-# 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;
# 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 > $NPROC_MAX_DEFAULT;
}
# public (for now?)
sub init_inbox {
- my ($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 ($$;$$) {
$ibx->msg_by_smsg($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};
$pr->("$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) {