X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiStore.pm;h=094e1555a3fcafe8b92d03c8c1b2f15b391d105e;hb=842e684f0a4154787274843eb3c9be2eef11b160;hp=b5d43b7eea125a94e71168490baed27cb2867e8e;hpb=5be0cb101bab44167a78af7a2d167f254c95bdb3;p=public-inbox.git

diff --git a/lib/PublicInbox/LeiStore.pm b/lib/PublicInbox/LeiStore.pm
index b5d43b7e..094e1555 100644
--- a/lib/PublicInbox/LeiStore.pm
+++ b/lib/PublicInbox/LeiStore.pm
@@ -3,14 +3,20 @@
 #
 # Local storage (cache/memo) for lei(1), suitable for personal/private
 # mail iff on encrypted device/FS.  Based on v2, but only deduplicates
-# based on git OID.
+# git storage based on git OID (index deduplication is done in ContentHash)
 #
 # for xref3, the following are constant: $eidx_key = '.', $xnum = -1
+#
+# We rely on the synchronous IPC API for this in lei-daemon and
+# multiple lei clients to write to it at once.  This allows the
+# lei/store IPC process to be decoupled from network latency in
+# lei WQ workers.
 package PublicInbox::LeiStore;
 use strict;
 use v5.10.1;
 use parent qw(PublicInbox::Lock PublicInbox::IPC);
 use PublicInbox::ExtSearchIdx;
+use PublicInbox::Eml;
 use PublicInbox::Import;
 use PublicInbox::InboxWritable qw(eml_from_path);
 use PublicInbox::V2Writable;
@@ -18,7 +24,10 @@ use PublicInbox::ContentHash qw(content_hash);
 use PublicInbox::MID qw(mids);
 use PublicInbox::LeiSearch;
 use PublicInbox::MDA;
+use PublicInbox::Spawn qw(spawn);
 use List::Util qw(max);
+use File::Temp ();
+use POSIX ();
 
 sub new {
 	my (undef, $dir, $opt) = @_;
@@ -51,8 +60,9 @@ sub git_epoch_max  {
 
 sub git_ident ($) {
 	my ($git) = @_;
-	chomp(my $i = $git->qx(qw(var GIT_COMMITTER_IDENT)));
-	warn "$git->{git_dir} GIT_COMMITTER_IDENT failed\n" if $?;
+	my $rdr = {};
+	open $rdr->{2}, '>', '/dev/null' or die "open /dev/null: $!";
+	chomp(my $i = $git->qx([qw(var GIT_COMMITTER_IDENT)], undef, $rdr));
 	$i =~ /\A(.+) <([^>]+)> [0-9]+ [-\+]?[0-9]+$/ ? ($1, $2) :
 		('lei user', 'x@example.com')
 }
@@ -77,7 +87,10 @@ sub importer {
 		my $old = -e $latest;
 		PublicInbox::Import::init_bare($latest);
 		my $git = PublicInbox::Git->new($latest);
-		$git->qx(qw(config core.sharedRepository 0600)) if !$old;
+		if (!$old) {
+			$git->qx(qw(config core.sharedRepository 0600));
+			$self->done; # force eidx_init on next round
+		}
 		my $packed_bytes = $git->packed_bytes;
 		my $unpacked_bytes = $packed_bytes / $self->packing_factor;
 		if ($unpacked_bytes >= $self->rotate_bytes) {
@@ -97,18 +110,27 @@ sub search {
 	PublicInbox::LeiSearch->new($_[0]->{priv_eidx}->{topdir});
 }
 
+# follows the stderr file
+sub _tail_err {
+	my ($self) = @_;
+	print { $self->{-err_wr} } readline($self->{-tmp_err});
+}
+
 sub eidx_init {
 	my ($self) = @_;
 	my $eidx = $self->{priv_eidx};
+	my $tl = wantarray && $self->{-err_wr} ?
+			PublicInbox::OnDestroy->new($$, \&_tail_err, $self) :
+			undef;
 	$eidx->idx_init({-private => 1});
-	$eidx;
+	wantarray ? ($eidx, $tl) : $eidx;
 }
 
 sub _docids_for ($$) {
 	my ($self, $eml) = @_;
 	my %docids;
+	my $eidx = $self->{priv_eidx};
 	my ($chash, $mids) = PublicInbox::LeiSearch::content_key($eml);
-	my $eidx = eidx_init($self);
 	my $oidx = $eidx->{oidx};
 	my $im = $self->{im};
 	for my $mid (@$mids) {
@@ -131,18 +153,18 @@ sub _docids_for ($$) {
 }
 
 sub set_eml_vmd {
-	my ($self, $eml, $vmd) = @_;
-	my $eidx = eidx_init($self);
-	my @docids = _docids_for($self, $eml);
-	for my $docid (@docids) {
+	my ($self, $eml, $vmd, $docids) = @_;
+	my ($eidx, $tl) = eidx_init($self);
+	$docids //= [ _docids_for($self, $eml) ];
+	for my $docid (@$docids) {
 		$eidx->idx_shard($docid)->ipc_do('set_vmd', $docid, $vmd);
 	}
-	\@docids;
+	$docids;
 }
 
 sub add_eml_vmd {
 	my ($self, $eml, $vmd) = @_;
-	my $eidx = eidx_init($self);
+	my ($eidx, $tl) = eidx_init($self);
 	my @docids = _docids_for($self, $eml);
 	for my $docid (@docids) {
 		$eidx->idx_shard($docid)->ipc_do('add_vmd', $docid, $vmd);
@@ -152,7 +174,7 @@ sub add_eml_vmd {
 
 sub remove_eml_vmd {
 	my ($self, $eml, $vmd) = @_;
-	my $eidx = eidx_init($self);
+	my ($eidx, $tl) = eidx_init($self);
 	my @docids = _docids_for($self, $eml);
 	for my $docid (@docids) {
 		$eidx->idx_shard($docid)->ipc_do('remove_vmd', $docid, $vmd);
@@ -163,7 +185,7 @@ sub remove_eml_vmd {
 sub add_eml {
 	my ($self, $eml, $vmd, $xoids) = @_;
 	my $im = $self->importer; # may create new epoch
-	my $eidx = eidx_init($self); # writes ALL.git/objects/info/alternates
+	my ($eidx, $tl) = eidx_init($self); # updates/writes alternates file
 	my $oidx = $eidx->{oidx}; # PublicInbox::Import::add checks this
 	my $smsg = bless { -oidx => $oidx }, 'PublicInbox::Smsg';
 	$im->add($eml, undef, $smsg) or return; # duplicate returns undef
@@ -228,9 +250,31 @@ sub set_eml {
 		set_eml_vmd($self, $eml, $vmd);
 }
 
+sub _external_only ($$$) {
+	my ($self, $xoids, $eml) = @_;
+	my $eidx = $self->{priv_eidx};
+	my $oidx = $eidx->{oidx} // die 'BUG: {oidx} missing';
+	my $smsg = bless { blob => '' }, 'PublicInbox::Smsg';
+	$smsg->{num} = $oidx->adj_counter('eidx_docid', '+');
+	# save space for an externals-only message
+	my $hdr = $eml->header_obj;
+	$smsg->populate($hdr); # sets lines == 0
+	$smsg->{bytes} = 0;
+	delete @$smsg{qw(From Subject)};
+	$smsg->{to} = $smsg->{cc} = $smsg->{from} = '';
+	$oidx->add_overview($hdr, $smsg); # subject+references for threading
+	$smsg->{subject} = '';
+	for my $oid (keys %$xoids) {
+		$oidx->add_xref3($smsg->{num}, -1, $oid, '.');
+	}
+	my $idx = $eidx->idx_shard($smsg->{num});
+	$idx->index_eml(PublicInbox::Eml->new("\n\n"), $smsg);
+	($smsg, $idx);
+}
+
 sub update_xvmd {
-	my ($self, $xoids, $vmd_mod) = @_;
-	my $eidx = eidx_init($self);
+	my ($self, $xoids, $eml, $vmd_mod) = @_;
+	my ($eidx, $tl) = eidx_init($self);
 	my $oidx = $eidx->{oidx};
 	my %seen;
 	for my $oid (keys %$xoids) {
@@ -242,14 +286,32 @@ sub update_xvmd {
 			my $idx = $eidx->idx_shard($docid);
 			$idx->ipc_do('update_vmd', $docid, $vmd_mod);
 		}
+		delete $xoids->{$oid};
+	}
+	return unless scalar(keys(%$xoids));
+
+	# see if it was indexed, but with different OID(s)
+	if (my @docids = _docids_for($self, $eml)) {
+		for my $docid (@docids) {
+			next if $seen{$docid};
+			for my $oid (keys %$xoids) {
+				$oidx->add_xref3($docid, -1, $oid, '.');
+			}
+			my $idx = $eidx->idx_shard($docid);
+			$idx->ipc_do('update_vmd', $docid, $vmd_mod);
+		}
+		return;
 	}
+	# totally unseen
+	my ($smsg, $idx) = _external_only($self, $xoids, $eml);
+	$idx->ipc_do('update_vmd', $smsg->{num}, $vmd_mod);
 }
 
 # set or update keywords for external message, called via ipc_do
 sub set_xvmd {
 	my ($self, $xoids, $eml, $vmd) = @_;
 
-	my $eidx = eidx_init($self);
+	my ($eidx, $tl) = eidx_init($self);
 	my $oidx = $eidx->{oidx};
 	my %seen;
 
@@ -267,33 +329,12 @@ sub set_xvmd {
 	}
 	return unless scalar(keys(%$xoids));
 
-	# see if it was indexed, but with different OID(s)
-	if (my @docids = _docids_for($self, $eml)) {
-		for my $docid (@docids) {
-			for my $oid (keys %$xoids) {
-				$oidx->add_xref3($docid, -1, $oid, '.');
-			}
-			my $idx = $eidx->idx_shard($docid);
-			$idx->ipc_do('set_vmd', $docid, $vmd);
-		}
-		return;
-	}
-	# totally unseen
-	my $smsg = bless { blob => '' }, 'PublicInbox::Smsg';
-	$smsg->{num} = $oidx->adj_counter('eidx_docid', '+');
-	# save space for an externals-only message
-	my $hdr = $eml->header_obj;
-	$smsg->populate($hdr); # sets lines == 0
-	$smsg->{bytes} = 0;
-	delete @$smsg{qw(From Subject)};
-	$smsg->{to} = $smsg->{cc} = $smsg->{from} = '';
-	$oidx->add_overview($hdr, $smsg); # subject+references for threading
-	$smsg->{subject} = '';
-	for my $oid (keys %$xoids) {
-		$oidx->add_xref3($smsg->{num}, -1, $oid, '.');
-	}
-	my $idx = $eidx->idx_shard($smsg->{num});
-	$idx->index_eml(PublicInbox::Eml->new("\n\n"), $smsg);
+	# n.b. we don't do _docids_for here, we expect the caller
+	# already checked $lse->kw_changed before calling this sub
+
+	return unless (@{$vmd->{kw} // []}) || (@{$vmd->{L} // []});
+	# totally unseen:
+	my ($smsg, $idx) = _external_only($self, $xoids, $eml);
 	$idx->ipc_do('add_vmd', $smsg->{num}, $vmd);
 }
 
@@ -305,6 +346,21 @@ sub checkpoint {
 	$self->{priv_eidx}->checkpoint($wait);
 }
 
+sub xchg_stderr {
+	my ($self) = @_;
+	_tail_err($self) if $self->{-err_wr};
+	my $dir = $self->{priv_eidx}->{topdir};
+	return unless -e $dir;
+	my $old = delete $self->{-tmp_err};
+	my $pfx = POSIX::strftime('%Y%m%d%H%M%S', gmtime(time));
+	my $err = File::Temp->new(TEMPLATE => "$pfx.$$.lei_storeXXXX",
+				SUFFIX => '.err', DIR => $dir);
+	open STDERR, '>>', $err->filename or die "dup2: $!";
+	STDERR->autoflush(1); # shared with shard subprocesses
+	$self->{-tmp_err} = $err; # separate file description for RO access
+	undef;
+}
+
 sub done {
 	my ($self) = @_;
 	my $err = '';
@@ -315,26 +371,44 @@ sub done {
 			warn $err;
 		}
 	}
-	$self->{priv_eidx}->done;
+	$self->{priv_eidx}->done; # V2Writable::done
+	xchg_stderr($self);
 	die $err if $err;
 }
 
 sub ipc_atfork_child {
 	my ($self) = @_;
 	my $lei = $self->{lei};
-	$lei->lei_atfork_child(1) if $lei;
+	$lei->_lei_atfork_child(1) if $lei;
+	xchg_stderr($self);
+	if (my $err = delete($self->{err_pipe})) {
+		close $err->[0];
+		$self->{-err_wr} = $err->[1];
+	}
+	$SIG{__WARN__} = PublicInbox::Eml::warn_ignore_cb();
 	$self->SUPER::ipc_atfork_child;
 }
 
 sub write_prepare {
 	my ($self, $lei) = @_;
 	unless ($self->{-ipc_req}) {
-		$self->ipc_lock_init($lei->store_path . '/ipc.lock');
+		my $d = $lei->store_path;
+		$self->ipc_lock_init("$d/ipc.lock");
+		substr($d, -length('/lei/store'), 10, '');
+		my $err_pipe;
+		unless ($lei->{oneshot}) {
+			pipe(my ($r, $w)) or die "pipe: $!";
+			$err_pipe = [ $r, $w ];
+		}
 		# Mail we import into lei are private, so headers filtered out
 		# by -mda for public mail are not appropriate
 		local @PublicInbox::MDA::BAD_HEADERS = ();
-		$self->ipc_worker_spawn('lei_store', $lei->oldset,
-					{ lei => $lei });
+		$self->ipc_worker_spawn("lei/store $d", $lei->oldset,
+					{ lei => $lei, err_pipe => $err_pipe });
+		if ($err_pipe) {
+			require PublicInbox::LeiStoreErr;
+			PublicInbox::LeiStoreErr->new($err_pipe->[0], $lei);
+		}
 	}
 	$lei->{sto} = $self;
 }