-# Copyright (C) 2018-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# This interface wraps and mimics PublicInbox::Import
use strict;
use warnings;
use base qw(PublicInbox::Lock);
+use 5.010_001;
use PublicInbox::SearchIdxShard;
use PublicInbox::MIME;
use PublicInbox::Git;
use PublicInbox::Inbox;
use PublicInbox::OverIdx;
use PublicInbox::Msgmap;
-use PublicInbox::Spawn qw(spawn);
+use PublicInbox::Spawn qw(spawn popen_rd);
use PublicInbox::SearchIdx;
-use IO::Handle;
+use IO::Handle; # ->autoflush
+use File::Temp qw(tempfile);
# an estimate of the post-packed size to the raw uncompressed size
my $PACKING_FACTOR = 0.4;
# to increase Xapian shards
our $NPROC_MAX_DEFAULT = 4;
-sub nproc_shards ($) {
- my ($creat_opt) = @_;
- if (ref($creat_opt) eq 'HASH') {
- if (defined(my $n = $creat_opt->{nproc})) {
- return $n
- }
+sub detect_nproc () {
+ for my $nproc (qw(nproc gnproc)) { # GNU coreutils nproc
+ `$nproc 2>/dev/null` =~ /^(\d+)$/ and return $1;
}
- my $n = $ENV{NPROC};
+ # getconf(1) is POSIX, but *NPROCESSORS* vars are not
+ for (qw(_NPROCESSORS_ONLN NPROCESSORS_ONLN)) {
+ `getconf $_ 2>/dev/null` =~ /^(\d+)$/ and return $1;
+ }
+
+ # should we bother with `sysctl hw.ncpu`? Those only give
+ # us total processor count, not online processor count.
+ undef
+}
+
+sub nproc_shards ($) {
+ my ($creat_opt) = @_;
+ my $n = $creat_opt->{nproc} if ref($creat_opt) eq 'HASH';
+ $n //= $ENV{NPROC};
if (!$n) {
- chomp($n = `nproc 2>/dev/null`);
- # assume 2 cores if GNU nproc(1) is not available
- $n = 2 if !$n;
+ # assume 2 cores if not detectable or zero
+ state $NPROC_DETECTED = detect_nproc() || 2;
+ $n = $NPROC_DETECTED;
$n = $NPROC_MAX_DEFAULT if $n > $NPROC_MAX_DEFAULT;
}
# Also, shard count may change while -watch is running
# due to "xcpdb --reshard"
if (-d $xpfx) {
+ require PublicInbox::Search;
+ PublicInbox::Search::load_xapian();
+ my $XapianDatabase = $PublicInbox::Search::X{Database};
foreach my $shard (<$xpfx/*>) {
-d $shard && $shard =~ m!/[0-9]+\z! or next;
eval {
- Search::Xapian::Database->new($shard)->close;
+ $XapianDatabase->new($shard)->close;
$n++;
};
}
# $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->{inboxdir} or die "no inboxdir in inbox\n";
+ $v2ibx = PublicInbox::InboxWritable->new($v2ibx);
+ my $dir = $v2ibx->assert_usable_dir;
unless (-d $dir) {
if ($creat) {
require File::Path;
die "$dir does not exist\n";
}
}
-
- $v2ibx = PublicInbox::InboxWritable->new($v2ibx);
$v2ibx->umask_prepare;
my $xpfx = "$dir/xap" . PublicInbox::Search::SCHEMA_VERSION;
# public (for now?)
sub init_inbox {
- my ($self, $parallel, $skip_epoch) = @_;
- $self->{parallel} = $parallel;
+ my ($self, $shards, $skip_epoch) = @_;
+ if (defined $shards) {
+ $self->{parallel} = 0 if $shards == 0;
+ $self->{shards} = $shards if $shards > 0;
+ }
$self->idx_init;
my $epoch_max = -1;
git_dir_latest($self, \$epoch_max);
# indexes a message, returns true if checkpointing is needed
sub do_idx ($$$$$$$) {
my ($self, $msgref, $mime, $len, $num, $oid, $mid0) = @_;
- $self->{over}->add_overview($mime, $len, $num, $oid, $mid0);
+ my $smsg = bless {
+ bytes => $len,
+ num => $num,
+ blob => $oid,
+ mid => $mid0,
+ }, 'PublicInbox::Smsg';
+ $self->{over}->add_overview($mime, $smsg, $self);
my $idx = idx_shard($self, $num % $self->{shards});
- $idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime);
+ $idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime, $self);
my $n = $self->{transact_bytes} += $len;
$n >= (PublicInbox::SearchIdx::BATCH_BYTES * $self->{shards});
}
defined $num or return; # duplicate
defined $mid0 or die "BUG: $mid0 undefined\n";
my $im = $self->importer;
- my $cmt = $im->add($mime);
+ my $cmt = $im->add($mime, undef, $self); # sets $self->{(au|co)time}
$cmt = $im->get_mark($cmt);
$self->{last_commit}->[$self->{epoch_max}] = $cmt;
# crap, Message-ID is already known, hope somebody just resent:
foreach my $m (@$mids) {
# read-only lookup now safe to do after above barrier
- my $existing = lookup_content($self, $mime, $m);
# easy, don't store duplicates
# note: do not add more diagnostic info here since
# it gets noisy on public-inbox-watch restarts
- return () if $existing;
+ return () if content_exists($self, $mime, $m);
}
# AltId may pre-populate article numbers (e.g. X-Mail-Count
}
my $over = $self->{over};
my $cids = content_ids($old_mime);
- my $removed;
+ my @removed;
my $mids = mids($old_mime->header_obj);
# We avoid introducing new blobs into git since the raw content
my $mark;
foreach my $mid (@$mids) {
- my %gone; # num => [ smsg, raw ]
+ my %gone; # num => [ smsg, $mime, raw ]
my ($id, $prev);
while (my $smsg = $over->next_by_mid($mid, \$id, \$prev)) {
my $msg = get_blob($self, $smsg);
my $orig = $$msg;
my $cur = PublicInbox::MIME->new($msg);
if (content_matches($cids, $cur)) {
- $smsg->{mime} = $cur;
- $gone{$smsg->{num}} = [ $smsg, \$orig ];
+ $gone{$smsg->{num}} = [ $smsg, $cur, \$orig ];
}
}
my $n = scalar keys %gone;
join(',', sort keys %gone), "\n";
}
foreach my $num (keys %gone) {
- my ($smsg, $orig) = @{$gone{$num}};
- # $removed should only be set once assuming
+ my ($smsg, $mime, $orig) = @{$gone{$num}};
+ # @removed should only be set once assuming
# no bugs in our deduplication code:
- $removed = $smsg;
+ @removed = (undef, $mime, $smsg);
my $oid = $smsg->{blob};
if ($replace_map) {
$replace_map->{$oid} = $sref;
} else {
($mark, undef) = $im->remove($orig, $cmt_msg);
+ $removed[0] = $mark;
}
$orig = undef;
if ($need_reindex) { # ->replace
my $rewrites = _replace_oids($self, $new_mime, $replace_map);
return { rewrites => $rewrites, need_reindex => $need_reindex };
}
- $removed;
+ defined($mark) ? @removed : undef;
}
-# public
+# public (see PublicInbox::Import->remove), but note the 3rd element
+# (retval[2]) is not part of the stable API shared with Import->remove
sub remove {
my ($self, $mime, $cmt_msg) = @_;
+ my @ret;
$self->{-inbox}->with_umask(sub {
- rewrite_internal($self, $mime, $cmt_msg);
+ @ret = rewrite_internal($self, $mime, $cmt_msg);
});
+ defined($ret[0]) ? @ret : undef;
}
sub _replace ($$;$$) {
print $tmp_fh $$raw or die "print \$tmp_fh: $!";
sysseek($tmp_fh, 0, 0) or die "seek failed: $!";
- my ($r, $w);
- pipe($r, $w) or die "failed to create pipe: $!";
- my $rdr = { 0 => fileno($tmp_fh), 1 => fileno($w) };
my $git_dir = $self->{-inbox}->git->{git_dir};
my $cmd = ['git', "--git-dir=$git_dir", qw(hash-object --stdin)];
- my $pid = spawn($cmd, undef, $rdr);
- close $w;
+ my $r = popen_rd($cmd, undef, { 0 => $tmp_fh });
local $/ = "\n";
chomp(my $oid = <$r>);
- waitpid($pid, 0) == $pid or die "git hash-object did not finish";
- die "git hash-object failed: $?" if $?;
+ close $r or die "git hash-object failed: $?";
$oid =~ /\A[a-f0-9]{40}\z/ or die "OID not expected: $oid";
$oid;
}
unless (-d $all) {
PublicInbox::Import::init_bare($all);
}
- my $alt = "$all/objects/info/alternates";
- my %alts;
- my @add;
+ my $info_dir = "$all/objects/info";
+ my $alt = "$info_dir/alternates";
+ my (%alt, $new);
+ my $mode = 0644;
if (-e $alt) {
open(my $fh, '<', $alt) or die "open < $alt: $!\n";
- %alts = map { chomp; $_ => 1 } (<$fh>);
+ $mode = (stat($fh))[2] & 07777;
+
+ # we assign a sort score to every alternate and favor
+ # the newest (highest numbered) one when we
+ my $score;
+ my $other = 0; # in case admin adds non-epoch repos
+ %alt = map {;
+ if (m!\A\Q../../\E([0-9]+)\.git/objects\z!) {
+ $score = $1 + 0;
+ } else {
+ $score = --$other;
+ }
+ $_ => $score;
+ } split(/\n+/, do { local $/; <$fh> });
}
+
foreach my $i (0..$epoch) {
my $dir = "../../git/$i.git/objects";
- push @add, $dir if !$alts{$dir} && -d "$pfx/$i.git";
- }
- 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";
+ if (!exists($alt{$dir}) && -d "$pfx/$i.git") {
+ $alt{$dir} = $i;
+ $new = 1;
+ }
}
- close $fh or die "close $alt: $!\n";
+ return unless $new;
+
+ my ($fh, $tmp) = tempfile('alt-XXXXXXXX', DIR => $info_dir);
+ print $fh join("\n", sort { $alt{$b} <=> $alt{$a} } keys %alt), "\n"
+ or die "print $tmp: $!\n";
+ chmod($mode, $fh) or die "fchmod $tmp: $!\n";
+ close $fh or die "close $tmp $!\n";
+ rename($tmp, $alt) or die "rename $tmp => $alt: $!\n";
}
sub git_init {
# XXX experimental
sub diff ($$$) {
my ($mid, $cur, $new) = @_;
- use File::Temp qw(tempfile);
my ($ah, $an) = tempfile('email-cur-XXXXXXXX', TMPDIR => 1);
print $ah $cur->as_string or die "print: $!";
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);
}
$ibx->msg_by_smsg($smsg);
}
-sub lookup_content ($$$) {
+sub content_exists ($$$) {
my ($self, $mime, $mid) = @_;
my $over = $self->{over};
my $cids = content_ids($mime);
next;
}
my $cur = PublicInbox::MIME->new($msg);
- if (content_matches($cids, $cur)) {
- $smsg->{mime} = $cur;
- return $smsg;
- }
-
+ return 1 if content_matches($cids, $cur);
# XXX DEBUG_DIFF is experimental and may be removed
diff($mid, $cur, $mime) if $ENV{DEBUG_DIFF};
}
# only for a few odd messages with multiple Message-IDs
-sub reindex_oid_m ($$$$) {
- my ($self, $sync, $git, $oid) = @_;
+sub reindex_oid_m ($$$$;$) {
+ my ($self, $sync, $git, $oid, $regen_num) = @_;
+ $self->{current_info} = "multi_mid $oid";
my ($num, $mid0, $len);
my $msgref = $git->cat_file($oid, \$len);
my $mime = PublicInbox::MIME->new($$msgref);
delete($sync->{D}->{"$mid\0$cid"}) and
die "BUG: reindex_oid should handle <$mid> delete";
}
+ my $over = $self->{over};
for my $mid (reverse @$mids) {
- ($num, $mid0) = $self->{over}->num_mid0_for_oid($oid, $mid);
- last if defined $num;
+ ($num, $mid0) = $over->num_mid0_for_oid($oid, $mid);
+ next unless defined $num;
+ if (defined($regen_num) && $regen_num != $num) {
+ die "BUG: regen(#$regen_num) != over(#$num)";
+ }
}
unless (defined($num)) {
for my $mid (reverse @$mids) {
# is this a number we got before?
- $num = $sync->{mm_tmp}->num_for($mid);
- next unless defined $num;
- $mid0 = $mid;
+ my $n = $sync->{mm_tmp}->num_for($mid);
+ next unless defined $n;
+ next if defined($regen_num) && $regen_num != $n;
+ ($num, $mid0) = ($n, $mid);
last;
}
}
if (defined($num)) {
$sync->{mm_tmp}->num_delete($num);
- } else {
- $num = $sync->{regen}--;
- if ($num <= 0) {
- # fixup bugs in old mirrors on reindex
- for my $mid (reverse @$mids) {
- $num = $self->{mm}->mid_insert($mid);
- next unless defined $num;
- $mid0 = $mid;
- last;
- }
- if (defined $mid0) {
- if ($sync->{reindex}) {
- warn "reindex added #$num <$mid0>\n";
- }
- } else {
- warn "E: cannot find article #\n";
- return;
- }
- } else { # $num > 0, use the new article number
- for my $mid (reverse @$mids) {
- $self->{mm}->mid_set($num, $mid) == 1 or next;
- $mid0 = $mid;
- last;
- }
- unless (defined $mid0) {
- warn "E: cannot regen #$num\n";
- return;
+ } elsif (defined $regen_num) {
+ $num = $regen_num;
+ for my $mid (reverse @$mids) {
+ $self->{mm}->mid_set($num, $mid) == 1 or next;
+ $mid0 = $mid;
+ last;
+ }
+ unless (defined $mid0) {
+ warn "E: cannot regen #$num\n";
+ return;
+ }
+ } else { # fixup bugs in old mirrors on reindex
+ for my $mid (reverse @$mids) {
+ $num = $self->{mm}->mid_insert($mid);
+ next unless defined $num;
+ $mid0 = $mid;
+ last;
+ }
+ if (defined $mid0) {
+ if ($sync->{reindex}) {
+ warn "reindex added #$num <$mid0>\n";
}
+ } else {
+ warn "E: cannot find article #\n";
+ return;
}
}
$sync->{nr}++;
}
}
+# reuse Msgmap to store num => oid mapping (rather than num => mid)
+sub multi_mid_q_new () {
+ my ($fh, $fn) = tempfile('multi_mid-XXXXXXX', EXLOCK => 0, TMPDIR => 1);
+ my $multi_mid = PublicInbox::Msgmap->new_file($fn, 1);
+ $multi_mid->{dbh}->do('PRAGMA synchronous = OFF');
+ # for Msgmap->DESTROY:
+ $multi_mid->{tmp_name} = $fn;
+ $multi_mid->{pid} = $$;
+ close $fh or die "failed to close $fn: $!";
+ $multi_mid
+}
+
+sub multi_mid_q_push ($$) {
+ my ($sync, $oid) = @_;
+ my $multi_mid = $sync->{multi_mid} //= multi_mid_q_new();
+ if ($sync->{reindex}) { # no regen on reindex
+ $multi_mid->mid_insert($oid);
+ } else {
+ my $num = $sync->{regen}--;
+ die "BUG: ran out of article numbers" if $num <= 0;
+ $multi_mid->mid_set($num, $oid);
+ }
+}
+
sub reindex_oid ($$$$) {
my ($self, $sync, $git, $oid) = @_;
my ($num, $mid0, $len);
check_unindexed($self, $num, $mid0);
} else {
$num = $sync->{regen}--;
- die "BUG: ran out of article numbers\n" if $num <= 0;
+ die "BUG: ran out of article numbers" if $num <= 0;
if ($self->{mm}->mid_set($num, $mid) != 1) {
warn "E: unable to assign $num => <$mid>\n";
return;
# do not delete from {mm_tmp}, since another
# single-MID message may use it.
} else { # handle them at the end:
- push @{$sync->{multi_mid} //= []}, $oid;
+ multi_mid_q_push($sync, $oid);
}
return;
}
--no-notes --no-color --no-renames
--diff-filter=AM), $range, '--', 'm');
++$n while <$fh>;
+ close $fh or die "git log failed: \$?=$?";
$pr->("$n\n") if $pr;
$regen_max += $n;
}
unindex_oid($self, $git, $1, $unindexed);
}
delete $self->{reindex_pipe};
- $fh = undef;
+ close $fh or die "git log failed: \$?=$?";
return unless $sync->{-opt}->{prune};
my $after = scalar keys %$unindexed;
# ensure any blob can not longer be accessed via dumb HTTP
PublicInbox::Import::run_die(['git', "--git-dir=$git->{git_dir}",
- qw(-c gc.reflogExpire=now gc --prune=all)]);
+ qw(-c gc.reflogExpire=now gc --prune=all --quiet)]);
}
sub sync_ranges ($$$) {
$pr->("$i.git indexing $range\n");
}
- my @cmd = qw(log --raw -r --pretty=tformat:%H
+ my @cmd = qw(log --raw -r --pretty=tformat:%H.%at.%ct
--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 = $_;
+ if (/\A($x40)\.([0-9]+)\.([0-9]+)$/o) {
+ $cmt //= $1;
+ $self->{autime} = $2;
+ $self->{cotime} = $3;
} 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;
+ close $fh or die "git log failed: \$?=$?";
delete $self->{reindex_pipe};
update_last_commit($self, $git, $i, $cmt) if defined $cmt;
}
}
if (my $multi_mid = delete $sync->{multi_mid}) {
$git //= $self->{-inbox}->git;
-
- while (defined(my $oid = pop(@$multi_mid))) {
- $self->{current_info} = "multi_mid $oid";
- reindex_oid_m($self, $sync, $git, $oid);
+ my ($min, $max) = $multi_mid->minmax;
+ if ($sync->{reindex}) {
+ # we may need to create new Message-IDs if mirrors
+ # were initially indexed with old versions
+ for (my $i = $max; $i >= $min; $i--) {
+ my $oid = $multi_mid->mid_for($i);
+ next unless defined $oid;
+ reindex_oid_m($self, $sync, $git, $oid);
+ }
+ } else { # regen on initial index
+ for my $num ($min..$max) {
+ my $oid = $multi_mid->mid_for($num);
+ next unless defined $oid;
+ reindex_oid_m($self, $sync, $git, $oid, $num);
+ }
}
}
$git->cleanup if $git;