X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FGit.pm;h=181026c7bc1b726ff562e1b488f3256a0bf98c87;hb=b80dccff433cc529040e3c11604d76f669570511;hp=776e483291b61fc639aa6b4aac5a4b66ce8c350a;hpb=10ee3548084c125f20fe2c830faea2a43413be92;p=public-inbox.git

diff --git a/lib/PublicInbox/Git.pm b/lib/PublicInbox/Git.pm
index 776e4832..181026c7 100644
--- a/lib/PublicInbox/Git.pm
+++ b/lib/PublicInbox/Git.pm
@@ -8,15 +8,17 @@
 # There are also API changes to simplify our usage and data set.
 package PublicInbox::Git;
 use strict;
-use warnings;
+use v5.10.1;
+use parent qw(Exporter);
 use POSIX ();
 use IO::Handle; # ->autoflush
+use Errno qw(EINTR);
 use File::Glob qw(bsd_glob GLOB_NOSORT);
+use Time::HiRes qw(stat);
 use PublicInbox::Spawn qw(popen_rd);
 use PublicInbox::Tmpfile;
-use base qw(Exporter);
+use Carp qw(croak);
 our @EXPORT_OK = qw(git_unquote git_quote);
-use Errno qw(EINTR);
 our $PIPE_BUFSIZ = 65536; # Linux default
 our $in_cleanup;
 
@@ -230,26 +232,71 @@ sub cat_file {
 	$result->[0];
 }
 
-sub check {
-	my ($self, $obj) = @_;
-	_bidi_pipe($self, qw(--batch-check in_c out_c pid_c err_c));
-	print { $self->{out_c} } $obj, "\n" or fail($self, "write error: $!");
-	my $rbuf = ''; # TODO: async + {chk_rbuf}
-	chomp(my $line = my_readline($self->{in_c}, \$rbuf));
-	my ($hex, $type, $size) = split(' ', $line);
+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->{rbuf_c}) // \(my $new = '');
+	chomp(my $line = my_readline($self->{in_c}, $rbuf));
+	my ($hex, $type, $size) = split(/ /, $line);
 
-	# Future versions of git.git may show 'ambiguous', but for now,
+	# Future versions of git.git may have type=ambiguous, but for now,
 	# we must handle 'dangling' below (and maybe some other oddball
 	# stuff):
 	# https://public-inbox.org/git/20190118033845.s2vlrb3wd3m2jfzu@dcvr/T/
-	return if $type eq 'missing' || $type eq 'ambiguous';
-
 	if ($hex eq 'dangling' || $hex eq 'notdir' || $hex eq 'loop') {
-		my $ret = my_read($self->{in_c}, \$rbuf, $type + 1);
+		my $ret = my_read($self->{in_c}, $rbuf, $type + 1);
 		fail($self, defined($ret) ? 'read EOF' : "read: $!") if !$ret;
-		return;
 	}
+	eval { $cb->($hex, $type, $size, $arg, $self) };
+	warn "E: check($req) $@\n" if $@;
+	$self->{rbuf_c} = $rbuf if $$rbuf ne '';
+}
 
+sub check_async_wait ($) {
+	my ($self) = @_;
+	my $inflight_c = delete $self->{inflight_c} or return;
+	while (scalar(@$inflight_c)) {
+		check_async_step($self, $inflight_c);
+	}
+}
+
+sub check_async_begin ($) {
+	my ($self) = @_;
+	cleanup($self) if alternates_changed($self);
+	_bidi_pipe($self, qw(--batch-check in_c out_c pid_c err_c));
+	die 'BUG: already in async check' if $self->{inflight_c};
+	$self->{inflight_c} = [];
+}
+
+sub check_async ($$$$) {
+	my ($self, $oid, $cb, $arg) = @_;
+	my $inflight_c = $self->{inflight_c} // check_async_begin($self);
+	if (scalar(@$inflight_c) >= MAX_INFLIGHT) {
+		check_async_step($self, $inflight_c);
+	}
+	print { $self->{out_c} } $oid, "\n" or fail($self, "write error: $!");
+	push(@$inflight_c, $oid, $cb, $arg);
+}
+
+sub _check_cb { # check_async callback
+	my ($hex, $type, $size, $result) = @_;
+	@$result = ($hex, $type, $size);
+}
+
+sub check {
+	my ($self, $oid) = @_;
+	my $result = [];
+	check_async($self, $oid, \&_check_cb, $result);
+	check_async_wait($self);
+	my ($hex, $type, $size) = @$result;
+
+	# Future versions of git.git may show 'ambiguous', but for now,
+	# we must handle 'dangling' below (and maybe some other oddball
+	# stuff):
+	# https://public-inbox.org/git/20190118033845.s2vlrb3wd3m2jfzu@dcvr/T/
+	return if $type eq 'missing' || $type eq 'ambiguous';
+	return if $hex eq 'dangling' || $hex eq 'notdir' || $hex eq 'loop';
 	($hex, $type, $size);
 }
 
@@ -273,7 +320,7 @@ sub cat_async_abort ($) {
 sub fail {
 	my ($self, $msg) = @_;
 	$self->{inflight} ? cat_async_abort($self) : cleanup($self);
-	die $msg;
+	croak("git $self->{git_dir}: $msg");
 }
 
 sub popen {
@@ -296,6 +343,7 @@ sub cleanup {
 	my ($self) = @_;
 	local $in_cleanup = 1;
 	delete $self->{async_cat};
+	check_async_wait($self);
 	cat_async_wait($self);
 	_destroy($self, qw(cat_rbuf in out pid));
 	_destroy($self, qw(chk_rbuf in_c out_c pid_c err_c));
@@ -363,6 +411,22 @@ sub cat_async ($$$;$) {
 	push(@$inflight, $oid, $cb, $arg);
 }
 
+# this is safe to call inside $cb, but not guaranteed to enqueue
+# returns true if successful, undef if not.
+sub async_prefetch {
+	my ($self, $oid, $cb, $arg) = @_;
+	if (defined($self->{async_cat}) && (my $inflight = $self->{inflight})) {
+		# we could use MAX_INFLIGHT here w/o the halving,
+		# but lets not allow one client to monopolize a git process
+		if (scalar(@$inflight) < int(MAX_INFLIGHT/2)) {
+			print { $self->{out} } $oid, "\n" or
+						fail($self, "write error: $!");
+			return push(@$inflight, $oid, $cb, $arg);
+		}
+	}
+	undef;
+}
+
 sub extract_cmt_time {
 	my ($bref, undef, undef, undef, $modified) = @_;