Merge remote-tracking branch 'origin/purge'

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

diff --git a/lib/PublicInbox/Git.pm b/lib/PublicInbox/Git.pm
index b655921b00f06e1ef3be428901b1919abe2fbeba..a756684a70355b6435b26b753f1dc6593e5481fa 100644 (file)
--- a/lib/PublicInbox/Git.pm
+++ b/lib/PublicInbox/Git.pm
@@ -50,13 +50,22 @@ sub new {
        my ($class, $git_dir) = @_;
        my @st;
        $st[7] = $st[10] = 0;
-       # may contain {-wt} field (working-tree (File::Temp::Dir))
-       bless { git_dir => $git_dir, st => \@st }, $class
+       # may contain {-tmp} field for File::Temp::Dir
+       bless { git_dir => $git_dir, st => \@st, -git_path => {} }, $class
+}
+
+sub git_path ($$) {
+       my ($self, $path) = @_;
+       $self->{-git_path}->{$path} ||= do {
+               local $/ = "\n";
+               chomp(my $str = $self->qx(qw(rev-parse --git-path), $path));
+               $str;
+       };
 }
 
 sub alternates_changed {
        my ($self) = @_;
-       my $alt = "$self->{git_dir}/objects/info/alternates";
+       my $alt = git_path($self, 'objects/info/alternates');
        my @st = stat($alt) or return 0;
        my $old_st = $self->{st};
        # 10 - ctime, 7 - size
@@ -179,11 +188,13 @@ sub check {
        local $/ = "\n";
        chomp(my $line = $self->{in_c}->getline);
        my ($hex, $type, $size) = split(' ', $line);
-       return if $type eq 'missing';
 
-       # "dead" in git.git shows "dangling 4\ndead\n", not sure why
-       # https://public-inbox.org/git/20190118033845.s2vlrb3wd3m2jfzu@dcvr/
-       # so handle the oddball stuff just in case
+       # 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' || $type eq 'ambiguous';
+
        if ($hex eq 'dangling' || $hex eq 'notdir' || $hex eq 'loop') {
                $size = $type + length("\n");
                my $r = read($self->{in_c}, my $buf, $size);
@@ -195,7 +206,15 @@ sub check {
 }
 
 sub _destroy {
-       my ($self, $in, $out, $pid) = @_;
+       my ($self, $in, $out, $pid, $expire) = @_;
+       my $rfh = $self->{$in} or return;
+       if (defined $expire) {
+               # at least FreeBSD 11.2 and Linux 4.20 update mtime of the
+               # read end of a pipe when the pipe is written to; dunno
+               # about other OSes.
+               my $mtime = (stat($rfh))[9];
+               return if $mtime > $expire;
+       }
        my $p = delete $self->{$pid} or return;
        foreach my $f ($in, $out) {
                delete $self->{$f};
@@ -225,10 +244,12 @@ sub qx {
        <$fh>
 }
 
+# returns true if there are pending "git cat-file" processes
 sub cleanup {
-       my ($self) = @_;
-       _destroy($self, qw(in out pid));
-       _destroy($self, qw(in_c out_c pid_c));
+       my ($self, $expire) = @_;
+       _destroy($self, qw(in out pid), $expire);
+       _destroy($self, qw(in_c out_c pid_c), $expire);
+       !!($self->{pid} || $self->{pid_c});
 }
 
 # assuming a well-maintained repo, this should be a somewhat
@@ -237,7 +258,8 @@ sub cleanup {
 sub packed_bytes {
        my ($self) = @_;
        my $n = 0;
-       foreach my $p (glob("$self->{git_dir}/objects/pack/*.pack")) {
+       my $pack_dir = git_path($self, 'objects/pack');
+       foreach my $p (glob("$pack_dir/*.pack")) {
                $n += -s $p;
        }
        $n