diff options
Diffstat (limited to 'lib/PublicInbox/V2Writable.pm')
| -rw-r--r-- | lib/PublicInbox/V2Writable.pm | 1434 |
1 files changed, 692 insertions, 742 deletions
diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm index fc2f33f9..43f37f60 100644 --- a/lib/PublicInbox/V2Writable.pm +++ b/lib/PublicInbox/V2Writable.pm @@ -1,90 +1,44 @@ -# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org> +# Copyright (C) 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 # Used to write to V2 inboxes (see L<public-inbox-v2-format(5)>). package PublicInbox::V2Writable; use strict; -use warnings; -use base qw(PublicInbox::Lock); -use 5.010_001; +use v5.10.1; +use parent qw(PublicInbox::Lock PublicInbox::IPC); use PublicInbox::SearchIdxShard; -use PublicInbox::MIME; +use PublicInbox::IPC qw(nproc_shards); +use PublicInbox::Eml; use PublicInbox::Git; use PublicInbox::Import; +use PublicInbox::MultiGit; use PublicInbox::MID qw(mids references); -use PublicInbox::ContentId qw(content_id content_digest); -use PublicInbox::Inbox; +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; +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 qw(tempfile); +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; - -# SATA storage lags behind what CPUs are capable of, so relying on -# nproc(1) can be misleading and having extra Xapian shards is a -# waste of FDs and space. It can also lead to excessive IO latency -# and slow things down. Users on NVME or other fast storage can -# use the NPROC env or switches in our script/public-inbox-* programs -# to increase Xapian shards -our $NPROC_MAX_DEFAULT = 4; - -sub detect_nproc () { - for my $nproc (qw(nproc gnproc)) { # GNU coreutils nproc - `$nproc 2>/dev/null` =~ /^(\d+)$/ and return $1; - } - - # getconf(1) is POSIX, but *NPROCESSORS* vars are not - for (qw(_NPROCESSORS_ONLN NPROCESSORS_ONLN)) { - `getconf $_ 2>/dev/null` =~ /^(\d+)$/ 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; - $n = $NPROC_DETECTED; - $n = $NPROC_MAX_DEFAULT if $n > $NPROC_MAX_DEFAULT; - } - - # subtract for the main process and git-fast-import - $n -= 1; - $n < 1 ? 1 : $n; -} +our $PACKING_FACTOR = 0.4; sub count_shards ($) { 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) { - require PublicInbox::Search; - PublicInbox::Search::load_xapian(); - my $XapianDatabase = $PublicInbox::Search::X{Database}; - foreach my $shard (<$xpfx/*>) { - -d $shard && $shard =~ m!/[0-9]+\z! or next; - eval { - $XapianDatabase->new($shard)->close; - $n++; - }; - } + 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); } - $n; } sub new { @@ -94,75 +48,72 @@ 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 = { - -inbox => $v2ibx, + ibx => $v2ibx, + mg => PublicInbox::MultiGit->new($dir, 'all.git', 'git'), im => undef, # PublicInbox::Import parallel => 1, transact_bytes => 0, + total_bytes => 0, current_info => '', xpfx => $xpfx, - over => PublicInbox::OverIdx->new("$xpfx/over.sqlite3", 1), + 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 repo -> commit + last_commit => [], # git epoch -> commit }; + $self->{oidx}->{-no_fsync} = 1 if $v2ibx->{-no_fsync}; $self->{shards} = count_shards($self) || nproc_shards($creat); bless $self, $class; } # public (for now?) sub init_inbox { - my ($self, $shards, $skip_epoch) = @_; + my ($self, $shards, $skip_epoch, $skip_artnum) = @_; if (defined $shards) { $self->{parallel} = 0 if $shards == 0; $self->{shards} = $shards if $shards > 0; } $self->idx_init; - 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); + $self->{mm}->skip_artnum($skip_artnum) if defined $skip_artnum; + my $max = $self->{ibx}->max_git_epoch; + $max = $skip_epoch if (defined($skip_epoch) && !defined($max)); + $self->{mg}->add_epoch($max // 0); $self->done; } -# returns undef on duplicate or spam -# mimics Import::add and wraps it for v2 -sub add { - my ($self, $mime, $check_cb) = @_; - $self->{-inbox}->with_umask(sub { - _add($self, $mime, $check_cb) - }); +sub idx_shard ($$) { + my ($self, $num) = @_; + $self->{idx_shards}->[$num % scalar(@{$self->{idx_shards}})]; } # indexes a message, returns true if checkpointing is needed -sub do_idx ($$$$$$$) { - my ($self, $msgref, $mime, $len, $num, $oid, $mid0) = @_; - $self->{over}->add_overview($mime, $len, $num, $oid, $mid0); - my $idx = idx_shard($self, $num % $self->{shards}); - $idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime); - my $n = $self->{transact_bytes} += $len; - $n >= (PublicInbox::SearchIdx::BATCH_BYTES * $self->{shards}); +sub do_idx ($$$) { + 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 >= $self->{batch_bytes}; } -sub _add { +# returns undef on duplicate or spam +# mimics Import::add and wraps it for v2 +sub add { my ($self, $mime, $check_cb) = @_; + my $restore = $self->{ibx}->with_umask; # spam check: if ($check_cb) { - $mime = $check_cb->($mime) or return; + $mime = $check_cb->($mime, $self->{ibx}) or return; } # All pipes (> $^F) known to Perl 5.6+ have FD_CLOEXEC set, @@ -174,23 +125,22 @@ sub _add { my ($num, $mid0) = v2_num_for($self, $mime); defined $num or return; # duplicate - defined $mid0 or die "BUG: $mid0 undefined\n"; + defined $mid0 or die "BUG: \$mid0 undefined\n"; my $im = $self->importer; - my $cmt = $im->add($mime); + my $smsg = bless { mid => $mid0, num => $num }, 'PublicInbox::Smsg'; + my $cmt = $im->add($mime, undef, $smsg); # sets $smsg->{ds|ts|blob} $cmt = $im->get_mark($cmt); $self->{last_commit}->[$self->{epoch_max}] = $cmt; - my ($oid, $len, $msgref) = @{$im->{last_object}}; - if (do_idx($self, $msgref, $mime, $len, $num, $oid, $mid0)) { + if (do_idx($self, $mime, $smsg)) { $self->checkpoint; } - $cmt; } sub v2_num_for { my ($self, $mime) = @_; - my $mids = mids($mime->header_obj); + my $mids = mids($mime); if (@$mids) { my $mid = $mids->[0]; my $num = $self->{mm}->mid_insert($mid); @@ -201,21 +151,20 @@ sub v2_num_for { # crap, Message-ID is already known, hope somebody just resent: foreach my $m (@$mids) { # read-only lookup now safe to do after above barrier - my $existing = lookup_content($self, $mime, $m); # easy, don't store duplicates # note: do not add more diagnostic info here since # it gets noisy on public-inbox-watch restarts - return () if $existing; + return () if content_exists($self, $mime, $m); } # AltId may pre-populate article numbers (e.g. X-Mail-Count # or NNTP article number), use that article number if it's # not in Over. - my $altid = $self->{-inbox}->{altid}; + my $altid = $self->{ibx}->{altid}; if ($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, $mid); } } @@ -238,88 +187,79 @@ sub v2_num_for { } sub v2_num_for_harder { - my ($self, $mime) = @_; + my ($self, $eml) = @_; - my $hdr = $mime->header_obj; - my $dig = content_digest($mime); - my $mid0 = PublicInbox::Import::digest2mid($dig, $hdr); + my $dig = content_digest($eml); + my $mid0 = PublicInbox::Import::digest2mid($dig, $eml); my $num = $self->{mm}->mid_insert($mid0); unless (defined $num) { # it's hard to spoof the last Received: header - my @recvd = $hdr->header_raw('Received'); + my @recvd = $eml->header_raw('Received'); $dig->add("Received: $_") foreach (@recvd); - $mid0 = PublicInbox::Import::digest2mid($dig, $hdr); + $mid0 = PublicInbox::Import::digest2mid($dig, $eml); $num = $self->{mm}->mid_insert($mid0); # fall back to a random Message-ID and give up determinism: until (defined($num)) { $dig->add(rand); - $mid0 = PublicInbox::Import::digest2mid($dig, $hdr); + $mid0 = PublicInbox::Import::digest2mid($dig, $eml); warn "using random Message-ID <$mid0> as fallback\n"; $num = $self->{mm}->mid_insert($mid0); } } - PublicInbox::Import::append_mid($hdr, $mid0); + PublicInbox::Import::append_mid($eml, $mid0); ($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->{oidx}->create; + + # xcpdb can change shard count while -watch is idle + my $nshards = count_shards($self); + $self->{shards} = $nshards if $nshards && $nshards != $self->{shards}; + $self->{batch_bytes} = $opt->{batch_size} // + $PublicInbox::SearchIdx::BATCH_BYTES; + + # 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 = $self->{mm} = PublicInbox::Msgmap->new_file($ibx, 1); + $mm->{dbh}->begin_work; +} + +sub parallel_init ($$) { + my ($self, $indexlevel) = @_; + $self->{parallel} = 0 if ($indexlevel // 'full') eq 'basic'; } # idempotent sub idx_init { my ($self, $opt) = @_; return if $self->{idx_shards}; - my $ibx = $self->{-inbox}; + my $ibx = $self->{ibx}; # do not leak read-only FDs to child processes, we only have these # FDs for duplicate detection so they should not be # frequently activated. - delete $ibx->{$_} foreach (qw(git mm search)); + delete @$ibx{qw(mm search)}; + $ibx->git->cleanup; - my $indexlevel = $ibx->{indexlevel}; - if ($indexlevel && $indexlevel eq 'basic') { - $self->{parallel} = 0; - } - - if ($self->{parallel}) { - pipe(my ($r, $w)) or die "pipe failed: $!"; - # pipe for barrier notifications doesn't need to be big, - # 1031: F_SETPIPE_SZ - fcntl($w, 1031, 4096) if $^O eq 'linux'; - $self->{bnote} = [ $r, $w ]; - $w->autoflush(1); - } - - my $over = $self->{over}; - $ibx->umask_prepare; - $ibx->with_umask(sub { - $self->lock_acquire unless ($opt && $opt->{-skip_lock}); - $over->create; - - # xcpdb can change shard count while -watch is idle - my $nshards = count_shards($self); - if ($nshards && $nshards != $self->{shards}) { - $self->{shards} = $nshards; - } - - # need to create all shards before initializing msgmap FD - my $max = $self->{shards} - 1; - - # idx_shards must be visible to all forked processes - my $idx = $self->{idx_shards} = []; - for my $i (0..$max) { - push @$idx, PublicInbox::SearchIdxShard->new($self, $i); - } - - # Now that all subprocesses are up, we can open the FDs - # for SQLite: - my $mm = $self->{mm} = PublicInbox::Msgmap->new_file( - "$self->{-inbox}->{inboxdir}/msgmap.sqlite3", 1); - $mm->{dbh}->begin_work; - }); + parallel_init($self, $ibx->{indexlevel}); + $ibx->with_umask(\&_idx_init, $self, $opt); } # returns an array mapping [ epoch => latest_commit ] @@ -328,14 +268,10 @@ sub idx_init { sub _replace_oids ($$$) { my ($self, $mime, $replace_map) = @_; $self->done; - my $pfx = "$self->{-inbox}->{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"; @@ -348,62 +284,62 @@ sub _replace_oids ($$$) { $rewrites; } -sub content_ids ($) { +sub content_hashes ($) { my ($mime) = @_; - my @cids = ( content_id($mime) ); + my @chashes = ( content_hash($mime) ); + # We still support Email::MIME, here, and # Email::MIME->as_string doesn't always round-trip, so we may - # use a second content_id - my $rt = content_id(PublicInbox::MIME->new(\($mime->as_string))); - push @cids, $rt if $cids[0] ne $rt; - \@cids; + # use a second content_hash + my $rt = content_hash(PublicInbox::Eml->new(\($mime->as_string))); + push @chashes, $rt if $chashes[0] ne $rt; + \@chashes; } sub content_matches ($$) { - my ($cids, $existing) = @_; - my $cid = content_id($existing); - foreach (@$cids) { - return 1 if $_ eq $cid + my ($chashes, $existing) = @_; + my $chash = content_hash($existing); + foreach (@$chashes) { + return 1 if $_ eq $chash } 0 } # used for removing or replacing (purging) sub rewrite_internal ($$;$$$) { - my ($self, $old_mime, $cmt_msg, $new_mime, $sref) = @_; + my ($self, $old_eml, $cmt_msg, $new_eml, $sref) = @_; $self->idx_init; my ($im, $need_reindex, $replace_map); if ($sref) { $replace_map = {}; # oid => sref - $need_reindex = [] if $new_mime; + $need_reindex = [] if $new_eml; } else { $im = $self->importer; } - my $over = $self->{over}; - my $cids = content_ids($old_mime); - my $removed; - my $mids = mids($old_mime->header_obj); + my $oidx = $self->{oidx}; + my $chashes = content_hashes($old_eml); + my $removed = []; + my $mids = mids($old_eml); # We avoid introducing new blobs into git since the raw content # can be slightly different, so we do not need the user-supplied - # message now that we have the mids and content_id - $old_mime = undef; + # message now that we have the mids and content_hash + $old_eml = undef; my $mark; foreach my $mid (@$mids) { - my %gone; # num => [ smsg, raw ] + my %gone; # num => [ smsg, $mime, raw ] my ($id, $prev); - while (my $smsg = $over->next_by_mid($mid, \$id, \$prev)) { + while (my $smsg = $oidx->next_by_mid($mid, \$id, \$prev)) { my $msg = get_blob($self, $smsg); if (!defined($msg)) { warn "broken smsg for $mid\n"; next; # continue } my $orig = $$msg; - my $cur = PublicInbox::MIME->new($msg); - if (content_matches($cids, $cur)) { - $smsg->{mime} = $cur; - $gone{$smsg->{num}} = [ $smsg, \$orig ]; + my $cur = PublicInbox::Eml->new($msg); + if (content_matches($chashes, $cur)) { + $gone{$smsg->{num}} = [ $smsg, $cur, \$orig ]; } } my $n = scalar keys %gone; @@ -413,15 +349,16 @@ sub rewrite_internal ($$;$$$) { join(',', sort keys %gone), "\n"; } foreach my $num (keys %gone) { - my ($smsg, $orig) = @{$gone{$num}}; + my ($smsg, $mime, $orig) = @{$gone{$num}}; # $removed should only be set once assuming # no bugs in our deduplication code: - $removed = $smsg; + $removed = [ undef, $mime, $smsg ]; my $oid = $smsg->{blob}; if ($replace_map) { $replace_map->{$oid} = $sref; } else { ($mark, undef) = $im->remove($orig, $cmt_msg); + $removed->[0] = $mark; } $orig = undef; if ($need_reindex) { # ->replace @@ -429,7 +366,7 @@ sub rewrite_internal ($$;$$$) { } else { # ->purge or ->remove $self->{mm}->num_delete($num); } - unindex_oid_remote($self, $oid, $mid); + unindex_oid_aux($self, $oid, $mid); } } @@ -438,26 +375,26 @@ sub rewrite_internal ($$;$$$) { $self->{last_commit}->[$self->{epoch_max}] = $cmt; } if ($replace_map && scalar keys %$replace_map) { - my $rewrites = _replace_oids($self, $new_mime, $replace_map); + my $rewrites = _replace_oids($self, $new_eml, $replace_map); return { rewrites => $rewrites, need_reindex => $need_reindex }; } - $removed; + defined($mark) ? $removed : undef; } -# public +# public (see PublicInbox::Import->remove), but note the 3rd element +# (retval[2]) is not part of the stable API shared with Import->remove sub remove { - my ($self, $mime, $cmt_msg) = @_; - $self->{-inbox}->with_umask(sub { - rewrite_internal($self, $mime, $cmt_msg); - }); + my ($self, $eml, $cmt_msg) = @_; + my $restore = $self->{ibx}->with_umask; + my $r = rewrite_internal($self, $eml, $cmt_msg); + defined($r) && defined($r->[0]) ? @$r: undef; } sub _replace ($$;$$) { - my ($self, $old_mime, $new_mime, $sref) = @_; - my $rewritten = $self->{-inbox}->with_umask(sub { - rewrite_internal($self, $old_mime, undef, $new_mime, $sref); - }) or return; - + my ($self, $old_eml, $new_eml, $sref) = @_; + my $restore = $self->{ibx}->with_umask; + my $rewritten = rewrite_internal($self, $old_eml, undef, + $new_eml, $sref) or return; my $rewrites = $rewritten->{rewrites}; # ->done is called if there are rewrites since we gc+prune from git $self->idx_init if @$rewrites; @@ -476,25 +413,6 @@ sub purge { $rewritten->{rewrites} } -# returns the git object_id of $fh, does not write the object to FS -sub git_hash_raw ($$) { - my ($self, $raw) = @_; - # grab the expected OID we have to reindex: - open my $tmp_fh, '+>', undef or die "failed to open tmp: $!"; - $tmp_fh->autoflush(1); - print $tmp_fh $$raw or die "print \$tmp_fh: $!"; - sysseek($tmp_fh, 0, 0) or die "seek failed: $!"; - - my $git_dir = $self->{-inbox}->git->{git_dir}; - my $cmd = ['git', "--git-dir=$git_dir", qw(hash-object --stdin)]; - my $r = popen_rd($cmd, undef, { 0 => $tmp_fh }); - local $/ = "\n"; - chomp(my $oid = <$r>); - close $r or die "git hash-object failed: $?"; - $oid =~ /\A[a-f0-9]{40}\z/ or die "OID not expected: $oid"; - $oid; -} - sub _check_mids_match ($$$) { my ($old_list, $new_list, $hdrs) = @_; my %old_mids = map { $_ => 1 } @$old_list; @@ -513,9 +431,7 @@ sub _check_mids_match ($$$) { # Message-IDs are pretty complex and rethreading hasn't been fully # implemented, yet. sub check_mids_match ($$) { - my ($old_mime, $new_mime) = @_; - my $old = $old_mime->header_obj; - my $new = $new_mime->header_obj; + my ($old, $new) = @_; _check_mids_match(mids($old), mids($new), 'Message-ID(s)'); _check_mids_match(references($old), references($new), 'References/In-Reply-To'); @@ -531,7 +447,7 @@ sub replace ($$$) { 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}; @@ -549,17 +465,23 @@ W: $list } # make sure we really got the OID: - my ($oid, $type, $len) = $self->{-inbox}->git->check($expect_oid); - $oid eq $expect_oid or die "BUG: $expect_oid not found after replace"; + my ($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->{-inbox}->git->cleanup; + $self->git->cleanup; # reindex modified messages: for my $smsg (@$need_reindex) { - my $num = $smsg->{num}; - my $mid0 = $smsg->{mid}; - do_idx($self, \$raw, $new_mime, $len, $num, $oid, $mid0); + my $new_smsg = bless { + blob => $blob, + num => $smsg->{num}, + mid => $smsg->{mid}, + }, 'PublicInbox::Smsg'; + my $sync = { autime => $smsg->{ds}, cotime => $smsg->{ts} }; + $new_smsg->populate($new_mime, $sync); + $new_smsg->set_bytes($raw, $bytes); + do_idx($self, $new_mime, $new_smsg); } $rewritten->{rewrites}; } @@ -570,7 +492,7 @@ sub last_epoch_commit ($$;$) { $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}; @@ -581,66 +503,59 @@ sub set_last_commits ($) { } } -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 = $r->getline) 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) = @_; - if (my $im = $self->{im}) { - if ($wait) { - $im->barrier; - } else { - $im->checkpoint; - } - } + $self->{im}->barrier if $self->{im}; 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->{over}->commit_lazy; + $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 - $_->remote_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 { - $_->remote_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; } @@ -649,100 +564,46 @@ sub checkpoint ($;$) { # public sub barrier { checkpoint($_[0], 1) }; +# true if locked and active +sub active { !!$_[0]->{im} } + # public sub done { my ($self) = @_; - my $im = delete $self->{im}; - $im->done if $im; # PublicInbox::Import::done - checkpoint($self); - my $mm = delete $self->{mm}; - $mm->{dbh}->commit if $mm; - my $shards = delete $self->{idx_shards}; - if ($shards) { - $_->remote_close for @$shards; + my $err = ''; + if (my $im = delete $self->{im}) { + eval { $im->done }; # PublicInbox::Import::done + $err .= "import done: $@\n" if $@; } - $self->{over}->disconnect; - delete $self->{bnote}; - $self->{transact_bytes} = 0; - $self->lock_release if $shards; - $self->{-inbox}->git->cleanup; -} - -sub fill_alternates ($$) { - my ($self, $epoch) = @_; - - my $pfx = "$self->{-inbox}->{inboxdir}/git"; - my $all = "$self->{-inbox}->{inboxdir}/all.git"; - - unless (-d $all) { - PublicInbox::Import::init_bare($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 when we - 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> }); + if (!$err) { + eval { checkpoint($self) }; + $err .= "checkpoint: $@\n" if $@; } - - foreach my $i (0..$epoch) { - my $dir = "../../git/$i.git/objects"; - if (!exists($alt{$dir}) && -d "$pfx/$i.git") { - $alt{$dir} = $i; - $new = 1; - } + if (my $mm = delete $self->{mm}) { + my $m = $err ? 'rollback' : 'commit'; + 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 $@; } - return unless $new; - - my ($fh, $tmp) = tempfile('alt-XXXXXXXX', DIR => $info_dir); - 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: $!\n"; -} - -sub git_init { - my ($self, $epoch) = @_; - my $git_dir = "$self->{-inbox}->{inboxdir}/git/$epoch.git"; - my @cmd = (qw(git init --bare -q), $git_dir); - PublicInbox::Import::run_die(\@cmd); - @cmd = (qw/git config/, "--file=$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) = @_; - $$max = -1; - my $pfx = "$self->{-inbox}->{inboxdir}/git"; - return unless -d $pfx; - my $latest; - opendir my $dh, $pfx or die "opendir $pfx: $!\n"; - while (defined(my $git_dir = readdir($dh))) { - $git_dir =~ m!\A([0-9]+)\.git\z! or next; - if ($1 > $$max) { - $$max = $1; - $latest = "$pfx/$git_dir"; + my $shards = delete $self->{idx_shards}; + if ($shards) { + for (@$shards) { + eval { $_->shard_close }; + $err .= "shard close: $@\n" if $@; } } - $latest; + eval { $self->{oidx}->dbh_close }; + $err .= "over close: $@\n" if $@; + delete $self->{midx}; + my $nbytes = $self->{total_bytes}; + $self->{total_bytes} = 0; + $self->lock_release(!!$nbytes) if $shards; + $self->git->cleanup; + die $err if $err; } sub importer { @@ -756,14 +617,14 @@ sub importer { $im->done; $im = undef; $self->checkpoint; - my $git_dir = $self->git_init(++$self->{epoch_max}); - my $git = PublicInbox::Git->new($git_dir); + my $dir = $self->{mg}->add_epoch(++$self->{epoch_max}); + my $git = PublicInbox::Git->new($dir); return $self->import_init($git, 0); } } my $epoch = 0; my $max; - my $latest = git_dir_latest($self, \$max); + my $latest = $self->{ibx}->git_dir_latest(\$max); if (defined $latest) { my $git = PublicInbox::Git->new($latest); my $packed_bytes = $git->packed_bytes; @@ -777,39 +638,20 @@ sub importer { } } $self->{epoch_max} = $epoch; - $latest = $self->git_init($epoch); - $self->import_init(PublicInbox::Git->new($latest), 0); + my $dir = $self->{mg}->add_epoch($epoch); + $self->import_init(PublicInbox::Git->new($dir), 0); } sub import_init { my ($self, $git, $packed_bytes, $tmp) = @_; - my $im = PublicInbox::Import->new($git, undef, undef, $self->{-inbox}); + my $im = PublicInbox::Import->new($git, undef, undef, $self->{ibx}); $im->{bytes_added} = int($packed_bytes / $PACKING_FACTOR); - $im->{want_object_info} = 1; $im->{lock_path} = undef; $im->{path_type} = 'v2'; $self->{im} = $im unless $tmp; $im; } -# XXX experimental -sub diff ($$$) { - my ($mid, $cur, $new) = @_; - - my ($ah, $an) = tempfile('email-cur-XXXXXXXX', TMPDIR => 1); - print $ah $cur->as_string or die "print: $!"; - close $ah or die "close: $!"; - my ($bh, $bn) = tempfile('email-new-XXXXXXXX', TMPDIR => 1); - PublicInbox::Import::drop_unwanted_headers($new); - print $bh $new->as_string or die "print: $!"; - close $bh or die "close: $!"; - my $cmd = [ qw(diff -u), $an, $bn ]; - print STDERR "# MID conflict <$mid>\n"; - my $pid = spawn($cmd, undef, { 1 => 2 }); - waitpid($pid, 0) == $pid or die "diff did not finish"; - unlink($an, $bn); -} - sub get_blob ($$) { my ($self, $smsg) = @_; if (my $im = $self->{im}) { @@ -817,273 +659,199 @@ sub get_blob ($$) { return $msg if $msg; } # older message, should be in alternates - my $ibx = $self->{-inbox}; - $ibx->msg_by_smsg($smsg); + $self->{ibx}->msg_by_smsg($smsg); } -sub lookup_content ($$$) { +sub content_exists ($$$) { my ($self, $mime, $mid) = @_; - my $over = $self->{over}; - my $cids = content_ids($mime); + 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"; next; } - my $cur = PublicInbox::MIME->new($msg); - if (content_matches($cids, $cur)) { - $smsg->{mime} = $cur; - return $smsg; - } - - - # XXX DEBUG_DIFF is experimental and may be removed - diff($mid, $cur, $mime) if $ENV{DEBUG_DIFF}; + my $cur = PublicInbox::Eml->new($msg); + return 1 if content_matches($chashes, $cur); } undef; } sub atfork_child { my ($self) = @_; - my $fh = delete $self->{reindex_pipe}; - close $fh if $fh; - 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 mark_deleted ($$$$) { - my ($self, $sync, $git, $oid) = @_; - my $msgref = $git->cat_file($oid); - my $mime = PublicInbox::MIME->new($$msgref); - my $mids = mids($mime->header_obj); - my $cid = content_id($mime); - foreach my $mid (@$mids) { - $sync->{D}->{"$mid\0$cid"} = $oid; +sub reindex_checkpoint ($$) { + my ($self, $sync) = @_; + + $self->git->async_wait_all; + $self->update_last_commit($sync); + ${$sync->{need_checkpoint}} = 0; + my $mm_tmp = $sync->{mm_tmp}; + $mm_tmp->atfork_prepare if $mm_tmp; + die 'BUG: {im} during reindex' if $self->{im}; + if ($self->{ibx_map} && !$sync->{checkpoint_unlocks}) { + checkpoint($self, 1); # no need to release lock on pure index + } else { + $self->done; # release lock } -} -sub reindex_checkpoint ($$$) { - my ($self, $sync, $git) = @_; - - $git->cleanup; - $sync->{mm_tmp}->atfork_prepare; - $self->done; # release lock - - if (my $pr = $sync->{-opt}->{-progress}) { - my ($bn) = (split('/', $git->{git_dir}))[-1]; - $pr->("$bn ".sprintf($sync->{-regen_fmt}, $sync->{nr})); + 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; # reacquire lock - $sync->{mm_tmp}->atfork_parent; -} - -# only for a few odd messages with multiple Message-IDs -sub reindex_oid_m ($$$$;$) { - my ($self, $sync, $git, $oid, $regen_num) = @_; - $self->{current_info} = "multi_mid $oid"; - my ($num, $mid0, $len); - my $msgref = $git->cat_file($oid, \$len); - my $mime = PublicInbox::MIME->new($$msgref); - my $mids = mids($mime->header_obj); - my $cid = content_id($mime); - die "BUG: reindex_oid_m called for <=1 mids" if scalar(@$mids) <= 1; - - for my $mid (reverse @$mids) { - delete($sync->{D}->{"$mid\0$cid"}) and - die "BUG: reindex_oid should handle <$mid> delete"; - } - my $over = $self->{over}; - for my $mid (reverse @$mids) { - ($num, $mid0) = $over->num_mid0_for_oid($oid, $mid); - next unless defined $num; - if (defined($regen_num) && $regen_num != $num) { - die "BUG: regen(#$regen_num) != over(#$num)"; - } - } - unless (defined($num)) { - for my $mid (reverse @$mids) { - # is this a number we got before? - my $n = $sync->{mm_tmp}->num_for($mid); - next unless defined $n; - next if defined($regen_num) && $regen_num != $n; - ($num, $mid0) = ($n, $mid); - last; - } - } - if (defined($num)) { - $sync->{mm_tmp}->num_delete($num); - } elsif (defined $regen_num) { - $num = $regen_num; - for my $mid (reverse @$mids) { - $self->{mm}->mid_set($num, $mid) == 1 or next; - $mid0 = $mid; - last; - } - unless (defined $mid0) { - warn "E: cannot regen #$num\n"; - return; - } - } else { # fixup bugs in old mirrors on reindex - for my $mid (reverse @$mids) { - $num = $self->{mm}->mid_insert($mid); - next unless defined $num; - $mid0 = $mid; - last; - } - if (defined $mid0) { - if ($sync->{reindex}) { - warn "reindex added #$num <$mid0>\n"; - } - } else { - warn "E: cannot find article #\n"; - return; - } - } - $sync->{nr}++; - if (do_idx($self, $msgref, $mime, $len, $num, $oid, $mid0)) { - reindex_checkpoint($self, $sync, $git); + $self->idx_init($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 check_unindexed ($$$) { - my ($self, $num, $mid0) = @_; - my $unindexed = $self->{unindexed} // {}; - my $n = delete($unindexed->{$mid0}); - defined $n or return; - if ($n != $num) { - die "BUG: unindexed $n != $num <$mid0>\n"; - } else { - $self->{mm}->mid_set($num, $mid0); - } +sub index_finalize ($$) { + 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} } -# reuse Msgmap to store num => oid mapping (rather than num => mid) -sub multi_mid_q_new () { - my ($fh, $fn) = tempfile('multi_mid-XXXXXXX', EXLOCK => 0, TMPDIR => 1); - my $multi_mid = PublicInbox::Msgmap->new_file($fn, 1); - $multi_mid->{dbh}->do('PRAGMA synchronous = OFF'); - # for Msgmap->DESTROY: - $multi_mid->{tmp_name} = $fn; - $multi_mid->{pid} = $$; - close $fh or die "failed to close $fn: $!"; - $multi_mid -} - -sub multi_mid_q_push ($$) { - my ($sync, $oid) = @_; - my $multi_mid = $sync->{multi_mid} //= multi_mid_q_new(); - if ($sync->{reindex}) { # no regen on reindex - $multi_mid->mid_insert($oid); - } else { - my $num = $sync->{regen}--; - die "BUG: ran out of article numbers" if $num <= 0; - $multi_mid->mid_set($num, $oid); - } -} - -sub reindex_oid ($$$$) { - my ($self, $sync, $git, $oid) = @_; - my ($num, $mid0, $len); - my $msgref = $git->cat_file($oid, \$len); - return if $len == 0; # purged - my $mime = PublicInbox::MIME->new($$msgref); - my $mids = mids($mime->header_obj); - my $cid = content_id($mime); +sub index_oid { # cat_async callback + my ($bref, $oid, $type, $size, $arg) = @_; + is_bad_blob($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); if (scalar(@$mids) == 0) { warn "E: $oid has no Message-ID, skipping\n"; return; - } elsif (scalar(@$mids) == 1) { - my $mid = $mids->[0]; + } - # was the file previously marked as deleted?, skip if so - if (delete($sync->{D}->{"$mid\0$cid"})) { - if (!$sync->{reindex}) { - $num = $sync->{regen}--; - $self->{mm}->num_highwater($num); + # {unindexed} is unlikely + 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) { + $self->{mm}->mid_set($num, $mid0); + if (scalar(@$u) == 0) { # done with current OID + delete $unindexed->{$oidbin}; + delete($arg->{unindexed}) if !keys(%$unindexed); } - return; } + } + my $oidx = $self->{oidx}; + if (!defined($num)) { # reuse if reindexing (or duplicates) + 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]); - # is this a number we got before? - $num = $sync->{mm_tmp}->num_for($mid); - if (defined $num) { - $mid0 = $mid; - check_unindexed($self, $num, $mid0); - } else { - $num = $sync->{regen}--; - die "BUG: ran out of article numbers" if $num <= 0; - if ($self->{mm}->mid_set($num, $mid) != 1) { - warn "E: unable to assign $num => <$mid>\n"; - return; - } - $mid0 = $mid; + # 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; } - } else { # multiple MIDs are a weird case: - my $del = 0; - for (@$mids) { - $del += delete($sync->{D}->{"$_\0$cid"}) // 0; + defined($num) ? $mids->[0] : undef; + }; + if (!defined($num)) { + for (my $i = $#$mids; $i >= 1; $i--) { + $num = $arg->{mm_tmp}->num_for($mids->[$i]); + if (defined($num)) { + $mid0 = $mids->[$i]; + last; + } } - if ($del) { - unindex_oid_remote($self, $oid, $_) for @$mids; - # do not delete from {mm_tmp}, since another - # single-MID message may use it. - } else { # handle them at the end: - multi_mid_q_push($sync, $oid); + } + if (defined($num)) { + $arg->{mm_tmp}->num_delete($num); + } else { # never seen + $num = $self->{mm}->mid_insert($mids->[0]); + if (defined($num)) { + $mid0 = $mids->[0]; + } else { # rare, try the rest of them, backwards + for (my $i = $#$mids; $i >= 1; $i--) { + $num = $self->{mm}->mid_insert($mids->[$i]); + if (defined($num)) { + $mid0 = $mids->[$i]; + last; + } + } } - return; } - $sync->{mm_tmp}->mid_delete($mid0) or - die "failed to delete <$mid0> for article #$num\n"; - $sync->{nr}++; - if (do_idx($self, $msgref, $mime, $len, $num, $oid, $mid0)) { - reindex_checkpoint($self, $sync, $git); + if (!defined($num)) { + warn "E: $oid <", join('> <', @$mids), "> is a duplicate\n"; + return; } + ++${$arg->{nr}}; + my $smsg = bless { + num => $num, + blob => $oid, + mid => $mid0, + }, 'PublicInbox::Smsg'; + $smsg->populate($eml, $arg); + $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 ($$$$) { - my ($self, $git, $i, $cmt) = @_; - my $last = last_epoch_commit($self, $i); - if (defined $last && is_ancestor($git, $last, $cmt)) { - my @cmd = (qw(rev-list --count), "$last..$cmt"); - chomp(my $n = $git->qx(@cmd)); +sub update_last_commit { + my ($self, $sync, $stk) = @_; + my $unit = $sync->{unit} // return; + my $latest_cmt = $stk ? $stk->{latest_cmt} : ${$sync->{latest_cmt}}; + defined($latest_cmt) or return; + my $last = last_epoch_commit($self, $unit->{epoch}); + if (defined $last && is_ancestor($self->git, $last, $latest_cmt)) { + my @cmd = (qw(rev-list --count), "$last..$latest_cmt"); + chomp(my $n = $unit->{git}->qx(@cmd)); return if $n ne '' && $n == 0; } - last_epoch_commit($self, $i, $cmt); -} + # don't rewind if --{since,until,before,after} are in use + return if (defined($last) && + grep(defined, @{$sync->{-opt}}{qw(since until)}) && + is_ancestor($self->git, $latest_cmt, $last)); -sub git_dir_n ($$) { "$_[0]->{-inbox}->{inboxdir}/git/$_[1].git" } + last_epoch_commit($self, $unit->{epoch}, $latest_cmt); +} -sub last_commits ($$) { - my ($self, $epoch_max) = @_; +sub last_commits { + my ($self, $sync) = @_; my $heads = []; - for (my $i = $epoch_max; $i >= 0; $i--) { + for (my $i = $sync->{epoch_max}; $i >= 0; $i--) { $heads->[$i] = last_epoch_commit($self, $i); } $heads; } -*is_ancestor = *PublicInbox::SearchIdx::is_ancestor; - # returns a revision range for git-log(1) -sub log_range ($$$$$) { - my ($self, $sync, $git, $i, $tip) = @_; +sub log_range ($$$) { + 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") if $pr; + $pr->("$i.git indexing all of $tip\n") if $pr; return $tip; # all of it }; @@ -1095,7 +863,8 @@ sub log_range ($$$$$) { my $range = "$cur..$tip"; $pr->("$i.git checking contiguity... ") if $pr; - if (is_ancestor($git, $cur, $tip)) { # common case + my $git = $unit->{git}; + if (is_ancestor($sync->{self}->git, $cur, $tip)) { # common case $pr->("OK\n") if $pr; my $n = $git->qx(qw(rev-list --count), $range); chomp($n); @@ -1120,129 +889,196 @@ Rewritten history? (in $git->{git_dir}) warn "discarding history at $cur\n"; } warn <<""; -reindexing $git->{git_dir} starting at -$range - - $sync->{unindex_range}->{$i} = "$base..$cur"; +reindexing $git->{git_dir} +starting at $range + + # $cur^0 may no longer exist if pruned by git + if ($git->qx(qw(rev-parse -q --verify), "$cur^0")) { + $unit->{unindex_range} = "$base..$cur"; + } elsif ($base && $git->qx(qw(rev-parse -q --verify), $base)) { + $unit->{unindex_range} = "$base.."; + } else { + warn "W: unable to unindex before $range\n"; + } } $range; } -sub sync_prepare ($$$) { - 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->{-inbox}->{ref_head} || 'refs/heads/master'; - - # 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--) { - die 'BUG: already indexing!' if $self->{reindex_pipe}; - 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; - $sync->{ranges}->[$i] = $range; - + 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; - my $n = 0; - my $fh = $git->popen(qw(log --pretty=tformat:%H - --no-notes --no-color --no-renames - --diff-filter=AM), $range, '--', 'm'); - ++$n while <$fh>; - close $fh or die "git log failed: \$?=$?"; - $pr->("$n\n") if $pr; - $regen_max += $n; + $pr->("$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); + return 0 if $sync->{quit}; + my $nr = $stk ? $stk->num_records : 0; + $pr->("$nr\n") if $pr; + $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"); + local $self->{current_info} = 'leftover '; + my $unindex_oid = $self->can('unindex_oid'); + for my $oid (@leftovers) { + last if $sync->{quit}; + $oid = unpack('H*', $oid); + my $req = { %$sync, oid => $oid }; + $self->git->cat_async($oid, $unindex_oid, $req); + } + $self->git->async_wait_all; + } + return 0 if $sync->{quit}; + if (!$regen_max) { + $sync->{-regen_fmt} = "%u/?\n"; + return 0; } - - return 0 if (!$regen_max && !keys(%{$self->{unindex_range}})); # reindex should NOT see new commits anymore, if we do, # it's a problem and we need to notice it via die() my $pad = length($regen_max) + 1; $sync->{-regen_fmt} = "% ${pad}u/$regen_max\n"; - $sync->{nr} = 0; + $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) = @_; - $_->remote_remove($oid, $mid) foreach @{$self->{idx_shards}}; - $self->{over}->remove_oid($oid, $mid); + my @removed = $self->{oidx}->remove_oid($oid, $mid); + return unless $self->{-need_xapian}; + for my $num (@removed) { + idx_shard($self, $num)->ipc_do('xdb_remove', $num); + } } -sub unindex_oid ($$$;$) { - my ($self, $git, $oid, $unindexed) = @_; +sub unindex_oid ($$;$) { # git->cat_async callback + my ($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 $msgref = $git->cat_file($oid); - my $mime = PublicInbox::MIME->new($msgref); - my $mids = mids($mime->header_obj); - $mime = $msgref = undef; - my $over = $self->{over}; + my $mids = mids(PublicInbox::Eml->new($bref)); + undef $$bref; + my $oidx = $self->{oidx}; foreach my $mid (@$mids) { my %gone; my ($id, $prev); - while (my $smsg = $over->next_by_mid($mid, \$id, \$prev)) { + while (my $smsg = $oidx->next_by_mid($mid, \$id, \$prev)) { $gone{$smsg->{num}} = 1 if $oid eq $smsg->{blob}; - 1; # continue } - my $n = scalar keys %gone; - next unless $n; + my $n = scalar(keys(%gone)) or next; if ($n > 1) { warn "BUG: multiple articles linked to $oid\n", join(',',sort keys %gone), "\n"; } - foreach my $num (keys %gone) { + # reuse (num => mid) mapping in ascending numeric order + for my $num (sort { $a <=> $b } keys %gone) { + $num += 0; if ($unindexed) { my $mid0 = $mm->mid_for($num); - $unindexed->{$mid0} = $num; + my $oidbin = pack('H*', $oid); + push @{$unindexed->{$oidbin}}, $num, $mid0; } $mm->num_delete($num); } - unindex_oid_remote($self, $oid, $mid); + unindex_oid_aux($self, $oid, $mid); } + index_finalize($arg, 0); } -my $x40 = qr/[a-f0-9]{40}/; -sub unindex ($$$$) { - my ($self, $sync, $git, $unindex_range) = @_; - my $unindexed = $self->{unindexed} ||= {}; # $mid0 => $num +sub git { $_[0]->{ibx}->git } + +# this is rare, it only happens when we get discontiguous history in +# a mirror because the source used -purge or -edit +sub unindex_todo ($$$) { + 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 = $self->{reindex_pipe} = $git->popen(@cmd, $unindex_range); + 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 $x40 ($x40) [AM]\tm$/o or next; - unindex_oid($self, $git, $1, $unindexed); + /\A:\d{6} 100644 $OID ($OID) [AM]\tm$/o or next; + $self->git->cat_async($1, $unindex_oid, { %$sync, oid => $1 }); } - delete $self->{reindex_pipe}; - close $fh or die "git log failed: \$?=$?"; + $fh->close or die "git log failed: \$?=$?"; + $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; @@ -1252,119 +1088,233 @@ sub sync_ranges ($$$) { $ranges; } -sub index_epoch ($$$) { - my ($self, $sync, $i) = @_; +sub index_xap_only { # git->cat_async callback + my ($bref, $oid, $type, $size, $smsg) = @_; + 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}; +} - my $git_dir = git_dir_n($self, $i); - die 'BUG: already reindexing!' if $self->{reindex_pipe}; - -d $git_dir or return; # missing epochs are fine - fill_alternates($self, $i); - my $git = PublicInbox::Git->new($git_dir); - if (my $unindex_range = delete $sync->{unindex_range}->{$i}) { - unindex($self, $sync, $git, $unindex_range); - } - defined(my $range = $sync->{ranges}->[$i]) or return; +sub index_xap_step ($$$;$) { + my ($self, $sync, $beg, $step) = @_; + my $end = $sync->{art_end}; + return if $beg > $end; # nothing to do + + $step //= $self->{shards}; + my $ibx = $self->{ibx}; if (my $pr = $sync->{-opt}->{-progress}) { - $pr->("$i.git indexing $range\n"); + $pr->("Xapian indexlevel=$ibx->{indexlevel} ". + "$beg..$end (% $step)\n"); + } + for (my $num = $beg; $num <= $end; $num += $step) { + last if $sync->{quit}; + my $smsg = $ibx->over->get_art($num) or next; + $smsg->{self} = $self; + $ibx->git->cat_async($smsg->{blob}, \&index_xap_only, $smsg); + if ($self->{transact_bytes} >= $self->{batch_bytes}) { + ${$sync->{nr}} = $num; + reindex_checkpoint($self, $sync); + } } +} - my @cmd = qw(log --raw -r --pretty=tformat:%H - --no-notes --no-color --no-abbrev --no-renames); - my $fh = $self->{reindex_pipe} = $git->popen(@cmd, $range); - my $cmt; - while (<$fh>) { - chomp; - $self->{current_info} = "$i.git $_"; - if (/\A$x40$/o && !defined($cmt)) { - $cmt = $_; - } elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\tm$/o) { - reindex_oid($self, $sync, $git, $1); - } elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\td$/o) { - mark_deleted($self, $sync, $git, $1); +sub index_todo ($$$) { + 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') { + if ($sync->{max_size}) { + $req->{git} = $all; + $all->check_async($oid, \&check_size, $req); + } else { + $all->cat_async($oid, $index_oid, $req); + } + } elsif ($f eq 'd') { + $all->cat_async($oid, $unindex_oid, $req); + } + if (${$sync->{need_checkpoint}}) { + reindex_checkpoint($self, $sync); + } + } + $all->async_wait_all; + $self->update_last_commit($sync, $stk); +} + +sub xapian_only { + my ($self, $opt, $sync, $art_beg) = @_; + my $seq = $opt->{'sequential-shard'}; + $art_beg //= 0; + local $self->{parallel} = 0 if $seq; + $self->idx_init($opt); # acquire lock + if (my $art_end = $self->{ibx}->mm->max) { + $sync //= { + need_checkpoint => \(my $bool = 0), + -opt => $opt, + self => $self, + nr => \(my $nr = 0), + -regen_fmt => "%u/?\n", + }; + $sync->{art_end} = $art_end; + if ($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, $sync); + } + } + } else { # parallel (maybe) + index_xap_step($self, $sync, $art_beg, 1); } } - close $fh or die "git log failed: \$?=$?"; - delete $self->{reindex_pipe}; - update_last_commit($self, $git, $i, $cmt) if defined $cmt; + $self->git->async_wait_all; + $self->{ibx}->cleanup; + $self->done; } # public, called by public-inbox-index sub index_sync { my ($self, $opt) = @_; - $opt ||= {}; - my $pr = $opt->{-progress}; + $opt //= {}; + return xapian_only($self, $opt) if $opt->{xapian_only}; + 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 $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 + $self->{mg}->fill_alternates; + $self->{oidx}->rethread_prepare($opt); my $sync = { - D => {}, # "$mid\0$cid" => $oid - unindex_range => {}, # EPOCH => oid_old..oid_new + need_checkpoint => \(my $bool = 0), reindex => $opt->{reindex}, - -opt => $opt + -opt => $opt, + self => $self, + ibx => $self->{ibx}, + epoch_max => $epoch_max, }; - $sync->{ranges} = sync_ranges($self, $sync, $epoch_max); - $sync->{regen} = sync_prepare($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->{regen}) { + 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; # only for batch performance. $self->{mm}->{dbh}->rollback; $self->{mm}->{dbh}->begin_work; - $sync->{mm_tmp} = $self->{mm}->tmp_clone; - } + $sync->{mm_tmp} = + $self->{mm}->tmp_clone($self->{ibx}->{inboxdir}); - # work backwards through history - for (my $i = $epoch_max; $i >= 0; $i--) { - index_epoch($self, $sync, $i); - } - - # unindex is required for leftovers if "deletes" affect messages - # in a previous fetch+index window: - my $git; - if (my @leftovers = values %{delete $sync->{D}}) { - $git = $self->{-inbox}->git; - for my $oid (@leftovers) { - $self->{current_info} = "leftover $oid"; - unindex_oid($self, $git, $oid); - } - } - if (my $multi_mid = delete $sync->{multi_mid}) { - $git //= $self->{-inbox}->git; - my ($min, $max) = $multi_mid->minmax; - if ($sync->{reindex}) { - # we may need to create new Message-IDs if mirrors - # were initially indexed with old versions - for (my $i = $max; $i >= $min; $i--) { - my $oid = $multi_mid->mid_for($i); - next unless defined $oid; - reindex_oid_m($self, $sync, $git, $oid); - } - } else { # regen on initial index - for my $num ($min..$max) { - my $oid = $multi_mid->mid_for($num); - next unless defined $oid; - reindex_oid_m($self, $sync, $git, $oid, $num); - } + # xapian_only works incrementally w/o --reindex + if ($seq && !$opt->{reindex}) { + $art_beg = $sync->{mm_tmp}->max || -1; + $art_beg++; } } - $git->cleanup if $git; + # work forwards through history + index_todo($self, $sync, $_) for @{delete($sync->{todo}) // []}; + $self->{oidx}->rethread_done($opt) unless $sync->{quit}; $self->done; if (my $nr = $sync->{nr}) { my $pr = $sync->{-opt}->{-progress}; - $pr->('all.git '.sprintf($sync->{-regen_fmt}, $nr)) if $pr; + $pr->('all.git '.sprintf($sync->{-regen_fmt}, $$nr)) if $pr; + } + + my $quit_warn; + # deal with Xapian shards sequentially + if ($seq && delete($sync->{mm_tmp})) { + if ($sync->{quit}) { + $quit_warn = 1; + } else { + $self->{ibx}->{indexlevel} = $idxlevel; + xapian_only($self, $opt, $sync, $art_beg); + $quit_warn = 1 if $sync->{quit}; + } + } + + # --reindex on the command-line + if (!$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) { + my $n = $xdb->get_metadata('has_threadid'); + $xdb->set_metadata('has_threadid', '1') if $n ne '1'; + } + $s0->idx_release; + $self->lock_release; } # reindex does not pick up new changes, so we rerun w/o it: - if ($opt->{reindex}) { + if ($opt->{reindex} && !$sync->{quit} && + !grep(defined, @$opt{qw(since until)})) { my %again = %$opt; $sync = undef; - delete @again{qw(reindex -skip_lock)}; + delete @again{qw(rethread reindex -skip_lock)}; index_sync($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; |