v2writable: allow setting nproc via creat options

[public-inbox.git] / lib / PublicInbox / V2Writable.pm

diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 970244eb433944cb4ebecb064146002fc427667c..afcac4d2db863103f5e92dfd82bbbeb5301279a5 100644 (file)
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -24,7 +24,14 @@ use IO::Handle;
 my $PACKING_FACTOR = 0.4;
 
 # assume 2 cores if GNU nproc(1) is not available
-sub nproc_parts () {
+sub nproc_parts ($) {
+       my ($creat_opt) = @_;
+       if (ref($creat_opt) eq 'HASH') {
+               if (defined(my $n = $creat_opt->{nproc})) {
+                       return $n
+               }
+       }
+
        my $n = int($ENV{NPROC} || `nproc 2>/dev/null` || 2);
        # subtract for the main process and git-fast-import
        $n -= 1;
@@ -52,6 +59,8 @@ sub count_partitions ($) {
 }
 
 sub new {
+       # $creat may be any true value, or 0/undef.  A hashref is true,
+       # and $creat->{nproc} may be set to an integer
        my ($class, $v2ibx, $creat) = @_;
        my $dir = $v2ibx->{mainrepo} or die "no mainrepo in inbox\n";
        unless (-d $dir) {
@@ -72,6 +81,7 @@ sub new {
                im => undef, #  PublicInbox::Import
                parallel => 1,
                transact_bytes => 0,
+               current_info => '',
                xpfx => $xpfx,
                over => PublicInbox::OverIdx->new("$xpfx/over.sqlite3", 1),
                lock_path => "$dir/inbox.lock",
@@ -79,7 +89,7 @@ sub new {
                rotate_bytes => int((1024 * 1024 * 1024) / $PACKING_FACTOR),
                last_commit => [], # git repo -> commit
        };
-       $self->{partitions} = count_partitions($self) || nproc_parts();
+       $self->{partitions} = count_partitions($self) || nproc_parts($creat);
        bless $self, $class;
 }
 
@@ -285,12 +295,19 @@ sub purge_oids {
        $self->done;
        my $pfx = "$self->{-inbox}->{mainrepo}/git";
        my $purges = [];
-       foreach my $i (0..$self->{epoch_max}) {
+       my $max = $self->{epoch_max};
+
+       unless (defined($max)) {
+               defined(my $latest = git_dir_latest($self, \$max)) or return;
+               $self->{epoch_max} = $max;
+       }
+       foreach my $i (0..$max) {
                my $git_dir = "$pfx/$i.git";
                -d $git_dir or next;
                my $git = PublicInbox::Git->new($git_dir);
                my $im = $self->import_init($git, 0, 1);
                $purges->[$i] = $im->purge_oids($purge);
+               $im->done;
        }
        $purges;
 }
@@ -499,25 +516,19 @@ sub done {
        delete $self->{bnote};
        $self->{transact_bytes} = 0;
        $self->lock_release if $parts;
+       $self->{-inbox}->git->cleanup;
 }
 
-sub git_init {
+sub fill_alternates ($$) {
        my ($self, $epoch) = @_;
-       my $pfx = "$self->{-inbox}->{mainrepo}/git";
-       my $git_dir = "$pfx/$epoch.git";
-       my @cmd = (qw(git init --bare -q), $git_dir);
-       PublicInbox::Import::run_die(\@cmd);
 
+       my $pfx = "$self->{-inbox}->{mainrepo}/git";
        my $all = "$self->{-inbox}->{mainrepo}/all.git";
+       my @cmd;
        unless (-d $all) {
-               @cmd = (qw(git init --bare -q), $all);
-               PublicInbox::Import::run_die(\@cmd);
-               @cmd = (qw/git config/, "--file=$all/config",
-                               'repack.writeBitmaps', 'true');
-               PublicInbox::Import::run_die(\@cmd);
+               PublicInbox::Import::init_bare($all);
        }
-
-       @cmd = (qw/git config/, "--file=$git_dir/config",
+       @cmd = (qw/git config/, "--file=$pfx/$epoch.git/config",
                        'include.path', '../../all.git/config');
        PublicInbox::Import::run_die(\@cmd);
 
@@ -532,12 +543,20 @@ sub git_init {
                my $dir = "../../git/$i.git/objects";
                push @add, $dir if !$alts{$dir} && -d "$pfx/$i.git";
        }
-       return $git_dir unless @add;
+       return unless @add;
        open my $fh, '>>', $alt or die "open >> $alt: $!\n";
        foreach my $dir (@add) {
                print $fh "$dir\n" or die "print >> $alt: $!\n";
        }
        close $fh or die "close $alt: $!\n";
+}
+
+sub git_init {
+       my ($self, $epoch) = @_;
+       my $git_dir = "$self->{-inbox}->{mainrepo}/git/$epoch.git";
+       my @cmd = (qw(git init --bare -q), $git_dir);
+       PublicInbox::Import::run_die(\@cmd);
+       fill_alternates($self, $epoch);
        $git_dir
 }
 
@@ -580,7 +599,9 @@ sub importer {
        if (defined $latest) {
                my $git = PublicInbox::Git->new($latest);
                my $packed_bytes = $git->packed_bytes;
-               if ($packed_bytes >= $self->{rotate_bytes}) {
+               my $unpacked_bytes = $packed_bytes / $PACKING_FACTOR;
+
+               if ($unpacked_bytes >= $self->{rotate_bytes}) {
                        $epoch = $max + 1;
                } else {
                        $self->{epoch_max} = $max;
@@ -926,6 +947,7 @@ sub index_sync {
                my $git_dir = git_dir_n($self, $i);
                die "already reindexing!\n" if delete $self->{reindex_pipe};
                -d $git_dir or next; # missing parts are fine
+               fill_alternates($self, $i);
                my $git = PublicInbox::Git->new($git_dir);
                my $unindex = delete $self->{"unindex-range.$i"};
                $self->unindex($opts, $git, $unindex) if $unindex;
@@ -933,8 +955,10 @@ sub index_sync {
                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)) {
-                               chomp($cmt = $_);
+                               $cmt = $_;
                        } elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\tm$/o) {
                                $self->reindex_oid($mm_tmp, $D, $git, $1,
                                                $regen, $reindex);