package PublicInbox::V2Writable;
use strict;
use warnings;
-use Fcntl qw(:flock :DEFAULT);
+use base qw(PublicInbox::Lock);
use PublicInbox::SearchIdxPart;
use PublicInbox::SearchIdxSkeleton;
use PublicInbox::MIME;
xap_rw => undef, # PublicInbox::V2SearchIdx
xap_ro => undef,
partitions => $nparts,
+ parallel => 1,
transact_bytes => 0,
+ lock_path => "$dir/inbox.lock",
# limit each repo to 1GB or so
rotate_bytes => int((1024 * 1024 * 1024) / $PACKING_FACTOR),
};
- bless $self, $class
+ bless $self, $class;
+}
+
+sub init_inbox {
+ my ($self, $parallel) = @_;
+ $self->{parallel} = $parallel;
+ $self->idx_init;
+ $self->git_init(0);
+ $self->done;
}
# returns undef on duplicate or spam
my $nparts = $self->{partitions};
my $part = $num % $nparts;
my $idx = $self->idx_part($part);
- $idx->index_raw($len, $msgref, $num, $oid, $mid0);
+ $idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime);
my $n = $self->{transact_bytes} += $len;
if ($n > (PublicInbox::SearchIdx::BATCH_BYTES * $nparts)) {
$self->checkpoint;
foreach my $m (@$mids) {
# read-only lookup now safe to do after above barrier
my $existing = $self->lookup_content($mime, $m);
- if ($existing) {
- warn "<$m> resent\n";
- return; # easy, don't store duplicates
- }
+ # easy, don't store duplicates
+ # note: do not add more diagnostic info here since
+ # it gets noisy on public-inbox-watch restarts
+ return if $existing;
}
# very unlikely:
my $hdr = $mime->header_obj;
my $dig = content_digest($mime);
- $$mid0 = $dig->clone->hexdigest . '@localhost';
+ $$mid0 = PublicInbox::Import::digest2mid($dig);
my $num = $self->{skel}->{mm}->mid_insert($$mid0);
unless (defined $num) {
# it's hard to spoof the last Received: header
my @recvd = $hdr->header_raw('Received');
$dig->add("Received: $_") foreach (@recvd);
- $$mid0 = $dig->clone->hexdigest . '@localhost';
+ $$mid0 = PublicInbox::Import::digest2mid($dig);
$num = $self->{skel}->{mm}->mid_insert($$mid0);
# fall back to a random Message-ID and give up determinism:
until (defined($num)) {
$dig->add(rand);
- $$mid0 = $dig->clone->hexdigest . '@localhost';
+ $$mid0 = PublicInbox::Import::digest2mid($dig);
warn "using random Message-ID <$$mid0> as fallback\n";
$num = $self->{skel}->{mm}->mid_insert($$mid0);
}
# frequently activated.
delete $ibx->{$_} foreach (qw(git mm search));
+ $self->lock_acquire;
+
# first time initialization, first we create the skeleton pipe:
my $skel = $self->{skel} = PublicInbox::SearchIdxSkeleton->new($self);
my $mm = $skel->{mm};
my $removed;
my $mids = mids($mime->header_obj);
+
+ # We avoid introducing new blobs into git since the raw content
+ # can be slightly different, so we do not need the user-supplied
+ # message now that we have the mids and content_id
+ $mime = undef;
+
foreach my $mid (@$mids) {
$srch->reopen->each_smsg_by_mid($mid, sub {
my ($smsg) = @_;
warn "broken smsg for $mid\n";
return 1; # continue
}
+ my $orig = $$msg;
my $cur = PublicInbox::MIME->new($msg);
if (content_id($cur) eq $cid) {
$mm->num_delete($smsg->num);
# no bugs in our deduplication code:
$removed = $smsg;
$removed->{mime} = $cur;
- $im->remove($cur, $cmt_msg);
+ $im->remove(\$orig, $cmt_msg);
+ $orig = undef;
$removed->num; # memoize this for callers
my $oid = $smsg->{blob};
sub done {
my ($self) = @_;
+ my $locked = defined $self->{idx_parts};
my $im = delete $self->{im};
$im->done if $im; # PublicInbox::Import::done
$self->searchidx_checkpoint(0);
+ $self->lock_release if $locked;
}
sub checkpoint {
sub barrier {
my ($self) = @_;
- # For safety, we ensure git checkpoint is complete before because
- # the data in git is still more important than what is in Xapian.
- # Performance may be gained by delaying ->progress call but we
- # lose safety
if (my $im = $self->{im}) {
- $im->checkpoint;
- $im->progress('checkpoint');
+ $im->barrier;
}
my $skel = $self->{skel};
my $parts = $self->{idx_parts};
# Now deal with Xapian
$skel->barrier_init(scalar(@$parts));
# each partition needs to issue a barrier command to skel:
- $_->barrier foreach @$parts;
+ $_->remote_barrier foreach @$parts;
$skel->barrier_wait; # wait for each Xapian partition
$git_dir
}
+sub git_dir_latest {
+ my ($self, $max) = @_;
+ $$max = -1;
+ my $pfx = "$self->{-inbox}->{mainrepo}/git";
+ return unless -d $pfx;
+ my $latest;
+ opendir my $dh, $pfx or die "opendir $pfx: $!\n";
+ while (defined(my $git_dir = readdir($dh))) {
+ $git_dir =~ m!\A(\d+)\.git\z! or next;
+ if ($1 > $$max) {
+ $$max = $1;
+ $latest = "$pfx/$git_dir";
+ }
+ }
+ $latest;
+}
+
sub importer {
my ($self) = @_;
my $im = $self->{im};
return $self->import_init($git, 0);
}
}
- my $latest;
- my $max = -1;
my $new = 0;
- my $pfx = "$self->{-inbox}->{mainrepo}/git";
- if (-d $pfx) {
- foreach my $git_dir (glob("$pfx/*.git")) {
- $git_dir =~ m!/(\d+)\.git\z! or next;
- my $n = $1;
- if ($n > $max) {
- $max = $n;
- $latest = $git_dir;
- }
- }
- }
+ my $max;
+ my $latest = git_dir_latest($self, \$max);
if (defined $latest) {
my $git = PublicInbox::Git->new($latest);
my $packed_bytes = $git->packed_bytes;
my $im = PublicInbox::Import->new($git, undef, undef, $self->{-inbox});
$im->{bytes_added} = int($packed_bytes / $PACKING_FACTOR);
$im->{want_object_info} = 1;
- $im->{ssoma_lock} = 0;
+ $im->{lock_path} = undef;
$im->{path_type} = 'v2';
$self->{im} = $im;
}
+# XXX experimental
+sub diff ($$$) {
+ my ($mid, $cur, $new) = @_;
+ use File::Temp qw(tempfile);
+ use PublicInbox::Spawn qw(spawn);
+
+ my ($ah, $an) = tempfile('email-cur-XXXXXXXX', TMPDIR => 1);
+ print $ah $cur->as_string or die "print: $!";
+ close $ah or die "close: $!";
+ my ($bh, $bn) = tempfile('email-new-XXXXXXXX', TMPDIR => 1);
+ PublicInbox::Import::drop_unwanted_headers($new);
+ print $bh $new->as_string or die "print: $!";
+ close $bh or die "close: $!";
+ my $cmd = [ qw(diff -u), $an, $bn ];
+ print STDERR "# MID conflict <$mid>\n";
+ my $pid = spawn($cmd, undef, { 1 => 2 });
+ defined $pid or die "diff failed to spawn $!";
+ waitpid($pid, 0) == $pid or die "diff did not finish";
+ unlink($an, $bn);
+}
+
sub lookup_content {
my ($self, $mime, $mid) = @_;
my $ibx = $self->{-inbox};
$found = $smsg;
return 0; # break out of loop
}
+
+ # XXX DEBUG_DIFF is experimental and may be removed
+ diff($mid, $cur, $mime) if $ENV{DEBUG_DIFF};
+
1; # continue
});
$found;
sub atfork_child {
my ($self) = @_;
+ my $fh = delete $self->{reindex_pipe};
+ close $fh if $fh;
if (my $parts = $self->{idx_parts}) {
$_->atfork_child foreach @$parts;
}
}
}
+sub mark_deleted {
+ my ($self, $D, $git, $oid) = @_;
+ my $msgref = $git->cat_file($oid);
+ my $mime = PublicInbox::MIME->new($$msgref);
+ my $mids = mids($mime->header_obj);
+ my $cid = content_id($mime);
+ foreach my $mid (@$mids) {
+ $D->{$mid.$cid} = 1;
+ }
+}
+
+sub reindex_oid {
+ my ($self, $mm_tmp, $D, $git, $oid, $regen) = @_;
+ my $len;
+ my $msgref = $git->cat_file($oid, \$len);
+ my $mime = PublicInbox::MIME->new($$msgref);
+ my $mids = mids($mime->header_obj);
+ my $cid = content_id($mime);
+
+ # get the NNTP article number we used before, highest number wins
+ # and gets deleted from mm_tmp;
+ my $mid0;
+ my $num = -1;
+ my $del = 0;
+ foreach my $mid (@$mids) {
+ $del += (delete $D->{$mid.$cid} || 0);
+ my $n = $mm_tmp->num_for($mid);
+ if (defined $n && $n > $num) {
+ $mid0 = $mid;
+ $num = $n;
+ }
+ }
+ if (!defined($mid0) && $regen && !$del) {
+ $num = $$regen--;
+ die "BUG: ran out of article numbers\n" if $num <= 0;
+ my $mm = $self->{skel}->{mm};
+ foreach my $mid (@$mids) {
+ if ($mm->mid_set($num, $mid) == 1) {
+ $mid0 = $mid;
+ last;
+ }
+ }
+ if (!defined($mid0)) {
+ my $id = '<' . join('> <', @$mids) . '>';
+ warn "Message-Id $id unusable for $num\n";
+ }
+ }
+
+ if (!defined($mid0) || $del) {
+ if (!defined($mid0) && $del) { # expected for deletes
+ $$regen--;
+ return
+ }
+
+ my $id = '<' . join('> <', @$mids) . '>';
+ defined($mid0) or
+ warn "Skipping $id, no article number found\n";
+ if ($del && defined($mid0)) {
+ warn "$id was deleted $del " .
+ "time(s) but mapped to article #$num\n";
+ }
+ return;
+
+ }
+ $mm_tmp->mid_delete($mid0) or
+ die "failed to delete <$mid0> for article #$num\n";
+
+ my $nparts = $self->{partitions};
+ my $part = $num % $nparts;
+ my $idx = $self->idx_part($part);
+ $idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime);
+ my $n = $self->{transact_bytes} += $len;
+ if ($n > (PublicInbox::SearchIdx::BATCH_BYTES * $nparts)) {
+ $git->cleanup;
+ $mm_tmp->atfork_prepare;
+ $self->done; # release lock
+ # allow -watch or -mda to write...
+ $self->idx_init; # reacquire lock
+ $mm_tmp->atfork_parent;
+ }
+}
+
+sub reindex {
+ my ($self, $regen) = @_;
+ my $ibx = $self->{-inbox};
+ my $pfx = "$ibx->{mainrepo}/git";
+ my $max_git;
+ my $latest = git_dir_latest($self, \$max_git);
+ return unless defined $latest;
+ my $head = $ibx->{ref_head} || 'refs/heads/master';
+ $self->idx_init; # acquire lock
+ my $x40 = qr/[a-f0-9]{40}/;
+ my $mm_tmp = $self->{skel}->{mm}->tmp_clone;
+ if (!$regen) {
+ my (undef, $max) = $mm_tmp->minmax;
+ unless (defined $max) {
+ $regen = 1;
+ warn
+"empty msgmap.sqlite3, regenerating article numbers\n";
+ }
+ }
+ my $tip; # latest commit out of all git repos
+ if ($regen) {
+ my $regen_max = 0;
+ for (my $cur = $max_git; $cur >= 0; $cur--) {
+ die "already reindexing!\n" if $self->{reindex_pipe};
+ my $git = PublicInbox::Git->new("$pfx/$cur.git");
+ chomp($tip = $git->qx('rev-parse', $head)) unless $tip;
+ my $h = $cur == $max_git ? $tip : $head;
+ my @count = ('rev-list', '--count', $h, '--', 'm');
+ $regen_max += $git->qx(@count);
+ }
+ die "No messages found in $pfx/*.git, bug?\n" unless $regen_max;
+ $regen = \$regen_max;
+ }
+ my $D = {};
+ my @cmd = qw(log --raw -r --pretty=tformat:%h
+ --no-notes --no-color --no-abbrev);
+
+ # if we are regenerating, we must not use a newer tip commit than what
+ # the regeneration counter used:
+ $tip ||= $head;
+
+ # work backwards through history
+ for (my $cur = $max_git; $cur >= 0; $cur--) {
+ die "already reindexing!\n" if delete $self->{reindex_pipe};
+ my $cmt;
+ my $git_dir = "$pfx/$cur.git";
+ my $git = PublicInbox::Git->new($git_dir);
+ my $h = $cur == $max_git ? $tip : $head;
+ my $fh = $self->{reindex_pipe} = $git->popen(@cmd, $h);
+ while (<$fh>) {
+ if (/\A$x40$/o) {
+ chomp($cmt = $_);
+ } elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\tm$/o) {
+ $self->reindex_oid($mm_tmp, $D, $git, $1,
+ $regen);
+ } elsif (m!\A:\d{6} 100644 $x40 ($x40) [AM]\t_/D$!o) {
+ $self->mark_deleted($D, $git, $1);
+ }
+ }
+ delete $self->{reindex_pipe};
+ }
+ my ($min, $max) = $mm_tmp->minmax;
+ defined $max and die "leftover article numbers at $min..$max\n";
+}
+
1;