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;
# due to -compact
if (-d $xpfx) {
foreach my $part (<$xpfx/*>) {
- -d $part && $part =~ m!/\d+\z! or next;
+ -d $part && $part =~ m!/[0-9]+\z! or next;
eval {
Search::Xapian::Database->new($part)->close;
$nparts++;
}
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, $class;
}
+# public (for now?)
sub init_inbox {
- my ($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;
# crap, Message-ID is already known, hope somebody just resent:
foreach my $m (@$mids) {
# read-only lookup now safe to do after above barrier
- my $existing = $self->lookup_content($mime, $m);
+ my $existing = lookup_content($self, $mime, $m);
# easy, don't store duplicates
# note: do not add more diagnostic info here since
# it gets noisy on public-inbox-watch restarts
# idempotent
sub idx_init {
- my ($self) = @_;
+ my ($self, $opt) = @_;
return if $self->{idx_parts};
my $ibx = $self->{-inbox};
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
});
}
-sub purge_oids {
+sub purge_oids ($$) {
my ($self, $purge) = @_; # $purge = { $object_id => 1, ... }
$self->done;
my $pfx = "$self->{-inbox}->{mainrepo}/git";
0
}
-sub remove_internal {
+sub remove_internal ($$$$) {
my ($self, $mime, $cmt_msg, $purge) = @_;
$self->idx_init;
my $im = $self->importer unless $purge;
($mark, undef) = $im->remove($orig, $cmt_msg);
}
$orig = undef;
- $self->unindex_oid_remote($oid, $mid);
+ unindex_oid_remote($self, $oid, $mid);
}
}
$removed;
}
+# public
sub remove {
my ($self, $mime, $cmt_msg) = @_;
$self->{-inbox}->with_umask(sub {
- remove_internal($self, $mime, $cmt_msg);
+ remove_internal($self, $mime, $cmt_msg, undef);
});
}
+# public
sub purge {
my ($self, $mime) = @_;
my $purges = $self->{-inbox}->with_umask(sub {
}
}
+# public
sub checkpoint ($;$) {
my ($self, $wait) = @_;
# issue a write barrier to ensure all data is visible to other processes
# and read-only ops. Order of data importance is: git > SQLite > Xapian
+# public
sub barrier { checkpoint($_[0], 1) };
+# public
sub done {
my ($self) = @_;
my $im = delete $self->{im};
my $all = "$self->{-inbox}->{mainrepo}/all.git";
my @cmd;
unless (-d $all) {
- @cmd = (qw(git init --bare -q), $all);
- PublicInbox::Import::run_die(\@cmd);
- @cmd = (qw/git config/, "--file=$all/config",
- 'repack.writeBitmaps', 'true');
- PublicInbox::Import::run_die(\@cmd);
+ PublicInbox::Import::init_bare($all);
}
@cmd = (qw/git config/, "--file=$pfx/$epoch.git/config",
'include.path', '../../all.git/config');
my $latest;
opendir my $dh, $pfx or die "opendir $pfx: $!\n";
while (defined(my $git_dir = readdir($dh))) {
- $git_dir =~ m!\A(\d+)\.git\z! or next;
+ $git_dir =~ m!\A([0-9]+)\.git\z! or next;
if ($1 > $$max) {
$$max = $1;
$latest = "$pfx/$git_dir";
$ibx->msg_by_smsg($smsg);
}
-sub lookup_content {
+sub lookup_content ($$$) {
my ($self, $mime, $mid) = @_;
my $over = $self->{over};
my $cids = content_ids($mime);
$self->{bnote}->[1];
}
-sub mark_deleted {
- my ($self, $D, $git, $oid) = @_;
+sub mark_deleted ($$$$) {
+ my ($self, $sync, $git, $oid) = @_;
my $msgref = $git->cat_file($oid);
my $mime = PublicInbox::MIME->new($$msgref);
my $mids = mids($mime->header_obj);
my $cid = content_id($mime);
foreach my $mid (@$mids) {
- $D->{"$mid\0$cid"} = $oid;
+ $sync->{D}->{"$mid\0$cid"} = $oid;
}
}
-sub reindex_oid {
- my ($self, $mm_tmp, $D, $git, $oid, $regen, $reindex) = @_;
+sub reindex_oid ($$$$) {
+ my ($self, $sync, $git, $oid) = @_;
my $len;
my $msgref = $git->cat_file($oid, \$len);
my $mime = PublicInbox::MIME->new($$msgref);
my $cid = content_id($mime);
# get the NNTP article number we used before, highest number wins
- # and gets deleted from mm_tmp;
+ # and gets deleted from sync->{mm_tmp};
my $mid0;
my $num = -1;
my $del = 0;
foreach my $mid (@$mids) {
- $del += delete($D->{"$mid\0$cid"}) ? 1 : 0;
- my $n = $mm_tmp->num_for($mid);
+ $del += delete($sync->{D}->{"$mid\0$cid"}) ? 1 : 0;
+ my $n = $sync->{mm_tmp}->num_for($mid);
if (defined $n && $n > $num) {
$mid0 = $mid;
$num = $n;
$self->{mm}->mid_set($num, $mid0);
}
}
- if (!defined($mid0) && $regen && !$del) {
- $num = $$regen--;
+ if (!defined($mid0) && !$del) {
+ $num = $sync->{regen}--;
die "BUG: ran out of article numbers\n" if $num <= 0;
my $mm = $self->{mm};
foreach my $mid (reverse @$mids) {
if (!defined($mid0) || $del) {
if (!defined($mid0) && $del) { # expected for deletes
- $num = $$regen--;
- $self->{mm}->num_highwater($num) unless $reindex;
+ $num = $sync->{regen}--;
+ $self->{mm}->num_highwater($num) if !$sync->{reindex};
return
}
return;
}
- $mm_tmp->mid_delete($mid0) or
+ $sync->{mm_tmp}->mid_delete($mid0) or
die "failed to delete <$mid0> for article #$num\n";
$self->{over}->add_overview($mime, $len, $num, $oid, $mid0);
my $idx = $self->idx_part($part);
$idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime);
my $n = $self->{transact_bytes} += $len;
+ $sync->{nr}++;
if ($n > (PublicInbox::SearchIdx::BATCH_BYTES * $nparts)) {
$git->cleanup;
- $mm_tmp->atfork_prepare;
+ $sync->{mm_tmp}->atfork_prepare;
$self->done; # release lock
+
+ if (my $pr = $sync->{-opt}->{-progress}) {
+ my ($bn) = (split('/', $git->{git_dir}))[-1];
+ $pr->("$bn ".sprintf($sync->{-regen_fmt}, $sync->{nr}));
+ }
+
# allow -watch or -mda to write...
$self->idx_init; # reacquire lock
- $mm_tmp->atfork_parent;
+ $sync->{mm_tmp}->atfork_parent;
}
}
# only update last_commit for $i on reindex iff newer than current
-sub update_last_commit {
+sub update_last_commit ($$$$) {
my ($self, $git, $i, $cmt) = @_;
my $last = last_commit_part($self, $i);
if (defined $last && is_ancestor($git, $last, $cmt)) {
sub git_dir_n ($$) { "$_[0]->{-inbox}->{mainrepo}/git/$_[1].git" }
-sub last_commits {
+sub last_commits ($$) {
my ($self, $epoch_max) = @_;
my $heads = [];
for (my $i = $epoch_max; $i >= 0; $i--) {
*is_ancestor = *PublicInbox::SearchIdx::is_ancestor;
-sub index_prepare {
- my ($self, $opts, $epoch_max, $ranges) = @_;
+# returns a revision range for git-log(1)
+sub log_range ($$$$$) {
+ my ($self, $sync, $git, $i, $tip) = @_;
+ my $opt = $sync->{-opt};
+ my $pr = $opt->{-progress} if (($opt->{verbose} || 0) > 1);
+ my $cur = $sync->{ranges}->[$i] or do {
+ $pr->("$i.git indexing all of $tip") if $pr;
+ return $tip; # all of it
+ };
+
+ # fast equality check to avoid (v)fork+execve overhead
+ if ($cur eq $tip) {
+ $sync->{ranges}->[$i] = undef;
+ return;
+ }
+
+ my $range = "$cur..$tip";
+ $pr->("$i.git checking contiguity... ") if $pr;
+ if (is_ancestor($git, $cur, $tip)) { # common case
+ $pr->("OK\n") if $pr;
+ my $n = $git->qx(qw(rev-list --count), $range);
+ chomp($n);
+ if ($n == 0) {
+ $sync->{ranges}->[$i] = undef;
+ $pr->("$i.git has nothing new\n") if $pr;
+ return; # nothing to do
+ }
+ $pr->("$i.git has $n changes since $cur\n") if $pr;
+ } else {
+ $pr->("FAIL\n") if $pr;
+ warn <<"";
+discontiguous range: $range
+Rewritten history? (in $git->{git_dir})
+
+ chomp(my $base = $git->qx('merge-base', $tip, $cur));
+ if ($base) {
+ $range = "$base..$tip";
+ warn "found merge-base: $base\n"
+ } else {
+ $range = $tip;
+ warn "discarding history at $cur\n";
+ }
+ warn <<"";
+reindexing $git->{git_dir} starting at
+$range
+
+ $sync->{unindex_range}->{$i} = "$base..$cur";
+ }
+ $range;
+}
+
+sub sync_prepare ($$$) {
+ my ($self, $sync, $epoch_max) = @_;
+ my $pr = $sync->{-opt}->{-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 $sync->{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);
+ 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;
- 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;
+ next if $?; # new repo
+ my $range = log_range($self, $sync, $git, $i, $tip) or next;
+ $sync->{ranges}->[$i] = $range;
# can't use 'rev-list --count' if we use --diff-filter
+ $pr->("$i.git counting $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 += $n;
}
- \$regen_max;
+
+ return 0 if (!$regen_max && !keys(%{$self->{unindex_range}}));
+
+ # reindex should NOT see new commits anymore, if we do,
+ # it's a problem and we need to notice it via die()
+ my $pad = length($regen_max) + 1;
+ $sync->{-regen_fmt} = "% ${pad}u/$regen_max\n";
+ $sync->{nr} = 0;
+ return -1 if $sync->{reindex};
+ $regen_max + $self->{mm}->num_highwater() || 0;
}
-sub unindex_oid_remote {
+sub unindex_oid_remote ($$$) {
my ($self, $oid, $mid) = @_;
$_->remote_remove($oid, $mid) foreach @{$self->{idx_parts}};
$self->{over}->remove_oid($oid, $mid);
}
-sub unindex_oid {
+sub unindex_oid ($$$) {
my ($self, $git, $oid) = @_;
my $msgref = $git->cat_file($oid);
my $mime = PublicInbox::MIME->new($msgref);
$self->{unindexed}->{$_}++;
$self->{mm}->num_delete($num);
}
- $self->unindex_oid_remote($oid, $mid);
+ unindex_oid_remote($self, $oid, $mid);
}
}
my $x40 = qr/[a-f0-9]{40}/;
-sub unindex {
- my ($self, $opts, $git, $unindex_range) = @_;
+sub unindex ($$$$) {
+ my ($self, $sync, $git, $unindex_range) = @_;
my $un = $self->{unindexed} ||= {}; # num => removal count
my $before = scalar keys %$un;
my @cmd = qw(log --raw -r
my $fh = $self->{reindex_pipe} = $git->popen(@cmd, $unindex_range);
while (<$fh>) {
/\A:\d{6} 100644 $x40 ($x40) [AM]\tm$/o or next;
- $self->unindex_oid($git, $1);
+ unindex_oid($self, $git, $1);
}
delete $self->{reindex_pipe};
$fh = undef;
- return unless $opts->{prune};
+ return unless $sync->{-opt}->{prune};
my $after = scalar keys %$un;
return if $before == $after;
qw(-c gc.reflogExpire=now gc --prune=all)]);
}
+sub sync_ranges ($$$) {
+ my ($self, $sync, $epoch_max) = @_;
+ my $reindex = $sync->{reindex};
+
+ return last_commits($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;
+}
+
+sub index_epoch ($$$) {
+ my ($self, $sync, $i) = @_;
+
+ my $git_dir = git_dir_n($self, $i);
+ die 'BUG: already reindexing!' if $self->{reindex_pipe};
+ -d $git_dir or return; # missing parts are fine
+ fill_alternates($self, $i);
+ my $git = PublicInbox::Git->new($git_dir);
+ if (my $unindex_range = delete $sync->{unindex_range}->{$i}) {
+ unindex($self, $sync, $git, $unindex_range);
+ }
+ defined(my $range = $sync->{ranges}->[$i]) or return;
+ if (my $pr = $sync->{-opt}->{-progress}) {
+ $pr->("$i.git indexing $range\n");
+ }
+
+ my @cmd = qw(log --raw -r --pretty=tformat:%H
+ --no-notes --no-color --no-abbrev --no-renames);
+ my $fh = $self->{reindex_pipe} = $git->popen(@cmd, $range);
+ my $cmt;
+ while (<$fh>) {
+ chomp;
+ $self->{current_info} = "$i.git $_";
+ if (/\A$x40$/o && !defined($cmt)) {
+ $cmt = $_;
+ } elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\tm$/o) {
+ reindex_oid($self, $sync, $git, $1);
+ } elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\td$/o) {
+ mark_deleted($self, $sync, $git, $1);
+ }
+ }
+ $fh = undef;
+ delete $self->{reindex_pipe};
+ update_last_commit($self, $git, $i, $cmt) if defined $cmt;
+}
+
+# public, called by public-inbox-index
sub index_sync {
- my ($self, $opts) = @_;
- $opts ||= {};
+ my ($self, $opt) = @_;
+ $opt ||= {};
+ my $pr = $opt->{-progress};
my $epoch_max;
my $latest = git_dir_latest($self, \$epoch_max);
return unless defined $latest;
- $self->idx_init; # acquire lock
- my $mm_tmp = $self->{mm}->tmp_clone;
- my $reindex = $opts->{reindex};
- my $ranges = $reindex ? [] : $self->last_commits($epoch_max);
-
- my $high = $self->{mm}->num_highwater();
- my $regen = $self->index_prepare($opts, $epoch_max, $ranges);
- $$regen += $high if $high;
- my $D = {}; # "$mid\0$cid" => $oid
- my @cmd = qw(log --raw -r --pretty=tformat:%H
- --no-notes --no-color --no-abbrev --no-renames);
+ $self->idx_init($opt); # acquire lock
+ my $sync = {
+ D => {}, # "$mid\0$cid" => $oid
+ unindex_range => {}, # EPOCH => oid_old..oid_new
+ reindex => $opt->{reindex},
+ -opt => $opt
+ };
+ $sync->{ranges} = sync_ranges($self, $sync, $epoch_max);
+ $sync->{regen} = sync_prepare($self, $sync, $epoch_max);
+
+ if ($sync->{regen}) {
+ # tmp_clone seems to fail if inside a transaction, so
+ # we rollback here (because we opened {mm} for reading)
+ # Note: we do NOT rely on DBI transactions for atomicity;
+ # only for batch performance.
+ $self->{mm}->{dbh}->rollback;
+ $self->{mm}->{dbh}->begin_work;
+ $sync->{mm_tmp} = $self->{mm}->tmp_clone;
+ }
# 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};
- -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;
- defined(my $range = $ranges->[$i]) or next;
- my $fh = $self->{reindex_pipe} = $git->popen(@cmd, $range);
- my $cmt;
- while (<$fh>) {
- 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,
- $regen, $reindex);
- } elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\td$/o) {
- $self->mark_deleted($D, $git, $1);
- }
- }
- $fh = undef;
- delete $self->{reindex_pipe};
- $self->update_last_commit($git, $i, $cmt) if defined $cmt;
+ index_epoch($self, $sync, $i);
}
# unindex is required for leftovers if "deletes" affect messages
# in a previous fetch+index window:
- if (scalar keys %$D) {
+ if (my @leftovers = values %{delete $sync->{D}}) {
my $git = $self->{-inbox}->git;
- $self->unindex_oid($git, $_) for values %$D;
+ unindex_oid($self, $git, $_) for @leftovers;
$git->cleanup;
}
$self->done;
+
+ if (my $nr = $sync->{nr}) {
+ my $pr = $sync->{-opt}->{-progress};
+ $pr->('all.git '.sprintf($sync->{-regen_fmt}, $nr)) if $pr;
+ }
+
+ # reindex does not pick up new changes, so we rerun w/o it:
+ if ($opt->{reindex}) {
+ my %again = %$opt;
+ $sync = undef;
+ delete @again{qw(reindex -skip_lock)};
+ index_sync($self, \%again);
+ }
}
1;