# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# This interface wraps and mimics PublicInbox::Import
+# Used to write to V2 inboxes (see L<public-inbox-v2-format(5)>).
package PublicInbox::V2Writable;
use strict;
use warnings;
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;
}
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) {
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",
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, $class;
}
sub init_inbox {
- my ($self, $parallel, $skip) = @_;
+ my ($self, $parallel, $skip_epoch) = @_;
$self->{parallel} = $parallel;
$self->idx_init;
my $epoch_max = -1;
git_dir_latest($self, \$epoch_max);
- if (defined $skip && $epoch_max == -1) {
- $epoch_max = $skip;
+ if (defined $skip_epoch && $epoch_max == -1) {
+ $epoch_max = $skip_epoch;
}
$self->git_init($epoch_max >= 0 ? $epoch_max : 0);
$self->done;
return if $existing;
}
+ # AltId may pre-populate article numbers (e.g. X-Mail-Count
+ # or NNTP article number), use that article number if it's
+ # not in Over.
+ my $altid = $self->{-inbox}->{altid};
+ if ($altid && grep(/:file=msgmap\.sqlite3\z/, @$altid)) {
+ my $num = $self->{mm}->num_for($mid);
+
+ if (defined $num && !$self->{over}->get_art($num)) {
+ $$mid0 = $mid;
+ return $num;
+ }
+ }
+
# very unlikely:
warn "<$mid> reused for mismatched content\n";
# idempotent
sub idx_init {
- my ($self) = @_;
+ my ($self, $opt) = @_;
return if $self->{idx_parts};
my $ibx = $self->{-inbox};
if ($self->{parallel}) {
pipe(my ($r, $w)) or die "pipe failed: $!";
+ # pipe for barrier notifications doesn't need to be big,
+ # 1031: F_SETPIPE_SZ
+ fcntl($w, 1031, 4096) if $^O eq 'linux';
$self->{bnote} = [ $r, $w ];
$w->autoflush(1);
}
my $over = $self->{over};
$ibx->umask_prepare;
$ibx->with_umask(sub {
- $self->lock_acquire;
+ $self->lock_acquire unless ($opt && $opt->{-skip_lock});
$over->create;
# -compact can change partition count while -watch is idle
$self->done;
my $pfx = "$self->{-inbox}->{mainrepo}/git";
my $purges = [];
- foreach my $i (0..$self->{epoch_max}) {
- my $git = PublicInbox::Git->new("$pfx/$i.git");
+ my $max = $self->{epoch_max};
+
+ unless (defined($max)) {
+ defined(my $latest = git_dir_latest($self, \$max)) or return;
+ $self->{epoch_max} = $max;
+ }
+ foreach my $i (0..$max) {
+ my $git_dir = "$pfx/$i.git";
+ -d $git_dir or next;
+ my $git = PublicInbox::Git->new($git_dir);
my $im = $self->import_init($git, 0, 1);
$purges->[$i] = $im->purge_oids($purge);
+ $im->done;
}
$purges;
}
my ($self, $mime) = @_;
my $purges = $self->{-inbox}->with_umask(sub {
remove_internal($self, $mime, undef, {});
- });
+ }) or return;
$self->idx_init if @$purges; # ->done is called on purges
for my $i (0..$#$purges) {
defined(my $cmt = $purges->[$i]) or next;
delete $self->{bnote};
$self->{transact_bytes} = 0;
$self->lock_release if $parts;
+ $self->{-inbox}->git->cleanup;
}
-sub git_init {
+sub fill_alternates ($$) {
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);
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
}
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;
$git->cleanup;
$mm_tmp->atfork_prepare;
$self->done; # release lock
+
+ # TODO: print progress info, here
+
# allow -watch or -mda to write...
$self->idx_init; # reacquire lock
$mm_tmp->atfork_parent;
*is_ancestor = *PublicInbox::SearchIdx::is_ancestor;
+# returns a revision range for git-log(1)
+sub log_range ($$$$$) {
+ my ($self, $git, $ranges, $i, $tip) = @_;
+ my $cur = $ranges->[$i] or return $tip; # all of it
+ my $range = "$cur..$tip";
+ if (is_ancestor($git, $cur, $tip)) { # common case
+ my $n = $git->qx(qw(rev-list --count), $range);
+ chomp($n);
+ if ($n == 0) {
+ $ranges->[$i] = undef;
+ return; # nothing to do
+ }
+ } else {
+ warn <<"";
+discontiguous range: $range
+Rewritten history? (in $git->{git_dir})
+
+ chomp(my $base = $git->qx('merge-base', $tip, $cur));
+ if ($base) {
+ $range = "$base..$tip";
+ warn "found merge-base: $base\n"
+ } else {
+ $range = $tip;
+ warn "discarding history at $cur\n";
+ }
+ warn <<"";
+reindexing $git->{git_dir} starting at
+$range
+
+ $self->{"unindex-range.$i"} = "$base..$cur";
+ }
+ $range;
+}
+
sub index_prepare {
my ($self, $opts, $epoch_max, $ranges) = @_;
+ my $pr = $opts->{-progress};
my $regen_max = 0;
my $head = $self->{-inbox}->{ref_head} || 'refs/heads/master';
+
+ # reindex stops at the current heads and we later rerun index_sync
+ # without {reindex}
+ my $reindex_heads = last_commits($self, $epoch_max) if $opts->{reindex};
+
for (my $i = $epoch_max; $i >= 0; $i--) {
- die "already indexing!\n" if $self->{index_pipe};
+ die 'BUG: already indexing!' if $self->{reindex_pipe};
my $git_dir = git_dir_n($self, $i);
-d $git_dir or next; # missing parts are fine
my $git = PublicInbox::Git->new($git_dir);
- chomp(my $tip = $git->qx('rev-parse', $head));
- my $range;
- if (defined(my $cur = $ranges->[$i])) {
- $range = "$cur..$tip";
- if (is_ancestor($git, $cur, $tip)) { # common case
- my $n = $git->qx(qw(rev-list --count), $range);
- chomp($n);
- if ($n == 0) {
- $ranges->[$i] = undef;
- next;
- }
- } else {
- warn <<"";
-discontiguous range: $range
-Rewritten history? (in $git_dir)
-
- my $base = $git->qx('merge-base', $tip, $cur);
- chomp $base;
- if ($base) {
- $range = "$base..$tip";
- warn "found merge-base: $base\n"
- } else {
- $range = $tip;
- warn <<"";
-discarding history at $cur
-
- }
- warn <<"";
-reindexing $git_dir starting at
-$range
-
- $self->{"unindex-range.$i"} = "$base..$cur";
- }
- } else {
- $range = $tip; # all of it
+ 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($self, $git, $ranges, $i, $tip) or next;
$ranges->[$i] = $range;
# can't use 'rev-list --count' if we use --diff-filter
+ $pr->("$i.git counting changes\n\t$range ... ") if $pr;
+ my $n = 0;
my $fh = $git->popen(qw(log --pretty=tformat:%H
--no-notes --no-color --no-renames
--diff-filter=AM), $range, '--', 'm');
- ++$regen_max while <$fh>;
+ ++$n while <$fh>;
+ $pr->("$n\n") if $pr;
+ $regen_max += $n;
}
\$regen_max;
}
qw(-c gc.reflogExpire=now gc --prune=all)]);
}
+sub index_ranges ($$$) {
+ my ($self, $reindex, $epoch_max) = @_;
+ return last_commits($self, $epoch_max) unless $reindex;
+
+ return [] if ref($reindex) ne 'HASH';
+
+ my $ranges = $reindex->{from}; # arrayref;
+ if (ref($ranges) ne 'ARRAY') {
+ die 'BUG: $reindex->{from} not an ARRAY';
+ }
+ $ranges;
+}
+
+# called for public-inbox-index
sub index_sync {
my ($self, $opts) = @_;
$opts ||= {};
my $epoch_max;
my $latest = git_dir_latest($self, \$epoch_max);
return unless defined $latest;
- $self->idx_init; # acquire lock
+ $self->idx_init($opts); # acquire lock
my $mm_tmp = $self->{mm}->tmp_clone;
my $reindex = $opts->{reindex};
- my $ranges = $reindex ? [] : $self->last_commits($epoch_max);
+ my $ranges = index_ranges($self, $reindex, $epoch_max);
my $high = $self->{mm}->num_highwater();
my $regen = $self->index_prepare($opts, $epoch_max, $ranges);
- $$regen += $high if $high;
+ if ($opts->{reindex}) {
+ # reindex should NOT see new commits anymore, if we do,
+ # it's a problem and we need to notice it via die()
+ $$regen = -1;
+ } else {
+ $$regen += $high;
+ }
+
my $D = {}; # "$mid\0$cid" => $oid
my @cmd = qw(log --raw -r --pretty=tformat:%H
--no-notes --no-color --no-abbrev --no-renames);
# work backwards through history
- my $last_commit = [];
for (my $i = $epoch_max; $i >= 0; $i--) {
my $git_dir = git_dir_n($self, $i);
- die "already reindexing!\n" if delete $self->{reindex_pipe};
+ die 'BUG: already reindexing!' if $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;
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);
$git->cleanup;
}
$self->done;
+
+ # reindex does not pick up new changes, so we rerun w/o it:
+ if ($opts->{reindex}) {
+ my %again = %$opts;
+ $mm_tmp = undef;
+ delete @again{qw(reindex -skip_lock)};
+ index_sync($self, \%again);
+ }
}
1;