treewide: replace /^I: / prefix with /^# /

[public-inbox.git] / lib / PublicInbox / Gcf2.pm

diff --git a/lib/PublicInbox/Gcf2.pm b/lib/PublicInbox/Gcf2.pm
index 64945ca69cff7fa3cec96539fad0ac0a8f9bfe9d..54b3d6aa17aa6487f6e42ff98f59627338e5bccd 100644 (file)
--- a/lib/PublicInbox/Gcf2.pm
+++ b/lib/PublicInbox/Gcf2.pm
@@ -1,4 +1,4 @@
-# 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>
 
 # backend for a git-cat-file-workalike based on libgit2,
@@ -8,13 +8,18 @@ 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 File::Path qw(make_path);
+use PublicInbox::Git;
+
 BEGIN {
        my (%CFG, $c_src);
        # PublicInbox::Spawn will set PERL_INLINE_DIRECTORY
        # to ~/.cache/public-inbox/inline-c if it exists
        my $inline_dir = $ENV{PERL_INLINE_DIRECTORY} //
                die 'PERL_INLINE_DIRECTORY not defined';
+       make_path($inline_dir);
        my $f = "$inline_dir/.public-inbox.lock";
        open my $fh, '+>', $f or die "open($f): $!";
 
@@ -77,7 +82,8 @@ 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
@@ -96,33 +102,54 @@ 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 (<STDIN>) {
                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 = ();
+                               }
+                       }
                }
        }
 }