use PublicInbox::Inbox;
use PublicInbox::OverIdxFork;
use PublicInbox::Msgmap;
+use PublicInbox::Spawn;
use IO::Handle;
# an estimate of the post-packed size to the raw uncompressed size
int($ENV{NPROC} || `nproc 2>/dev/null` || 2);
}
-sub new {
- my ($class, $v2ibx, $creat) = @_;
- my $dir = $v2ibx->{mainrepo} or die "no mainrepo in inbox\n";
- unless (-d $dir) {
- if ($creat) {
- require File::Path;
- File::Path::mkpath($dir);
- } else {
- die "$dir does not exist\n";
- }
- }
-
+sub count_partitions ($) {
+ my ($self) = @_;
my $nparts = 0;
- my $xpfx = "$dir/xap" . PublicInbox::Search::SCHEMA_VERSION;
+ my $xpfx = $self->{xpfx};
# always load existing partitions in case core count changes:
+ # Also, partition count may change while -watch is running
+ # due to -compact
if (-d $xpfx) {
foreach my $part (<$xpfx/*>) {
-d $part && $part =~ m!/\d+\z! or next;
};
}
}
- $nparts = nproc() if ($nparts == 0);
+ $nparts;
+}
+
+sub new {
+ my ($class, $v2ibx, $creat) = @_;
+ my $dir = $v2ibx->{mainrepo} or die "no mainrepo in inbox\n";
+ unless (-d $dir) {
+ if ($creat) {
+ require File::Path;
+ File::Path::mkpath($dir);
+ } else {
+ die "$dir does not exist\n";
+ }
+ }
$v2ibx = PublicInbox::InboxWritable->new($v2ibx);
+
+ my $xpfx = "$dir/xap" . PublicInbox::Search::SCHEMA_VERSION;
my $self = {
-inbox => $v2ibx,
im => undef, # PublicInbox::Import
- partitions => $nparts,
parallel => 1,
transact_bytes => 0,
+ xpfx => $xpfx,
over => PublicInbox::OverIdxFork->new("$xpfx/over.sqlite3"),
lock_path => "$dir/inbox.lock",
- # limit each repo to 1GB or so
+ # limit each git repo (epoch) to 1GB or so
rotate_bytes => int((1024 * 1024 * 1024) / $PACKING_FACTOR),
+ last_commit => [], # git repo -> commit
};
+ $self->{partitions} = count_partitions($self) || nproc();
bless $self, $class;
}
my ($self, $parallel) = @_;
$self->{parallel} = $parallel;
$self->idx_init;
- my $max_git = -1;
- git_dir_latest($self, \$max_git);
- $self->git_init($max_git >= 0 ? $max_git : 0);
+ my $epoch_max = -1;
+ git_dir_latest($self, \$epoch_max);
+ $self->git_init($epoch_max >= 0 ? $epoch_max : 0);
$self->done;
}
my $nparts = $self->{partitions};
my $part = $num % $nparts;
+ $self->{last_commit}->[$self->{epoch_max}] = $cmt;
my $idx = $self->idx_part($part);
$idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime);
my $n = $self->{transact_bytes} += $len;
$self->checkpoint;
}
- $mime;
+ $cmt;
}
sub num_for {
$self->lock_acquire;
$over->create($self);
+ # -compact can change partition count while -watch is idle
+ my $nparts = count_partitions($self);
+ if ($nparts && $nparts != $self->{partitions}) {
+ $self->{partitions} = $nparts;
+ }
+
# need to create all parts before initializing msgmap FD
my $max = $self->{partitions} - 1;
$self->done;
my $pfx = "$self->{-inbox}->{mainrepo}/git";
my $purges = [];
- foreach my $i (0..$self->{max_git}) {
+ foreach my $i (0..$self->{epoch_max}) {
my $git = PublicInbox::Git->new("$pfx/$i.git");
- my $im = $self->import_init($git, 0);
+ my $im = $self->import_init($git, 0, 1);
$purges->[$i] = $im->purge_oids($purge);
}
$purges;
# can be slightly different, so we do not need the user-supplied
# message now that we have the mids and content_id
$mime = undef;
+ my $mark;
foreach my $mid (@$mids) {
- $srch->reopen->each_smsg_by_mid($mid, sub {
- my ($smsg) = @_;
- $smsg->load_expand;
+ my %gone;
+ my ($id, $prev);
+ while (my $smsg = $srch->next_by_mid($mid, \$id, \$prev)) {
my $msg = $ibx->msg_by_smsg($smsg);
if (!defined($msg)) {
warn "broken smsg for $mid\n";
- return 1; # continue
+ next; # continue
}
my $orig = $$msg;
my $cur = PublicInbox::MIME->new($msg);
if (content_id($cur) eq $cid) {
- $mm->num_delete($smsg->num);
- # $removed should only be set once assuming
- # no bugs in our deduplication code:
- $removed = $smsg;
- $removed->{mime} = $cur;
- my $oid = $smsg->{blob};
- if ($purge) {
- $purge->{$oid} = 1;
- } else {
- $im->remove(\$orig, $cmt_msg);
- }
- $orig = undef;
- $removed->num; # memoize this for callers
-
- foreach my $idx (@$parts) {
- $idx->remote_remove($oid, $mid);
- }
- $self->{over}->remove_oid($oid, $mid);
+ $smsg->{mime} = $cur;
+ $gone{$smsg->{num}} = [ $smsg, \$orig ];
}
- 1; # continue
- });
+ }
+ my $n = scalar keys %gone;
+ next unless $n;
+ if ($n > 1) {
+ warn "BUG: multiple articles linked to <$mid>\n",
+ join(',', sort keys %gone), "\n";
+ }
+ foreach my $num (keys %gone) {
+ my ($smsg, $orig) = @{$gone{$num}};
+ $mm->num_delete($num);
+ # $removed should only be set once assuming
+ # no bugs in our deduplication code:
+ $removed = $smsg;
+ my $oid = $smsg->{blob};
+ if ($purge) {
+ $purge->{$oid} = 1;
+ } else {
+ ($mark, undef) = $im->remove($orig, $cmt_msg);
+ }
+ $orig = undef;
+ foreach my $idx (@$parts) {
+ $idx->remote_remove($oid, $mid);
+ }
+ }
$self->barrier;
}
+
+ if (defined $mark) {
+ my $cmt = $im->get_mark($mark);
+ $self->{last_commit}->[$self->{epoch_max}] = $cmt;
+ }
if ($purge && scalar keys %$purge) {
return purge_oids($self, $purge);
}
sub purge {
my ($self, $mime) = @_;
- remove_internal($self, $mime, undef, {});
+ my $purges = remove_internal($self, $mime, undef, {});
+ $self->idx_init if @$purges; # ->done is called on purges
+ for my $i (0..$#$purges) {
+ defined(my $cmt = $purges->[$i]) or next;
+ $self->{last_commit}->[$i] = $cmt;
+ }
+ $purges;
}
+sub last_commit_part ($$;$) {
+ my ($self, $i, $cmt) = @_;
+ my $v = PublicInbox::Search::SCHEMA_VERSION();
+ $self->{mm}->last_commit_xap($v, $i, $cmt);
+}
+
+sub set_last_commits ($) {
+ my ($self) = @_;
+ defined(my $epoch_max = $self->{epoch_max}) or return;
+ my $last_commit = $self->{last_commit};
+ foreach my $i (0..$epoch_max) {
+ defined(my $cmt = $last_commit->[$i]) or next;
+ $last_commit->[$i] = undef;
+ last_commit_part($self, $i, $cmt);
+ }
+}
sub done {
my ($self) = @_;
my $im = delete $self->{im};
$im->done if $im; # PublicInbox::Import::done
- if (my $mm = delete $self->{mm}) {
- $mm->{dbh}->commit;
- }
+ my $mm = $self->{mm};
+ $mm->{dbh}->commit if $mm;
# order matters, we can only close {over} after all partitions
# are done because the partitions also write to {over}
my $over = $self->{over};
$over->remote_commit;
$over->remote_close;
+
+ if ($mm) {
+ $mm->{dbh}->begin_work;
+ set_last_commits($self);
+ $mm->{dbh}->commit;
+ delete $self->{mm};
+ }
+
$self->{transact_bytes} = 0;
$self->lock_release if $parts;
}
# issue a write barrier to ensure all data is visible to other processes
# and read-only ops. Order of data importance is: git > SQLite > Xapian
sub barrier {
- my ($self, $fsync) = @_;
+ my ($self) = @_;
if (my $im = $self->{im}) {
$im->barrier;
$_->remote_barrier foreach @$parts;
$over->barrier_wait; # wait for each Xapian partition
- $over->commit_fsync if $fsync;
+
+ # last_commit is special, don't commit these until
+ # remote partitions are done:
+ $dbh->begin_work;
+ set_last_commits($self);
+ $dbh->commit;
$dbh->begin_work;
}
}
sub git_init {
- my ($self, $new) = @_;
+ my ($self, $epoch) = @_;
my $pfx = "$self->{-inbox}->{mainrepo}/git";
- my $git_dir = "$pfx/$new.git";
+ my $git_dir = "$pfx/$epoch.git";
my @cmd = (qw(git init --bare -q), $git_dir);
PublicInbox::Import::run_die(\@cmd);
PublicInbox::Import::run_die(\@cmd);
my $alt = "$all/objects/info/alternates";
- my $new_obj_dir = "../../git/$new.git/objects";
+ my $new_obj_dir = "../../git/$epoch.git/objects";
my %alts;
if (-e $alt) {
open(my $fh, '<', $alt) or die "open < $alt: $!\n";
$im->done;
$self->barrier(1);
$im = undef;
- my $git_dir = $self->git_init(++$self->{max_git});
+ my $git_dir = $self->git_init(++$self->{epoch_max});
my $git = PublicInbox::Git->new($git_dir);
return $self->import_init($git, 0);
}
}
- my $new = 0;
+ my $epoch = 0;
my $max;
my $latest = git_dir_latest($self, \$max);
if (defined $latest) {
my $git = PublicInbox::Git->new($latest);
my $packed_bytes = $git->packed_bytes;
if ($packed_bytes >= $self->{rotate_bytes}) {
- $new = $max + 1;
+ $epoch = $max + 1;
} else {
- $self->{max_git} = $max;
+ $self->{epoch_max} = $max;
return $self->import_init($git, $packed_bytes);
}
}
- $self->{max_git} = $new;
- $latest = $self->git_init($new);
+ $self->{epoch_max} = $epoch;
+ $latest = $self->git_init($epoch);
$self->import_init(PublicInbox::Git->new($latest), 0);
}
sub import_init {
- my ($self, $git, $packed_bytes) = @_;
+ my ($self, $git, $packed_bytes, $tmp) = @_;
my $im = PublicInbox::Import->new($git, undef, undef, $self->{-inbox});
$im->{bytes_added} = int($packed_bytes / $PACKING_FACTOR);
$im->{want_object_info} = 1;
$im->{lock_path} = undef;
$im->{path_type} = 'v2';
- $self->{im} = $im;
+ $self->{im} = $im unless $tmp;
+ $im;
}
# XXX experimental
my $srch = $ibx->search->reopen;
my $cid = content_id($mime);
my $found;
- $srch->each_smsg_by_mid($mid, sub {
- my ($smsg) = @_;
- $smsg->load_expand;
+ my ($id, $prev);
+ while (my $smsg = $srch->next_by_mid($mid, \$id, \$prev)) {
my $msg = $ibx->msg_by_smsg($smsg);
if (!defined($msg)) {
warn "broken smsg for $mid\n";
- return 1; # continue
+ next;
}
my $cur = PublicInbox::MIME->new($msg);
if (content_id($cur) eq $cid) {
$smsg->{mime} = $cur;
$found = $smsg;
- return 0; # break out of loop
+ last;
}
# XXX DEBUG_DIFF is experimental and may be removed
diff($mid, $cur, $mime) if $ENV{DEBUG_DIFF};
-
- 1; # continue
- });
+ }
$found;
}
}
}
-sub reindex {
- my ($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 = $self->{mm}->tmp_clone;
- if (!$regen) {
- my (undef, $max) = $mm_tmp->minmax;
- unless (defined $max) {
- $regen = 1;
- warn
-"empty msgmap.sqlite3, regenerating article numbers\n";
+# only update last_commit for $i on reindex iff newer than current
+sub update_last_commit {
+ my ($self, $git, $i, $cmt) = @_;
+ my $last = last_commit_part($self, $i);
+ if (defined $last && is_ancestor($git, $last, $cmt)) {
+ my @cmd = (qw(rev-list --count), "$last..$cmt");
+ chomp(my $n = $git->qx(@cmd));
+ return if $n ne '' && $n == 0;
+ }
+ last_commit_part($self, $i, $cmt);
+}
+
+sub git_dir_n ($$) { "$_[0]->{-inbox}->{mainrepo}/git/$_[1].git" }
+
+sub last_commits {
+ my ($self, $epoch_max) = @_;
+ my $heads = [];
+ for (my $i = $epoch_max; $i >= 0; $i--) {
+ $heads->[$i] = last_commit_part($self, $i);
+ }
+ $heads;
+}
+
+sub is_ancestor ($$$) {
+ my ($git, $cur, $tip) = @_;
+ return 0 unless $git->check($cur);
+ my $cmd = [ 'git', "--git-dir=$git->{git_dir}",
+ qw(merge-base --is-ancestor), $cur, $tip ];
+ my $pid = spawn($cmd);
+ defined $pid or die "spawning ".join(' ', @$cmd)." failed: $!";
+ waitpid($pid, 0) == $pid or die join(' ', @$cmd) .' did not finish';
+ $? == 0;
+}
+
+sub index_prepare {
+ my ($self, $opts, $epoch_max, $ranges) = @_;
+ my $regen_max = 0;
+ my $head = $self->{-inbox}->{ref_head} || 'refs/heads/master';
+ for (my $i = $epoch_max; $i >= 0; $i--) {
+ die "already indexing!\n" if $self->{index_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
}
+ $ranges->[$i] = $range;
+
+ # can't use 'rev-list --count' if we use --diff-filter
+ my $fh = $git->popen(qw(log --pretty=tformat:%h
+ --no-notes --no-color --no-renames
+ --diff-filter=AM), $range, '--', 'm');
+ ++$regen_max while <$fh>;
}
- 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");
- -d $git->{git_dir} or next; # missing parts are fine
- chomp($tip = $git->qx('rev-parse', $head)) unless $tip;
- my $h = $cur == $max_git ? $tip : $head;
-
- # can't use 'rev-list --count' if we use --diff-filter
- my $fh = $git->popen(qw(log --pretty=tformat:%h
- --no-notes --no-color --no-renames
- --diff-filter=AM), $h, '--', 'm');
- ++$regen_max while <$fh>;
+ \$regen_max;
+}
+
+sub unindex_oid {
+ my ($self, $git, $oid) = @_;
+ my $msgref = $git->cat_file($oid);
+ my $mime = PublicInbox::MIME->new($msgref);
+ my $mids = mids($mime->header_obj);
+ $mime = $msgref = undef;
+ my $srch = $self->{-inbox}->search;
+ foreach my $mid (@$mids) {
+ my %gone;
+ my ($id, $prev);
+ while (my $smsg = $srch->next_by_mid($mid, \$id, \$prev)) {
+ $gone{$smsg->num} = 1 if $oid eq $smsg->{blob};
+ 1; # continue
+ }
+ my $n = scalar keys %gone;
+ next unless $n;
+ if ($n > 1) {
+ warn "BUG: multiple articles linked to $oid\n",
+ join(',',sort keys %gone), "\n";
}
- die "No messages found in $pfx/*.git, bug?\n" unless $regen_max;
- $regen = \$regen_max;
+ $self->{unindexed}->{$_}++ foreach keys %gone;
+ $_->remote_remove($oid, $mid) foreach @{$self->{idx_parts}};
+ $self->{over}->remove_oid($oid, $mid);
+ $self->barrier;
}
+}
+
+my $x40 = qr/[a-f0-9]{40}/;
+sub unindex {
+ my ($self, $opts, $git, $unindex_range) = @_;
+ my $un = $self->{unindexed} ||= {}; # num => removal count
+ $self->barrier;
+ my $before = scalar keys %$un;
+ my @cmd = qw(log --raw -r
+ --no-notes --no-color --no-abbrev --no-renames);
+ my $fh = $self->{reindex_pipe} = $git->popen(@cmd, $unindex_range);
+ while (<$fh>) {
+ /\A:\d{6} 100644 $x40 ($x40) [AM]\tm$/o or next;
+ $self->unindex_oid($git, $1);
+ }
+ delete $self->{reindex_pipe};
+ $fh = undef;
+
+ return unless $opts->{prune};
+ my $after = scalar keys %$un;
+ return if $before == $after;
+
+ # ensure any blob can not longer be accessed via dumb HTTP
+ PublicInbox::Import::run_die(['git', "--git-dir=$git->{git_dir}",
+ qw(-c gc.reflogExpire=now gc --prune=all)]);
+}
+
+sub index_sync {
+ my ($self, $opts) = @_;
+ $opts ||= {};
+ my $ibx = $self->{-inbox};
+ my $epoch_max;
+ my $latest = git_dir_latest($self, \$epoch_max);
+ return unless defined $latest;
+ $self->idx_init; # acquire lock
+ my $mm_tmp = $self->{mm}->tmp_clone;
+ my $ranges = $opts->{reindex} ? [] : $self->last_commits($epoch_max);
+
+ my ($min, $max) = $mm_tmp->minmax;
+ my $regen = $self->index_prepare($opts, $epoch_max, $ranges);
+ $$regen += $max if $max;
my $D = {};
my @cmd = qw(log --raw -r --pretty=tformat:%h
--no-notes --no-color --no-abbrev --no-renames);
- # if we are regenerating, we must not use a newer tip commit than what
- # the regeneration counter used:
- $tip ||= $head;
-
# work backwards through history
- for (my $cur = $max_git; $cur >= 0; $cur--) {
+ my $last_commit = [];
+ for (my $i = $epoch_max; $i >= 0; $i--) {
+ my $git_dir = git_dir_n($self, $i);
die "already reindexing!\n" if delete $self->{reindex_pipe};
- my $cmt;
- my $git_dir = "$pfx/$cur.git";
-d $git_dir or next; # missing parts are fine
my $git = PublicInbox::Git->new($git_dir);
- my $h = $cur == $max_git ? $tip : $head;
- my $fh = $self->{reindex_pipe} = $git->popen(@cmd, $h);
+ my $unindex = delete $self->{"unindex-range.$i"};
+ $self->unindex($opts, $git, $unindex) if $unindex;
+ defined(my $range = $ranges->[$i]) or next;
+ my $fh = $self->{reindex_pipe} = $git->popen(@cmd, $range);
+ my $cmt;
while (<$fh>) {
- if (/\A$x40$/o) {
+ if (/\A$x40$/o && !defined($cmt)) {
chomp($cmt = $_);
} elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\tm$/o) {
$self->reindex_oid($mm_tmp, $D, $git, $1,
$self->mark_deleted($D, $git, $1);
}
}
+ $fh = undef;
delete $self->{reindex_pipe};
+ $self->update_last_commit($git, $i, $cmt) if defined $cmt;
}
- my $gaps;
- if ($regen && $$regen != 0) {
- warn "W: leftover article number ($$regen)\n";
- $gaps = 1;
- }
- my ($min, $max) = $mm_tmp->minmax;
- if (defined $max) {
- warn "W: leftover article numbers at $min..$max\n";
- $gaps = 1;
- }
- warn "W: were old git partitions deleted?\n" if $gaps;
my @d = sort keys %$D;
if (@d) {
warn "BUG: ", scalar(@d)," unseen deleted messages marked\n";
warn "<$mid>\n";
}
}
+ $self->done;
}
1;