searchidxshard: ensure we set indexlevel on shard[0]

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

diff --git a/lib/PublicInbox/SearchIdxShard.pm b/lib/PublicInbox/SearchIdxShard.pm
index 15ec6578e67ee9190a246d27e40677ca233f8b2e..1ea01095c4fa6829fd6dc914cefdb0da3dc23f24 100644 (file)
--- a/lib/PublicInbox/SearchIdxShard.pm
+++ b/lib/PublicInbox/SearchIdxShard.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # used to interface with a single Xapian shard in V2 repos.
@@ -7,35 +7,38 @@ package PublicInbox::SearchIdxShard;
 use strict;
 use warnings;
 use base qw(PublicInbox::SearchIdx);
+use IO::Handle (); # autoflush
 
 sub new {
        my ($class, $v2writable, $shard) = @_;
-       my $self = $class->SUPER::new($v2writable->{-inbox}, 1, $shard);
+       my $ibx = $v2writable->{-inbox};
+       my $self = $class->SUPER::new($ibx, 1, $shard);
        # create the DB before forking:
        $self->_xdb_acquire;
+       $self->set_indexlevel;
        $self->_xdb_release;
        $self->spawn_worker($v2writable, $shard) if $v2writable->{parallel};
        $self;
 }
 
 sub spawn_worker {
-       my ($self, $v2writable, $shard) = @_;
+       my ($self, $v2w, $shard) = @_;
        my ($r, $w);
        pipe($r, $w) or die "pipe failed: $!\n";
        binmode $r, ':raw';
        binmode $w, ':raw';
+       $w->autoflush(1);
        my $pid = fork;
        defined $pid or die "fork failed: $!\n";
        if ($pid == 0) {
-               my $bnote = $v2writable->atfork_child;
-               $v2writable = undef;
+               my $bnote = $v2w->atfork_child;
                close $w or die "failed to close: $!";
 
                # F_SETPIPE_SZ = 1031 on Linux; increasing the pipe size here
                # speeds V2Writable batch imports across 8 cores by nearly 20%
                fcntl($r, 1031, 1048576) if $^O eq 'linux';
 
-               eval { shard_worker_loop($self, $r, $shard, $bnote) };
+               eval { shard_worker_loop($self, $v2w, $r, $shard, $bnote) };
                die "worker $shard died: $@\n" if $@;
                die "unexpected MM $self->{mm}" if $self->{mm};
                exit;
@@ -45,18 +48,12 @@ sub spawn_worker {
        close $r or die "failed to close: $!";
 }
 
-sub shard_worker_loop ($$$$) {
-       my ($self, $r, $shard, $bnote) = @_;
+sub shard_worker_loop ($$$$$) {
+       my ($self, $v2w, $r, $shard, $bnote) = @_;
        $0 = "pi-v2-shard[$shard]";
-       my $current_info = '';
-       my $warn_cb = $SIG{__WARN__} || sub { print STDERR @_ };
-       local $SIG{__WARN__} = sub {
-               chomp $current_info;
-               $warn_cb->("[$shard] $current_info: ", @_);
-       };
        $self->begin_txn_lazy;
        while (my $line = $r->getline) {
-               $current_info = $line;
+               $v2w->{current_info} = "[$shard] $line";
                if ($line eq "commit\n") {
                        $self->commit_txn_lazy;
                } elsif ($line eq "close\n") {
@@ -72,13 +69,21 @@ sub shard_worker_loop ($$$$) {
                        $self->remove_by_oid($oid, $mid);
                } else {
                        chomp $line;
-                       my ($len, $artnum, $oid, $mid0) = split(/ /, $line);
+                       my ($bytes, $num, $blob, $mid, $ds, $ts) =
+                                                       split(/ /, $line);
                        $self->begin_txn_lazy;
-                       my $n = read($r, my $msg, $len) or die "read: $!\n";
-                       $n == $len or die "short read: $n != $len\n";
+                       my $n = read($r, my $msg, $bytes) or die "read: $!\n";
+                       $n == $bytes or die "short read: $n != $bytes\n";
                        my $mime = PublicInbox::MIME->new(\$msg);
-                       $artnum = int($artnum);
-                       $self->add_message($mime, $n, $artnum, $oid, $mid0);
+                       my $smsg = bless {
+                               bytes => $bytes,
+                               num => $num + 0,
+                               blob => $blob,
+                               mid => $mid,
+                               ds => $ds,
+                               ts => $ts,
+                       }, 'PublicInbox::Smsg';
+                       $self->add_message($mime, $smsg);
                }
        }
        $self->worker_done;
@@ -86,15 +91,14 @@ sub shard_worker_loop ($$$$) {
 
 # called by V2Writable
 sub index_raw {
-       my ($self, $bytes, $msgref, $artnum, $oid, $mid0, $mime) = @_;
+       my ($self, $msgref, $mime, $smsg) = @_;
        if (my $w = $self->{w}) {
-               print $w "$bytes $artnum $oid $mid0\n", $$msgref or die
-                       "failed to write shard $!\n";
-               $w->flush or die "failed to flush: $!\n";
+               print $w join(' ', @$smsg{qw(bytes num blob mid ds ts)}),
+                       "\n", $$msgref or die "failed to write shard $!\n";
        } else {
                $$msgref = undef;
                $self->begin_txn_lazy;
-               $self->add_message($mime, $bytes, $artnum, $oid, $mid0);
+               $self->add_message($mime, $smsg);
        }
 }
 
@@ -107,7 +111,6 @@ sub remote_barrier {
        my ($self) = @_;
        if (my $w = $self->{w}) {
                print $w "barrier\n" or die "failed to print: $!";
-               $w->flush or die "failed to flush: $!";
        } else {
                $self->commit_txn_lazy;
        }