No ext_urls

[public-inbox.git] / lib / PublicInbox / GitAsyncCat.pm

diff --git a/lib/PublicInbox/GitAsyncCat.pm b/lib/PublicInbox/GitAsyncCat.pm
index cea3f539234ab2cb3864865c2798c5e073a4ba8d..c428f6ef0a520851e209365289060decbe250d4a 100644 (file)
--- a/lib/PublicInbox/GitAsyncCat.pm
+++ b/lib/PublicInbox/GitAsyncCat.pm
@@ -1,14 +1,15 @@
-# Copyright (C) 2020-2021 all contributors <meta@public-inbox.org>
+# Copyright (C) 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"
 package PublicInbox::GitAsyncCat;
-use strict;
+use v5.12;
 use parent qw(PublicInbox::DS Exporter);
+use PublicInbox::DS qw(awaitpid);
 use POSIX qw(WNOHANG);
 use PublicInbox::Syscall qw(EPOLLIN EPOLLET);
-our @EXPORT = qw(ibx_async_cat ibx_async_prefetch);
+our @EXPORT = qw(ibx_async_cat ibx_async_prefetch async_check);
 use PublicInbox::Git ();
 
 our $GCF2C; # singleton PublicInbox::Gcf2Client
@@ -21,6 +22,8 @@ sub close {
        $self->SUPER::close; # PublicInbox::DS::close
 }
 
+sub aclose { $_[1]->close } # ignore PID ($_[0])
+
 sub event_step {
        my ($self) = @_;
        my $git = $self->{git} or return;
@@ -36,22 +39,28 @@ sub event_step {
                        # 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 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);
+               awaitpid($git->{pid}, \&aclose, $self);
+               \undef; # this is a true ref()
+       };
+}
+
 sub ibx_async_cat ($$$$) {
        my ($ibx, $oid, $cb, $arg) = @_;
-       my $git = $ibx->git;
+       my $git = $ibx->{git} // $ibx->git;
        # {topdir} means ExtSearch (likely [extindex "all"]) with potentially
        # 100K alternates.  git(1) has a proposed patch for 100K alternates:
        # <https://lore.kernel.org/git/20210624005806.12079-1-e@80x24.org/>
-       if (!defined($ibx->{topdir}) && ($GCF2C //= eval {
+       if (!defined($ibx->{topdir}) && !defined($git->{-tmp}) &&
+               ($GCF2C //= eval {
                require PublicInbox::Gcf2Client;
                PublicInbox::Gcf2Client::new();
        } // 0)) { # 0: do not retry if libgit2 or Inline::C are missing
@@ -59,35 +68,64 @@ sub ibx_async_cat ($$$$) {
                \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);
        }
 }
 
+sub async_check ($$$$) {
+       my ($ibx, $oidish, $cb, $arg) = @_; # $ibx may be $ctx
+       my $git = $ibx->{git} // $ibx->git;
+       $git->check_async($oidish, $cb, $arg);
+       return watch_cat($git) if $git->{-bc}; # --batch-command
+       $git->{async_chk} //= do {
+               my $self = bless { git => $git }, 'PublicInbox::GitAsyncCheck';
+               $git->{in_c}->blocking(0);
+               $self->SUPER::new($git->{in_c}, EPOLLIN|EPOLLET);
+               awaitpid($git->{pid_c}, \&aclose, $self);
+               \undef; # this is a true ref()
+       };
+}
+
 # this is safe to call inside $cb, but not guaranteed to enqueue
-# returns true if successful, undef if not.
+# returns true if successful, undef if not.  For fairness, we only
+# prefetch if there's no in-flight requests.
 sub ibx_async_prefetch {
        my ($ibx, $oid, $cb, $arg) = @_;
        my $git = $ibx->git;
        if (!defined($ibx->{topdir}) && $GCF2C) {
-               if (!$GCF2C->{wbuf}) {
+               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)) {
-                       print { $git->{out} } $oid, "\n" or
-                                               $git->fail("write error: $!");
-                       return push(@$inflight, $oid, $cb, $arg);
-               }
+       } elsif ($git->{async_cat}) {
+               return $git->async_prefetch($oid, $cb, $arg);
        }
        undef;
 }
 
 1;
+package PublicInbox::GitAsyncCheck;
+use v5.12;
+our @ISA = qw(PublicInbox::GitAsyncCat);
+use POSIX qw(WNOHANG);
+use PublicInbox::Syscall qw(EPOLLIN EPOLLET);
+
+sub event_step {
+       my ($self) = @_;
+       my $git = $self->{git} or return;
+       return $self->close if ($git->{in_c} // 0) != ($self->{sock} // 1);
+       my $inflight = $git->{inflight_c};
+       if ($inflight && @$inflight) {
+               $git->check_async_step($inflight);
+
+               # child death?
+               if (($git->{in_c} // 0) != ($self->{sock} // 1)) {
+                       $self->close;
+               } elsif (@$inflight || exists $git->{rbuf_c}) {
+                       # ok, more to do, requeue for fairness
+                       $self->requeue;
+               }
+       }
+}
+
+1;