* [PATCH 05/13] t/v[12]reindex.t: Test that the resulting msgmap is as expected
2018-08-01 16:41 7% [PATCH 00/13]: Incremental index fixes Eric W. Biederman
@ 2018-08-01 16:43 6% ` Eric W. Biederman
0 siblings, 0 replies; 2+ results
From: Eric W. Biederman @ 2018-08-01 16:43 UTC (permalink / raw)
To: Eric Wong; +Cc: meta, Eric W. Biederman
Deeply inspect the entire message map in the reindexing tests
as the actual message order is significant and can result
in surprises.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
t/v1reindex.t | 35 +++++++++++++++++++++++++++++++++++
t/v2reindex.t | 33 +++++++++++++++++++++++++++++++++
2 files changed, 68 insertions(+)
diff --git a/t/v1reindex.t b/t/v1reindex.t
index de4fafda5ae9..877e70390910 100644
--- a/t/v1reindex.t
+++ b/t/v1reindex.t
@@ -32,6 +32,7 @@ my $mime = PublicInbox::MIME->create(
body => "hello world\n",
);
my $minmax;
+my $msgmap;
{
my %config = %$ibx_config;
my $ibx = PublicInbox::Inbox->new(\%config);
@@ -57,6 +58,19 @@ my $minmax;
$minmax = [ $ibx->mm->minmax ];
ok(defined $minmax->[0] && defined $minmax->[1], 'minmax defined');
is_deeply($minmax, [ 1, 10 ], 'minmax as expected');
+
+ my ($min, $max) = @$minmax;
+ $msgmap = $ibx->mm->msg_range(\$min, $max);
+ is_deeply($msgmap, [
+ [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');
}
{
@@ -67,6 +81,9 @@ my $minmax;
eval { $rw->index_sync({reindex => 1}) };
is($@, '', 'no error from reindexing');
$im->done;
+
+ my ($min, $max) = $ibx->mm->minmax;
+ is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
my $xap = "$mainrepo/public-inbox/xapian".PublicInbox::Search::SCHEMA_VERSION();
@@ -85,6 +102,9 @@ ok(!-d $xap, 'Xapian directories removed');
delete $ibx->{mm};
is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
+
+ my ($min, $max) = $ibx->mm->minmax;
+ is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
ok(unlink "$mainrepo/public-inbox/msgmap.sqlite3", 'remove msgmap');
@@ -104,6 +124,9 @@ ok(!-d $xap, 'Xapian directories removed again');
ok(-d $xap, 'Xapian directories recreated');
delete $ibx->{mm};
is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
+
+ my ($min, $max) = $ibx->mm->minmax;
+ is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
ok(unlink "$mainrepo/public-inbox/msgmap.sqlite3", 'remove msgmap');
@@ -123,6 +146,9 @@ ok(!-d $xap, 'Xapian directories removed again');
ok(-d $xap, 'Xapian directories recreated');
delete $ibx->{mm};
is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
+
+ my ($min, $max) = @$minmax;
+ is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
ok(unlink "$mainrepo/public-inbox/msgmap.sqlite3", 'remove msgmap');
@@ -145,6 +171,9 @@ ok(!-d $xap, 'Xapian directories removed again');
is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
my $mset = $ibx->search->query('hello world', {mset=>1});
isnt($mset->size, 0, 'got Xapian search results');
+
+ my ($min, $max) = $ibx->mm->minmax;
+ is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
ok(unlink "$mainrepo/public-inbox/msgmap.sqlite3", 'remove msgmap');
@@ -167,6 +196,9 @@ ok(!-d $xap, 'Xapian directories removed again');
is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
my $mset = $ibx->search->reopen->query('hello world', {mset=>1});
is($mset->size, 0, "no Xapian search results");
+
+ my ($min, $max) = $ibx->mm->minmax;
+ is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
# upgrade existing basic to medium
@@ -185,6 +217,9 @@ ok(!-d $xap, 'Xapian directories removed again');
is_deeply(\@warn, [], 'no warnings');
my $mset = $ibx->search->reopen->query('hello world', {mset=>1});
isnt($mset->size, 0, 'search OK after basic -> medium');
+
+ my ($min, $max) = $ibx->mm->minmax;
+ is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
done_testing();
diff --git a/t/v2reindex.t b/t/v2reindex.t
index 67d8be787a78..31e61d5b2578 100644
--- a/t/v2reindex.t
+++ b/t/v2reindex.t
@@ -32,6 +32,7 @@ my $mime = PublicInbox::MIME->create(
);
local $ENV{NPROC} = 2;
my $minmax;
+my $msgmap;
{
my %config = %$ibx_config;
my $ibx = PublicInbox::Inbox->new(\%config);
@@ -53,6 +54,19 @@ my $minmax;
$minmax = [ $ibx->mm->minmax ];
ok(defined $minmax->[0] && defined $minmax->[1], 'minmax defined');
is_deeply($minmax, [ 1, 10 ], 'minmax as expected');
+
+ my ($min, $max) = @$minmax;
+ $msgmap = $ibx->mm->msg_range(\$min, $max);
+ is_deeply($msgmap, [
+ [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');
}
{
@@ -65,6 +79,9 @@ my $minmax;
delete $ibx->{mm};
is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
+
+ my ($min, $max) = $ibx->mm->minmax;
+ is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
my $xap = "$mainrepo/xap".PublicInbox::Search::SCHEMA_VERSION();
@@ -81,6 +98,9 @@ ok(!-d $xap, 'Xapian directories removed');
delete $ibx->{mm};
is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
+
+ my ($min, $max) = $ibx->mm->minmax;
+ is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
ok(unlink "$mainrepo/msgmap.sqlite3", 'remove msgmap');
@@ -99,6 +119,9 @@ ok(!-d $xap, 'Xapian directories removed again');
ok(-d $xap, 'Xapian directories recreated');
delete $ibx->{mm};
is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
+
+ my ($min, $max) = $ibx->mm->minmax;
+ is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
my %sizes;
@@ -121,6 +144,9 @@ ok(!-d $xap, 'Xapian directories removed again');
my $mset = $ibx->search->query('"hello world"', {mset=>1});
isnt($mset->size, 0, "phrase search succeeds on indexlevel=full");
for (<"$xap/*/*">) { $sizes{$ibx->{indexlevel}} += -s _ if -f $_ }
+
+ my ($min, $max) = $ibx->mm->minmax;
+ is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
ok(unlink "$mainrepo/msgmap.sqlite3", 'remove msgmap');
@@ -153,6 +179,10 @@ ok(!-d $xap, 'Xapian directories removed again');
isnt($mset->size, 0, "normal search works on indexlevel=medium");
for (<"$xap/*/*">) { $sizes{$ibx->{indexlevel}} += -s _ if -f $_ }
ok($sizes{full} > $sizes{medium}, 'medium is smaller than full');
+
+
+ my ($min, $max) = $ibx->mm->minmax;
+ is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
ok(unlink "$mainrepo/msgmap.sqlite3", 'remove msgmap');
@@ -176,6 +206,9 @@ ok(!-d $xap, 'Xapian directories removed again');
is($mset->size, 0, "search fails on indexlevel='basic'");
for (<"$xap/*/*">) { $sizes{$ibx->{indexlevel}} += -s _ if -f $_ }
ok($sizes{medium} > $sizes{basic}, 'basic is smaller than medium');
+
+ my ($min, $max) = $ibx->mm->minmax;
+ is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
done_testing();
--
2.17.1
^ permalink raw reply related [relevance 6%]
* [PATCH 00/13]: Incremental index fixes
@ 2018-08-01 16:41 7% Eric W. Biederman
2018-08-01 16:43 6% ` [PATCH 05/13] t/v[12]reindex.t: Test that the resulting msgmap is as expected Eric W. Biederman
0 siblings, 1 reply; 2+ results
From: Eric W. Biederman @ 2018-08-01 16:41 UTC (permalink / raw)
To: Eric Wong; +Cc: meta
Eric,
Recently I noticed some weird indexing on one of my mailboxes. So I dug
in and made the index_sync tests more robust and found several corner
cases where the current code can be problematic. What follows are the
test cases and fixes for those cases.
The big one is when a message with the highest message number is
deleted. This can cause message numbers to be reassigned so I
explicitly track the highest message number assigned.
Very confusing when reading mail there is a case in SearchIdx
that has been assigning message numbers in the wrong order. Depending
on your time range that can be very confusing as old messages show up
before newer ones.
Finally in v2 deleted messages have not been being deleted from the
msgmap. Which while great for keeping message numbers from going
backwards it means things still show up that shouldn't.
Eric W. Biederman (13):
Import.pm: Don't assume {in} and {out} always exist
t/v1reindex.t: Isolate the test cases
t/v2reindex.t: Isolate the test cases more
t/v[12]reindex.t: Place expected second in Xapian tests
t/v[12]reindex.t: Test that the resulting msgmap is as expected
t/v[12]reindex.t: Test incremental indexing works
SearchIdx.pm: Always assign numbers backwards during incremental indexing
Msgmap.pm: Track the largest value of num ever assigned
t/v[12]reindex.t Verify num_highwater
t/v[12]reindex.t: Verify the num highwater is as expected
SearchIdx,V2Writeable: Update num_highwater on optimized deletes
V2Writeable.pm: Ensure that a found message number is in the msgmap
V2Writeable.pm: In unindex_oid delete the message from msgmap
lib/PublicInbox/Import.pm | 1 +
lib/PublicInbox/Msgmap.pm | 23 ++-
lib/PublicInbox/SearchIdx.pm | 30 ++--
lib/PublicInbox/V2Writable.pm | 20 ++-
t/v1reindex.t | 359 ++++++++++++++++++++++++++++++++++++------
t/v2reindex.t | 335 +++++++++++++++++++++++++++++++++++----
6 files changed, 666 insertions(+), 102 deletions(-)
Eric
^ permalink raw reply [relevance 7%]
Results 1-2 of 2 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2018-08-01 16:41 7% [PATCH 00/13]: Incremental index fixes Eric W. Biederman
2018-08-01 16:43 6% ` [PATCH 05/13] t/v[12]reindex.t: Test that the resulting msgmap is as expected Eric W. Biederman
Code repositories for project(s) associated with this public inbox
https://80x24.org/public-inbox.git
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).