config: lazy-load coderepos, support extindex

[public-inbox.git] / lib / PublicInbox / Xapcmd.pm

diff --git a/lib/PublicInbox/Xapcmd.pm b/lib/PublicInbox/Xapcmd.pm
index 348621cef0bfd724eb9366d69e9ffd05294def30..e2d67f6ac85e3cb40031556c3aacb4250ad283db 100644 (file)
--- a/lib/PublicInbox/Xapcmd.pm
+++ b/lib/PublicInbox/Xapcmd.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 package PublicInbox::Xapcmd;
 use strict;
@@ -9,7 +9,7 @@ use PublicInbox::SearchIdx;
 use File::Temp 0.19 (); # ->newdir
 use File::Path qw(remove_tree);
 use File::Basename qw(dirname);
-use POSIX ();
+use POSIX qw(WNOHANG _exit);
 
 # support testing with dev versions of Xapian which installs
 # commands with a version number suffix (e.g. "xapian-compact-1.5")
@@ -19,7 +19,6 @@ our @COMPACT_OPT = qw(jobs|j=i quiet|q blocksize|b=s no-full|n fuller|F);
 sub commit_changes ($$$$) {
        my ($ibx, $im, $tmp, $opt) = @_;
        my $reshard = $opt->{reshard};
-       my $reindex = $opt->{reindex};
 
        $SIG{INT} or die 'BUG: $SIG{INT} not handled';
        my @old_shard;
@@ -38,7 +37,7 @@ sub commit_changes ($$$$) {
                        defined $new or die "BUG: $over exists when culling v2";
                        $over = PublicInbox::Over->new($over);
                        my $tmp_over = "$new/over.sqlite3";
-                       $over->connect->sqlite_backup_to_file($tmp_over);
+                       $over->dbh->sqlite_backup_to_file($tmp_over);
                        $over = undef;
                        $over_chg = 1;
                }
@@ -82,17 +81,21 @@ sub commit_changes ($$$$) {
                                $im->{shards} = $n;
                        }
                }
-
+               my $env = $opt->{-idx_env};
+               local %ENV = (%ENV, %$env) if $env;
                PublicInbox::Admin::index_inbox($ibx, $im, $opt);
        }
 }
 
 sub cb_spawn {
        my ($cb, $args, $opt) = @_; # $cb = cpdb() or compact()
-       defined(my $pid = fork) or die "fork: $!";
+       my $seed = rand(0xffffffff);
+       my $pid = fork // die "fork: $!";
        return $pid if $pid > 0;
+       srand($seed);
+       $SIG{__DIE__} = sub { warn @_; _exit(1) }; # don't jump up stack
        $cb->($args, $opt);
-       POSIX::_exit(0);
+       _exit(0);
 }
 
 sub runnable_or_die ($) {
@@ -101,17 +104,16 @@ sub runnable_or_die ($) {
 }
 
 sub prepare_reindex ($$$) {
-       my ($ibx, $im, $reindex) = @_;
+       my ($ibx, $im, $opt) = @_;
        if ($ibx->version == 1) {
                my $dir = $ibx->search->xdir(1);
                my $xdb = $PublicInbox::Search::X{Database}->new($dir);
                if (my $lc = $xdb->get_metadata('last_commit')) {
-                       $reindex->{from} = $lc;
+                       $opt->{reindex}->{from} = $lc;
                }
        } else { # v2
-               my $max;
-               $im->git_dir_latest(\$max) or return;
-               my $from = $reindex->{from};
+               my $max = $ibx->max_git_epoch // return;
+               my $from = $opt->{reindex}->{from};
                my $mm = $ibx->mm;
                my $v = PublicInbox::Search::SCHEMA_VERSION();
                foreach my $i (0..$max) {
@@ -151,14 +153,17 @@ sub process_queue {
                        $pids{cb_spawn($cb, $args, $opt)} = $args;
                }
 
+               my $flags = 0;
                while (scalar keys %pids) {
-                       my $pid = waitpid(-1, 0);
+                       my $pid = waitpid(-1, $flags) or last;
+                       last if $pid < 0;
                        my $args = delete $pids{$pid};
                        if ($args) {
                                die join(' ', @$args)." failed: $?\n" if $?;
                        } else {
                                warn "unknown PID($pid) reaped: $?\n";
                        }
+                       $flags = WNOHANG if scalar(@$queue);
                }
        }
 }
@@ -233,15 +238,15 @@ sub prepare_run {
 
 sub check_compact () { runnable_or_die($XAPIAN_COMPACT) }
 
-sub _run {
-       my ($ibx, $cb, $opt, $reindex) = @_;
+sub _run { # with_umask callback
+       my ($ibx, $cb, $opt) = @_;
        my $im = $ibx->importer(0);
        $im->lock_acquire;
        my ($tmp, $queue) = prepare_run($ibx, $opt);
 
        # fine-grained locking if we prepare for reindex
        if (!$opt->{-coarse_lock}) {
-               prepare_reindex($ibx, $im, $reindex);
+               prepare_reindex($ibx, $im, $opt);
                $im->lock_release;
        }
 
@@ -253,24 +258,22 @@ sub _run {
 
 sub run {
        my ($ibx, $task, $opt) = @_; # task = 'cpdb' or 'compact'
-       my $cb = \&${\"PublicInbox::Xapcmd::$task"};
+       my $cb = \&$task;
        PublicInbox::Admin::progress_prepare($opt ||= {});
        defined(my $dir = $ibx->{inboxdir}) or die "no inboxdir defined\n";
        -d $dir or die "inboxdir=$dir does not exist\n";
        check_compact() if $opt->{compact} && $ibx->search;
-       my $reindex; # v1:{ from => $x40 }, v2:{ from => [ $x40, $x40, .. ] } }
 
        if (!$opt->{-coarse_lock}) {
-               $reindex = $opt->{reindex} = { # per-epoch ranges for v2
-                       from => $ibx->version == 1 ? '' : [],
-               };
+               # per-epoch ranges for v2
+               # v1:{ from => $OID }, v2:{ from => [ $OID, $OID, $OID ] } }
+               $opt->{reindex} = { from => $ibx->version == 1 ? '' : [] };
                PublicInbox::SearchIdx::load_xapian_writable();
        }
 
        local %SIG = %SIG;
        setup_signals();
-       $ibx->umask_prepare;
-       $ibx->with_umask(\&_run, $ibx, $cb, $opt, $reindex);
+       $ibx->with_umask(\&_run, $ibx, $cb, $opt);
 }
 
 sub cpdb_retryable ($$) {
@@ -301,7 +304,7 @@ sub kill_compact { # setup_signals callback
 }
 
 # xapian-compact wrapper
-sub compact ($$) {
+sub compact ($$) { # cb_spawn callback
        my ($args, $opt) = @_;
        my ($src, $newdir) = @$args;
        my $dst = ref($newdir) ? $newdir->dirname : $newdir;
@@ -382,7 +385,7 @@ sub cpdb_loop ($$$;$$) {
 
 # Like copydatabase(1), this is horribly slow; and it doesn't seem due
 # to the overhead of Perl.
-sub cpdb ($$) {
+sub cpdb ($$) { # cb_spawn callback
        my ($args, $opt) = @_;
        my ($old, $newdir) = @$args;
        my $new = $newdir->dirname;