From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net X-Spam-Level: X-Spam-ASN: X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,BAYES_00 shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2 Received: from localhost (dcvr.yhbt.net [127.0.0.1]) by dcvr.yhbt.net (Postfix) with ESMTP id D58C21F622 for ; Fri, 20 Mar 2020 08:18:22 +0000 (UTC) From: Eric Wong To: meta@public-inbox.org Subject: [PATCH 7/9] v2: pass smsg in more places Date: Fri, 20 Mar 2020 08:18:19 +0000 Message-Id: <20200320081821.21715-8-e@yhbt.net> In-Reply-To: <20200320081821.21715-1-e@yhbt.net> References: <20200320081821.21715-1-e@yhbt.net> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit List-Id: We can pass fewer order-dependent args to V2Writable::do_idx and SearchIdxShard::index_raw by passing the smsg object, instead. --- lib/PublicInbox/SearchIdxShard.pm | 27 ++++++---------- lib/PublicInbox/V2Writable.pm | 52 +++++++++++++++++++------------ 2 files changed, 42 insertions(+), 37 deletions(-) diff --git a/lib/PublicInbox/SearchIdxShard.pm b/lib/PublicInbox/SearchIdxShard.pm index d29e6090..21e81b16 100644 --- a/lib/PublicInbox/SearchIdxShard.pm +++ b/lib/PublicInbox/SearchIdxShard.pm @@ -67,20 +67,19 @@ sub shard_worker_loop ($$$$$) { $self->remove_by_oid($oid, $mid); } else { chomp $line; - my ($len, $artnum, $oid, $mid0, $autime, $cotime) = + my ($bytes, $num, $blob, $mid, $autime, $cotime) = split(/ /, $line); $self->begin_txn_lazy; - my $n = read($r, my $msg, $len) or die "read: $!\n"; - $n == $len or die "short read: $n != $len\n"; + my $n = read($r, my $msg, $bytes) or die "read: $!\n"; + $n == $bytes or die "short read: $n != $bytes\n"; my $mime = PublicInbox::MIME->new(\$msg); - $artnum = int($artnum); $self->{autime} = $autime; $self->{cotime} = $cotime; my $smsg = bless { - bytes => $len, - num => $artnum, - blob => $oid, - mid => $mid0, + bytes => $bytes, + num => $num + 0, + blob => $blob, + mid => $mid, }, 'PublicInbox::Smsg'; $self->add_message($mime, $smsg); } @@ -90,23 +89,17 @@ sub shard_worker_loop ($$$$$) { # called by V2Writable sub index_raw { - my ($self, $bytes, $msgref, $artnum, $oid, $mid0, $mime, $times) = @_; + my ($self, $msgref, $mime, $smsg, $times) = @_; my $at = $times->{autime} // time; my $ct = $times->{cotime} // time; if (my $w = $self->{w}) { - print $w "$bytes $artnum $oid $mid0 $at $ct\n", $$msgref or - die "failed to write shard $!\n"; + print $w join(' ', @$smsg{qw(bytes num blob mid)}, $at, $ct), + "\n", $$msgref or die "failed to write shard $!\n"; } else { $$msgref = undef; $self->begin_txn_lazy; $self->{autime} = $at; $self->{cotime} = $ct; - my $smsg = bless { - bytes => $bytes, - num => $artnum, - blob => $oid, - mid => $mid0, - }, 'PublicInbox::Smsg'; $self->add_message($mime, $smsg); } } diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm index 34dd139b..b5332da4 100644 --- a/lib/PublicInbox/V2Writable.pm +++ b/lib/PublicInbox/V2Writable.pm @@ -148,18 +148,12 @@ sub add { } # indexes a message, returns true if checkpointing is needed -sub do_idx ($$$$$$$) { - my ($self, $msgref, $mime, $len, $num, $oid, $mid0) = @_; - my $smsg = bless { - bytes => $len, - num => $num, - blob => $oid, - mid => $mid0, - }, 'PublicInbox::Smsg'; +sub do_idx ($$$$) { + my ($self, $msgref, $mime, $smsg) = @_; $self->{over}->add_overview($mime, $smsg, $self); - my $idx = idx_shard($self, $num % $self->{shards}); - $idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime, $self); - my $n = $self->{transact_bytes} += $len; + my $idx = idx_shard($self, $smsg->{num} % $self->{shards}); + $idx->index_raw($msgref, $mime, $smsg, $self); + my $n = $self->{transact_bytes} += $smsg->{bytes}; $n >= (PublicInbox::SearchIdx::BATCH_BYTES * $self->{shards}); } @@ -186,8 +180,10 @@ sub _add { $cmt = $im->get_mark($cmt); $self->{last_commit}->[$self->{epoch_max}] = $cmt; - my ($oid, $len, $msgref) = @{$im->{last_object}}; - if (do_idx($self, $msgref, $mime, $len, $num, $oid, $mid0)) { + my $msgref; + my $smsg = bless { mid => $mid0, num => $num }, 'PublicInbox::Smsg'; + ($smsg->{blob}, $smsg->{bytes}, $msgref) = @{$im->{last_object}}; + if (do_idx($self, $msgref, $mime, $smsg)) { $self->checkpoint; } @@ -557,17 +553,21 @@ W: $list } # make sure we really got the OID: - my ($oid, $type, $len) = $self->{-inbox}->git->check($expect_oid); - $oid eq $expect_oid or die "BUG: $expect_oid not found after replace"; + my ($blob, $type, $bytes) = $self->{-inbox}->git->check($expect_oid); + $blob eq $expect_oid or die "BUG: $expect_oid not found after replace"; # don't leak FDs to Xapian: $self->{-inbox}->git->cleanup; # reindex modified messages: for my $smsg (@$need_reindex) { - my $num = $smsg->{num}; - my $mid0 = $smsg->{mid}; - do_idx($self, \$raw, $new_mime, $len, $num, $oid, $mid0); + my $new_smsg = bless { + blob => $blob, + bytes => $bytes, + num => $smsg->{num}, + mid => $smsg->{mid}, + }, 'PublicInbox::Smsg'; + do_idx($self, \$raw, $new_mime, $new_smsg); } $rewritten->{rewrites}; } @@ -955,7 +955,13 @@ sub reindex_oid_m ($$$$;$) { } } $sync->{nr}++; - if (do_idx($self, $msgref, $mime, $len, $num, $oid, $mid0)) { + my $smsg = bless { + bytes => $len, + num => $num, + blob => $oid, + mid => $mid0, + }, 'PublicInbox::Smsg'; + if (do_idx($self, $msgref, $mime, $smsg)) { reindex_checkpoint($self, $sync, $git); } } @@ -1051,7 +1057,13 @@ sub reindex_oid ($$$$) { $sync->{mm_tmp}->mid_delete($mid0) or die "failed to delete <$mid0> for article #$num\n"; $sync->{nr}++; - if (do_idx($self, $msgref, $mime, $len, $num, $oid, $mid0)) { + my $smsg = bless { + bytes => $len, + num => $num, + blob => $oid, + mid => $mid0, + }, 'PublicInbox::Smsg'; + if (do_idx($self, $msgref, $mime, $smsg)) { reindex_checkpoint($self, $sync, $git); } }