From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 25/28] cindex: implement reindex
Date: Tue, 21 Mar 2023 23:07:40 +0000 [thread overview]
Message-ID: <20230321230743.3020032-25-e@80x24.org> (raw)
In-Reply-To: <20230321230743.3020032-1-e@80x24.org>
This allows changing --indexlevel at the moment and will allow
us to fix some yet-to-be-discovered bugs or backwards-compatible
improvements in the future.
---
lib/PublicInbox/CodeSearchIdx.pm | 33 ++++++++++++++++++++++----------
t/cindex.t | 4 ++++
2 files changed, 27 insertions(+), 10 deletions(-)
diff --git a/lib/PublicInbox/CodeSearchIdx.pm b/lib/PublicInbox/CodeSearchIdx.pm
index 095c153e..5e6c0d22 100644
--- a/lib/PublicInbox/CodeSearchIdx.pm
+++ b/lib/PublicInbox/CodeSearchIdx.pm
@@ -43,7 +43,8 @@ our (
@RDONLY_SHARDS, # Xapian::Database
@IDX_SHARDS, # clones of self
$MAX_SIZE,
- $TMP_GIT, # PublicInbox::Git object for --reindex and --prune
+ $TMP_GIT, # PublicInbox::Git object for --prune
+ $REINDEX, # PublicInbox::SharedKV
);
# stop walking history if we see >$SEEN_MAX existing commits, this assumes
@@ -89,12 +90,13 @@ sub new {
# TODO: may be used for reshard/compact
sub count_shards { scalar($_[0]->xdb_shards_flat) }
-sub add_commit ($$) {
+sub update_commit ($$) {
my ($self, $cmt) = @_; # fields from @FMT
my $x = 'Q'.$cmt->{H};
- for (docids_by_postlist($self, $x)) {
- $self->{xdb}->delete_document($_)
- }
+ my ($docid, @extra) = sort { $a <=> $b } docids_by_postlist($self, $x);
+ @extra and warn "W: $cmt->{H} indexed multiple times, pruning ",
+ join(', ', map { "#$_" } @extra), "\n";
+ $self->{xdb}->delete_document($_) for @extra;
my $doc = $PublicInbox::Search::X{Document}->new;
$doc->add_boolean_term($x);
$doc->add_boolean_term('G'.$_) for @{$self->{roots}};
@@ -119,7 +121,8 @@ sub add_commit ($$) {
$x = delete $cmt->{b};
$self->index_body_text($doc, \$x) if $x =~ /\S/s;
- $self->{xdb}->add_document($doc);
+ defined($docid) ? $self->{xdb}->replace_document($docid, $doc) :
+ $self->{xdb}->add_document($doc);
}
sub progress {
@@ -235,7 +238,7 @@ sub shard_index { # via wq_io_do
cidx_ckpoint($self, "[$n] $nr");
$TXN_BYTES = $batch_bytes - $len;
}
- add_commit($self, $cmt);
+ update_commit($self, $cmt);
++$nr;
if ($TXN_BYTES <= 0) {
cidx_ckpoint($self, "[$n] $nr");
@@ -398,7 +401,7 @@ sub check_existing { # retry_reopen callback
my $docid = shift(@docids) // return get_roots($self, $git);
my $doc = $shard->{xdb}->get_document($docid) //
die "BUG: no #$docid ($git->{git_dir})";
- my $old_fp = $doc->get_data;
+ my $old_fp = $REINDEX ? "\0invalid" : $doc->get_data;
if ($old_fp eq $git->{-repo}->{fp}) { # no change
delete $git->{-repo};
return;
@@ -426,7 +429,10 @@ sub partition_refs ($$$) {
while (defined(my $cmt = <$rfh>)) {
chomp $cmt;
my $n = hex(substr($cmt, 0, 8)) % scalar(@RDONLY_SHARDS);
- if (seen($RDONLY_SHARDS[$n], 'Q'.$cmt)) {
+ if ($REINDEX && $REINDEX->set_maybe(pack('H*', $cmt), '')) {
+ say { $shard_in[$n] } $cmt or die "say: $!";
+ ++$nchange;
+ } elsif (seen($RDONLY_SHARDS[$n], 'Q'.$cmt)) {
last if ++$seen > $SEEN_MAX;
} else {
say { $shard_in[$n] } $cmt or die "say: $!";
@@ -687,7 +693,7 @@ sub parent_quit {
sub init_tmp_git_dir ($) {
my ($self) = @_;
- return unless ($self->{-opt}->{prune} || $self->{-opt}->{reindex});
+ return unless $self->{-opt}->{prune};
require File::Temp;
require PublicInbox::Import;
my $tmp = File::Temp->newdir('cidx-all-git-XXXX', TMPDIR => 1);
@@ -729,6 +735,13 @@ sub cidx_run { # main entry point
$cb->($m, @_);
};
load_existing($self);
+ local $REINDEX;
+ if ($self->{-opt}->{reindex}) {
+ require PublicInbox::SharedKV;
+ $REINDEX = PublicInbox::SharedKV->new;
+ delete $REINDEX->{lock_path};
+ $REINDEX->dbh;
+ }
my @nc = grep { File::Spec->canonpath($_) ne $_ } @{$self->{git_dirs}};
if (@nc) {
warn "E: BUG? paths in $self->{cidx_dir} not canonicalized:\n";
diff --git a/t/cindex.t b/t/cindex.t
index 5d269217..eb66b2e6 100644
--- a/t/cindex.t
+++ b/t/cindex.t
@@ -93,6 +93,10 @@ EOM
ok(run_script([qw(-cindex -qu -d), "$tmp/ext"]), '-cindex -u');
$mset = $csrch->reopen->mset('dfn:for-update');
is(scalar($mset->items), 1, 'got updated result');
+
+ ok(run_script([qw(-cindex -qu --reindex -d), "$tmp/ext"]), 'reindex');
+ $mset = $csrch->reopen->mset('dfn:for-update');
+ is(scalar($mset->items), 1, 'same result after reindex');
}
if ('--prune') {
next prev parent reply other threads:[~2023-03-21 23:07 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-21 23:07 [PATCH 00/28] cindex coderepo commit indexer Eric Wong
2023-03-21 23:07 ` [PATCH 01/28] ipc: move nproc_shards from v2writable Eric Wong
2023-03-21 23:07 ` [PATCH 02/28] search: relocate all_terms from lei_search Eric Wong
2023-03-21 23:07 ` [PATCH 03/28] admin: hoist out resolve_git_dir Eric Wong
2023-03-21 23:07 ` [PATCH 04/28] admin: ensure resolved GIT_DIR is absolute Eric Wong
2023-03-21 23:07 ` [PATCH 05/28] test_common: create_inbox: use `$!' properly on mkdir failure Eric Wong
2023-03-21 23:07 ` [PATCH 06/28] codesearch: initial cut w/ -cindex tool Eric Wong
2023-03-21 23:07 ` [PATCH 07/28] cindex: parallelize prep phases Eric Wong
2023-03-21 23:07 ` [PATCH 08/28] cindex: use read-only shards during " Eric Wong
2023-03-21 23:07 ` [PATCH 09/28] searchidxshard: improve comment wording Eric Wong
2023-03-21 23:07 ` [PATCH 10/28] cindex: use DS and workqueues for parallelism Eric Wong
2023-03-21 23:07 ` [PATCH 11/28] ds: @post_loop_do replaces SetPostLoopCallback Eric Wong
2023-03-21 23:07 ` [PATCH 12/28] cindex: implement --exclude= like -clone Eric Wong
2023-03-21 23:07 ` [PATCH 13/28] cindex: show shard number in progress message Eric Wong
2023-03-21 23:07 ` [PATCH 14/28] cindex: drop `unchanged' " Eric Wong
2023-03-21 23:07 ` [PATCH 15/28] cindex: handle graceful shutdown by default Eric Wong
2023-03-21 23:07 ` [PATCH 16/28] sigfd: pass signal name rather than number to callback Eric Wong
2023-03-21 23:07 ` [PATCH 17/28] cindex: implement --max-size=SIZE Eric Wong
2023-03-21 23:07 ` [PATCH 18/28] cindex: check for checkpoint before giant messages Eric Wong
2023-03-21 23:07 ` [PATCH 19/28] cindex: truncate or drop body for over-sized commits Eric Wong
2023-03-21 23:07 ` [PATCH 20/28] cindex: attempt to give oldest commits lowest docids Eric Wong
2023-03-21 23:07 ` [PATCH 21/28] cindex: improve granularity of quit checks Eric Wong
2023-03-21 23:07 ` [PATCH 22/28] spawn: show failing directory for chdir failures Eric Wong
2023-03-21 23:07 ` [PATCH 23/28] cindex: filter out non-existent git directories Eric Wong
2023-03-21 23:07 ` [PATCH 24/28] cindex: add support for --prune Eric Wong
2023-03-21 23:07 ` Eric Wong [this message]
2023-03-21 23:07 ` [PATCH 26/28] cindex: squelch incompatible options Eric Wong
2023-03-21 23:07 ` [PATCH 27/28] cindex: respect existing permissions Eric Wong
2023-03-21 23:07 ` [PATCH 28/28] cindex: ignore SIGPIPE Eric Wong
2023-03-24 10:40 ` [PATCH 29/28] cindex: --prune checkpoints to avoid OOM Eric Wong
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: https://public-inbox.org/README
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230321230743.3020032-25-e@80x24.org \
--to=e@80x24.org \
--cc=meta@public-inbox.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).