X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FV2Writable.pm;h=7bef1c89a21ef220933ff67bd9992cd72b7a1ab1;hb=ac43c3b17f452b02edf1cce3632a433e998de5ca;hp=ca60f2a16f88334eed088a363b6bf8a0b395ff96;hpb=5146114b3bc0dbee255a936703fe821ee4a1eebf;p=public-inbox.git diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm index ca60f2a1..7bef1c89 100644 --- a/lib/PublicInbox/V2Writable.pm +++ b/lib/PublicInbox/V2Writable.pm @@ -567,7 +567,7 @@ sub last_epoch_commit ($$;$) { $self->{mm}->last_commit_xap($v, $i, $cmt); } -sub set_last_commits ($) { +sub set_last_commits ($) { # this is NOT for ExtSearchIdx my ($self) = @_; defined(my $epoch_max = $self->{epoch_max}) or return; my $last_commit = $self->{last_commit}; @@ -620,17 +620,20 @@ sub checkpoint ($;$) { # Now deal with Xapian if ($wait) { - my $barrier = $self->barrier_init(scalar @$shards); + my $barrier = barrier_init($self, scalar @$shards); # each shard needs to issue a barrier command $_->shard_barrier for @$shards; # wait for each Xapian shard - $self->barrier_wait($barrier); + barrier_wait($self, $barrier); } else { $_->shard_commit for @$shards; } + my $midx = $self->{midx}; # misc index + $midx->commit_txn if $midx; + # last_commit is special, don't commit these until # Xapian shards are done: $dbh->begin_work if $dbh; @@ -639,6 +642,7 @@ sub checkpoint ($;$) { $dbh->commit; $dbh->begin_work; } + $midx->begin_txn if $midx; } $self->{total_bytes} += $self->{transact_bytes}; $self->{transact_bytes} = 0; @@ -678,6 +682,7 @@ sub done { } eval { $self->{oidx}->dbh_close }; $err .= "over close: $@\n" if $@; + delete $self->{midx}; delete $self->{bnote}; my $nbytes = $self->{total_bytes}; $self->{total_bytes} = 0; @@ -860,11 +865,17 @@ sub atfork_child { sub reindex_checkpoint ($$) { my ($self, $sync) = @_; - $self->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}) { + checkpoint($self, 1); # no need to release lock on pure index + } else { + $self->done; # release lock + } if (my $pr = $sync->{-opt}->{-progress}) { $pr->(sprintf($sync->{-regen_fmt}, ${$sync->{nr}})); @@ -877,12 +888,13 @@ sub reindex_checkpoint ($$) { sub index_oid { # cat_async callback my ($bref, $oid, $type, $size, $arg) = @_; + my $self = $arg->{self}; + local $self->{current_info} = "$self->{current_info} $oid"; return if $size == 0; # purged my ($num, $mid0); my $eml = PublicInbox::Eml->new($$bref); my $mids = mids($eml); my $chash = content_hash($eml); - my $self = $arg->{self}; if (scalar(@$mids) == 0) { warn "E: $oid has no Message-ID, skipping\n"; @@ -949,19 +961,22 @@ sub index_oid { # cat_async callback if (do_idx($self, $bref, $eml, $smsg)) { ${$arg->{need_checkpoint}} = 1; } + ${$arg->{latest_cmt}} = $arg->{cur_cmt} // die 'BUG: {cur_cmt} missing'; } # only update last_commit for $i on reindex iff newer than current -# $sync will be used by subclasses sub update_last_commit { - my ($self, $sync, $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 = $git->qx(@cmd)); + my ($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, $cmt); + last_epoch_commit($self, $unit->{epoch}, $latest_cmt); } sub last_commits { @@ -974,10 +989,11 @@ sub last_commits { } # returns a revision range for git-log(1) -sub log_range ($$$$) { - my ($sync, $git, $i, $tip) = @_; +sub log_range ($$$) { + 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 @@ -991,7 +1007,8 @@ sub log_range ($$$$) { my $range = "$cur..$tip"; $pr->("$i.git checking contiguity... ") if $pr; - if (is_ancestor($git, $cur, $tip)) { # common case + my $git = $unit->{git}; + if (is_ancestor($sync->{self}->git, $cur, $tip)) { # common case $pr->("OK\n") if $pr; my $n = $git->qx(qw(rev-list --count), $range); chomp($n); @@ -1016,10 +1033,17 @@ Rewritten history? (in $git->{git_dir}) warn "discarding history at $cur\n"; } warn <<""; -reindexing $git->{git_dir} starting at -$range - - $sync->{unindex_range}->{$i} = "$base..$cur"; +reindexing $git->{git_dir} +starting at $range + + # $cur^0 may no longer exist if pruned by git + if ($git->qx(qw(rev-parse -q --verify), "$cur^0")) { + $unit->{unindex_range} = "$base..$cur"; + } elsif ($base && $git->qx(qw(rev-parse -q --verify), $base)) { + $unit->{unindex_range} = "$base.."; + } else { + warn "W: unable to unindex before $range\n"; + } } $range; } @@ -1033,49 +1057,63 @@ sub sync_prepare ($$) { my $pr = $sync->{-opt}->{-progress}; my $regen_max = 0; my $head = $sync->{ibx}->{ref_head} || 'HEAD'; + my $pfx; + if ($pr) { + ($pfx) = ($sync->{ibx}->{inboxdir} =~ m!([^/]+)\z!g); + $pfx //= $sync->{ibx}->{inboxdir}; + } # reindex stops at the current heads and we later rerun index_sync # without {reindex} my $reindex_heads = $self->last_commits($sync) if $sync->{reindex}; + if ($sync->{max_size} = $sync->{-opt}->{max_size}) { + $sync->{index_oid} = $self->can('index_oid'); + } for (my $i = $sync->{epoch_max}; $i >= 0; $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); + my $unit = { git => $git, epoch => $i }; if ($reindex_heads) { $head = $reindex_heads->[$i] or next; } chomp(my $tip = $git->qx(qw(rev-parse -q --verify), $head)); - next if $?; # new repo - my $range = log_range($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); + 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 = { self => $self }; + local $self->{current_info} = 'leftover '; my $unindex_oid = $self->can('unindex_oid'); for my $oid (@leftovers) { $oid = unpack('H*', $oid); - $self->{current_info} = "leftover $oid"; - $self->git->cat_async($oid, $unindex_oid, $arg); + my $req = { %$sync, oid => $oid }; + $self->git->cat_async($oid, $unindex_oid, $req); + last if $sync->{quit}; } $self->git->cat_async_wait; } + return 0 if $sync->{quit}; if (!$regen_max) { $sync->{-regen_fmt} = "%u/?\n"; return 0; @@ -1102,6 +1140,7 @@ sub unindex_oid_aux ($$$) { sub unindex_oid ($$;$) { # git->cat_async callback my ($bref, $oid, $type, $size, $sync) = @_; my $self = $sync->{self}; + local $self->{current_info} = "$self->{current_info} $oid"; my $unindexed = $sync->{in_unindex} ? $sync->{unindexed} : undef; my $mm = $self->{mm}; my $mids = mids(PublicInbox::Eml->new($bref)); @@ -1133,19 +1172,19 @@ 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_epoch ($$$$) { - my ($self, $sync, $git, $unindex_range) = @_; +sub unindex_todo ($$$) { + my ($self, $sync, $unit) = @_; + my $unindex_range = delete($unit->{unindex_range}) // return; my $unindexed = $sync->{unindexed} //= {}; # $mid0 => $num 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 $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; - $self->git->cat_async($1, $unindex_oid, $sync); + $self->git->cat_async($1, $unindex_oid, { %$sync, oid => $1 }); } close $fh or die "git log failed: \$?=$?"; $self->git->cat_async_wait; @@ -1155,7 +1194,8 @@ sub unindex_epoch ($$$$) { return if $before == $after; # ensure any blob can not longer be accessed via dumb HTTP - PublicInbox::Import::run_die(['git', "--git-dir=$git->{git_dir}", + PublicInbox::Import::run_die(['git', + "--git-dir=$unit->{git}->{git_dir}", qw(-c gc.reflogExpire=now gc --prune=all --quiet)]); } @@ -1203,23 +1243,32 @@ sub index_xap_step ($$$;$) { } } -sub index_epoch ($$$) { - my ($self, $sync, $i) = @_; - - my $git_dir = $sync->{ibx}->git_dir_n($i); - -d $git_dir or return; # missing epochs are fine - my $git = PublicInbox::Git->new($git_dir); - if (my $unindex_range = delete $sync->{unindex_range}->{$i}) { # rare - unindex_epoch($self, $sync, $git, $unindex_range); - } - defined(my $stk = $sync->{stacks}->[$i]) or return; - $sync->{stacks}->[$i] = undef; +sub index_todo ($$$) { + 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 = $self->can('unindex_oid'); - while (my ($f, $at, $ct, $oid) = $stk->pop_rec) { - $self->{current_info} = "$i.git $oid"; - my $req = { %$sync, autime => $at, cotime => $ct, oid => $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) { + my $req = { + %$sync, + autime => $at, + cotime => $ct, + oid => $oid, + cur_cmt => $cmt + }; if ($f eq 'm') { if ($sync->{max_size}) { $all->check_async($oid, \&check_size, $req); @@ -1229,12 +1278,18 @@ sub index_epoch ($$$) { } elsif ($f eq 'd') { $all->cat_async($oid, $unindex_oid, $req); } + if ($sync->{quit}) { + warn "waiting to quit...\n"; + $all->async_wait_all; + $self->update_last_commit($sync); + return; + } if (${$sync->{need_checkpoint}}) { reindex_checkpoint($self, $sync); } } $all->async_wait_all; - $self->update_last_commit($sync, $git, $i, $stk->{latest_cmt}); + $self->update_last_commit($sync, $stk); } sub xapian_only { @@ -1289,13 +1344,17 @@ sub index_sync { $self->{oidx}->rethread_prepare($opt); my $sync = { need_checkpoint => \(my $bool = 0), - unindex_range => {}, # EPOCH => oid_old..oid_new reindex => $opt->{reindex}, -opt => $opt, self => $self, ibx => $self->{ibx}, epoch_max => $epoch_max, }; + my $quit = sub { $sync->{quit} = 1 }; + local $SIG{QUIT} = $quit; + local $SIG{INT} = $quit; + local $SIG{TERM} = $quit; + if (sync_prepare($self, $sync)) { # tmp_clone seems to fail if inside a transaction, so # we rollback here (because we opened {mm} for reading) @@ -1308,16 +1367,13 @@ sub index_sync { # xapian_only works incrementally w/o --reindex if ($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} = $self->can('index_oid'); - } # work forwards through history - index_epoch($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}) {