searchidx: put all shard-related stuff in SearchIdxShard.pm

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

diff --git a/lib/PublicInbox/SearchIdxShard.pm b/lib/PublicInbox/SearchIdxShard.pm
index baf7352a3d9ca36c9c03e9e17da2a31cb1f15ab5..c0f8be8964939e5c95aa33b4894b0bde8cc05d40 100644 (file)
--- a/lib/PublicInbox/SearchIdxShard.pm
+++ b/lib/PublicInbox/SearchIdxShard.pm
@@ -1,7 +1,7 @@
 # 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.
+# Internal interface for a single Xapian shard in V2 inboxes.
 # See L<public-inbox-v2-format(5)> for more info on how we shard Xapian
 package PublicInbox::SearchIdxShard;
 use strict;
@@ -11,14 +11,14 @@ use IO::Handle (); # autoflush
 use PublicInbox::Eml;
 
 sub new {
-       my ($class, $v2writable, $shard) = @_;
-       my $ibx = $v2writable->{-inbox};
+       my ($class, $v2w, $shard) = @_;
+       my $ibx = $v2w->{ibx};
        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->idx_acquire;
+       $self->set_metadata_once;
+       $self->idx_release;
+       $self->spawn_worker($v2w, $shard) if $v2w->{parallel};
        $self;
 }
 
@@ -26,8 +26,6 @@ sub spawn_worker {
        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";
@@ -49,6 +47,7 @@ sub spawn_worker {
        close $r or die "failed to close: $!";
 }
 
+# this reads all the writes to $self->{w} from the parent process
 sub shard_worker_loop ($$$$$) {
        my ($self, $v2w, $r, $shard, $bnote) = @_;
        $0 = "pi-v2-shard[$shard]";
@@ -58,16 +57,14 @@ sub shard_worker_loop ($$$$$) {
                if ($line eq "commit\n") {
                        $self->commit_txn_lazy;
                } elsif ($line eq "close\n") {
-                       $self->_xdb_release;
+                       $self->idx_release;
                } elsif ($line eq "barrier\n") {
                        $self->commit_txn_lazy;
                        # no need to lock < 512 bytes is atomic under POSIX
                        print $bnote "barrier $shard\n" or
                                        die "write failed for barrier $!\n";
-               } elsif ($line =~ /\AD ([a-f0-9]{40,}) (.+)\n\z/s) {
-                       my ($oid, $mid) = ($1, $2);
-                       $self->begin_txn_lazy;
-                       $self->remove_by_oid($oid, $mid);
+               } elsif ($line =~ /\AD ([a-f0-9]{40,}) ([0-9]+)\n\z/s) {
+                       $self->remove_by_oid($1, $2 + 0);
                } else {
                        chomp $line;
                        # n.b. $mid may contain spaces(!)
@@ -91,18 +88,21 @@ sub shard_worker_loop ($$$$$) {
        $self->worker_done;
 }
 
-# called by V2Writable
 sub index_raw {
-       my ($self, $msgref, $mime, $smsg) = @_;
+       my ($self, $msgref, $eml, $smsg) = @_;
        if (my $w = $self->{w}) {
                # mid must be last, it can contain spaces (but not LF)
                print $w join(' ', @$smsg{qw(raw_bytes bytes
                                                num blob ds ts mid)}),
                        "\n", $$msgref or die "failed to write shard $!\n";
        } else {
-               $$msgref = undef;
+               if ($eml) {
+                       undef $$msgref;
+               } else { # --xapian-only + --sequential-shard:
+                       $eml = PublicInbox::Eml->new($msgref);
+               }
                $self->begin_txn_lazy;
-               $self->add_message($mime, $smsg);
+               $self->add_message($eml, $smsg);
        }
 }
 
@@ -110,8 +110,7 @@ sub atfork_child {
        close $_[0]->{w} or die "failed to close write pipe: $!\n";
 }
 
-# called by V2Writable:
-sub remote_barrier {
+sub shard_barrier {
        my ($self) = @_;
        if (my $w = $self->{w}) {
                print $w "barrier\n" or die "failed to print: $!";
@@ -120,4 +119,36 @@ sub remote_barrier {
        }
 }
 
+sub shard_commit {
+       my ($self) = @_;
+       if (my $w = $self->{w}) {
+               print $w "commit\n" or die "failed to write commit: $!";
+       } else {
+               $self->commit_txn_lazy;
+       }
+}
+
+sub shard_close {
+       my ($self) = @_;
+       if (my $w = delete $self->{w}) {
+               my $pid = delete $self->{pid} or die "no process to wait on\n";
+               print $w "close\n" or die "failed to write to pid:$pid: $!\n";
+               close $w or die "failed to close pipe for pid:$pid: $!\n";
+               waitpid($pid, 0) == $pid or die "remote process did not finish";
+               $? == 0 or die ref($self)." pid:$pid exited with: $?";
+       } else {
+               die "transaction in progress $self\n" if $self->{txn};
+               $self->idx_release if $self->{xdb};
+       }
+}
+
+sub shard_remove {
+       my ($self, $oid, $num) = @_;
+       if (my $w = $self->{w}) { # triggers remove_by_oid in a shard child
+               print $w "D $oid $num\n" or die "failed to write remove $!";
+       } else { # same process
+               $self->remove_by_oid($oid, $num);
+       }
+}
+
 1;