X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FGitAsyncCat.pm;h=613dbf7e9966ed153c09144cc0a507ad03070eed;hb=6dec9bf8c0e1b859703d7a5dfb87052cf4e87846;hp=7d1a13dbb48bb11fa1b68f97a4f32a1a65ccd6e0;hpb=f87d3c32bace1552ab7f3a0437e5d6628d0ab5c5;p=public-inbox.git

diff --git a/lib/PublicInbox/GitAsyncCat.pm b/lib/PublicInbox/GitAsyncCat.pm
index 7d1a13db..613dbf7e 100644
--- a/lib/PublicInbox/GitAsyncCat.pm
+++ b/lib/PublicInbox/GitAsyncCat.pm
@@ -8,7 +8,7 @@ use strict;
 use parent qw(PublicInbox::DS Exporter);
 use POSIX qw(WNOHANG);
 use PublicInbox::Syscall qw(EPOLLIN EPOLLET);
-our @EXPORT = qw(git_async_cat git_async_prefetch);
+our @EXPORT = qw(ibx_async_cat ibx_async_prefetch);
 use PublicInbox::Git ();
 
 our $GCF2C; # singleton PublicInbox::Gcf2Client
@@ -16,7 +16,7 @@ our $GCF2C; # singleton PublicInbox::Gcf2Client
 sub close {
 	my ($self) = @_;
 	if (my $git = delete $self->{git}) {
-		$git->cat_async_abort;
+		$git->async_abort;
 	}
 	$self->SUPER::close; # PublicInbox::DS::close
 }
@@ -32,7 +32,7 @@ sub event_step {
 		# child death?
 		if (($git->{in} // 0) != ($self->{sock} // 1)) {
 			$self->close;
-		} elsif (@$inflight || exists $git->{cat_rbuf}) {
+		} elsif (@$inflight || exists $git->{rbuf}) {
 			# ok, more to do, requeue for fairness
 			$self->requeue;
 		}
@@ -45,38 +45,48 @@ sub event_step {
 	}
 }
 
-sub git_async_cat ($$$$) {
-	my ($git, $oid, $cb, $arg) = @_;
-	if ($GCF2C //= eval {
+sub watch_cat {
+	my ($git) = @_;
+	$git->{async_cat} //= do {
+		my $self = bless { git => $git }, __PACKAGE__;
+		$git->{in}->blocking(0);
+		$self->SUPER::new($git->{in}, EPOLLIN|EPOLLET);
+		\undef; # this is a true ref()
+	};
+}
+
+sub ibx_async_cat ($$$$) {
+	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
+	} // 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);
-		$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()
-		};
+		watch_cat($git);
 	}
 }
 
 # this is safe to call inside $cb, but not guaranteed to enqueue
-# returns true if successful, undef if not.
-sub git_async_prefetch {
-	my ($git, $oid, $cb, $arg) = @_;
-	if ($GCF2C) {
-		if (!$GCF2C->{wbuf}) {
+# returns true if successful, undef if not.  For fairness, we only
+# prefetch if there's no in-flight requests.
+sub ibx_async_prefetch {
+	my ($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 = $git->{inflight})) {
-		# we could use MAX_INFLIGHT here w/o the halving,
-		# but lets not allow one client to monopolize a git process
-		if (@$inflight < int(PublicInbox::Git::MAX_INFLIGHT/2)) {
+		if (!@$inflight) {
 			print { $git->{out} } $oid, "\n" or
 						$git->fail("write error: $!");
 			return push(@$inflight, $oid, $cb, $arg);