-# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2021 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# This interface wraps and mimics PublicInbox::Import
package PublicInbox::V2Writable;
use strict;
use v5.10.1;
-use parent qw(PublicInbox::Lock);
+use parent qw(PublicInbox::Lock PublicInbox::IPC);
use PublicInbox::SearchIdxShard;
+use PublicInbox::IPC;
use PublicInbox::Eml;
use PublicInbox::Git;
use PublicInbox::Import;
+use PublicInbox::MultiGit;
use PublicInbox::MID qw(mids references);
-use PublicInbox::ContentHash qw(content_hash content_digest);
+use PublicInbox::ContentHash qw(content_hash content_digest git_sha);
use PublicInbox::InboxWritable;
use PublicInbox::OverIdx;
use PublicInbox::Msgmap;
use PublicInbox::Spawn qw(spawn popen_rd run_die);
-use PublicInbox::SearchIdx qw(log2stack crlf_adjust is_ancestor check_size
- is_bad_blob);
+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
# 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 > $NPROC_MAX_DEFAULT;
}
sub count_shards ($) {
my ($self) = @_;
+ # always load existing shards in case core count changes:
+ # Also, shard count may change while -watch is running
if (my $ibx = $self->{ibx}) {
- # always load existing shards in case core count changes:
- # Also, shard count may change while -watch is running
my $srch = $ibx->search or return 0;
delete $ibx->{search};
$srch->{nshard} // 0
} else { # ExtSearchIdx
- $self->{nshard} ||= scalar($self->xdb_shards_flat);
+ $self->{nshard} = scalar($self->xdb_shards_flat);
}
}
$v2ibx = PublicInbox::InboxWritable->new($v2ibx);
my $dir = $v2ibx->assert_usable_dir;
unless (-d $dir) {
- if ($creat) {
- require File::Path;
- File::Path::mkpath($dir);
- } else {
- die "$dir does not exist\n";
- }
+ die "$dir does not exist\n" if !$creat;
+ require File::Path;
+ File::Path::mkpath($dir);
}
my $xpfx = "$dir/xap" . PublicInbox::Search::SCHEMA_VERSION;
my $self = {
ibx => $v2ibx,
+ mg => PublicInbox::MultiGit->new($dir, 'all.git', 'git'),
im => undef, # PublicInbox::Import
parallel => 1,
transact_bytes => 0,
$self->{mm}->skip_artnum($skip_artnum) if defined $skip_artnum;
my $max = $self->{ibx}->max_git_epoch;
$max = $skip_epoch if (defined($skip_epoch) && !defined($max));
- $self->git_init($max // 0);
+ $self->{mg}->add_epoch($max // 0);
$self->done;
}
}
# indexes a message, returns true if checkpointing is needed
-sub do_idx ($$$$) {
- my ($self, $msgref, $mime, $smsg) = @_;
- $smsg->{bytes} = $smsg->{raw_bytes} + crlf_adjust($$msgref);
- $self->{oidx}->add_overview($mime, $smsg);
- my $idx = idx_shard($self, $smsg->{num});
- $idx->index_raw($msgref, $mime, $smsg);
- my $n = $self->{transact_bytes} += $smsg->{raw_bytes};
+sub do_idx ($$$) {
+ my ($self, $eml, $smsg) = @_;
+ $self->{oidx}->add_overview($eml, $smsg);
+ if ($self->{-need_xapian}) {
+ my $idx = idx_shard($self, $smsg->{num});
+ $idx->index_eml($eml, $smsg);
+ }
+ my $n = $self->{transact_bytes} += $smsg->{bytes};
$n >= $self->{batch_bytes};
}
$cmt = $im->get_mark($cmt);
$self->{last_commit}->[$self->{epoch_max}] = $cmt;
- my $msgref = delete $smsg->{-raw_email};
- if (do_idx($self, $msgref, $mime, $smsg)) {
+ if (do_idx($self, $mime, $smsg)) {
$self->checkpoint;
}
my $max = $self->{shards} - 1;
my $idx = $self->{idx_shards} = [];
push @$idx, PublicInbox::SearchIdxShard->new($self, $_) for (0..$max);
+ $self->{-need_xapian} = $idx->[0]->need_xapian;
# SearchIdxShard may do their own flushing, so don't scale
# until after forking
# Now that all subprocesses are up, we can open the FDs
# for SQLite:
- my $mm = $self->{mm} = PublicInbox::Msgmap->new_file(
- "$ibx->{inboxdir}/msgmap.sqlite3",
- $ibx->{-no_fsync} ? 2 : 1);
+ my $mm = $self->{mm} = PublicInbox::Msgmap->new_file($ibx, 1);
$mm->{dbh}->begin_work;
}
sub parallel_init ($$) {
my ($self, $indexlevel) = @_;
- if (($indexlevel // 'full') eq 'basic') {
- $self->{parallel} = 0;
- } else {
- pipe(my ($r, $w)) or die "pipe failed: $!";
- # pipe for barrier notifications doesn't need to be big,
- # 1031: F_SETPIPE_SZ
- fcntl($w, 1031, 4096) if $^O eq 'linux';
- $self->{bnote} = [ $r, $w ];
- $w->autoflush(1);
- }
+ $self->{parallel} = 0 if ($indexlevel // 'full') eq 'basic';
}
# idempotent
$rewritten->{rewrites}
}
-# returns the git object_id of $fh, does not write the object to FS
-sub git_hash_raw ($$) {
- my ($self, $raw) = @_;
- # grab the expected OID we have to reindex:
- pipe(my($in, $w)) or die "pipe: $!";
- my $git_dir = $self->git->{git_dir};
- my $cmd = ['git', "--git-dir=$git_dir", qw(hash-object --stdin)];
- my $r = popen_rd($cmd, undef, { 0 => $in });
- print $w $$raw or die "print \$w: $!";
- close $w or die "close \$w: $!";
- local $/ = "\n";
- chomp(my $oid = <$r>);
- close $r or die "git hash-object failed: $?";
- $oid =~ /\A$OID\z/ or die "OID not expected: $oid";
- $oid;
-}
-
sub _check_mids_match ($$$) {
my ($old_list, $new_list, $hdrs) = @_;
my %old_mids = map { $_ => 1 } @$old_list;
PublicInbox::Import::drop_unwanted_headers($new_mime);
my $raw = $new_mime->as_string;
- my $expect_oid = git_hash_raw($self, \$raw);
+ my $expect_oid = git_sha(1, \$raw)->hexdigest;
my $rewritten = _replace($self, $old_mime, $new_mime, \$raw) or return;
my $need_reindex = $rewritten->{need_reindex};
for my $smsg (@$need_reindex) {
my $new_smsg = bless {
blob => $blob,
- raw_bytes => $bytes,
num => $smsg->{num},
mid => $smsg->{mid},
}, 'PublicInbox::Smsg';
my $sync = { autime => $smsg->{ds}, cotime => $smsg->{ts} };
$new_smsg->populate($new_mime, $sync);
- do_idx($self, \$raw, $new_mime, $new_smsg);
+ $new_smsg->set_bytes($raw, $bytes);
+ do_idx($self, $new_mime, $new_smsg);
}
$rewritten->{rewrites};
}
}
}
-sub barrier_init {
- my ($self, $n) = @_;
- $self->{bnote} or return;
- --$n;
- my $barrier = { map { $_ => 1 } (0..$n) };
-}
-
-sub barrier_wait {
- my ($self, $barrier) = @_;
- my $bnote = $self->{bnote} or return;
- my $r = $bnote->[0];
- while (scalar keys %$barrier) {
- defined(my $l = readline($r)) or die "EOF on barrier_wait: $!";
- $l =~ /\Abarrier (\d+)/ or die "bad line on barrier_wait: $l";
- delete $barrier->{$1} or die "bad shard[$1] on barrier wait";
- }
-}
-
# public
sub checkpoint ($;$) {
my ($self, $wait) = @_;
}
my $shards = $self->{idx_shards};
if ($shards) {
- my $mm = $self->{mm};
- my $dbh = $mm->{dbh} if $mm;
+ my $dbh = $self->{mm}->{dbh} if $self->{mm};
# SQLite msgmap data is second in importance
$dbh->commit if $dbh;
+ eval { $dbh->do('PRAGMA optimize') };
# SQLite overview is third
$self->{oidx}->commit_lazy;
# Now deal with Xapian
- if ($wait) {
- my $barrier = barrier_init($self, scalar @$shards);
-
- # each shard needs to issue a barrier command
- $_->shard_barrier for @$shards;
- # wait for each Xapian shard
- barrier_wait($self, $barrier);
- } else {
- $_->shard_commit for @$shards;
+ # start commit_txn_lazy asynchronously on all parallel shards
+ # (non-parallel waits here)
+ $_->ipc_do('commit_txn_lazy') for @$shards;
+
+ # transactions started on parallel shards,
+ # wait for them by issuing an echo command (echo can only
+ # run after commit_txn_lazy is done)
+ if ($wait && $self->{parallel}) {
+ my $i = 0;
+ for my $shard (@$shards) {
+ my $echo = $shard->ipc_do('echo', $i);
+ $echo == $i or die <<"";
+shard[$i] bad echo:$echo != $i waiting for txn commit
+
+ ++$i;
+ }
}
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:
$dbh->commit;
$dbh->begin_work;
}
- $midx->begin_txn if $midx;
}
$self->{total_bytes} += $self->{transact_bytes};
$self->{transact_bytes} = 0;
eval { $mm->{dbh}->$m };
$err .= "msgmap $m: $@\n" if $@;
}
+ if ($self->{oidx} && $self->{oidx}->{dbh} && $err) {
+ eval { $self->{oidx}->rollback_lazy };
+ $err .= "overview rollback: $@\n" if $@;
+ }
+
my $shards = delete $self->{idx_shards};
if ($shards) {
for (@$shards) {
eval { $self->{oidx}->dbh_close };
$err .= "over close: $@\n" if $@;
delete $self->{midx};
- delete $self->{bnote};
my $nbytes = $self->{total_bytes};
$self->{total_bytes} = 0;
$self->lock_release(!!$nbytes) if $shards;
die $err if $err;
}
-sub write_alternates ($$$) {
- my ($info_dir, $mode, $out) = @_;
- my $fh = File::Temp->new(TEMPLATE => 'alt-XXXXXXXX', DIR => $info_dir);
- my $tmp = $fh->filename;
- print $fh @$out or die "print $tmp: $!\n";
- chmod($mode, $fh) or die "fchmod $tmp: $!\n";
- close $fh or die "close $tmp $!\n";
- my $alt = "$info_dir/alternates";
- rename($tmp, $alt) or die "rename $tmp => $alt: $!\n";
- $fh->unlink_on_destroy(0);
-}
-
-sub fill_alternates ($$) {
- my ($self, $epoch) = @_;
-
- my $pfx = "$self->{ibx}->{inboxdir}/git";
- my $all = "$self->{ibx}->{inboxdir}/all.git";
- PublicInbox::Import::init_bare($all) unless -d $all;
- my $info_dir = "$all/objects/info";
- my $alt = "$info_dir/alternates";
- my (%alt, $new);
- my $mode = 0644;
- if (-e $alt) {
- open(my $fh, '<', $alt) or die "open < $alt: $!\n";
- $mode = (stat($fh))[2] & 07777;
-
- # we assign a sort score to every alternate and favor
- # the newest (highest numbered) one because loose objects
- # require scanning epochs and only the latest epoch is
- # expected to see loose objects
- my $score;
- my $other = 0; # in case admin adds non-epoch repos
- %alt = map {;
- if (m!\A\Q../../\E([0-9]+)\.git/objects\z!) {
- $score = $1 + 0;
- } else {
- $score = --$other;
- }
- $_ => $score;
- } split(/\n+/, do { local $/; <$fh> });
- }
-
- foreach my $i (0..$epoch) {
- my $dir = "../../git/$i.git/objects";
- if (!exists($alt{$dir}) && -d "$pfx/$i.git") {
- $alt{$dir} = $i;
- $new = 1;
- }
- }
- return unless $new;
- write_alternates($info_dir, $mode,
- [join("\n", sort { $alt{$b} <=> $alt{$a} } keys %alt), "\n"]);
-}
-
-sub git_init {
- my ($self, $epoch) = @_;
- my $git_dir = "$self->{ibx}->{inboxdir}/git/$epoch.git";
- PublicInbox::Import::init_bare($git_dir);
- run_die([qw(git config), "--file=$git_dir/config",
- qw(include.path ../../all.git/config)]);
- fill_alternates($self, $epoch);
- $git_dir
-}
-
sub importer {
my ($self) = @_;
my $im = $self->{im};
$im->done;
$im = undef;
$self->checkpoint;
- my $git_dir = $self->git_init(++$self->{epoch_max});
- my $git = PublicInbox::Git->new($git_dir);
+ my $dir = $self->{mg}->add_epoch(++$self->{epoch_max});
+ my $git = PublicInbox::Git->new($dir);
return $self->import_init($git, 0);
}
}
}
}
$self->{epoch_max} = $epoch;
- $latest = $self->git_init($epoch);
- $self->import_init(PublicInbox::Git->new($latest), 0);
+ my $dir = $self->{mg}->add_epoch($epoch);
+ $self->import_init(PublicInbox::Git->new($dir), 0);
}
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, $bh->filename ];
sub atfork_child {
my ($self) = @_;
- if (my $shards = $self->{idx_shards}) {
- $_->atfork_child foreach @$shards;
+ if (my $older_siblings = $self->{idx_shards}) {
+ $_->ipc_sibling_atfork_child for @$older_siblings;
}
if (my $im = $self->{im}) {
$im->atfork_child;
}
- die "unexpected mm" if $self->{mm};
- close $self->{bnote}->[0] or die "close bnote[0]: $!\n";
- $self->{bnote}->[1];
+ die "BUG: unexpected mm" if $self->{mm};
}
sub reindex_checkpoint ($$) {
}
# {unindexed} is unlikely
- if ((my $unindexed = $arg->{unindexed}) && scalar(@$mids) == 1) {
- $num = delete($unindexed->{$mids->[0]});
+ if (my $unindexed = $arg->{unindexed}) {
+ my $oidbin = pack('H*', $oid);
+ my $u = $unindexed->{$oidbin};
+ ($num, $mid0) = splice(@$u, 0, 2) if $u;
if (defined $num) {
- $mid0 = $mids->[0];
$self->{mm}->mid_set($num, $mid0);
- delete($arg->{unindexed}) if !keys(%$unindexed);
+ if (scalar(@$u) == 0) { # done with current OID
+ delete $unindexed->{$oidbin};
+ delete($arg->{unindexed}) if !keys(%$unindexed);
+ }
}
}
+ my $oidx = $self->{oidx};
if (!defined($num)) { # reuse if reindexing (or duplicates)
- my $oidx = $self->{oidx};
for my $mid (@$mids) {
($num, $mid0) = $oidx->num_mid0_for_oid($oid, $mid);
last if defined $num;
}
$mid0 //= do { # is this a number we got before?
$num = $arg->{mm_tmp}->num_for($mids->[0]);
+
+ # don't clobber existing if Message-ID is reused:
+ if (my $x = defined($num) ? $oidx->get_art($num) : undef) {
+ undef($num) if $x->{blob} ne $oid;
+ }
defined($num) ? $mids->[0] : undef;
};
if (!defined($num)) {
}
++${$arg->{nr}};
my $smsg = bless {
- raw_bytes => $size,
num => $num,
blob => $oid,
mid => $mid0,
}, 'PublicInbox::Smsg';
$smsg->populate($eml, $arg);
- if (do_idx($self, $bref, $eml, $smsg)) {
+ $smsg->set_bytes($$bref, $size);
+ if (do_idx($self, $eml, $smsg)) {
${$arg->{need_checkpoint}} = 1;
}
index_finalize($arg, 1);
chomp(my $n = $unit->{git}->qx(@cmd));
return if $n ne '' && $n == 0;
}
+ # don't rewind if --{since,until,before,after} are in use
+ return if (defined($last) &&
+ grep(defined, @{$sync->{-opt}}{qw(since until)}) &&
+ is_ancestor($self->git, $latest_cmt, $last));
+
last_epoch_commit($self, $unit->{epoch}, $latest_cmt);
}
my $req = { %$sync, oid => $oid };
$self->git->cat_async($oid, $unindex_oid, $req);
}
- $self->git->cat_async_wait;
+ $self->git->async_wait_all;
}
return 0 if $sync->{quit};
if (!$regen_max) {
sub unindex_oid_aux ($$$) {
my ($self, $oid, $mid) = @_;
my @removed = $self->{oidx}->remove_oid($oid, $mid);
+ return unless $self->{-need_xapian};
for my $num (@removed) {
- my $idx = idx_shard($self, $num);
- $idx->shard_remove($num);
+ idx_shard($self, $num)->ipc_do('xdb_remove', $num);
}
}
warn "BUG: multiple articles linked to $oid\n",
join(',',sort keys %gone), "\n";
}
- foreach my $num (keys %gone) {
+ # reuse (num => mid) mapping in ascending numeric order
+ for my $num (sort { $a <=> $b } keys %gone) {
+ $num += 0;
if ($unindexed) {
my $mid0 = $mm->mid_for($num);
- $unindexed->{$mid0} = $num;
+ my $oidbin = pack('H*', $oid);
+ push @{$unindexed->{$oidbin}}, $num, $mid0;
}
$mm->num_delete($num);
}
sub unindex_todo ($$$) {
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
$self->git->cat_async($1, $unindex_oid, { %$sync, oid => $1 });
}
close $fh or die "git log failed: \$?=$?";
- $self->git->cat_async_wait;
+ $self->git->async_wait_all;
return unless $sync->{-opt}->{prune};
my $after = scalar keys %$unindexed;
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});
- $smsg->{raw_bytes} = $size;
- $idx->index_raw($bref, undef, $smsg);
- $self->{transact_bytes} += $size;
+ $idx->index_eml(PublicInbox::Eml->new($bref), $smsg);
+ $self->{transact_bytes} += $smsg->{bytes};
}
sub index_xap_step ($$$;$) {
sub xapian_only {
my ($self, $opt, $sync, $art_beg) = @_;
- my $seq = $opt->{sequential_shard};
+ my $seq = $opt->{'sequential-shard'};
$art_beg //= 0;
local $self->{parallel} = 0 if $seq;
$self->idx_init($opt); # acquire lock
index_xap_step($self, $sync, $art_beg, 1);
}
}
- $self->git->cat_async_wait;
+ $self->git->async_wait_all;
+ $self->{ibx}->cleanup;
$self->done;
}
}
my $pr = $opt->{-progress};
- my $seq = $opt->{sequential_shard};
+ my $seq = $opt->{'sequential-shard'};
my $art_beg; # the NNTP article number we start xapian_only at
my $idxlevel = $self->{ibx}->{indexlevel};
local $self->{ibx}->{indexlevel} = 'basic' if $seq;
$self->idx_init($opt); # acquire lock
- fill_alternates($self, $epoch_max);
+ $self->{mg}->fill_alternates;
$self->{oidx}->rethread_prepare($opt);
my $sync = {
need_checkpoint => \(my $bool = 0),
}
# reindex does not pick up new changes, so we rerun w/o it:
- if ($opt->{reindex} && !$sync->{quit}) {
+ if ($opt->{reindex} && !$sync->{quit} &&
+ !grep(defined, @$opt{qw(since until)})) {
my %again = %$opt;
$sync = undef;
delete @again{qw(rethread reindex -skip_lock)};
EOF
}
+sub ipc_atfork_child {
+ my ($self) = @_;
+ if (my $lei = delete $self->{lei}) {
+ $lei->_lei_atfork_child;
+ my $pkt_op_p = delete $lei->{pkt_op_p};
+ close($pkt_op_p->{op_p});
+ }
+ $self->SUPER::ipc_atfork_child;
+}
+
1;