X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FGitAsyncCat.pm;h=613dbf7e9966ed153c09144cc0a507ad03070eed;hb=6dec9bf8c0e1b859703d7a5dfb87052cf4e87846;hp=8a54c608d7e1a87fa34c58e53822ca8bb1d8114f;hpb=881a5493a8c970c10c051cc55d10d2968e71e691;p=public-inbox.git

diff --git a/lib/PublicInbox/GitAsyncCat.pm b/lib/PublicInbox/GitAsyncCat.pm
index 8a54c608..613dbf7e 100644
--- a/lib/PublicInbox/GitAsyncCat.pm
+++ b/lib/PublicInbox/GitAsyncCat.pm
@@ -1,44 +1,98 @@
-# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2020-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # internal class used by PublicInbox::Git + PublicInbox::DS
 # This parses the output pipe of "git cat-file --batch"
-#
-# Note: this does NOT set the non-blocking flag, we expect `git cat-file'
-# to be a local process, and git won't start writing a blob until it's
-# fully read.  So minimize context switching and read as much as possible
-# and avoid holding a buffer in our heap any longer than it has to live.
 package PublicInbox::GitAsyncCat;
 use strict;
 use parent qw(PublicInbox::DS Exporter);
+use POSIX qw(WNOHANG);
 use PublicInbox::Syscall qw(EPOLLIN EPOLLET);
-our @EXPORT = qw(git_async_cat);
+our @EXPORT = qw(ibx_async_cat ibx_async_prefetch);
+use PublicInbox::Git ();
+
+our $GCF2C; # singleton PublicInbox::Gcf2Client
+
+sub close {
+	my ($self) = @_;
+	if (my $git = delete $self->{git}) {
+		$git->async_abort;
+	}
+	$self->SUPER::close; # PublicInbox::DS::close
+}
 
 sub event_step {
 	my ($self) = @_;
-	my $gitish = $self->{gitish};
-	return $self->close if ($gitish->{in} // 0) != ($self->{sock} // 1);
-	my $inflight = $gitish->{inflight};
+	my $git = $self->{git} or return;
+	return $self->close if ($git->{in} // 0) != ($self->{sock} // 1);
+	my $inflight = $git->{inflight};
 	if ($inflight && @$inflight) {
-		$gitish->cat_async_step($inflight);
-		$self->requeue if @$inflight || exists $gitish->{cat_rbuf};
+		$git->cat_async_step($inflight);
+
+		# child death?
+		if (($git->{in} // 0) != ($self->{sock} // 1)) {
+			$self->close;
+		} elsif (@$inflight || exists $git->{rbuf}) {
+			# ok, more to do, requeue for fairness
+			$self->requeue;
+		}
+	} elsif ((my $pid = waitpid($git->{pid}, WNOHANG)) > 0) {
+		# May happen if the child process is killed by a BOFH
+		# (or segfaults)
+		delete $git->{pid};
+		warn "E: git $pid exited with \$?=$?\n";
+		$self->close;
 	}
 }
 
-sub git_async_cat ($$$$) {
-	my ($git, $oid, $cb, $arg) = @_;
-	my $gitish = $git->{gcf2c}; # PublicInbox::Gcf2Client
-	if ($gitish) {
-		$oid .= " $git->{git_dir}";
-	} else {
-		$gitish = $git;
-	}
-	$gitish->cat_async($oid, $cb, $arg);
-	$gitish->{async_cat} //= do {
-		my $self = bless { gitish => $gitish }, __PACKAGE__;
-		$self->SUPER::new($gitish->{in}, EPOLLIN|EPOLLET);
+sub watch_cat {
+	my ($git) = @_;
+	$git->{async_cat} //= do {
+		my $self = bless { git => $git }, __PACKAGE__;
+		$git->{in}->blocking(0);
+		$self->SUPER::new($git->{in}, EPOLLIN|EPOLLET);
 		\undef; # this is a true ref()
 	};
 }
 
+sub ibx_async_cat ($$$$) {
+	my ($ibx, $oid, $cb, $arg) = @_;
+	my $git = $ibx->{git} // $ibx->git;
+	# {topdir} means ExtSearch (likely [extindex "all"]) with potentially
+	# 100K alternates.  git(1) has a proposed patch for 100K alternates:
+	# <https://lore.kernel.org/git/20210624005806.12079-1-e@80x24.org/>
+	if (!defined($ibx->{topdir}) && !defined($git->{-tmp}) &&
+		($GCF2C //= eval {
+		require PublicInbox::Gcf2Client;
+		PublicInbox::Gcf2Client::new();
+	} // 0)) { # 0: do not retry if libgit2 or Inline::C are missing
+		$GCF2C->gcf2_async(\"$oid $git->{git_dir}\n", $cb, $arg);
+		\undef;
+	} else { # read-only end of git-cat-file pipe
+		$git->cat_async($oid, $cb, $arg);
+		watch_cat($git);
+	}
+}
+
+# this is safe to call inside $cb, but not guaranteed to enqueue
+# returns true if successful, undef if not.  For fairness, we only
+# prefetch if there's no in-flight requests.
+sub ibx_async_prefetch {
+	my ($ibx, $oid, $cb, $arg) = @_;
+	my $git = $ibx->git;
+	if (!defined($ibx->{topdir}) && $GCF2C) {
+		if (!@{$GCF2C->{inflight} // []}) {
+			$oid .= " $git->{git_dir}\n";
+			return $GCF2C->gcf2_async(\$oid, $cb, $arg); # true
+		}
+	} elsif ($git->{async_cat} && (my $inflight = $git->{inflight})) {
+		if (!@$inflight) {
+			print { $git->{out} } $oid, "\n" or
+						$git->fail("write error: $!");
+			return push(@$inflight, $oid, $cb, $arg);
+		}
+	}
+	undef;
+}
+
 1;