user/dev discussion of public-inbox itself
 help / color / Atom feed
From: "Eric W. Biederman" <ebiederm@xmission.com>
To: Eric Wong <e@80x24.org>
Cc: meta@public-inbox.org, "Eric W. Biederman" <ebiederm@xmission.com>
Subject: [PATCH 06/13] t/v[12]reindex.t: Test incremental indexing works
Date: Wed,  1 Aug 2018 11:43:37 -0500
Message-ID: <20180801164344.7911-6-ebiederm@xmission.com> (raw)
In-Reply-To: <878t5qkpis.fsf@xmission.com>

Capture interesting commits of the test repository in mark variables.

Use those marks to build interesting scenarios where index_sync proceeds
as if those marks are the heads of the repositor.  Use this capability to
test what happens when adds and deletes are mixed within a repository.

Be sad because things don't yet work as they should.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 t/v1reindex.t | 194 +++++++++++++++++++++++++++++++++++++++++++++++++
 t/v2reindex.t | 195 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 389 insertions(+)

diff --git a/t/v1reindex.t b/t/v1reindex.t
index 877e70390910..8e78aa761333 100644
--- a/t/v1reindex.t
+++ b/t/v1reindex.t
@@ -33,6 +33,7 @@ my $mime = PublicInbox::MIME->create(
 );
 my $minmax;
 my $msgmap;
+my ($mark1, $mark2, $mark3, $mark4);
 {
 	my %config = %$ibx_config;
 	my $ibx = PublicInbox::Inbox->new(\%config);
@@ -41,13 +42,17 @@ my $msgmap;
 		$mime->header_set('Message-Id', "<$i\@example.com>");
 		ok($im->add($mime), "message $i added");
 		if ($i == 4) {
+			$mark1 = $im->get_mark($im->{tip});
 			$im->remove($mime);
+			$mark2 = $im->get_mark($im->{tip});
 		}
 	}
 
 	if ('test remove later') {
+		$mark3 = $im->get_mark($im->{tip});
 		$mime->header_set('Message-Id', "<5\@example.com>");
 		$im->remove($mime);
+		$mark4 = $im->get_mark($im->{tip});
 	}
 
 	$im->done;
@@ -222,4 +227,193 @@ ok(!-d $xap, 'Xapian directories removed again');
 	is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
 }
 
+# An incremental indexing test
+ok(unlink "$mainrepo/public-inbox/msgmap.sqlite3", 'remove msgmap');
+remove_tree($xap);
+ok(!-d $xap, 'Xapian directories removed again');
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	my %config = %$ibx_config;
+	my $ibx = PublicInbox::Inbox->new(\%config);
+	my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+	my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+	# mark1 4 simple additions in the same index_sync
+	eval { $rw->index_sync({ref => $mark1}) };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	my ($min, $max) = $ibx->mm->minmax;
+	is($min, 1, 'min as expected');
+	is($max, 4, 'max as expected');
+	is_deeply($ibx->mm->msg_range(\$min, $max),
+		  [
+		   [1, '1@example.com' ],
+		   [2, '2@example.com' ],
+		   [3, '3@example.com' ],
+		   [4, '4@example.com' ],
+		  ], 'msgmap as expected' );
+}
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	my %config = %$ibx_config;
+	my $ibx = PublicInbox::Inbox->new(\%config);
+	my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+	my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+	# mark2 A delete separated form and add in the same index_sync
+	eval { $rw->index_sync({ref => $mark2}) };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	my ($min, $max) = $ibx->mm->minmax;
+	is($min, 1, 'min as expected');
+	is($max, 3, 'max as expected');
+	is_deeply($ibx->mm->msg_range(\$min, $max),
+		  [
+		   [1, '1@example.com' ],
+		   [2, '2@example.com' ],
+		   [3, '3@example.com' ],
+		  ], 'msgmap as expected' );
+}
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	my %config = %$ibx_config;
+	my $ibx = PublicInbox::Inbox->new(\%config);
+	my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+	my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+	# mark3 adds following the delete at mark2
+	eval { $rw->index_sync({ref => $mark3}) };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	my ($min, $max) = $ibx->mm->minmax;
+	is($min, 1, 'min as expected');
+	is($max, 10, 'max as expected');
+	is_deeply($ibx->mm->msg_range(\$min, $max),
+		  [
+		   [1, '1@example.com' ],
+		   [2, '2@example.com' ],
+		   [3, '3@example.com' ],
+		   [5, '5@example.com' ],
+		   [6, '6@example.com' ],
+		   [7, '7@example.com' ],
+		   [8, '8@example.com' ],
+		   [9, '9@example.com' ],
+		   [10, '10@example.com' ],
+		  ], 'msgmap as expected' );
+}
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	my %config = %$ibx_config;
+	my $ibx = PublicInbox::Inbox->new(\%config);
+	my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+	my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+	# mark4 A delete of an older message
+	eval { $rw->index_sync({ref => $mark4}) };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	my ($min, $max) = $ibx->mm->minmax;
+	is($min, 1, 'min as expected');
+	is($max, 10, 'max as expected');
+	is_deeply($ibx->mm->msg_range(\$min, $max),
+		  [
+		   [1, '1@example.com' ],
+		   [2, '2@example.com' ],
+		   [3, '3@example.com' ],
+		   [6, '6@example.com' ],
+		   [7, '7@example.com' ],
+		   [8, '8@example.com' ],
+		   [9, '9@example.com' ],
+		   [10, '10@example.com' ],
+		  ], 'msgmap as expected' );
+}
+
+
+# Another incremental indexing test
+ok(unlink "$mainrepo/public-inbox/msgmap.sqlite3", 'remove msgmap');
+remove_tree($xap);
+ok(!-d $xap, 'Xapian directories removed again');
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	my %config = %$ibx_config;
+	my $ibx = PublicInbox::Inbox->new(\%config);
+	my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+	my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+	# mark2 an add and it's delete in the same index_sync
+	eval { $rw->index_sync({ref => $mark2}) };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	my ($min, $max) = $ibx->mm->minmax;
+	is($min, 1, 'min as expected');
+	is($max, 3, 'max as expected');
+	is_deeply($ibx->mm->msg_range(\$min, $max),
+		  [
+		   [1, '1@example.com' ],
+		   [2, '2@example.com' ],
+		   [3, '3@example.com' ],
+		  ], 'msgmap as expected' );
+}
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	my %config = %$ibx_config;
+	my $ibx = PublicInbox::Inbox->new(\%config);
+	my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+	my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+	# mark3 adds following the delete at mark2
+	eval { $rw->index_sync({ref => $mark3}) };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	my ($min, $max) = $ibx->mm->minmax;
+	is($min, 1, 'min as expected');
+	is($max, 10, 'max as expected');
+	is_deeply($ibx->mm->msg_range(\$min, $max),
+		  [
+		   [1, '1@example.com' ],
+		   [2, '2@example.com' ],
+		   [3, '3@example.com' ],
+		   [5, '5@example.com' ],
+		   [6, '6@example.com' ],
+		   [7, '7@example.com' ],
+		   [8, '8@example.com' ],
+		   [9, '9@example.com' ],
+		   [10, '10@example.com' ],
+		  ], 'msgmap as expected' );
+}
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	my %config = %$ibx_config;
+	my $ibx = PublicInbox::Inbox->new(\%config);
+	my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+	my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+	# mark4 A delete of an older message
+	eval { $rw->index_sync({ref => $mark4}) };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	my ($min, $max) = $ibx->mm->minmax;
+	is($min, 1, 'min as expected');
+	is($max, 10, 'max as expected');
+	is_deeply($ibx->mm->msg_range(\$min, $max),
+		  [
+		   [1, '1@example.com' ],
+		   [2, '2@example.com' ],
+		   [3, '3@example.com' ],
+		   [6, '6@example.com' ],
+		   [7, '7@example.com' ],
+		   [8, '8@example.com' ],
+		   [9, '9@example.com' ],
+		   [10, '10@example.com' ],
+		  ], 'msgmap as expected' );
+}
+
+
 done_testing();
diff --git a/t/v2reindex.t b/t/v2reindex.t
index 31e61d5b2578..ce13a07c39c0 100644
--- a/t/v2reindex.t
+++ b/t/v2reindex.t
@@ -33,21 +33,27 @@ my $mime = PublicInbox::MIME->create(
 local $ENV{NPROC} = 2;
 my $minmax;
 my $msgmap;
+my ($mark1, $mark2, $mark3, $mark4);
 {
 	my %config = %$ibx_config;
 	my $ibx = PublicInbox::Inbox->new(\%config);
 	my $im = PublicInbox::V2Writable->new($ibx, 1);
+	my $im0 = $im->importer();
 	foreach my $i (1..10) {
 		$mime->header_set('Message-Id', "<$i\@example.com>");
 		ok($im->add($mime), "message $i added");
 		if ($i == 4) {
+			$mark1 = $im0->get_mark($im0->{tip});
 			$im->remove($mime);
+			$mark2 = $im0->get_mark($im0->{tip});
 		}
 	}
 
 	if ('test remove later') {
+		$mark3 = $im0->get_mark($im0->{tip});
 		$mime->header_set('Message-Id', "<5\@example.com>");
 		$im->remove($mime);
+		$mark4 = $im0->get_mark($im0->{tip});
 	}
 
 	$im->done;
@@ -211,4 +217,193 @@ ok(!-d $xap, 'Xapian directories removed again');
 	is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
 }
 
+
+# An incremental indexing test
+ok(unlink "$mainrepo/msgmap.sqlite3", 'remove msgmap');
+remove_tree($xap);
+ok(!-d $xap, 'Xapian directories removed again');
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	my %config = %$ibx_config;
+	my $ibx = PublicInbox::Inbox->new(\%config);
+	# mark1 4 simple additions in the same index_sync
+	$ibx->{ref_head} = $mark1;
+	my $im = PublicInbox::V2Writable->new($ibx);
+	eval { $im->index_sync() };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	my ($min, $max) = $ibx->mm->minmax;
+	is($min, 1, 'min as expected');
+	is($max, 4, 'max as expected');
+	is_deeply($ibx->mm->msg_range(\$min, $max),
+		  [
+		   [1, '1@example.com' ],
+		   [2, '2@example.com' ],
+		   [3, '3@example.com' ],
+		   [4, '4@example.com' ],
+		  ], 'msgmap as expected' );
+}
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	my %config = %$ibx_config;
+	my $ibx = PublicInbox::Inbox->new(\%config);
+	# mark2 A delete separated from an add in the same index_sync
+	$ibx->{ref_head} = $mark2;
+	my $im = PublicInbox::V2Writable->new($ibx);
+	eval { $im->index_sync() };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	my ($min, $max) = $ibx->mm->minmax;
+	is($min, 1, 'min as expected');
+	is($max, 3, 'max as expected');
+	is_deeply($ibx->mm->msg_range(\$min, $max),
+		  [
+		   [1, '1@example.com' ],
+		   [2, '2@example.com' ],
+		   [3, '3@example.com' ],
+		  ], 'msgmap as expected' );
+}
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	my %config = %$ibx_config;
+	my $ibx = PublicInbox::Inbox->new(\%config);
+	# mark3 adds following the delete at mark2
+	$ibx->{ref_head} = $mark3;
+	my $im = PublicInbox::V2Writable->new($ibx);
+	eval { $im->index_sync() };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	my ($min, $max) = $ibx->mm->minmax;
+	is($min, 1, 'min as expected');
+	is($max, 10, 'max as expected');
+	is_deeply($ibx->mm->msg_range(\$min, $max),
+		  [
+		   [1, '1@example.com' ],
+		   [2, '2@example.com' ],
+		   [3, '3@example.com' ],
+		   [5, '5@example.com' ],
+		   [6, '6@example.com' ],
+		   [7, '7@example.com' ],
+		   [8, '8@example.com' ],
+		   [9, '9@example.com' ],
+		   [10, '10@example.com' ],
+		  ], 'msgmap as expected' );
+}
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	my %config = %$ibx_config;
+	my $ibx = PublicInbox::Inbox->new(\%config);
+	# mark4 A delete of an older message
+	$ibx->{ref_head} = $mark4;
+	my $im = PublicInbox::V2Writable->new($ibx);
+	eval { $im->index_sync() };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	my ($min, $max) = $ibx->mm->minmax;
+	is($min, 1, 'min as expected');
+	is($max, 10, 'max as expected');
+	is_deeply($ibx->mm->msg_range(\$min, $max),
+		  [
+		   [1, '1@example.com' ],
+		   [2, '2@example.com' ],
+		   [3, '3@example.com' ],
+		   [6, '6@example.com' ],
+		   [7, '7@example.com' ],
+		   [8, '8@example.com' ],
+		   [9, '9@example.com' ],
+		   [10, '10@example.com' ],
+		  ], 'msgmap as expected' );
+}
+
+
+# Another incremental indexing test
+ok(unlink "$mainrepo/msgmap.sqlite3", 'remove msgmap');
+remove_tree($xap);
+ok(!-d $xap, 'Xapian directories removed again');
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	my %config = %$ibx_config;
+	my $ibx = PublicInbox::Inbox->new(\%config);
+	# mark2 an add and it's delete in the same index_sync
+	$ibx->{ref_head} = $mark2;
+	my $im = PublicInbox::V2Writable->new($ibx);
+	eval { $im->index_sync() };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	my ($min, $max) = $ibx->mm->minmax;
+	is($min, 1, 'min as expected');
+	is($max, 3, 'max as expected');
+	is_deeply($ibx->mm->msg_range(\$min, $max),
+		  [
+		   [1, '1@example.com' ],
+		   [2, '2@example.com' ],
+		   [3, '3@example.com' ],
+		  ], 'msgmap as expected' );
+}
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	my %config = %$ibx_config;
+	my $ibx = PublicInbox::Inbox->new(\%config);
+	# mark3 adds following the delete at mark2
+	$ibx->{ref_head} = $mark3;
+	my $im = PublicInbox::V2Writable->new($ibx);
+	eval { $im->index_sync() };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	my ($min, $max) = $ibx->mm->minmax;
+	is($min, 1, 'min as expected');
+	is($max, 10, 'max as expected');
+	is_deeply($ibx->mm->msg_range(\$min, $max),
+		  [
+		   [1, '1@example.com' ],
+		   [2, '2@example.com' ],
+		   [3, '3@example.com' ],
+		   [5, '5@example.com' ],
+		   [6, '6@example.com' ],
+		   [7, '7@example.com' ],
+		   [8, '8@example.com' ],
+		   [9, '9@example.com' ],
+		   [10, '10@example.com' ],
+		  ], 'msgmap as expected' );
+}
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	my %config = %$ibx_config;
+	my $ibx = PublicInbox::Inbox->new(\%config);
+	# mark4 A delete of an older message
+	$ibx->{ref_head} = $mark4;
+	my $im = PublicInbox::V2Writable->new($ibx);
+	eval { $im->index_sync() };
+	is($@, '', 'no error from reindexing without msgmap');
+	is_deeply(\@warn, [], 'no warnings');
+	$im->done;
+	my ($min, $max) = $ibx->mm->minmax;
+	is($min, 1, 'min as expected');
+	is($max, 10, 'max as expected');
+	is_deeply($ibx->mm->msg_range(\$min, $max),
+		  [
+		   [1, '1@example.com' ],
+		   [2, '2@example.com' ],
+		   [3, '3@example.com' ],
+		   [6, '6@example.com' ],
+		   [7, '7@example.com' ],
+		   [8, '8@example.com' ],
+		   [9, '9@example.com' ],
+		   [10, '10@example.com' ],
+		  ], 'msgmap as expected' );
+}
+
 done_testing();
-- 
2.17.1


  parent reply index

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-08-01 16:41 [PATCH 00/13]: Incremental index fixes ebiederm
2018-08-01 16:43 ` [PATCH 01/13] Import.pm: Don't assume {in} and {out} always exist Eric W. Biederman
2018-08-01 16:43 ` [PATCH 02/13] t/v1reindex.t: Isolate the test cases Eric W. Biederman
2018-08-01 16:43 ` [PATCH 03/13] t/v2reindex.t: Isolate the test cases more Eric W. Biederman
2018-08-01 16:43 ` [PATCH 04/13] t/v[12]reindex.t: Place expected second in Xapian tests Eric W. Biederman
2018-08-01 16:43 ` [PATCH 05/13] t/v[12]reindex.t: Test that the resulting msgmap is as expected Eric W. Biederman
2018-08-01 16:43 ` Eric W. Biederman [this message]
2018-08-01 16:43 ` [PATCH 07/13] SearchIdx.pm: Always assign numbers backwards during incremental indexing Eric W. Biederman
2018-08-01 16:43 ` [PATCH 08/13] Msgmap.pm: Track the largest value of num ever assigned Eric W. Biederman
2018-08-02  3:00   ` Eric Wong
2018-08-02  3:44     ` [WIP] searchidx: support incremental indexing on indexlevel=basic Eric Wong
2018-08-02 12:25       ` ebiederm
2018-08-02 17:12         ` ebiederm
2018-08-02 18:15           ` ebiederm
2019-05-14  2:04       ` [PATCH 0/3] incremental index fixes for indexlevel=basic Eric Wong
2019-05-14  2:04         ` [PATCH 1/3] v1writable: new wrapper which is closer to v2writable Eric Wong
2019-05-14  2:04         ` [PATCH 2/3] v2writable: allow setting nproc via creat options Eric Wong
2019-05-14  2:04         ` [PATCH 3/3] searchidx: fix incremental index with indexlevel=basic on v1 Eric Wong
2018-08-02 12:08     ` [PATCH 08/13] Msgmap.pm: Track the largest value of num ever assigned ebiederm
2018-08-01 16:43 ` [PATCH 09/13] t/v[12]reindex.t Verify num_highwater Eric W. Biederman
2018-08-01 16:43 ` [PATCH 10/13] t/v[12]reindex.t: Verify the num highwater is as expected Eric W. Biederman
2018-08-01 16:43 ` [PATCH 11/13] SearchIdx,V2Writeable: Update num_highwater on optimized deletes Eric W. Biederman
2018-08-01 16:43 ` [PATCH 12/13] V2Writeable.pm: Ensure that a found message number is in the msgmap Eric W. Biederman
2018-08-01 16:43 ` [PATCH 13/13] V2Writeable.pm: In unindex_oid delete the message from msgmap Eric W. Biederman

Reply instructions:

You may reply publically 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: http://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=20180801164344.7911-6-ebiederm@xmission.com \
    --to=ebiederm@xmission.com \
    --cc=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

user/dev discussion of public-inbox itself

Archives are clonable:
	git clone --mirror http://public-inbox.org/meta
	git clone --mirror http://czquwvybam4bgbro.onion/meta
	git clone --mirror http://hjrcffqmbrq6wope.onion/meta
	git clone --mirror http://ou63pmih66umazou.onion/meta

Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.mail.public-inbox.meta
	nntp://ou63pmih66umazou.onion/inbox.comp.mail.public-inbox.meta
	nntp://czquwvybam4bgbro.onion/inbox.comp.mail.public-inbox.meta
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.mail.public-inbox.meta
	nntp://news.gmane.org/gmane.mail.public-inbox.general

 note: .onion URLs require Tor: https://www.torproject.org/

AGPL code for this site: git clone https://public-inbox.org/ public-inbox