X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FGit.pm;h=374a3b4dd71d9849aea7a1c7dee2e8d2e2d8d1f6;hb=7b7d4bd01b564969eb0c1904a5bd9ee4f3dbba72;hp=5ef1db2f8c5da5fd94bf70e57255173f0ba16e3c;hpb=62181c1f4fa112e066e01ba5f2cf666b9639adf2;p=public-inbox.git

diff --git a/lib/PublicInbox/Git.pm b/lib/PublicInbox/Git.pm
index 5ef1db2f..374a3b4d 100644
--- a/lib/PublicInbox/Git.pm
+++ b/lib/PublicInbox/Git.pm
@@ -12,20 +12,21 @@ use v5.10.1;
 use parent qw(Exporter);
 use POSIX ();
 use IO::Handle; # ->autoflush
-use Errno qw(EINTR EAGAIN);
+use Errno qw(EINTR EAGAIN ENOENT);
 use File::Glob qw(bsd_glob GLOB_NOSORT);
 use File::Spec ();
 use Time::HiRes qw(stat);
 use PublicInbox::Spawn qw(popen_rd spawn);
 use PublicInbox::Tmpfile;
 use IO::Poll qw(POLLIN);
-use Carp qw(croak);
+use Carp qw(croak carp);
 use Digest::SHA ();
 use PublicInbox::DS qw(dwaitpid);
 our @EXPORT_OK = qw(git_unquote git_quote);
 our $PIPE_BUFSIZ = 65536; # Linux default
 our $in_cleanup;
 our $RDTIMEO = 60_000; # milliseconds
+our $async_warn; # true in read-only daemons
 
 use constant MAX_INFLIGHT => (POSIX::PIPE_BUF * 3) /
 	65; # SHA-256 hex size + "\n" in preparation for git using non-SHA1
@@ -62,6 +63,8 @@ sub git_quote ($) {
 
 sub new {
 	my ($class, $git_dir) = @_;
+	$git_dir =~ tr!/!/!s;
+	$git_dir =~ s!/*\z!!s;
 	# may contain {-tmp} field for File::Temp::Dir
 	bless { git_dir => $git_dir, alt_st => '', -git_path => {} }, $class
 }
@@ -110,18 +113,22 @@ sub _bidi_pipe {
 		}
 		return;
 	}
-	my ($out_r, $out_w);
-	pipe($out_r, $out_w) or $self->fail("pipe failed: $!");
-	my @cmd = (qw(git), "--git-dir=$self->{git_dir}",
+	pipe(my ($out_r, $out_w)) or $self->fail("pipe failed: $!");
+	my $rdr = { 0 => $out_r, pgid => 0 };
+	my $gd = $self->{git_dir};
+	if ($gd =~ s!/([^/]+/[^/]+)\z!/!) {
+		$rdr->{-C} = $gd;
+		$gd = $1;
+	}
+	my @cmd = (qw(git), "--git-dir=$gd",
 			qw(-c core.abbrev=40 cat-file), $batch);
-	my $redir = { 0 => $out_r };
 	if ($err) {
 		my $id = "git.$self->{git_dir}$batch.err";
 		my $fh = tmpfile($id) or $self->fail("tmpfile($id): $!");
 		$self->{$err} = $fh;
-		$redir->{2} = $fh;
+		$rdr->{2} = $fh;
 	}
-	my ($in_r, $p) = popen_rd(\@cmd, undef, $redir);
+	my ($in_r, $p) = popen_rd(\@cmd, undef, $rdr);
 	$self->{$pid} = $p;
 	$self->{"$pid.owner"} = $$;
 	$out_w->autoflush(1);
@@ -172,8 +179,8 @@ sub my_readline ($$) {
 	}
 }
 
-sub cat_async_retry ($$$$$) {
-	my ($self, $inflight, $req, $cb, $arg) = @_;
+sub cat_async_retry ($$) {
+	my ($self, $inflight) = @_;
 
 	# {inflight} may be non-existent, but if it isn't we delete it
 	# here to prevent cleanup() from waiting:
@@ -182,12 +189,13 @@ sub cat_async_retry ($$$$$) {
 
 	$self->{inflight} = $inflight;
 	batch_prepare($self);
-	my $buf = "$req\n";
+	my $buf = '';
 	for (my $i = 0; $i < @$inflight; $i += 3) {
 		$buf .= "$inflight->[$i]\n";
 	}
 	print { $self->{out} } $buf or $self->fail("write error: $!");
-	unshift(@$inflight, \$req, $cb, $arg); # \$ref to indicate retried
+	my $req = shift @$inflight;
+	unshift(@$inflight, \$req); # \$ref to indicate retried
 
 	cat_async_step($self, $inflight); # take one step
 }
@@ -195,8 +203,8 @@ sub cat_async_retry ($$$$$) {
 sub cat_async_step ($$) {
 	my ($self, $inflight) = @_;
 	die 'BUG: inflight empty or odd' if scalar(@$inflight) < 3;
-	my ($req, $cb, $arg) = splice(@$inflight, 0, 3);
-	my $rbuf = delete($self->{cat_rbuf}) // \(my $new = '');
+	my ($req, $cb, $arg) = @$inflight[0, 1, 2];
+	my $rbuf = delete($self->{rbuf}) // \(my $new = '');
 	my ($bref, $oid, $type, $size);
 	my $head = my_readline($self->{in}, $rbuf);
 	# ->fail may be called via Gcf2Client.pm
@@ -210,8 +218,7 @@ sub cat_async_step ($$) {
 		# ref($req) indicates it's already been retried
 		# -gcf2 retries internally, so it never hits this path:
 		if (!ref($req) && !$in_cleanup && $self->alternates_changed) {
-			return cat_async_retry($self, $inflight,
-						$req, $cb, $arg);
+			return cat_async_retry($self, $inflight);
 		}
 		$type = 'missing';
 		$oid = ref($req) ? $$req : $req if $oid eq '';
@@ -219,9 +226,10 @@ sub cat_async_step ($$) {
 		my $err = $! ? " ($!)" : '';
 		$self->fail("bad result from async cat-file: $head$err");
 	}
-	$self->{cat_rbuf} = $rbuf if $$rbuf ne '';
+	$self->{rbuf} = $rbuf if $$rbuf ne '';
+	splice(@$inflight, 0, 3); # don't retry $cb on ->fail
 	eval { $cb->($bref, $oid, $type, $size, $arg) };
-	warn "E: $oid: $@\n" if $@;
+	async_err($self, $req, $oid, $@, 'cat') if $@;
 }
 
 sub cat_async_wait ($) {
@@ -252,8 +260,8 @@ sub cat_file {
 sub check_async_step ($$) {
 	my ($self, $inflight_c) = @_;
 	die 'BUG: inflight empty or odd' if scalar(@$inflight_c) < 3;
-	my ($req, $cb, $arg) = splice(@$inflight_c, 0, 3);
-	my $rbuf = delete($self->{chk_rbuf}) // \(my $new = '');
+	my ($req, $cb, $arg) = @$inflight_c[0, 1, 2];
+	my $rbuf = delete($self->{rbuf_c}) // \(my $new = '');
 	chomp(my $line = my_readline($self->{in_c}, $rbuf));
 	my ($hex, $type, $size) = split(/ /, $line);
 
@@ -265,9 +273,10 @@ sub check_async_step ($$) {
 		my $ret = my_read($self->{in_c}, $rbuf, $type + 1);
 		$self->fail(defined($ret) ? 'read EOF' : "read: $!") if !$ret;
 	}
-	$self->{chk_rbuf} = $rbuf if $$rbuf ne '';
+	$self->{rbuf_c} = $rbuf if $$rbuf ne '';
+	splice(@$inflight_c, 0, 3); # don't retry $cb on ->fail
 	eval { $cb->($hex, $type, $size, $arg, $self) };
-	warn "E: check($req) $@\n" if $@;
+	async_err($self, $req, $hex, $@, 'check') if $@;
 }
 
 sub check_async_wait ($) {
@@ -327,27 +336,39 @@ sub _destroy {
 	dwaitpid($p) if $$ == $self->{"$pid.owner"};
 }
 
-sub cat_async_abort ($) {
+sub async_abort ($) {
 	my ($self) = @_;
-	if (my $inflight = $self->{inflight}) {
-		while (@$inflight) {
-			my ($req, $cb, $arg) = splice(@$inflight, 0, 3);
-			$req =~ s/ .*//; # drop git_dir for Gcf2Client
-			eval { $cb->(undef, $req, undef, undef, $arg) };
-			warn "E: $req: $@ (in abort)\n" if $@;
+	while (scalar(@{$self->{inflight_c} // []}) ||
+			scalar(@{$self->{inflight} // []})) {
+		for my $c ('', '_c') {
+			my $q = $self->{"inflight$c"};
+			while (@$q) {
+				my ($req, $cb, $arg) = splice(@$q, 0, 3);
+				$req = $$req if ref($req);
+				$req =~ s/ .*//; # drop git_dir for Gcf2Client
+				eval { $cb->(undef, $req, undef, undef, $arg) };
+				warn "E: (in abort) $req: $@" if $@;
+			}
+			delete $self->{"inflight$c"};
+			delete $self->{"rbuf$c"};
 		}
-		delete $self->{cat_rbuf};
-		delete $self->{inflight};
 	}
 	cleanup($self);
 }
 
 sub fail { # may be augmented in subclasses
 	my ($self, $msg) = @_;
-	cat_async_abort($self);
+	async_abort($self);
 	croak(ref($self) . ' ' . ($self->{git_dir} // '') . ": $msg");
 }
 
+sub async_err ($$$$$) {
+	my ($self, $req, $oid, $err, $action) = @_;
+	$req = $$req if ref($req); # retried
+	my $msg = "E: $action $req ($oid): $err";
+	$async_warn ? carp($msg) : $self->fail($msg);
+}
+
 # $git->popen(qw(show f00)); # or
 # $git->popen(qw(show f00), { GIT_CONFIG => ... }, { 2 => ... });
 sub popen {
@@ -385,25 +406,26 @@ sub async_wait_all ($) {
 	my ($self) = @_;
 	while (scalar(@{$self->{inflight_c} // []}) ||
 			scalar(@{$self->{inflight} // []})) {
-		$self->check_async_wait;
-		$self->cat_async_wait;
+		check_async_wait($self);
+		cat_async_wait($self);
 	}
 }
 
 # returns true if there are pending "git cat-file" processes
 sub cleanup {
-	my ($self) = @_;
+	my ($self, $lazy) = @_;
+	return 1 if $lazy && (scalar(@{$self->{inflight_c} // []}) ||
+				scalar(@{$self->{inflight} // []}));
 	local $in_cleanup = 1;
 	delete $self->{async_cat};
 	async_wait_all($self);
 	delete $self->{inflight};
 	delete $self->{inflight_c};
-	_destroy($self, qw(cat_rbuf in out pid));
-	_destroy($self, qw(chk_rbuf in_c out_c pid_c err_c));
-	!!($self->{pid} || $self->{pid_c});
+	_destroy($self, qw(rbuf in out pid));
+	_destroy($self, qw(rbuf_c in_c out_c pid_c err_c));
+	undef;
 }
 
-
 # assuming a well-maintained repo, this should be a somewhat
 # accurate estimation of its size
 # TODO: show this in the WWW UI as a hint to potential cloners
@@ -420,13 +442,8 @@ sub packed_bytes {
 sub DESTROY { cleanup(@_) }
 
 sub local_nick ($) {
-	my ($self) = @_;
-	my $ret = '???';
 	# don't show full FS path, basename should be OK:
-	if ($self->{git_dir} =~ m!/([^/]+)(?:/*\.git/*)?\z!) {
-		$ret = "$1.git";
-	}
-	wantarray ? ($ret) : $ret;
+	$_[0]->{git_dir} =~ m!/([^/]+?)(?:/*\.git/*)?\z! ? "$1.git" : '???';
 }
 
 sub host_prefix_url ($$) {
@@ -443,7 +460,7 @@ sub pub_urls {
 	if (my $urls = $self->{cgit_url}) {
 		return map { host_prefix_url($env, $_) } @$urls;
 	}
-	local_nick($self);
+	(local_nick($self));
 }
 
 sub cat_async_begin {
@@ -523,6 +540,28 @@ sub manifest_entry {
 	$ent;
 }
 
+# returns true if there are pending cat-file processes
+sub cleanup_if_unlinked {
+	my ($self) = @_;
+	return cleanup($self, 1) if $^O ne 'linux';
+	# Linux-specific /proc/$PID/maps access
+	# TODO: support this inside git.git
+	my $ret = 0;
+	for my $fld (qw(pid pid_c)) {
+		my $pid = $self->{$fld} // next;
+		open my $fh, '<', "/proc/$pid/maps" or return cleanup($self, 1);
+		while (<$fh>) {
+			# n.b. we do not restart for unlinked multi-pack-index
+			# since it's not too huge, and the startup cost may
+			# be higher.
+			/\.(?:idx|pack) \(deleted\)$/ and
+				return cleanup($self, 1);
+		}
+		++$ret;
+	}
+	$ret;
+}
+
 1;
 __END__
 =pod