sub count_shards ($) {
my ($self) = @_;
- my $n = 0;
- my $xpfx = $self->{xpfx};
-
- # always load existing shards in case core count changes:
- # Also, shard count may change while -watch is running
- # due to "xcpdb --reshard"
- if (-d $xpfx) {
- my $XapianDatabase;
- foreach my $shard (<$xpfx/*>) {
- -d $shard && $shard =~ m!/[0-9]+\z! or next;
- $XapianDatabase //= do {
- require PublicInbox::Search;
- PublicInbox::Search::load_xapian();
- $PublicInbox::Search::X{Database};
- };
- eval {
- $XapianDatabase->new($shard)->close;
- $n++;
- };
- }
- }
- $n;
+ $self->{ibx} ? do {
+ # 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
+ } : $self->{nshard}; # self->{nshard} is for ExtSearchIdx
}
sub new {
total_bytes => 0,
current_info => '',
xpfx => $xpfx,
- over => PublicInbox::OverIdx->new("$xpfx/over.sqlite3"),
+ oidx => PublicInbox::OverIdx->new("$xpfx/over.sqlite3"),
lock_path => "$dir/inbox.lock",
# limit each git repo (epoch) to 1GB or so
rotate_bytes => int((1024 * 1024 * 1024) / $PACKING_FACTOR),
last_commit => [], # git epoch -> commit
};
- $self->{over}->{-no_fsync} = 1 if $v2ibx->{-no_fsync};
+ $self->{oidx}->{-no_fsync} = 1 if $v2ibx->{-no_fsync};
$self->{shards} = count_shards($self) || nproc_shards($creat);
bless $self, $class;
}
$self->idx_init;
$self->{mm}->skip_artnum($skip_artnum) if defined $skip_artnum;
my $epoch_max = -1;
- git_dir_latest($self, \$epoch_max);
+ $self->{ibx}->git_dir_latest(\$epoch_max);
if (defined $skip_epoch && $epoch_max == -1) {
$epoch_max = $skip_epoch;
}
$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);
- $self->{over}->add_overview($mime, $smsg);
- my $idx = idx_shard($self, $smsg->{num} % $self->{shards});
+ $self->{oidx}->add_overview($mime, $smsg);
+ my $idx = idx_shard($self, $smsg->{num});
$idx->index_raw($msgref, $mime, $smsg);
my $n = $self->{transact_bytes} += $smsg->{raw_bytes};
$n >= $self->{batch_bytes};
if ($altid && grep(/:file=msgmap\.sqlite3\z/, @$altid)) {
my $num = $self->{mm}->num_for($mid);
- if (defined $num && !$self->{over}->get_art($num)) {
+ if (defined $num && !$self->{oidx}->get_art($num)) {
return ($num, $mid);
}
}
($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->{over}->create;
+ $self->{oidx}->create;
# xcpdb can change shard count while -watch is idle
my $nshards = count_shards($self);
my $max = $self->{shards} - 1;
my $idx = $self->{idx_shards} = [];
push @$idx, PublicInbox::SearchIdxShard->new($self, $_) for (0..$max);
+ 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",
- $self->{ibx}->{-no_fsync} ? 2 : 1);
+ "$ibx->{inboxdir}/msgmap.sqlite3",
+ $ibx->{-no_fsync} ? 2 : 1);
$mm->{dbh}->begin_work;
}
+sub parallel_init ($$) {
+ my ($self, $indexlevel) = @_;
+ if (($indexlevel // 'full') eq 'basic') {
+ $self->{parallel} = 0;
+ } else {
+ pipe(my ($r, $w)) or die "pipe failed: $!";
+ # pipe for barrier notifications doesn't need to be big,
+ # 1031: F_SETPIPE_SZ
+ fcntl($w, 1031, 4096) if $^O eq 'linux';
+ $self->{bnote} = [ $r, $w ];
+ $w->autoflush(1);
+ }
+}
+
# idempotent
sub idx_init {
my ($self, $opt) = @_;
delete @$ibx{qw(mm search)};
$ibx->git->cleanup;
- $self->{parallel} = 0 if ($ibx->{indexlevel}//'') eq 'basic';
- if ($self->{parallel}) {
- pipe(my ($r, $w)) or die "pipe failed: $!";
- # pipe for barrier notifications doesn't need to be big,
- # 1031: F_SETPIPE_SZ
- fcntl($w, 1031, 4096) if $^O eq 'linux';
- $self->{bnote} = [ $r, $w ];
- $w->autoflush(1);
- }
-
+ parallel_init($self, $ibx->{indexlevel});
$ibx->umask_prepare;
$ibx->with_umask(\&_idx_init, $self, $opt);
}
sub _replace_oids ($$$) {
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;
+ defined(my $latest = $ibx->git_dir_latest(\$max)) or return;
$self->{epoch_max} = $max;
}
} else {
$im = $self->importer;
}
- my $over = $self->{over};
+ my $oidx = $self->{oidx};
my $chashes = content_hashes($old_eml);
my $removed = [];
my $mids = mids($old_eml);
foreach my $mid (@$mids) {
my %gone; # num => [ smsg, $mime, raw ]
my ($id, $prev);
- while (my $smsg = $over->next_by_mid($mid, \$id, \$prev)) {
+ while (my $smsg = $oidx->next_by_mid($mid, \$id, \$prev)) {
my $msg = get_blob($self, $smsg);
if (!defined($msg)) {
warn "broken smsg for $mid\n";
} else { # ->purge or ->remove
$self->{mm}->num_delete($num);
}
- unindex_oid_remote($self, $oid, $mid);
+ unindex_oid_aux($self, $oid, $mid);
}
}
my ($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 $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 $$raw or die "print \$w: $!";
}
# make sure we really got the OID:
- my ($blob, $type, $bytes) = $self->{ibx}->git->check($expect_oid);
+ my ($blob, $type, $bytes) = $self->git->check($expect_oid);
$blob eq $expect_oid or die "BUG: $expect_oid not found after replace";
# don't leak FDs to Xapian:
- $self->{ibx}->git->cleanup;
+ $self->git->cleanup;
# reindex modified messages:
for my $smsg (@$need_reindex) {
}
my $shards = $self->{idx_shards};
if ($shards) {
- my $dbh = $self->{mm}->{dbh};
+ my $mm = $self->{mm};
+ my $dbh = $mm->{dbh} if $mm;
# SQLite msgmap data is second in importance
- $dbh->commit;
+ $dbh->commit if $dbh;
# SQLite overview is third
- $self->{over}->commit_lazy;
+ $self->{oidx}->commit_lazy;
# Now deal with Xapian
if ($wait) {
}
# last_commit is special, don't commit these until
- # remote shards are done:
- $dbh->begin_work;
+ # Xapian shards are done:
+ $dbh->begin_work if $dbh;
set_last_commits($self);
- $dbh->commit;
-
- $dbh->begin_work;
+ if ($dbh) {
+ $dbh->commit;
+ $dbh->begin_work;
+ }
}
$self->{total_bytes} += $self->{transact_bytes};
$self->{transact_bytes} = 0;
# public
sub barrier { checkpoint($_[0], 1) };
+# true if locked and active
+sub active { !!$_[0]->{im} }
+
# public
sub done {
my ($self) = @_;
$err .= "shard close: $@\n" if $@;
}
}
- eval { $self->{over}->disconnect };
- $err .= "over disconnect: $@\n" if $@;
+ eval { $self->{oidx}->dbh_close };
+ $err .= "over close: $@\n" if $@;
delete $self->{bnote};
my $nbytes = $self->{total_bytes};
$self->{total_bytes} = 0;
$self->lock_release(!!$nbytes) if $shards;
- $self->{ibx}->git->cleanup;
+ $self->git->cleanup;
die $err if $err;
}
+sub write_alternates ($$$) {
+ 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 ($$) {
my ($self, $epoch) = @_;
}
}
return unless $new;
-
- my $fh = File::Temp->new(TEMPLATE => 'alt-XXXXXXXX', DIR => $info_dir);
- my $tmp = $fh->filename;
- print $fh join("\n", sort { $alt{$b} <=> $alt{$a} } keys %alt), "\n"
- or die "print $tmp: $!\n";
- chmod($mode, $fh) or die "fchmod $tmp: $!\n";
- close $fh or die "close $tmp $!\n";
- rename($tmp, $alt) or die "rename $tmp => $alt: $!\n";
- $fh->unlink_on_destroy(0);
+ write_alternates($info_dir, $mode,
+ [join("\n", sort { $alt{$b} <=> $alt{$a} } keys %alt), "\n"]);
}
sub git_init {
$git_dir
}
-sub git_dir_latest {
- my ($self, $max) = @_;
- $$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};
}
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;
sub content_exists ($$$) {
my ($self, $mime, $mid) = @_;
- my $over = $self->{over};
+ my $oidx = $self->{oidx};
my $chashes = content_hashes($mime);
my ($id, $prev);
- while (my $smsg = $over->next_by_mid($mid, \$id, \$prev)) {
+ while (my $smsg = $oidx->next_by_mid($mid, \$id, \$prev)) {
my $msg = get_blob($self, $smsg);
if (!defined($msg)) {
warn "broken smsg for $mid\n";
sub reindex_checkpoint ($$) {
my ($self, $sync) = @_;
- $self->{ibx}->git->cleanup; # *async_wait
+ $self->git->cleanup; # *async_wait
${$sync->{need_checkpoint}} = 0;
my $mm_tmp = $sync->{mm_tmp};
$mm_tmp->atfork_prepare if $mm_tmp;
}
}
if (!defined($num)) { # reuse if reindexing (or duplicates)
- my $over = $self->{over};
+ my $oidx = $self->{oidx};
for my $mid (@$mids) {
- ($num, $mid0) = $over->num_mid0_for_oid($oid, $mid);
+ ($num, $mid0) = $oidx->num_mid0_for_oid($oid, $mid);
last if defined $num;
}
}
}
# only update last_commit for $i on reindex iff newer than current
-sub update_last_commit ($$$$) {
+sub update_last_commit {
my ($self, $git, $i, $cmt) = @_;
my $last = last_epoch_commit($self, $i);
if (defined $last && is_ancestor($git, $last, $cmt)) {
last_epoch_commit($self, $i, $cmt);
}
-sub git_dir_n ($$) { "$_[0]->{ibx}->{inboxdir}/git/$_[1].git" }
-
sub last_commits ($$) {
my ($self, $epoch_max) = @_;
my $heads = [];
}
# returns a revision range for git-log(1)
-sub log_range ($$$$$) {
- my ($self, $sync, $git, $i, $tip) = @_;
+sub log_range ($$$$) {
+ my ($sync, $git, $i, $tip) = @_;
my $opt = $sync->{-opt};
my $pr = $opt->{-progress} if (($opt->{verbose} || 0) > 1);
my $cur = $sync->{ranges}->[$i] or do {
my ($self, $sync, $epoch_max) = @_;
my $pr = $sync->{-opt}->{-progress};
my $regen_max = 0;
- my $head = $self->{ibx}->{ref_head} || 'refs/heads/master';
+ my $head = $sync->{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};
+ my $reindex_heads = $self->last_commits($epoch_max) if $sync->{reindex};
for (my $i = $epoch_max; $i >= 0; $i--) {
- my $git_dir = git_dir_n($self, $i);
+ my $git_dir = $sync->{ibx}->git_dir_n($i);
-d $git_dir or next; # missing epochs are fine
my $git = PublicInbox::Git->new($git_dir);
if ($reindex_heads) {
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, $git, $i, $tip) or next;
# can't use 'rev-list --count' if we use --diff-filter
$pr->("$i.git counting $range ... ") if $pr;
# Don't bump num_highwater on --reindex by using {D}.
# 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);
my $nr = $stk ? $stk->num_records : 0;
$pr->("$nr\n") if $pr;
$sync->{stacks}->[$i] = $stk if $stk;
if (my @leftovers = keys %{delete($sync->{D}) // {}}) {
warn('W: unindexing '.scalar(@leftovers)." leftovers\n");
my $arg = { v2w => $self };
- my $all = $self->{ibx}->git;
for my $oid (@leftovers) {
$oid = unpack('H*', $oid);
$self->{current_info} = "leftover $oid";
- $all->cat_async($oid, \&unindex_oid, $arg);
+ $self->git->cat_async($oid, \&unindex_oid, $arg);
}
- $all->cat_async_wait;
+ $self->git->cat_async_wait;
}
- if (!$regen_max && !keys(%{$self->{unindex_range}})) {
+ if (!$regen_max) {
$sync->{-regen_fmt} = "%u/?\n";
return 0;
}
$regen_max + $self->{mm}->num_highwater() || 0;
}
-sub unindex_oid_remote ($$$) {
+sub unindex_oid_aux ($$$) {
my ($self, $oid, $mid) = @_;
- my @removed = $self->{over}->remove_oid($oid, $mid);
+ my @removed = $self->{oidx}->remove_oid($oid, $mid);
for my $num (@removed) {
- my $idx = idx_shard($self, $num % $self->{shards});
+ my $idx = idx_shard($self, $num);
$idx->shard_remove($oid, $num);
}
}
my $mm = $self->{mm};
my $mids = mids(PublicInbox::Eml->new($bref));
undef $$bref;
- my $over = $self->{over};
+ my $oidx = $self->{oidx};
foreach my $mid (@$mids) {
my %gone;
my ($id, $prev);
- while (my $smsg = $over->next_by_mid($mid, \$id, \$prev)) {
+ while (my $smsg = $oidx->next_by_mid($mid, \$id, \$prev)) {
$gone{$smsg->{num}} = 1 if $oid eq $smsg->{blob};
}
my $n = scalar(keys(%gone)) or next;
}
$mm->num_delete($num);
}
- unindex_oid_remote($self, $oid, $mid);
+ unindex_oid_aux($self, $oid, $mid);
}
}
+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 ($$$$) {
+sub unindex_epoch ($$$$) {
my ($self, $sync, $git, $unindex_range) = @_;
my $unindexed = $sync->{unindexed} //= {}; # $mid0 => $num
my $before = scalar keys %$unindexed;
my @cmd = qw(log --raw -r
--no-notes --no-color --no-abbrev --no-renames);
my $fh = $git->popen(@cmd, $unindex_range);
- my $all = $self->{ibx}->git;
local $sync->{in_unindex} = 1;
while (<$fh>) {
/\A:\d{6} 100644 $OID ($OID) [AM]\tm$/o or next;
- $all->cat_async($1, \&unindex_oid, $sync);
+ $self->git->cat_async($1, \&unindex_oid, $sync);
}
close $fh or die "git log failed: \$?=$?";
- $all->cat_async_wait;
+ $self->git->cat_async_wait;
return unless $sync->{-opt}->{prune};
my $after = scalar keys %$unindexed;
sub index_xap_only { # git->cat_async callback
my ($bref, $oid, $type, $size, $smsg) = @_;
my $self = $smsg->{v2w};
- my $idx = idx_shard($self, $smsg->{num} % $self->{shards});
+ my $idx = idx_shard($self, $smsg->{num});
$smsg->{raw_bytes} = $size;
$idx->index_raw($bref, undef, $smsg);
$self->{transact_bytes} += $size;
sub index_epoch ($$$) {
my ($self, $sync, $i) = @_;
- my $git_dir = git_dir_n($self, $i);
+ my $git_dir = $sync->{ibx}->git_dir_n($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, $unindex_range);
+ unindex_epoch($self, $sync, $git, $unindex_range);
}
defined(my $stk = $sync->{stacks}->[$i]) or return;
$sync->{stacks}->[$i] = undef;
- my $all = $self->{ibx}->git;
+ my $all = $self->git;
while (my ($f, $at, $ct, $oid) = $stk->pop_rec) {
$self->{current_info} = "$i.git $oid";
if ($f eq 'm') {
reindex_checkpoint($self, $sync);
}
}
- $all->check_async_wait;
- $all->cat_async_wait;
- update_last_commit($self, $git, $i, $stk->{latest_cmt});
+ $all->async_wait_all;
+ $self->update_last_commit($git, $i, $stk->{latest_cmt});
}
sub xapian_only {
$sync->{art_end} = $art_end;
if ($seq || !$self->{parallel}) {
my $shard_end = $self->{shards} - 1;
- for (0..$shard_end) {
- index_xap_step($self, $sync, $art_beg + $_)
+ for my $i (0..$shard_end) {
+ index_xap_step($self, $sync, $art_beg + $i);
+ if ($i != $shard_end) {
+ reindex_checkpoint($self, $sync);
+ }
}
} else { # parallel (maybe)
index_xap_step($self, $sync, $art_beg, 1);
}
}
- $self->{ibx}->git->cat_async_wait;
+ $self->git->cat_async_wait;
$self->done;
}
# public, called by public-inbox-index
sub index_sync {
my ($self, $opt) = @_;
- $opt //= $_[1] //= {};
- goto \&xapian_only if $opt->{xapian_only};
+ $opt //= {};
+ return xapian_only($self, $opt) if $opt->{xapian_only};
my $pr = $opt->{-progress};
my $epoch_max;
- my $latest = git_dir_latest($self, \$epoch_max);
+ my $latest = $self->{ibx}->git_dir_latest(\$epoch_max);
return unless defined $latest;
my $seq = $opt->{sequential_shard};
$self->idx_init($opt); # acquire lock
fill_alternates($self, $epoch_max);
- $self->{over}->rethread_prepare($opt);
+ $self->{oidx}->rethread_prepare($opt);
my $sync = {
need_checkpoint => \(my $bool = 0),
unindex_range => {}, # EPOCH => oid_old..oid_new
reindex => $opt->{reindex},
-opt => $opt,
v2w => $self,
+ ibx => $self->{ibx},
};
$sync->{ranges} = sync_ranges($self, $sync, $epoch_max);
if (sync_prepare($self, $sync, $epoch_max)) {
}
# work forwards through history
index_epoch($self, $sync, $_) for (0..$epoch_max);
- $self->{over}->rethread_done($opt);
+ $self->{oidx}->rethread_done($opt);
$self->done;
if (my $nr = $sync->{nr}) {
my $s0 = PublicInbox::SearchIdx->new($self->{ibx}, 0, 0);
if (my $xdb = $s0->idx_acquire) {
my $n = $xdb->get_metadata('has_threadid');
- $xdb->set_metadata('has_threadid', 1) if $n ne '1';
+ $xdb->set_metadata('has_threadid', '1') if $n ne '1';
}
$s0->idx_release;
$self->lock_release;