X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FGcf2.pm;h=d13e6b1a2a6cc1a11582a90c1931ab1016a8e281;hb=refs%2Fheads%2Fmaster;hp=0d31b01462a7dfb486f5e6f072bc248fc5a3c363;hpb=dacde5e35071579fb25c3f5276355ec76c840151;p=public-inbox.git
diff --git a/lib/PublicInbox/Gcf2.pm b/lib/PublicInbox/Gcf2.pm
index 0d31b014..d13e6b1a 100644
--- a/lib/PublicInbox/Gcf2.pm
+++ b/lib/PublicInbox/Gcf2.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2020-2021 all contributors
+# Copyright (C) all contributors
# License: AGPL-3.0+
# backend for a git-cat-file-workalike based on libgit2,
@@ -8,45 +8,55 @@ use strict;
use v5.10.1;
use PublicInbox::Spawn qw(which popen_rd); # may set PERL_INLINE_DIRECTORY
use Fcntl qw(LOCK_EX SEEK_SET);
+use Time::HiRes qw(clock_gettime CLOCK_MONOTONIC);
use IO::Handle; # autoflush
+use PublicInbox::Git;
+
BEGIN {
my (%CFG, $c_src);
# PublicInbox::Spawn will set PERL_INLINE_DIRECTORY
- # to ~/.cache/public-inbox/inline-c if it exists
+ # to ~/.cache/public-inbox/inline-c if it exists and Inline::C works
my $inline_dir = $ENV{PERL_INLINE_DIRECTORY} //
die 'PERL_INLINE_DIRECTORY not defined';
my $f = "$inline_dir/.public-inbox.lock";
open my $fh, '+>', $f or die "open($f): $!";
+
+ # CentOS 7.x ships Inline 0.53, 0.64+ has built-in locking
+ flock($fh, LOCK_EX) or die "LOCK_EX($f): $!\n";
+
my $pc = which($ENV{PKG_CONFIG} // 'pkg-config') //
die "pkg-config missing for libgit2";
my ($dir) = (__FILE__ =~ m!\A(.+?)/[^/]+\z!);
- my $rdr = {};
- open $rdr->{2}, '>', '/dev/null' or die "open /dev/null: $!";
+ my $ef = "$inline_dir/.public-inbox.pkg-config.err";
+ open my $err, '+>', $ef or die "open($ef): $!";
for my $x (qw(libgit2)) {
- my $l = popen_rd([$pc, '--libs', $x], undef, $rdr);
+ my $rdr = { 2 => $err };
+ my ($l, $pid) = popen_rd([$pc, '--libs', $x], undef, $rdr);
$l = do { local $/; <$l> };
+ waitpid($pid, 0);
next if $?;
- my $c = popen_rd([$pc, '--cflags', $x], undef, $rdr);
+ (my $c, $pid) = popen_rd([$pc, '--cflags', $x], undef, $rdr);
$c = do { local $/; <$c> };
+ waitpid($pid, 0);
next if $?;
# note: we name C source files .h to prevent
# ExtUtils::MakeMaker from automatically trying to
# build them.
my $f = "$dir/gcf2_$x.h";
- if (open(my $fh, '<', $f)) {
- chomp($l, $c);
- local $/;
- defined($c_src = <$fh>) or die "read $f: $!";
- $CFG{LIBS} = $l;
- $CFG{CCFLAGSEX} = $c;
- last;
- } else {
- die "E: $f: $!";
- }
+ open(my $src, '<', $f) or die "E: open($f): $!";
+ chomp($l, $c);
+ local $/;
+ defined($c_src = <$src>) or die "read $f: $!";
+ $CFG{LIBS} = $l;
+ $CFG{CCFLAGSEX} = $c;
+ last;
+ }
+ unless ($c_src) {
+ seek($err, 0, SEEK_SET);
+ $err = do { local $/; <$err> };
+ die "E: libgit2 not installed: $err\n";
}
- die "E: libgit2 not installed\n" unless $c_src;
-
open my $oldout, '>&', \*STDOUT or die "dup(1): $!";
open my $olderr, '>&', \*STDERR or die "dup(2): $!";
open STDOUT, '>&', $fh or die "1>$f: $!";
@@ -54,14 +64,12 @@ BEGIN {
STDERR->autoflush(1);
STDOUT->autoflush(1);
- # CentOS 7.x ships Inline 0.53, 0.64+ has built-in locking
- flock($fh, LOCK_EX) or die "LOCK_EX($f): $!\n";
# we use Capitalized and ALLCAPS for compatibility with old Inline::C
eval <<'EOM';
use Inline C => Config => %CFG, BOOT => q[git_libgit2_init();];
use Inline C => $c_src, BUILD_NOISY => 1;
EOM
- my $err = $@;
+ $err = $@;
open(STDERR, '>&', $olderr) or warn "restore stderr: $!";
open(STDOUT, '>&', $oldout) or warn "restore stdout: $!";
if ($err) {
@@ -72,7 +80,8 @@ EOM
}
sub add_alt ($$) {
- my ($gcf2, $objdir) = @_;
+ my ($gcf2, $git_dir) = @_;
+ my $objdir = PublicInbox::Git->new($git_dir)->git_path('objects');
# libgit2 (tested 0.27.7+dfsg.1-0.2 and 0.28.3+dfsg.1-1~bpo10+1
# in Debian) doesn't handle relative epochs properly when nested
@@ -91,33 +100,54 @@ sub add_alt ($$) {
1;
}
-# Usage: $^X -MPublicInbox::Gcf2 -e PublicInbox::Gcf2::loop
+sub have_unlinked_files () {
+ # FIXME: port gcf2-like over to git.git so we won't need to
+ # deal with libgit2
+ return 1 if $^O ne 'linux';
+ open my $fh, '<', "/proc/$$/maps" or return;
+ while (<$fh>) { return 1 if /\.(?:idx|pack) \(deleted\)$/ }
+ undef;
+}
+
+# Usage: $^X -MPublicInbox::Gcf2 -e PublicInbox::Gcf2::loop [EXPIRE-TIMEOUT]
# (see lib/PublicInbox/Gcf2Client.pm)
-sub loop () {
+sub loop (;$) {
+ my $exp = $_[0] || $ARGV[0] || 60; # seconds
my $gcf2 = new();
- my %seen;
+ my (%seen, $check_at);
STDERR->autoflush(1);
STDOUT->autoflush(1);
while () {
chomp;
my ($oid, $git_dir) = split(/ /, $_, 2);
- $seen{$git_dir} //= add_alt($gcf2, "$git_dir/objects");
+ $seen{$git_dir} //= add_alt($gcf2, $git_dir);
if (!$gcf2->cat_oid(1, $oid)) {
# retry once if missing. We only get unabbreviated OIDs
# from SQLite or Xapian DBs, here, so malicious clients
# can't trigger excessive retries:
- warn "I: $$ $oid missing, retrying in $git_dir\n";
+ warn "# $$ $oid missing, retrying in $git_dir\n";
$gcf2 = new();
- %seen = ($git_dir => add_alt($gcf2,"$git_dir/objects"));
+ %seen = ($git_dir => add_alt($gcf2, $git_dir));
+ $check_at = clock_gettime(CLOCK_MONOTONIC) + $exp;
if ($gcf2->cat_oid(1, $oid)) {
- warn "I: $$ $oid found after retry\n";
+ warn "# $$ $oid found after retry\n";
} else {
warn "W: $$ $oid missing after retry\n";
print "$oid missing\n"; # mimic git-cat-file
}
+ } else { # check expiry to deal with deleted pack files
+ my $now = clock_gettime(CLOCK_MONOTONIC);
+ $check_at //= $now + $exp;
+ if ($now > $check_at) {
+ undef $check_at;
+ if (have_unlinked_files()) {
+ $gcf2 = new();
+ %seen = ();
+ }
+ }
}
}
}