git: set non-blocking flag in case of other bugs

This makes GitAsyncCat more resilient to bugs in Gcf2 or even
git-cat-file itself.  I noticed -imapd stuck on read(2) from
the Gcf2 pipe, so there may be a bug somewhere in Gcf2 or
PublicInbox::Git.  This should make us more resilient to them
and hopefully help us notice and fix them.

diff --git a/lib/PublicInbox/Git.pm b/lib/PublicInbox/Git.pm
index 917fa4a16e96b76a4a45ebd560035a4bac1b78a4..d53427d770f19acc4360851c65243337e6767fb7 100644 (file)
--- a/lib/PublicInbox/Git.pm
+++ b/lib/PublicInbox/Git.pm
@@ -12,17 +12,19 @@ use v5.10.1;
 use parent qw(Exporter);
 use POSIX ();
 use IO::Handle; # ->autoflush
-use Errno qw(EINTR);
+use Errno qw(EINTR EAGAIN);
 use File::Glob qw(bsd_glob GLOB_NOSORT);
 use File::Spec ();
 use Time::HiRes qw(stat);
 use PublicInbox::Spawn qw(popen_rd);
 use PublicInbox::Tmpfile;
+use IO::Poll qw(POLLIN);
 use Carp qw(croak);
 use Digest::SHA ();
 our @EXPORT_OK = qw(git_unquote git_quote);
 our $PIPE_BUFSIZ = 65536; # Linux default
 our $in_cleanup;
+our $RDTIMEO = 60_000; # milliseconds
 
 use constant MAX_INFLIGHT =>
        (($^O eq 'linux' ? 4096 : POSIX::_POSIX_PIPE_BUF()) * 3)
@@ -132,6 +134,8 @@ sub _bidi_pipe {
        $self->{$in} = $in_r;
 }
 
+sub poll_in ($) { IO::Poll::_poll($RDTIMEO, fileno($_[0]), my $ev = POLLIN) }
+
 sub my_read ($$$) {
        my ($fh, $rbuf, $len) = @_;
        my $left = $len - length($$rbuf);
@@ -140,9 +144,12 @@ sub my_read ($$$) {
                $r = sysread($fh, $$rbuf, $PIPE_BUFSIZ, length($$rbuf));
                if ($r) {
                        $left -= $r;
+               } elsif (defined($r)) { # EOF
+                       return 0;
                } else {
-                       next if (!defined($r) && $! == EINTR);
-                       return $r;
+                       next if ($! == EAGAIN and poll_in($fh));
+                       next if $! == EINTR; # may be set by sysread or poll_in
+                       return; # unrecoverable error
                }
        }
        \substr($$rbuf, 0, $len, '');
@@ -154,9 +161,15 @@ sub my_readline ($$) {
                if ((my $n = index($$rbuf, "\n")) >= 0) {
                        return substr($$rbuf, 0, $n + 1, '');
                }
-               my $r = sysread($fh, $$rbuf, $PIPE_BUFSIZ, length($$rbuf));
-               next if $r || (!defined($r) && $! == EINTR);
-               return defined($r) ? '' : undef; # EOF or error
+               my $r = sysread($fh, $$rbuf, $PIPE_BUFSIZ, length($$rbuf))
+                                                               and next;
+
+               # return whatever's left on EOF
+               return substr($$rbuf, 0, length($$rbuf)+1, '') if defined($r);
+
+               next if ($! == EAGAIN and poll_in($fh));
+               next if $! == EINTR; # may be set by sysread or poll_in
+               return; # unrecoverable error
        }
 }
 
@@ -204,7 +217,8 @@ sub cat_async_step ($$) {
                $type = 'missing';
                $oid = ref($req) ? $$req : $req if $oid eq '';
        } else {
-               $self->fail("Unexpected result from async git cat-file: $head");
+               my $err = $! ? " ($!)" : '';
+               $self->fail("bad result from async cat-file: $head$err");
        }
        $self->{cat_rbuf} = $rbuf if $$rbuf ne '';
        eval { $cb->($bref, $oid, $type, $size, $arg) };

diff --git a/lib/PublicInbox/GitAsyncCat.pm b/lib/PublicInbox/GitAsyncCat.pm
index be51f673317eae824b85cc9f28f61aa9a221ad8a..dc97af16c09ed3e06ba1b727a5563dd3f32ea251 100644 (file)
--- a/lib/PublicInbox/GitAsyncCat.pm
+++ b/lib/PublicInbox/GitAsyncCat.pm
@@ -3,11 +3,6 @@
 #
 # 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);
@@ -69,6 +64,7 @@ sub git_async_cat ($$$$) {
        $gitish->{async_cat} //= do {
                # read-only end of pipe (Gcf2Client is write-only end)
                my $self = bless { gitish => $gitish }, __PACKAGE__;
+               $gitish->{in}->blocking(0);
                $self->SUPER::new($gitish->{in}, EPOLLIN|EPOLLET);
                \undef; # this is a true ref()
        };