git: reduce stat buffer storage overhead

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

diff --git a/lib/PublicInbox/Git.pm b/lib/PublicInbox/Git.pm
index 9d0f660bae66a2afe63aef644dee08d38b660565..8410b2fce941d9d8b1e7f5b09557e97059a36146 100644 (file)
--- a/lib/PublicInbox/Git.pm
+++ b/lib/PublicInbox/Git.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2014-2020 all contributors <meta@public-inbox.org>
 # License: GPLv2 or later <https://www.gnu.org/licenses/gpl-2.0.txt>
 #
 # Used to read files from a git repository without excessive forking.
@@ -9,9 +9,10 @@
 package PublicInbox::Git;
 use strict;
 use warnings;
-use POSIX qw(dup2);
+use POSIX ();
 use IO::Handle; # ->autoflush
-use PublicInbox::Spawn qw(spawn popen_rd);
+use File::Glob qw(bsd_glob GLOB_NOSORT);
+use PublicInbox::Spawn qw(popen_rd);
 use PublicInbox::Tmpfile;
 use base qw(Exporter);
 our @EXPORT_OK = qw(git_unquote git_quote);
@@ -54,10 +55,8 @@ sub git_quote ($) {
 
 sub new {
        my ($class, $git_dir) = @_;
-       my @st;
-       $st[7] = $st[10] = 0;
        # may contain {-tmp} field for File::Temp::Dir
-       bless { git_dir => $git_dir, st => \@st, -git_path => {} }, $class
+       bless { git_dir => $git_dir, alt_st => '', -git_path => {} }, $class
 }
 
 sub git_path ($$) {
@@ -78,10 +77,11 @@ sub alternates_changed {
        my ($self) = @_;
        my $alt = git_path($self, 'objects/info/alternates');
        my @st = stat($alt) or return 0;
-       my $old_st = $self->{st};
-       # 10 - ctime, 7 - size
-       return 0 if ($st[10] == $old_st->[10] && $st[7] == $old_st->[7]);
-       $self->{st} = \@st;
+
+       # can't rely on 'q' on some 32-bit builds, but `d' works
+       my $st = pack('dd', $st[10], $st[7]); # 10: ctime, 7: size
+       return 0 if $self->{alt_st} eq $st;
+       $self->{alt_st} = $st; # always a true value
 }
 
 sub last_check_err {
@@ -103,28 +103,24 @@ sub _bidi_pipe {
                }
                return;
        }
-       my ($in_r, $in_w, $out_r, $out_w);
-
-       pipe($in_r, $in_w) or fail($self, "pipe failed: $!");
+       my ($out_r, $out_w);
        pipe($out_r, $out_w) or fail($self, "pipe failed: $!");
-       if ($^O eq 'linux') { # 1031: F_SETPIPE_SZ
-               fcntl($out_w, 1031, 4096);
-               fcntl($in_w, 1031, 4096) if $batch eq '--batch-check';
-       }
-
        my @cmd = (qw(git), "--git-dir=$self->{git_dir}",
                        qw(-c core.abbrev=40 cat-file), $batch);
-       my $redir = { 0 => $out_r, 1 => $in_w };
+       my $redir = { 0 => $out_r };
        if ($err) {
                my $id = "git.$self->{git_dir}$batch.err";
                my $fh = tmpfile($id) or fail($self, "tmpfile($id): $!");
                $self->{$err} = $fh;
                $redir->{2} = $fh;
        }
-       my $p = spawn(\@cmd, undef, $redir);
-       defined $p or fail($self, "spawn failed: $!");
+       my ($in_r, $p) = popen_rd(\@cmd, undef, $redir);
        $self->{$pid} = $p;
        $out_w->autoflush(1);
+       if ($^O eq 'linux') { # 1031: F_SETPIPE_SZ
+               fcntl($out_w, 1031, 4096);
+               fcntl($in_r, 1031, 4096) if $batch eq '--batch-check';
+       }
        $self->{$out} = $out_w;
        $self->{$in} = $in_r;
 }
@@ -256,7 +252,6 @@ sub popen {
 sub qx {
        my ($self, @cmd) = @_;
        my $fh = $self->popen(@cmd);
-       defined $fh or return;
        local $/ = "\n";
        return <$fh> if wantarray;
        local $/;
@@ -278,7 +273,7 @@ sub packed_bytes {
        my ($self) = @_;
        my $n = 0;
        my $pack_dir = git_path($self, 'objects/pack');
-       foreach my $p (glob("$pack_dir/*.pack")) {
+       foreach my $p (bsd_glob("$pack_dir/*.pack", GLOB_NOSORT)) {
                $n += -s $p;
        }
        $n
@@ -332,13 +327,6 @@ sub cat_async ($$$;$) {
        push(@$inflight, [ $cb, $arg ]);
 }
 
-sub commit_title ($$) {
-       my ($self, $oid) = @_; # PublicInbox::Git, $sha1hex
-       my $buf = cat_file($self, $oid) or return;
-       utf8::decode($$buf);
-       ($$buf =~ /\r?\n\r?\n([^\r\n]+)\r?\n?/)[0]
-}
-
 sub extract_cmt_time {
        my ($bref, undef, undef, undef, $modified) = @_;
 
@@ -354,10 +342,9 @@ sub modified ($) {
        my ($self) = @_;
        my $modified = 0;
        my $fh = popen($self, qw(rev-parse --branches));
-       defined $fh or return $modified;
        cat_async_begin($self);
        local $/ = "\n";
-       foreach my $oid (<$fh>) {
+       while (my $oid = <$fh>) {
                chomp $oid;
                cat_async($self, $oid, \&extract_cmt_time, \$modified);
        }