-# 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);
-use PublicInbox::SearchIdx qw(log2stack crlf_adjust is_ancestor check_size);
+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
-my $PACKING_FACTOR = 0.4;
+our $PACKING_FACTOR = 0.4;
# SATA storage lags behind what CPUs are capable of, so relying on
# nproc(1) can be misleading and having extra Xapian shards is a
# 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 > $NPROC_MAX_DEFAULT;
}
my ($self) = @_;
# always load existing shards in case core count changes:
# Also, shard count may change while -watch is running
- my $srch = $self->{ibx}->search or return 0;
- delete $self->{ibx}->{search};
- $srch->{nshard} // 0
+ if (my $ibx = $self->{ibx}) {
+ my $srch = $ibx->search or return 0;
+ delete $ibx->{search};
+ $srch->{nshard} // 0
+ } else { # ExtSearchIdx
+ $self->{nshard} = scalar($self->xdb_shards_flat);
+ }
}
sub new {
$v2ibx = PublicInbox::InboxWritable->new($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);
}
- $v2ibx->umask_prepare;
-
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->idx_init;
$self->{mm}->skip_artnum($skip_artnum) if defined $skip_artnum;
- my $epoch_max = -1;
- git_dir_latest($self, \$epoch_max);
- if (defined $skip_epoch && $epoch_max == -1) {
- $epoch_max = $skip_epoch;
- }
- $self->git_init($epoch_max >= 0 ? $epoch_max : 0);
+ my $max = $self->{ibx}->max_git_epoch;
+ $max = $skip_epoch if (defined($skip_epoch) && !defined($max));
+ $self->{mg}->add_epoch($max // 0);
$self->done;
}
$self->{ibx}->with_umask(\&_add, $self, $eml, $check_cb);
}
+sub idx_shard ($$) {
+ my ($self, $num) = @_;
+ $self->{idx_shards}->[$num % scalar(@{$self->{idx_shards}})];
+}
+
# indexes a message, returns true if checkpointing is needed
-sub do_idx ($$$$) {
- my ($self, $msgref, $mime, $smsg) = @_;
- $smsg->{bytes} = $smsg->{raw_bytes} + crlf_adjust($$msgref);
- $self->{oidx}->add_overview($mime, $smsg);
- my $idx = idx_shard($self, $smsg->{num} % $self->{shards});
- $idx->index_raw($msgref, $mime, $smsg);
- my $n = $self->{transact_bytes} += $smsg->{raw_bytes};
+sub do_idx ($$$) {
+ my ($self, $eml, $smsg) = @_;
+ $self->{oidx}->add_overview($eml, $smsg);
+ if ($self->{-need_xapian}) {
+ my $idx = idx_shard($self, $smsg->{num});
+ $idx->index_eml($eml, $smsg);
+ }
+ my $n = $self->{transact_bytes} += $smsg->{bytes};
$n >= $self->{batch_bytes};
}
$cmt = $im->get_mark($cmt);
$self->{last_commit}->[$self->{epoch_max}] = $cmt;
- my $msgref = delete $smsg->{-raw_email};
- if (do_idx($self, $msgref, $mime, $smsg)) {
+ if (do_idx($self, $mime, $smsg)) {
$self->checkpoint;
}
($num, $mid0);
}
-sub idx_shard {
- my ($self, $shard_i) = @_;
- $self->{idx_shards}->[$shard_i];
-}
-
sub _idx_init { # with_umask callback
my ($self, $opt) = @_;
$self->lock_acquire unless $opt && $opt->{-skip_lock};
$self->{shards} = $nshards if $nshards && $nshards != $self->{shards};
$self->{batch_bytes} = $opt->{batch_size} //
$PublicInbox::SearchIdx::BATCH_BYTES;
- $self->{batch_bytes} *= $self->{shards} if $self->{parallel};
# need to create all shards before initializing msgmap FD
# idx_shards must be visible to all forked processes
my $max = $self->{shards} - 1;
my $idx = $self->{idx_shards} = [];
push @$idx, PublicInbox::SearchIdxShard->new($self, $_) for (0..$max);
+ $self->{-need_xapian} = $idx->[0]->need_xapian;
+
+ # SearchIdxShard may do their own flushing, so don't scale
+ # until after forking
+ $self->{batch_bytes} *= $self->{shards} if $self->{parallel};
+
+ my $ibx = $self->{ibx} or return; # ExtIdxSearch
# Now that all subprocesses are up, we can open the FDs
# for SQLite:
- my $mm = $self->{mm} = PublicInbox::Msgmap->new_file(
- "$self->{ibx}->{inboxdir}/msgmap.sqlite3",
- $self->{ibx}->{-no_fsync} ? 2 : 1);
+ my $mm = $self->{mm} = PublicInbox::Msgmap->new_file($ibx, 1);
$mm->{dbh}->begin_work;
}
+sub parallel_init ($$) {
+ my ($self, $indexlevel) = @_;
+ $self->{parallel} = 0 if ($indexlevel // 'full') eq 'basic';
+}
+
# idempotent
sub idx_init {
my ($self, $opt) = @_;
delete @$ibx{qw(mm search)};
$ibx->git->cleanup;
- $self->{parallel} = 0 if ($ibx->{indexlevel}//'') eq 'basic';
- if ($self->{parallel}) {
- pipe(my ($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);
- }
-
- $ibx->umask_prepare;
+ parallel_init($self, $ibx->{indexlevel});
$ibx->with_umask(\&_idx_init, $self, $opt);
}
sub _replace_oids ($$$) {
my ($self, $mime, $replace_map) = @_;
$self->done;
- my $pfx = "$self->{ibx}->{inboxdir}/git";
+ my $ibx = $self->{ibx};
+ my $pfx = "$ibx->{inboxdir}/git";
my $rewrites = []; # epoch => commit
- my $max = $self->{epoch_max};
-
- unless (defined($max)) {
- defined(my $latest = git_dir_latest($self, \$max)) or return;
- $self->{epoch_max} = $max;
- }
+ my $max = $self->{epoch_max} //= $ibx->max_git_epoch // return;
foreach my $i (0..$max) {
my $git_dir = "$pfx/$i.git";
} else { # ->purge or ->remove
$self->{mm}->num_delete($num);
}
- unindex_oid_remote($self, $oid, $mid);
+ unindex_oid_aux($self, $oid, $mid);
}
}
$rewritten->{rewrites}
}
-# returns the git object_id of $fh, does not write the object to FS
-sub git_hash_raw ($$) {
- my ($self, $raw) = @_;
- # grab the expected OID we have to reindex:
- pipe(my($in, $w)) or die "pipe: $!";
- my $git_dir = $self->{ibx}->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 = $rewritten->{need_reindex};
}
# make sure we really got the OID:
- my ($blob, $type, $bytes) = $self->{ibx}->git->check($expect_oid);
+ my ($blob, $type, $bytes) = $self->git->check($expect_oid);
$blob eq $expect_oid or die "BUG: $expect_oid not found after replace";
# don't leak FDs to Xapian:
- $self->{ibx}->git->cleanup;
+ $self->git->cleanup;
# reindex modified messages:
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};
}
$self->{mm}->last_commit_xap($v, $i, $cmt);
}
-sub set_last_commits ($) {
+sub set_last_commits ($) { # this is NOT for ExtSearchIdx
my ($self) = @_;
defined(my $epoch_max = $self->{epoch_max}) or return;
my $last_commit = $self->{last_commit};
}
}
-sub barrier_init {
- my ($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 $dbh = $self->{mm}->{dbh};
+ my $dbh = $self->{mm}->{dbh} if $self->{mm};
# SQLite msgmap data is second in importance
- $dbh->commit;
+ $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 = $self->barrier_init(scalar @$shards);
- # each shard needs to issue a barrier command
- $_->shard_barrier for @$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;
+ }
+ }
- # wait for each Xapian shard
- $self->barrier_wait($barrier);
- } else {
- $_->shard_commit for @$shards;
+ my $midx = $self->{midx}; # misc index
+ if ($midx) {
+ $midx->commit_txn;
+ $PublicInbox::Search::X{CLOEXEC_UNSET} and
+ $self->git->cleanup;
}
# last_commit is special, don't commit these until
- # remote shards are done:
- $dbh->begin_work;
+ # Xapian shards are done:
+ $dbh->begin_work if $dbh;
set_last_commits($self);
- $dbh->commit;
-
- $dbh->begin_work;
+ if ($dbh) {
+ $dbh->commit;
+ $dbh->begin_work;
+ }
}
$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->{bnote};
+ delete $self->{midx};
my $nbytes = $self->{total_bytes};
$self->{total_bytes} = 0;
$self->lock_release(!!$nbytes) if $shards;
- $self->{ibx}->git->cleanup;
+ $self->git->cleanup;
die $err if $err;
}
-sub fill_alternates ($$) {
- my ($self, $epoch) = @_;
-
- my $pfx = "$self->{ibx}->{inboxdir}/git";
- my $all = "$self->{ibx}->{inboxdir}/all.git";
- PublicInbox::Import::init_bare($all) unless -d $all;
- my $info_dir = "$all/objects/info";
- my $alt = "$info_dir/alternates";
- my (%alt, $new);
- my $mode = 0644;
- if (-e $alt) {
- open(my $fh, '<', $alt) or die "open < $alt: $!\n";
- $mode = (stat($fh))[2] & 07777;
-
- # we assign a sort score to every alternate and favor
- # the newest (highest numbered) one because loose objects
- # require scanning epochs and only the latest epoch is
- # expected to see loose objects
- my $score;
- my $other = 0; # in case admin adds non-epoch repos
- %alt = map {;
- if (m!\A\Q../../\E([0-9]+)\.git/objects\z!) {
- $score = $1 + 0;
- } else {
- $score = --$other;
- }
- $_ => $score;
- } split(/\n+/, do { local $/; <$fh> });
- }
-
- foreach my $i (0..$epoch) {
- my $dir = "../../git/$i.git/objects";
- if (!exists($alt{$dir}) && -d "$pfx/$i.git") {
- $alt{$dir} = $i;
- $new = 1;
- }
- }
- return unless $new;
-
- my $fh = File::Temp->new(TEMPLATE => 'alt-XXXXXXXX', DIR => $info_dir);
- my $tmp = $fh->filename;
- print $fh join("\n", sort { $alt{$b} <=> $alt{$a} } keys %alt), "\n"
- or die "print $tmp: $!\n";
- chmod($mode, $fh) or die "fchmod $tmp: $!\n";
- close $fh or die "close $tmp $!\n";
- rename($tmp, $alt) or die "rename $tmp => $alt: $!\n";
- $fh->unlink_on_destroy(0);
-}
-
-sub git_init {
- my ($self, $epoch) = @_;
- my $git_dir = "$self->{ibx}->{inboxdir}/git/$epoch.git";
- PublicInbox::Import::init_bare($git_dir);
- my @cmd = (qw/git config/, "--file=$git_dir/config",
- 'include.path', '../../all.git/config');
- PublicInbox::Import::run_die(\@cmd);
- fill_alternates($self, $epoch);
- $git_dir
-}
-
-sub git_dir_latest {
- my ($self, $max) = @_;
- $$max = -1;
- my $pfx = "$self->{ibx}->{inboxdir}/git";
- return unless -d $pfx;
- my $latest;
- opendir my $dh, $pfx or die "opendir $pfx: $!\n";
- while (defined(my $git_dir = readdir($dh))) {
- $git_dir =~ m!\A([0-9]+)\.git\z! or next;
- if ($1 > $$max) {
- $$max = $1;
- $latest = "$pfx/$git_dir";
- }
- }
- $latest;
-}
-
sub importer {
my ($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);
}
}
my $epoch = 0;
my $max;
- my $latest = git_dir_latest($self, \$max);
+ my $latest = $self->{ibx}->git_dir_latest(\$max);
if (defined $latest) {
my $git = PublicInbox::Git->new($latest);
my $packed_bytes = $git->packed_bytes;
}
}
$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 ($$$) {
my ($mid, $cur, $new) = @_;
- my $ah = File::Temp->new(TEMPLATE => 'email-cur-XXXXXXXX', TMPDIR => 1);
+ my $ah = File::Temp->new(TEMPLATE => 'email-cur-XXXX', TMPDIR => 1);
print $ah $cur->as_string or die "print: $!";
$ah->flush or die "flush: $!";
PublicInbox::Import::drop_unwanted_headers($new);
- my $bh = File::Temp->new(TEMPLATE => 'email-new-XXXXXXXX', TMPDIR => 1);
+ my $bh = File::Temp->new(TEMPLATE => 'email-new-XXXX', TMPDIR => 1);
print $bh $new->as_string or die "print: $!";
$bh->flush or die "flush: $!";
my $cmd = [ qw(diff -u), $ah->filename, $bh->filename ];
sub atfork_child {
my ($self) = @_;
- if (my $shards = $self->{idx_shards}) {
- $_->atfork_child foreach @$shards;
+ if (my $older_siblings = $self->{idx_shards}) {
+ $_->ipc_sibling_atfork_child for @$older_siblings;
}
if (my $im = $self->{im}) {
$im->atfork_child;
}
- die "unexpected mm" if $self->{mm};
- close $self->{bnote}->[0] or die "close bnote[0]: $!\n";
- $self->{bnote}->[1];
+ die "BUG: unexpected mm" if $self->{mm};
}
sub reindex_checkpoint ($$) {
my ($self, $sync) = @_;
- $self->{ibx}->git->cleanup; # *async_wait
+ $self->git->async_wait_all;
+ $self->update_last_commit($sync);
${$sync->{need_checkpoint}} = 0;
my $mm_tmp = $sync->{mm_tmp};
$mm_tmp->atfork_prepare if $mm_tmp;
- $self->done; # release lock
+ die 'BUG: {im} during reindex' if $self->{im};
+ if ($self->{ibx_map} && !$sync->{checkpoint_unlocks}) {
+ checkpoint($self, 1); # no need to release lock on pure index
+ } else {
+ $self->done; # release lock
+ }
- if (my $pr = $sync->{-opt}->{-progress}) {
+ if (my $pr = $sync->{-regen_fmt} ? $sync->{-opt}->{-progress} : undef) {
$pr->(sprintf($sync->{-regen_fmt}, ${$sync->{nr}}));
}
# allow -watch or -mda to write...
$self->idx_init($sync->{-opt}); # reacquire lock
+ if (my $intvl = $sync->{check_intvl}) { # eidx
+ $sync->{next_check} = PublicInbox::DS::now() + $intvl;
+ }
$mm_tmp->atfork_parent if $mm_tmp;
}
+sub index_finalize ($$) {
+ my ($arg, $index) = @_;
+ ++$arg->{self}->{nidx};
+ if (defined(my $cur = $arg->{cur_cmt})) {
+ ${$arg->{latest_cmt}} = $cur;
+ } elsif ($index) {
+ die 'BUG: {cur_cmt} missing';
+ } # else { unindexing @leftovers doesn't set {cur_cmt}
+}
+
sub index_oid { # cat_async callback
my ($bref, $oid, $type, $size, $arg) = @_;
- return if $size == 0; # purged
+ is_bad_blob($oid, $type, $size, $arg->{oid}) and
+ return index_finalize($arg, 1); # size == 0 purged returns here
+ my $self = $arg->{self};
+ local $self->{current_info} = "$self->{current_info} $oid";
my ($num, $mid0);
my $eml = PublicInbox::Eml->new($$bref);
my $mids = mids($eml);
my $chash = content_hash($eml);
- my $self = $arg->{v2w};
if (scalar(@$mids) == 0) {
warn "E: $oid has no Message-ID, skipping\n";
}
# {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($$bref, $size);
+ if (do_idx($self, $eml, $smsg)) {
${$arg->{need_checkpoint}} = 1;
}
+ index_finalize($arg, 1);
}
# only update last_commit for $i on reindex iff newer than current
-sub update_last_commit ($$$$) {
- my ($self, $git, $i, $cmt) = @_;
- my $last = last_epoch_commit($self, $i);
- if (defined $last && is_ancestor($git, $last, $cmt)) {
- my @cmd = (qw(rev-list --count), "$last..$cmt");
- chomp(my $n = $git->qx(@cmd));
+sub update_last_commit {
+ my ($self, $sync, $stk) = @_;
+ my $unit = $sync->{unit} // return;
+ my $latest_cmt = $stk ? $stk->{latest_cmt} : ${$sync->{latest_cmt}};
+ defined($latest_cmt) or return;
+ my $last = last_epoch_commit($self, $unit->{epoch});
+ if (defined $last && is_ancestor($self->git, $last, $latest_cmt)) {
+ my @cmd = (qw(rev-list --count), "$last..$latest_cmt");
+ chomp(my $n = $unit->{git}->qx(@cmd));
return if $n ne '' && $n == 0;
}
- last_epoch_commit($self, $i, $cmt);
-}
+ # don't rewind if --{since,until,before,after} are in use
+ return if (defined($last) &&
+ grep(defined, @{$sync->{-opt}}{qw(since until)}) &&
+ is_ancestor($self->git, $latest_cmt, $last));
-sub git_dir_n ($$) { "$_[0]->{ibx}->{inboxdir}/git/$_[1].git" }
+ last_epoch_commit($self, $unit->{epoch}, $latest_cmt);
+}
-sub last_commits ($$) {
- my ($self, $epoch_max) = @_;
+sub last_commits {
+ my ($self, $sync) = @_;
my $heads = [];
- for (my $i = $epoch_max; $i >= 0; $i--) {
+ for (my $i = $sync->{epoch_max}; $i >= 0; $i--) {
$heads->[$i] = last_epoch_commit($self, $i);
}
$heads;
}
# returns a revision range for git-log(1)
-sub log_range ($$$$$) {
- my ($self, $sync, $git, $i, $tip) = @_;
+sub log_range ($$$) {
+ my ($sync, $unit, $tip) = @_;
my $opt = $sync->{-opt};
my $pr = $opt->{-progress} if (($opt->{verbose} || 0) > 1);
+ my $i = $unit->{epoch};
my $cur = $sync->{ranges}->[$i] or do {
$pr->("$i.git indexing all of $tip\n") if $pr;
return $tip; # all of it
my $range = "$cur..$tip";
$pr->("$i.git checking contiguity... ") if $pr;
- if (is_ancestor($git, $cur, $tip)) { # common case
+ my $git = $unit->{git};
+ if (is_ancestor($sync->{self}->git, $cur, $tip)) { # common case
$pr->("OK\n") if $pr;
my $n = $git->qx(qw(rev-list --count), $range);
chomp($n);
warn "discarding history at $cur\n";
}
warn <<"";
-reindexing $git->{git_dir} starting at
-$range
-
- $sync->{unindex_range}->{$i} = "$base..$cur";
+reindexing $git->{git_dir}
+starting at $range
+
+ # $cur^0 may no longer exist if pruned by git
+ if ($git->qx(qw(rev-parse -q --verify), "$cur^0")) {
+ $unit->{unindex_range} = "$base..$cur";
+ } elsif ($base && $git->qx(qw(rev-parse -q --verify), $base)) {
+ $unit->{unindex_range} = "$base..";
+ } else {
+ warn "W: unable to unindex before $range\n";
+ }
}
$range;
}
-sub sync_prepare ($$$) {
- my ($self, $sync, $epoch_max) = @_;
+# overridden by ExtSearchIdx
+sub artnum_max { $_[0]->{mm}->num_highwater }
+
+sub sync_prepare ($$) {
+ my ($self, $sync) = @_;
+ $sync->{ranges} = sync_ranges($self, $sync);
my $pr = $sync->{-opt}->{-progress};
my $regen_max = 0;
- my $head = $self->{ibx}->{ref_head} || 'HEAD';
-
- # reindex stops at the current heads and we later rerun index_sync
- # without {reindex}
- my $reindex_heads = last_commits($self, $epoch_max) if $sync->{reindex};
-
- for (my $i = $epoch_max; $i >= 0; $i--) {
- my $git_dir = git_dir_n($self, $i);
+ my $head = $sync->{ibx}->{ref_head} || 'HEAD';
+ my $pfx;
+ if ($pr) {
+ ($pfx) = ($sync->{ibx}->{inboxdir} =~ m!([^/]+)\z!g);
+ $pfx //= $sync->{ibx}->{inboxdir};
+ }
+
+ my $reindex_heads;
+ if ($self->{ibx_map}) {
+ # ExtSearchIdx won't index messages unless they're in
+ # over.sqlite3 for a given inbox, so don't read beyond
+ # what's in the per-inbox index.
+ $reindex_heads = [];
+ my $v = PublicInbox::Search::SCHEMA_VERSION;
+ my $mm = $sync->{ibx}->mm;
+ for my $i (0..$sync->{epoch_max}) {
+ $reindex_heads->[$i] = $mm->last_commit_xap($v, $i);
+ }
+ } elsif ($sync->{reindex}) { # V2 inbox
+ # reindex stops at the current heads and we later
+ # rerun index_sync without {reindex}
+ $reindex_heads = $self->last_commits($sync);
+ }
+ if ($sync->{max_size} = $sync->{-opt}->{max_size}) {
+ $sync->{index_oid} = $self->can('index_oid');
+ }
+ my $git_pfx = "$sync->{ibx}->{inboxdir}/git";
+ for (my $i = $sync->{epoch_max}; $i >= 0; $i--) {
+ my $git_dir = "$git_pfx/$i.git";
-d $git_dir or next; # missing epochs are fine
my $git = PublicInbox::Git->new($git_dir);
+ my $unit = { git => $git, epoch => $i };
+ my $tip;
if ($reindex_heads) {
- $head = $reindex_heads->[$i] or next;
+ $tip = $head = $reindex_heads->[$i] or next;
+ } else {
+ $tip = $git->qx(qw(rev-parse -q --verify), $head);
+ next if $?; # new repo
+ chomp $tip;
}
- chomp(my $tip = $git->qx(qw(rev-parse -q --verify), $head));
-
- next if $?; # new repo
- my $range = log_range($self, $sync, $git, $i, $tip) or next;
+ my $range = log_range($sync, $unit, $tip) or next;
# can't use 'rev-list --count' if we use --diff-filter
- $pr->("$i.git counting $range ... ") if $pr;
+ $pr->("$pfx $i.git counting $range ... ") if $pr;
# Don't bump num_highwater on --reindex by using {D}.
# We intentionally do NOT use {D} in the non-reindex case
# because we want NNTP article number gaps from unindexed
# messages to show up in mirrors, too.
$sync->{D} //= $sync->{reindex} ? {} : undef; # OID_BIN => NR
- my $stk = log2stack($sync, $git, $range, $self->{ibx});
+ my $stk = log2stack($sync, $git, $range);
+ return 0 if $sync->{quit};
my $nr = $stk ? $stk->num_records : 0;
$pr->("$nr\n") if $pr;
- $sync->{stacks}->[$i] = $stk if $stk;
+ $unit->{stack} = $stk; # may be undef
+ unshift @{$sync->{todo}}, $unit;
$regen_max += $nr;
}
+ return 0 if $sync->{quit};
# XXX this should not happen unless somebody bypasses checks in
# our code and blindly injects "d" file history into git repos
if (my @leftovers = keys %{delete($sync->{D}) // {}}) {
warn('W: unindexing '.scalar(@leftovers)." leftovers\n");
- my $arg = { v2w => $self };
- my $all = $self->{ibx}->git;
+ local $self->{current_info} = 'leftover ';
+ my $unindex_oid = $self->can('unindex_oid');
for my $oid (@leftovers) {
+ last if $sync->{quit};
$oid = unpack('H*', $oid);
- $self->{current_info} = "leftover $oid";
- $all->cat_async($oid, \&unindex_oid, $arg);
+ my $req = { %$sync, oid => $oid };
+ $self->git->cat_async($oid, $unindex_oid, $req);
}
- $all->cat_async_wait;
+ $self->git->async_wait_all;
}
+ return 0 if $sync->{quit};
if (!$regen_max) {
$sync->{-regen_fmt} = "%u/?\n";
return 0;
$sync->{-regen_fmt} = "% ${pad}u/$regen_max\n";
$sync->{nr} = \(my $nr = 0);
return -1 if $sync->{reindex};
- $regen_max + $self->{mm}->num_highwater() || 0;
+ $regen_max + $self->artnum_max || 0;
}
-sub unindex_oid_remote ($$$) {
+sub unindex_oid_aux ($$$) {
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 % $self->{shards});
- $idx->shard_remove($oid, $num);
+ idx_shard($self, $num)->ipc_do('xdb_remove', $num);
}
}
sub unindex_oid ($$;$) { # git->cat_async callback
- my ($bref, $oid, $type, $size, $sync) = @_;
- my $self = $sync->{v2w};
- my $unindexed = $sync->{in_unindex} ? $sync->{unindexed} : undef;
+ my ($bref, $oid, $type, $size, $arg) = @_;
+ is_bad_blob($oid, $type, $size, $arg->{oid}) and
+ return index_finalize($arg, 0);
+ my $self = $arg->{self};
+ local $self->{current_info} = "$self->{current_info} $oid";
+ my $unindexed = $arg->{in_unindex} ? $arg->{unindexed} : undef;
my $mm = $self->{mm};
my $mids = mids(PublicInbox::Eml->new($bref));
undef $$bref;
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);
}
- unindex_oid_remote($self, $oid, $mid);
+ unindex_oid_aux($self, $oid, $mid);
}
+ index_finalize($arg, 0);
}
+sub git { $_[0]->{ibx}->git }
+
# this is rare, it only happens when we get discontiguous history in
# a mirror because the source used -purge or -edit
-sub unindex ($$$$) {
- my ($self, $sync, $git, $unindex_range) = @_;
- my $unindexed = $sync->{unindexed} //= {}; # $mid0 => $num
+sub unindex_todo ($$$) {
+ my ($self, $sync, $unit) = @_;
+ my $unindex_range = delete($unit->{unindex_range}) // return;
+ my $unindexed = $sync->{unindexed} //= {}; # $oidbin => [$num, $mid0]
my $before = scalar keys %$unindexed;
# order does not matter, here:
- my @cmd = qw(log --raw -r
- --no-notes --no-color --no-abbrev --no-renames);
- my $fh = $git->popen(@cmd, $unindex_range);
- my $all = $self->{ibx}->git;
+ my $fh = $unit->{git}->popen(qw(log --raw -r --no-notes --no-color
+ --no-abbrev --no-renames), $unindex_range);
local $sync->{in_unindex} = 1;
+ my $unindex_oid = $self->can('unindex_oid');
while (<$fh>) {
/\A:\d{6} 100644 $OID ($OID) [AM]\tm$/o or next;
- $all->cat_async($1, \&unindex_oid, $sync);
+ $self->git->cat_async($1, $unindex_oid, { %$sync, oid => $1 });
}
close $fh or die "git log failed: \$?=$?";
- $all->cat_async_wait;
+ $self->git->async_wait_all;
return unless $sync->{-opt}->{prune};
my $after = scalar keys %$unindexed;
return if $before == $after;
# ensure any blob can not longer be accessed via dumb HTTP
- PublicInbox::Import::run_die(['git', "--git-dir=$git->{git_dir}",
+ run_die(['git', "--git-dir=$unit->{git}->{git_dir}",
qw(-c gc.reflogExpire=now gc --prune=all --quiet)]);
}
-sub sync_ranges ($$$) {
- my ($self, $sync, $epoch_max) = @_;
+sub sync_ranges ($$) {
+ my ($self, $sync) = @_;
my $reindex = $sync->{reindex};
-
- return last_commits($self, $epoch_max) unless $reindex;
+ return $self->last_commits($sync) unless $reindex;
return [] if ref($reindex) ne 'HASH';
my $ranges = $reindex->{from}; # arrayref;
sub index_xap_only { # git->cat_async callback
my ($bref, $oid, $type, $size, $smsg) = @_;
- my $self = $smsg->{v2w};
- my $idx = idx_shard($self, $smsg->{num} % $self->{shards});
- $smsg->{raw_bytes} = $size;
- $idx->index_raw($bref, undef, $smsg);
- $self->{transact_bytes} += $size;
+ 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};
}
sub index_xap_step ($$$;$) {
"$beg..$end (% $step)\n");
}
for (my $num = $beg; $num <= $end; $num += $step) {
+ last if $sync->{quit};
my $smsg = $ibx->over->get_art($num) or next;
- $smsg->{v2w} = $self;
+ $smsg->{self} = $self;
$ibx->git->cat_async($smsg->{blob}, \&index_xap_only, $smsg);
if ($self->{transact_bytes} >= $self->{batch_bytes}) {
${$sync->{nr}} = $num;
}
}
-sub index_epoch ($$$) {
- my ($self, $sync, $i) = @_;
-
- my $git_dir = git_dir_n($self, $i);
- -d $git_dir or return; # missing epochs are fine
- my $git = PublicInbox::Git->new($git_dir);
- if (my $unindex_range = delete $sync->{unindex_range}->{$i}) { # rare
- unindex($self, $sync, $git, $unindex_range);
- }
- defined(my $stk = $sync->{stacks}->[$i]) or return;
- $sync->{stacks}->[$i] = undef;
- my $all = $self->{ibx}->git;
- while (my ($f, $at, $ct, $oid) = $stk->pop_rec) {
- $self->{current_info} = "$i.git $oid";
+sub index_todo ($$$) {
+ my ($self, $sync, $unit) = @_;
+ return if $sync->{quit};
+ unindex_todo($self, $sync, $unit);
+ my $stk = delete($unit->{stack}) or return;
+ my $all = $self->git;
+ my $index_oid = $self->can('index_oid');
+ my $unindex_oid = $self->can('unindex_oid');
+ my $pfx;
+ if ($unit->{git}->{git_dir} =~ m!/([^/]+)/git/([0-9]+\.git)\z!) {
+ $pfx = "$1 $2"; # v2
+ } else { # v1
+ ($pfx) = ($unit->{git}->{git_dir} =~ m!/([^/]+)\z!g);
+ $pfx //= $unit->{git}->{git_dir};
+ }
+ local $self->{current_info} = "$pfx ";
+ local $sync->{latest_cmt} = \(my $latest_cmt);
+ local $sync->{unit} = $unit;
+ while (my ($f, $at, $ct, $oid, $cmt) = $stk->pop_rec) {
+ if ($sync->{quit}) {
+ warn "waiting to quit...\n";
+ $all->async_wait_all;
+ $self->update_last_commit($sync);
+ return;
+ }
+ my $req = {
+ %$sync,
+ autime => $at,
+ cotime => $ct,
+ oid => $oid,
+ cur_cmt => $cmt
+ };
if ($f eq 'm') {
- my $arg = { %$sync, autime => $at, cotime => $ct };
if ($sync->{max_size}) {
- $all->check_async($oid, \&check_size, $arg);
+ $all->check_async($oid, \&check_size, $req);
} else {
- $all->cat_async($oid, \&index_oid, $arg);
+ $all->cat_async($oid, $index_oid, $req);
}
} elsif ($f eq 'd') {
- $all->cat_async($oid, \&unindex_oid, $sync);
+ $all->cat_async($oid, $unindex_oid, $req);
}
if (${$sync->{need_checkpoint}}) {
reindex_checkpoint($self, $sync);
}
}
$all->async_wait_all;
- update_last_commit($self, $git, $i, $stk->{latest_cmt});
+ $self->update_last_commit($sync, $stk);
}
sub xapian_only {
my ($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
$sync //= {
need_checkpoint => \(my $bool = 0),
-opt => $opt,
- v2w => $self,
+ self => $self,
nr => \(my $nr = 0),
-regen_fmt => "%u/?\n",
};
if ($seq || !$self->{parallel}) {
my $shard_end = $self->{shards} - 1;
for my $i (0..$shard_end) {
+ last if $sync->{quit};
index_xap_step($self, $sync, $art_beg + $i);
if ($i != $shard_end) {
reindex_checkpoint($self, $sync);
index_xap_step($self, $sync, $art_beg, 1);
}
}
- $self->{ibx}->git->cat_async_wait;
+ $self->git->async_wait_all;
+ $self->{ibx}->cleanup;
$self->done;
}
$opt //= {};
return xapian_only($self, $opt) if $opt->{xapian_only};
- my $pr = $opt->{-progress};
my $epoch_max;
- my $latest = git_dir_latest($self, \$epoch_max);
- return unless defined $latest;
+ my $latest = $self->{ibx}->git_dir_latest(\$epoch_max) // return;
+ if ($opt->{'fast-noop'}) { # nanosecond (st_ctim) comparison
+ use Time::HiRes qw(stat);
+ if (my @mm = stat("$self->{ibx}->{inboxdir}/msgmap.sqlite3")) {
+ my $c = $mm[10]; # 10 = ctime (nsec NV)
+ my @hd = stat("$latest/refs/heads");
+ my @pr = stat("$latest/packed-refs");
+ return if $c > ($hd[10] // 0) && $c > ($pr[10] // 0);
+ }
+ }
- my $seq = $opt->{sequential_shard};
+ my $pr = $opt->{-progress};
+ 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),
- unindex_range => {}, # EPOCH => oid_old..oid_new
reindex => $opt->{reindex},
-opt => $opt,
- v2w => $self,
+ self => $self,
+ ibx => $self->{ibx},
+ epoch_max => $epoch_max,
};
- $sync->{ranges} = sync_ranges($self, $sync, $epoch_max);
- if (sync_prepare($self, $sync, $epoch_max)) {
+ my $quit = PublicInbox::SearchIdx::quit_cb($sync);
+ local $SIG{QUIT} = $quit;
+ local $SIG{INT} = $quit;
+ local $SIG{TERM} = $quit;
+
+ if (sync_prepare($self, $sync)) {
# tmp_clone seems to fail if inside a transaction, so
# we rollback here (because we opened {mm} for reading)
# Note: we do NOT rely on DBI transactions for atomicity;
# xapian_only works incrementally w/o --reindex
if ($seq && !$opt->{reindex}) {
- $art_beg = $sync->{mm_tmp}->max;
- $art_beg++ if defined($art_beg);
+ $art_beg = $sync->{mm_tmp}->max || -1;
+ $art_beg++;
}
}
- if ($sync->{max_size} = $opt->{max_size}) {
- $sync->{index_oid} = \&index_oid;
- }
# work forwards through history
- index_epoch($self, $sync, $_) for (0..$epoch_max);
- $self->{oidx}->rethread_done($opt);
+ index_todo($self, $sync, $_) for @{delete($sync->{todo}) // []};
+ $self->{oidx}->rethread_done($opt) unless $sync->{quit};
$self->done;
if (my $nr = $sync->{nr}) {
$pr->('all.git '.sprintf($sync->{-regen_fmt}, $$nr)) if $pr;
}
+ my $quit_warn;
# deal with Xapian shards sequentially
if ($seq && delete($sync->{mm_tmp})) {
- $self->{ibx}->{indexlevel} = $idxlevel;
- xapian_only($self, $opt, $sync, $art_beg);
+ if ($sync->{quit}) {
+ $quit_warn = 1;
+ } else {
+ $self->{ibx}->{indexlevel} = $idxlevel;
+ xapian_only($self, $opt, $sync, $art_beg);
+ $quit_warn = 1 if $sync->{quit};
+ }
}
# --reindex on the command-line
- if ($opt->{reindex} && !ref($opt->{reindex}) && $idxlevel ne 'basic') {
+ if (!$sync->{quit} && $opt->{reindex} &&
+ !ref($opt->{reindex}) && $idxlevel ne 'basic') {
$self->lock_acquire;
my $s0 = PublicInbox::SearchIdx->new($self->{ibx}, 0, 0);
if (my $xdb = $s0->idx_acquire) {
}
# reindex does not pick up new changes, so we rerun w/o it:
- if ($opt->{reindex}) {
+ if ($opt->{reindex} && !$sync->{quit} &&
+ !grep(defined, @$opt{qw(since until)})) {
my %again = %$opt;
$sync = undef;
delete @again{qw(rethread reindex -skip_lock)};
index_sync($self, \%again);
+ $opt->{quit} = $again{quit}; # propagate to caller
+ }
+ warn <<EOF if $quit_warn;
+W: interrupted, --xapian-only --reindex required upon restart
+EOF
+}
+
+sub ipc_atfork_child {
+ my ($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;