# 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;
-use warnings;
-use base qw(PublicInbox::SearchIdx);
+use v5.10.1;
+use parent qw(PublicInbox::SearchIdx);
use IO::Handle (); # autoflush
+use PublicInbox::Eml;
sub new {
- my ($class, $v2writable, $shard) = @_;
- my $self = $class->SUPER::new($v2writable->{-inbox}, 1, $shard);
+ my ($class, $v2w, $shard) = @_;
+ my $ibx = $v2w->{ibx};
+ my $self = $class->SUPER::new($ibx, 1, $shard);
# create the DB before forking:
- $self->_xdb_acquire;
- $self->_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};
$self;
}
my ($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";
close $r or die "failed to close: $!";
}
+# this reads all the writes to $self->{w} from the parent process
sub shard_worker_loop ($$$$$) {
my ($self, $v2w, $r, $shard, $bnote) = @_;
$0 = "pi-v2-shard[$shard]";
$self->begin_txn_lazy;
- while (my $line = $r->getline) {
+ while (my $line = readline($r)) {
$v2w->{current_info} = "[$shard] $line";
if ($line eq "commit\n") {
$self->commit_txn_lazy;
} elsif ($line eq "close\n") {
- $self->_xdb_release;
+ $self->idx_release;
} elsif ($line eq "barrier\n") {
$self->commit_txn_lazy;
# no need to lock < 512 bytes is atomic under POSIX
print $bnote "barrier $shard\n" or
die "write failed for barrier $!\n";
- } elsif ($line =~ /\AD ([a-f0-9]{40,}) (.+)\n\z/s) {
- my ($oid, $mid) = ($1, $2);
- $self->begin_txn_lazy;
- $self->remove_by_oid($oid, $mid);
+ } elsif ($line =~ /\AD ([a-f0-9]{40,}) ([0-9]+)\n\z/s) {
+ $self->remove_by_oid($1, $2 + 0);
} else {
chomp $line;
- my ($len, $artnum, $oid, $mid0, $autime, $cotime) =
- split(/ /, $line);
+ # n.b. $mid may contain spaces(!)
+ my ($to_read, $bytes, $num, $blob, $ds, $ts, $tid, $mid)
+ = split(/ /, $line, 8);
$self->begin_txn_lazy;
- my $n = read($r, my $msg, $len) or die "read: $!\n";
- $n == $len or die "short read: $n != $len\n";
- my $mime = PublicInbox::MIME->new(\$msg);
- $artnum = int($artnum);
- $self->{autime} = $autime;
- $self->{cotime} = $cotime;
+ my $n = read($r, my $msg, $to_read) or die "read: $!\n";
+ $n == $to_read or die "short read: $n != $to_read\n";
+ my $mime = PublicInbox::Eml->new(\$msg);
my $smsg = bless {
- bytes => $len,
- num => $artnum,
- blob => $oid,
- mid => $mid0,
+ bytes => $bytes,
+ num => $num + 0,
+ blob => $blob,
+ mid => $mid,
+ tid => $tid,
+ ds => $ds,
+ ts => $ts,
}, 'PublicInbox::Smsg';
$self->add_message($mime, $smsg);
}
$self->worker_done;
}
-# called by V2Writable
sub index_raw {
- my ($self, $bytes, $msgref, $artnum, $oid, $mid0, $mime, $times) = @_;
- my $at = $times->{autime} // time;
- my $ct = $times->{cotime} // time;
+ my ($self, $msgref, $eml, $smsg) = @_;
if (my $w = $self->{w}) {
- print $w "$bytes $artnum $oid $mid0 $at $ct\n", $$msgref or
- die "failed to write shard $!\n";
+ # mid must be last, it can contain spaces (but not LF)
+ print $w join(' ', @$smsg{qw(raw_bytes bytes
+ num blob ds ts tid 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->{autime} = $at;
- $self->{cotime} = $ct;
- my $smsg = bless {
- bytes => $bytes,
- num => $artnum,
- blob => $oid,
- mid => $mid0,
- }, 'PublicInbox::Smsg';
- $self->add_message($mime, $smsg);
+ $self->add_message($eml, $smsg);
}
}
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: $!";
}
}
+sub shard_commit {
+ my ($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;