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 778BF1F9E5; Wed, 21 Jul 2021 14:05:50 +0000 (UTC) From: Eric Wong To: meta@public-inbox.org Cc: Konstantin Ryabitsev Subject: [PATCH 1/2] extsearch: support publicinbox.*.boost parameter Date: Wed, 21 Jul 2021 14:05:49 +0000 Message-Id: <20210721140550.9901-1-e@80x24.org> In-Reply-To: <20210720211840.jl542wuyjh4ajowg@nitro.local> References: <20210720211840.jl542wuyjh4ajowg@nitro.local> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit List-Id: This behaves identically the lei external "boost" parameter in prioritizing raw messages for extindex. Relying exclusively on the config file order doesn't work well for mirrors since it's impossible to guarantee config file ordering via grokmirror hooks. Config file ordering remains the default if boost is unconfigured, or in case of ties. Note: I chose the name "boost" rather than "priority" or "rank" since I always get confused by whether higher or lower numbers take precedence when it comes to kernel scheduling. "weight" is also a part of Xapian API terminology, which we currently do not expose to configuration (but may in the future). --- Documentation/public-inbox-config.pod | 8 +++++ lib/PublicInbox/Config.pm | 2 +- lib/PublicInbox/ExtSearchIdx.pm | 43 +++++++++++++++++---------- t/extsearch.t | 32 ++++++++++++++++++++ 4 files changed, 69 insertions(+), 16 deletions(-) diff --git a/Documentation/public-inbox-config.pod b/Documentation/public-inbox-config.pod index 05d9ca62..5b86ef6c 100644 --- a/Documentation/public-inbox-config.pod +++ b/Documentation/public-inbox-config.pod @@ -124,6 +124,14 @@ allow for searching for phrases using quoted text. Default: C +=item publicinbox..boost + +Control indexing order for L, with ties +broken by config file order. This only affects indexing and does +not affect messages which are already indexed. + +Default: C<0> + =item publicinbox..indexSequentialShard See L diff --git a/lib/PublicInbox/Config.pm b/lib/PublicInbox/Config.pm index 8e46328d..7aa1f6c8 100644 --- a/lib/PublicInbox/Config.pm +++ b/lib/PublicInbox/Config.pm @@ -429,7 +429,7 @@ sub _fill_ibx { $ibx->{$k} = $v if defined $v; } for my $k (qw(filter inboxdir newsgroup replyto httpbackendmax feedmax - indexlevel indexsequentialshard)) { + indexlevel indexsequentialshard boost)) { my $v = get_1($self, $pfx, $k) // next; $ibx->{$k} = $v; } diff --git a/lib/PublicInbox/ExtSearchIdx.pm b/lib/PublicInbox/ExtSearchIdx.pm index 0e27bba6..357312b8 100644 --- a/lib/PublicInbox/ExtSearchIdx.pm +++ b/lib/PublicInbox/ExtSearchIdx.pm @@ -44,7 +44,7 @@ sub new { topdir => $dir, creat => $opt->{creat}, ibx_map => {}, # (newsgroup//inboxdir) => $ibx - ibx_list => [], + ibx_cfg => [], # by config section order indexlevel => $l, transact_bytes => 0, total_bytes => 0, @@ -62,7 +62,8 @@ sub new { sub attach_inbox { my ($self, $ibx) = @_; $self->{ibx_map}->{$ibx->eidx_key} //= do { - push @{$self->{ibx_list}}, $ibx; + delete $self->{-ibx_ary}; # invalidate cache + push @{$self->{ibx_cfg}}, $ibx; $ibx; } } @@ -388,7 +389,7 @@ sub _ibx_for ($$$) { my ($self, $sync, $smsg) = @_; my $ibx_id = delete($smsg->{ibx_id}) // die '{ibx_id} unset'; my $pos = $sync->{id2pos}->{$ibx_id} // die "$ibx_id no pos"; - $self->{ibx_list}->[$pos] // die "BUG: ibx for $smsg->{blob} not mapped" + $self->{-ibx_ary}->[$pos] // die "BUG: ibx for $smsg->{blob} not mapped" } sub _fd_constrained ($) { @@ -402,7 +403,7 @@ sub _fd_constrained ($) { chomp($soft = `sh -c 'ulimit -n'`); } if (defined($soft)) { - my $want = scalar(@{$self->{ibx_list}}) + 64; # estimate + my $want = scalar(@{$self->{-ibx_ary}}) + 64; # estimate my $ret = $want > $soft; if ($ret) { warn <{blob} is not referenced by inboxes during reindex return; } - # we sort {xr3r} in the reverse order of {ibx_list} so we can + # we sort {xr3r} in the reverse order of ibx_sorted so we can # hit the common case in _reindex_finalize without rereading # from git (or holding multiple messages in memory). - my $id2pos = $sync->{id2pos}; # index in {ibx_list} + my $id2pos = $sync->{id2pos}; # index in ibx_sorted @$xr3 = sort { $id2pos->{$b->[0]} <=> $id2pos->{$a->[0]} || @@ -621,6 +622,17 @@ EOF undef; } +sub ibx_sorted ($) { + my ($self) = @_; + $self->{-ibx_ary} //= do { + # highest boost first, stable for config-ordering tiebreaker + use sort 'stable'; + [ sort { + ($b->{boost} // 0) <=> ($a->{boost} // 0) + } @{$self->{ibx_cfg}} ]; + } +} + sub eidxq_process ($$) { # for reindexing my ($self, $sync) = @_; @@ -638,7 +650,7 @@ sub eidxq_process ($$) { # for reindexing $sync->{id2pos} //= do { my %id2pos; my $pos = 0; - $id2pos{$_->{-ibx_id}} = $pos++ for @{$self->{ibx_list}}; + $id2pos{$_->{-ibx_id}} = $pos++ for (@{ibx_sorted($self)}); \%id2pos; }; my ($del, $iter); @@ -829,7 +841,7 @@ sub eidx_reindex { warn "E: aborting --reindex\n"; return; } - for my $ibx (@{$self->{ibx_list}}) { + for my $ibx (@{ibx_sorted($self)}) { _reindex_inbox($self, $sync, $ibx); last if $sync->{quit}; } @@ -959,7 +971,7 @@ sub eidx_sync { # main entry point local $SIG{QUIT} = $quit; local $SIG{INT} = $quit; local $SIG{TERM} = $quit; - for my $ibx (@{$self->{ibx_list}}) { + for my $ibx (@{ibx_sorted($self)}) { $ibx->{-ibx_id} //= $self->{oidx}->ibx_id($ibx->eidx_key); } if (delete($opt->{dedupe})) { @@ -973,7 +985,7 @@ sub eidx_sync { # main entry point # don't use $_ here, it'll get clobbered by reindex_checkpoint if ($opt->{scan} // 1) { - for my $ibx (@{$self->{ibx_list}}) { + for my $ibx (@{ibx_sorted($self)}) { last if $sync->{quit}; sync_inbox($self, $sync, $ibx); } @@ -1115,7 +1127,7 @@ sub idx_init { # similar to V2Writable } undef $dh; } - for my $ibx (@{$self->{ibx_list}}) { + for my $ibx (@{ibx_sorted($self)}) { # create symlinks for multi-pack-index $git_midx += symlink_packs($ibx, $pd); # add new lines to our alternates file @@ -1180,7 +1192,8 @@ sub eidx_reload { # -extindex --watch SIGHUP handler my $pr = $self->{-watch_sync}->{-opt}->{-progress}; $pr->('reloading ...') if $pr; delete $self->{-resync_queue}; - @{$self->{ibx_list}} = (); + delete $self->{-ibx_ary}; + $self->{ibx_cfg} = []; %{$self->{ibx_map}} = (); delete $self->{-watch_sync}->{id2pos}; my $cfg = PublicInbox::Config->new; @@ -1194,7 +1207,7 @@ sub eidx_reload { # -extindex --watch SIGHUP handler sub eidx_resync_start ($) { # -extindex --watch SIGUSR1 handler my ($self) = @_; - $self->{-resync_queue} //= [ @{$self->{ibx_list}} ]; + $self->{-resync_queue} //= [ @{ibx_sorted($self)} ]; PublicInbox::DS::requeue($self); # trigger our ->event_step } @@ -1225,9 +1238,9 @@ sub eidx_watch { # public-inbox-extindex --watch main loop require PublicInbox::Sigfd; my $idler = PublicInbox::InboxIdle->new($self->{cfg}); if (!$self->{cfg}) { - $idler->watch_inbox($_) for @{$self->{ibx_list}}; + $idler->watch_inbox($_) for (@{ibx_sorted($self)}); } - $_->subscribe_unlock(__PACKAGE__, $self) for @{$self->{ibx_list}}; + $_->subscribe_unlock(__PACKAGE__, $self) for (@{ibx_sorted($self)}); my $pr = $opt->{-progress}; $pr->("performing initial scan ...\n") if $pr; my $sync = eidx_sync($self, $opt); # initial sync diff --git a/t/extsearch.t b/t/extsearch.t index 5f0cd866..46a6f2ec 100644 --- a/t/extsearch.t +++ b/t/extsearch.t @@ -60,6 +60,38 @@ ok(run_script([qw(-extindex --all), "$home/extindex"]), 'extindex init'); ok($es->has_threadid, '->has_threadid'); } +if ('with boost') { + xsys([qw(git config publicinbox.v1test.boost), 10], + { GIT_CONFIG => $cfg_path }); + ok(run_script([qw(-extindex --all), "$home/extindex-b"]), + 'extindex init with boost'); + my $es = PublicInbox::ExtSearch->new("$home/extindex-b"); + my $smsg = $es->over->get_art(1); + ok($smsg, 'got first article'); + my $xref3 = $es->over->get_xref3($smsg->{num}); + my @v1 = grep(/\Av1/, @$xref3); + my @v2 = grep(/\Av2/, @$xref3); + like($v1[0], qr/\Av1\.example.*?\b\Q$smsg->{blob}\E\b/, + 'smsg->{blob} respected boost'); + is(scalar(@$xref3), 2, 'only to entries'); + undef $es; + + xsys([qw(git config publicinbox.v2test.boost), 20], + { GIT_CONFIG => $cfg_path }); + ok(run_script([qw(-extindex --all --reindex), "$home/extindex-b"]), + 'extindex --reindex with altered boost'); + + $es = PublicInbox::ExtSearch->new("$home/extindex-b"); + $smsg = $es->over->get_art(1); + like($v2[0], qr/\Av2\.example.*?\b\Q$smsg->{blob}\E\b/, + 'smsg->{blob} respects boost after reindex'); + + xsys([qw(git config --unset publicinbox.v1test.boost)], + { GIT_CONFIG => $cfg_path }); + xsys([qw(git config --unset publicinbox.v2test.boost)], + { GIT_CONFIG => $cfg_path }); +} + { # TODO: -extindex should write this to config open $fh, '>>', $cfg_path or BAIL_OUT $!; print $fh <