treewide: shorten temporary filename

[public-inbox.git] / lib / PublicInbox / V2Writable.pm

diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 459c7e86eed189782c5b2c4517af5587fb7d8ee4..0461257feb7b483329d09f4b0e5e75f9b5913b0d 100644 (file)
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -8,6 +8,7 @@ use strict;
 use v5.10.1;
 use parent qw(PublicInbox::Lock);
 use PublicInbox::SearchIdxShard;
+use PublicInbox::IPC;
 use PublicInbox::Eml;
 use PublicInbox::Git;
 use PublicInbox::Import;
@@ -17,9 +18,11 @@ use PublicInbox::InboxWritable;
 use PublicInbox::OverIdx;
 use PublicInbox::Msgmap;
 use PublicInbox::Spawn qw(spawn popen_rd run_die);
+use PublicInbox::Search;
 use PublicInbox::SearchIdx qw(log2stack is_ancestor check_size is_bad_blob);
 use IO::Handle; # ->autoflush
 use File::Temp ();
+use POSIX ();
 
 my $OID = qr/[a-f0-9]{40,}/;
 # an estimate of the post-packed size to the raw uncompressed size
@@ -33,27 +36,13 @@ our $PACKING_FACTOR = 0.4;
 # to increase Xapian shards
 our $NPROC_MAX_DEFAULT = 4;
 
-sub detect_nproc () {
-       # getconf(1) is POSIX, but *NPROCESSORS* vars are not
-       for (qw(_NPROCESSORS_ONLN NPROCESSORS_ONLN)) {
-               `getconf $_ 2>/dev/null` =~ /^(\d+)$/ and return $1;
-       }
-       for my $nproc (qw(nproc gnproc)) { # GNU coreutils nproc
-               `$nproc 2>/dev/null` =~ /^(\d+)$/ and return $1;
-       }
-
-       # should we bother with `sysctl hw.ncpu`?  Those only give
-       # us total processor count, not online processor count.
-       undef
-}
-
 sub nproc_shards ($) {
        my ($creat_opt) = @_;
        my $n = $creat_opt->{nproc} if ref($creat_opt) eq 'HASH';
        $n //= $ENV{NPROC};
        if (!$n) {
                # assume 2 cores if not detectable or zero
-               state $NPROC_DETECTED = detect_nproc() || 2;
+               state $NPROC_DETECTED = PublicInbox::IPC::detect_nproc() || 2;
                $n = $NPROC_DETECTED;
                $n = $NPROC_MAX_DEFAULT if $n > $NPROC_MAX_DEFAULT;
        }
@@ -608,7 +597,11 @@ shard[$i] bad echo:$echo != $i waiting for txn commit
                }
 
                my $midx = $self->{midx}; # misc index
-               $midx->commit_txn if $midx;
+               if ($midx) {
+                       $midx->commit_txn;
+                       $PublicInbox::Search::X{CLOEXEC_UNSET} and
+                               $self->git->cleanup;
+               }
 
                # last_commit is special, don't commit these until
                # Xapian shards are done:
@@ -618,7 +611,6 @@ shard[$i] bad echo:$echo != $i waiting for txn commit
                        $dbh->commit;
                        $dbh->begin_work;
                }
-               $midx->begin_txn if $midx;
        }
        $self->{total_bytes} += $self->{transact_bytes};
        $self->{transact_bytes} = 0;
@@ -668,7 +660,7 @@ sub done {
 
 sub write_alternates ($$$) {
        my ($info_dir, $mode, $out) = @_;
-       my $fh = File::Temp->new(TEMPLATE => 'alt-XXXXXXXX', DIR => $info_dir);
+       my $fh = File::Temp->new(TEMPLATE => 'alt-XXXX', DIR => $info_dir);
        my $tmp = $fh->filename;
        print $fh @$out or die "print $tmp: $!\n";
        chmod($mode, $fh) or die "fchmod $tmp: $!\n";
@@ -780,11 +772,11 @@ sub import_init {
 sub diff ($$$) {
        my ($mid, $cur, $new) = @_;
 
-       my $ah = File::Temp->new(TEMPLATE => 'email-cur-XXXXXXXX', TMPDIR => 1);
+       my $ah = File::Temp->new(TEMPLATE => 'email-cur-XXXX', TMPDIR => 1);
        print $ah $cur->as_string or die "print: $!";
        $ah->flush or die "flush: $!";
        PublicInbox::Import::drop_unwanted_headers($new);
-       my $bh = File::Temp->new(TEMPLATE => 'email-new-XXXXXXXX', TMPDIR => 1);
+       my $bh = File::Temp->new(TEMPLATE => 'email-new-XXXX', TMPDIR => 1);
        print $bh $new->as_string or die "print: $!";
        $bh->flush or die "flush: $!";
        my $cmd = [ qw(diff -u), $ah->filename, $bh->filename ];
@@ -888,12 +880,16 @@ sub index_oid { # cat_async callback
        }
 
        # {unindexed} is unlikely
-       if ((my $unindexed = $arg->{unindexed}) && scalar(@$mids) == 1) {
-               $num = delete($unindexed->{$mids->[0]});
+       if (my $unindexed = $arg->{unindexed}) {
+               my $oidbin = pack('H*', $oid);
+               my $u = $unindexed->{$oidbin};
+               ($num, $mid0) = splice(@$u, 0, 2) if $u;
                if (defined $num) {
-                       $mid0 = $mids->[0];
                        $self->{mm}->mid_set($num, $mid0);
-                       delete($arg->{unindexed}) if !keys(%$unindexed);
+                       if (scalar(@$u) == 0) { # done with current OID
+                               delete $unindexed->{$oidbin};
+                               delete($arg->{unindexed}) if !keys(%$unindexed);
+                       }
                }
        }
        if (!defined($num)) { # reuse if reindexing (or duplicates)
@@ -1160,10 +1156,13 @@ sub unindex_oid ($$;$) { # git->cat_async callback
                        warn "BUG: multiple articles linked to $oid\n",
                                join(',',sort keys %gone), "\n";
                }
-               foreach my $num (keys %gone) {
+               # reuse (num => mid) mapping in ascending numeric order
+               for my $num (sort { $a <=> $b } keys %gone) {
+                       $num += 0;
                        if ($unindexed) {
                                my $mid0 = $mm->mid_for($num);
-                               $unindexed->{$mid0} = $num;
+                               my $oidbin = pack('H*', $oid);
+                               push @{$unindexed->{$oidbin}}, $num, $mid0;
                        }
                        $mm->num_delete($num);
                }
@@ -1179,7 +1178,7 @@ sub git { $_[0]->{ibx}->git }
 sub unindex_todo ($$$) {
        my ($self, $sync, $unit) = @_;
        my $unindex_range = delete($unit->{unindex_range}) // return;
-       my $unindexed = $sync->{unindexed} //= {}; # $mid0 => $num
+       my $unindexed = $sync->{unindexed} //= {}; # $oidbin => [$num, $mid0]
        my $before = scalar keys %$unindexed;
        # order does not matter, here:
        my $fh = $unit->{git}->popen(qw(log --raw -r --no-notes --no-color
@@ -1217,7 +1216,7 @@ sub sync_ranges ($$) {
 
 sub index_xap_only { # git->cat_async callback
        my ($bref, $oid, $type, $size, $smsg) = @_;
-       my $self = $smsg->{self};
+       my $self = delete $smsg->{self};
        my $idx = idx_shard($self, $smsg->{num});
        $idx->index_eml(PublicInbox::Eml->new($bref), $smsg);
        $self->{transact_bytes} += $smsg->{bytes};
@@ -1324,6 +1323,7 @@ sub xapian_only {
                }
        }
        $self->git->cat_async_wait;
+       $self->{ibx}->cleanup;
        $self->done;
 }