 		$im->atfork_child;
@@ -849,103 +841,179 @@ sub mark_deleted ($$$$) {
 	}
 }
 
-sub reindex_oid ($$$$) {
+sub reindex_checkpoint ($$$) {
+	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 ($$$$) {
 	my ($self, $sync, $git, $oid) = @_;
-	my $len;
+	my ($num, $mid0, $len);
 	my $msgref = $git->cat_file($oid, \$len);
 	my $mime = PublicInbox::MIME->new($$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) {
+	for my $mid (reverse @$mids) {
+		delete($sync->{D}->{"$mid\0$cid"}) and
+			die "BUG: reindex_oid should handle <$mid> delete";
+	}
+	for my $mid (reverse @$mids) {
+		($num, $mid0) = $self->{over}->num_mid0_for_oid($oid, $mid);
+		last if defined $num;
+	}
+	unless (defined($num)) {
+		for my $mid (reverse @$mids) {
+			# is this a number we got before?
+			$num = $sync->{mm_tmp}->num_for($mid);
+			next unless defined $num;
 			$mid0 = $mid;
-			$num = $n;
-			$self->{mm}->mid_set($num, $mid0);
+			last;
 		}
 	}
-	if (!defined($mid0) && !$del) {
+	if (defined($num)) {
+		$sync->{mm_tmp}->num_delete($num);
+	} else {
 		$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, $mid) == 1) {
+		if ($num <= 0) {
+			# 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)) {
-			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 $mid0) {
+				if ($sync->{reindex}) {
+					warn "reindex added #$num <$mid0>\n";
+				}
+			} else {
+				warn "E: cannot find article #\n";
+				return;
+			}
+		} else { # $num > 0, use the new article number
+			for my $mid (reverse @$mids) {
+				$self->{mm}->mid_set($num, $mid) == 1 or next;
+				$mid0 = $mid;
+				last;
+			}
+			unless (defined $mid0) {
+				warn "E: cannot regen #$num\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 ($$$) {
+	my ($self, $num, $mid0) = @_;
+	my $unindexed = $self->{unindexed} // {};
+	my $n = delete($unindexed->{$mid0});
+	defined $n or return;
+	if ($n != $num) {
+		die "BUG: unindexed $n != $num <$mid0>\n";
+	} else {
+		$self->{mm}->mid_set($num, $mid0);
+	}
+}
+
+sub reindex_oid ($$$$) {
+	my ($self, $sync, $git, $oid) = @_;
+	my ($num, $mid0, $len);
+	my $msgref = $git->cat_file($oid, \$len);
+	return if $len == 0; # purged
+	my $mime = PublicInbox::MIME->new($$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\n" 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:
+			push @{$sync->{multi_mid} //= []}, $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 ($$) {
 	my ($self, $epoch_max) = @_;
 	my $heads = [];
 	for (my $i = $epoch_max; $i >= 0; $i--) {
-		$heads->[$i] = last_commit_part($self, $i);
+		$heads->[$i] = last_epoch_commit($self, $i);
 	}
 	$heads;
 }
@@ -1016,7 +1084,7 @@ sub sync_prepare ($$$) {
 	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;
@@ -1051,12 +1119,13 @@ sub sync_prepare ($$$) {
 
 sub unindex_oid_remote ($$$) {
 	my ($self, $oid, $mid) = @_;
-	$_->remote_remove($oid, $mid) foreach @{$self->{idx_parts}};
+	$_->remote_remove($oid, $mid) foreach @{$self->{idx_shards}};
 	$self->{over}->remove_oid($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);
@@ -1076,8 +1145,11 @@ sub unindex_oid ($$$) {
 				join(',',sort keys %gone), "\n";
 		}
 		foreach my $num (keys %gone) {
-			$self->{unindexed}->{$_}++;
-			$self->{mm}->num_delete($num);
+			if ($unindexed) {
+				my $mid0 = $mm->mid_for($num);
+				$unindexed->{$mid0} = $num;
+			}
+			$mm->num_delete($num);
 		}
 		unindex_oid_remote($self, $oid, $mid);
 	}
@@ -1086,20 +1158,21 @@ sub unindex_oid ($$$) {
 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;
 
 	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
@@ -1126,7 +1199,7 @@ sub index_epoch ($$$) {
 
 	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}) {
@@ -1192,11 +1265,23 @@ sub index_sync {
 
 	# 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;
+
+		while (defined(my $oid = pop(@$multi_mid))) {
+			$self->{current_info} = "multi_mid $oid";
+			reindex_oid_m($self, $sync, $git, $oid);
+		}
 	}
+	$git->cleanup if $git;
 	$self->done;
 
 	if (my $nr = $sync->{nr}) {