public-inbox-init -V2 for lkml

public-inbox-init -V2 for lkml

[Eric W. Biederman]

I was playing with using git to get my own local copy of lkml and
unless I did something wrong I have found a bug in publc-inbox-init.

Baring some cheats (aka cloning from git.kernel.org) I followed
the directions up on lore.kernel.org, and the archives did not display.

#	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
#	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
#	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
#	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
#	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
#	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
#	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
#
#	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml linux-kernel@vger.kernel.org linux-kernel@archiver.kernel.org
#
#	public-inbox-index lkml

I was able to solve my issue by applying the following patch to
objects/info/alternatives.

--- all.git/objects/info/alternates-old 2018-07-04 04:18:17.734755092 -0500
+++ all.git/objects/info/alternates     2018-07-04 04:18:11.874754952 -0500
@@ -1 +1,7 @@
+../../git/0.git/objects
+../../git/1.git/objects
+../../git/2.git/objects
+../../git/3.git/objects
+../../git/4.git/objects
+../../git/5.git/objects
 ../../git/6.git/objects

AKA adding the older git directories to all.git.

Is that the correct fix?  Am I write in thinking that public-inbox-init
is failing to do that?  Or am I missing something?

Eric

[PATCH] v2: fill alternates with old epochs on init from mirrors

[Eric Wong]

"Eric W. Biederman" <ebiederm@xmission.com> wrote:
> Is that the correct fix?  Am I write in thinking that public-inbox-init
> is failing to do that?  Or am I missing something?

Yes, filling in alternates is the correct fix.  Sorry about that,
you've found a bug which I failed to test :x

Below patch should fix it, thanks for the report:

-------8<------
Subject: [PATCH] v2: fill alternates with old epochs on init from mirrors

For v2 repositories with multiple epochs, we must not forget
about earlier epochs in clones.  Ensure we update the alternates
file with all known epochs up to the current one.

Reported-by: Eric W. Biederman <ebiederm@xmission.com>
  https://public-inbox.org/meta/871scj2vzi.fsf@xmission.com/
---
 lib/PublicInbox/V2Writable.pm | 12 +++++++++---
 t/v2mirror.t                  | 32 ++++++++++++++++++++++++--------
 2 files changed, 33 insertions(+), 11 deletions(-)

diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index d8d75ec..412eb6a 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -495,15 +495,21 @@ sub git_init {
 	PublicInbox::Import::run_die(\@cmd);
 
 	my $alt = "$all/objects/info/alternates";
-	my $new_obj_dir = "../../git/$epoch.git/objects";
 	my %alts;
+	my @add;
 	if (-e $alt) {
 		open(my $fh, '<', $alt) or die "open < $alt: $!\n";
 		%alts = map { chomp; $_ => 1 } (<$fh>);
 	}
-	return $git_dir if $alts{$new_obj_dir};
+	foreach my $i (0..$epoch) {
+		my $dir = "../../git/$i.git/objects";
+		push @add, $dir if !$alts{$dir} && -d "$pfx/$i.git";
+	}
+	return $git_dir unless @add;
 	open my $fh, '>>', $alt or die "open >> $alt: $!\n";
-	print $fh "$new_obj_dir\n" or die "print >> $alt: $!\n";
+	foreach my $dir (@add) {
+		print $fh "$dir\n" or die "print >> $alt: $!\n";
+	}
 	close $fh or die "close $alt: $!\n";
 	$git_dir
 }
diff --git a/t/v2mirror.t b/t/v2mirror.t
index 4cd369b..c0c329c 100644
--- a/t/v2mirror.t
+++ b/t/v2mirror.t
@@ -45,11 +45,16 @@ To: You <you@example.com>
 Subject: a
 Date: Thu, 01 Jan 1970 00:00:00 +0000
 
+my $old_rotate_bytes = $v2w->{rotate_bytes};
+$v2w->{rotate_bytes} = 500; # force rotating
 for my $i (1..9) {
 	$mime->header_set('Message-ID', "<$i\@example.com>");
 	$mime->header_set('Subject', "subject = $i");
 	ok($v2w->add($mime), "add msg $i OK");
 }
+
+my $epoch_max = $v2w->{epoch_max};
+ok($epoch_max > 0, "multiple epochs");
 $v2w->done;
 
 my %opts = (
@@ -79,11 +84,14 @@ ok(defined $pid, 'forked httpd process successfully');
 my ($host, $port) = ($sock->sockhost, $sock->sockport);
 $sock = undef;
 
-my @cmd = (qw(git clone --mirror -q), "http://$host:$port/v2/0",
-	"$tmpdir/m/git/0.git");
+my @cmd;
+foreach my $i (0..$epoch_max) {
+	@cmd = (qw(git clone --mirror -q), "http://$host:$port/v2/$i",
+		"$tmpdir/m/git/$i.git");
 
-is(system(@cmd), 0, 'cloned OK');
-ok(-d "$tmpdir/m/git/0.git", 'mirror OK');;
+	is(system(@cmd), 0, 'cloned OK');
+	ok(-d "$tmpdir/m/git/$i.git", 'mirror OK');
+}
 
 @cmd = ("$script-init", '-V2', 'm', "$tmpdir/m", 'http://example.com/m',
 	'alt@example.com');
@@ -94,14 +102,23 @@ my $mibx = { mainrepo => "$tmpdir/m", address => 'alt@example.com' };
 $mibx = PublicInbox::Inbox->new($mibx);
 is_deeply([$mibx->mm->minmax], [$ibx->mm->minmax], 'index synched minmax');
 
+$v2w->{rotate_bytes} = $old_rotate_bytes;
 for my $i (10..15) {
 	$mime->header_set('Message-ID', "<$i\@example.com>");
 	$mime->header_set('Subject', "subject = $i");
 	ok($v2w->add($mime), "add msg $i OK");
 }
 $v2w->barrier;
-is(system('git', "--git-dir=$tmpdir/m/git/0.git", 'fetch', '-q'), 0,
-	'fetch successful');
+
+sub fetch_each_epoch {
+	foreach my $i (0..$epoch_max) {
+		my $dir = "$tmpdir/m/git/$i.git";
+		is(system('git', "--git-dir=$dir", 'fetch', '-q'), 0,
+			'fetch successful');
+	}
+}
+
+fetch_each_epoch();
 
 my $mset = $mibx->search->reopen->query('m:15@example.com', {mset => 1});
 is(scalar($mset->items), 0, 'new message not found in mirror, yet');
@@ -131,8 +148,7 @@ like($to_purge, qr/\A[a-f0-9]{40,}\z/, 'read blob to be purged');
 $mset = $ibx->search->reopen->query('m:10@example.com', {mset => 1});
 is(scalar($mset->items), 0, 'purged message gone from origin');
 
-is(system('git', "--git-dir=$tmpdir/m/git/0.git", 'fetch', '-q'), 0,
-	'fetch successful');
+fetch_each_epoch();
 {
 	open my $err, '+>', "$tmpdir/index-err" or die "open: $!";
 	my $ipid = fork;
-- 
zero. one. infinity!

Re: [PATCH] v2: fill alternates with old epochs on init from mirrors

[Eric W. Biederman]

Eric Wong <e@80x24.org> writes:

> "Eric W. Biederman" <ebiederm@xmission.com> wrote:
>> Is that the correct fix?  Am I write in thinking that public-inbox-init
>> is failing to do that?  Or am I missing something?
>
> Yes, filling in alternates is the correct fix.  Sorry about that,
> you've found a bug which I failed to test :x
>
> Below patch should fix it, thanks for the report:
>
> -------8<------
> Subject: [PATCH] v2: fill alternates with old epochs on init from mirrors
>
> For v2 repositories with multiple epochs, we must not forget
> about earlier epochs in clones.  Ensure we update the alternates
> file with all known epochs up to the current one.
>
> Reported-by: Eric W. Biederman <ebiederm@xmission.com>
>   https://public-inbox.org/meta/871scj2vzi.fsf@xmission.com/

Tested-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>


I just reran my test case and objects/info/alternatives now lists
all of the repos.

Thanky you for the quick fix.


> ---
>  lib/PublicInbox/V2Writable.pm | 12 +++++++++---
>  t/v2mirror.t                  | 32 ++++++++++++++++++++++++--------
>  2 files changed, 33 insertions(+), 11 deletions(-)
>
> diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
> index d8d75ec..412eb6a 100644
> --- a/lib/PublicInbox/V2Writable.pm
> +++ b/lib/PublicInbox/V2Writable.pm
> @@ -495,15 +495,21 @@ sub git_init {
>  	PublicInbox::Import::run_die(\@cmd);
>  
>  	my $alt = "$all/objects/info/alternates";
> -	my $new_obj_dir = "../../git/$epoch.git/objects";
>  	my %alts;
> +	my @add;
>  	if (-e $alt) {
>  		open(my $fh, '<', $alt) or die "open < $alt: $!\n";
>  		%alts = map { chomp; $_ => 1 } (<$fh>);
>  	}
> -	return $git_dir if $alts{$new_obj_dir};
> +	foreach my $i (0..$epoch) {
> +		my $dir = "../../git/$i.git/objects";
> +		push @add, $dir if !$alts{$dir} && -d "$pfx/$i.git";
> +	}
> +	return $git_dir unless @add;
>  	open my $fh, '>>', $alt or die "open >> $alt: $!\n";
> -	print $fh "$new_obj_dir\n" or die "print >> $alt: $!\n";
> +	foreach my $dir (@add) {
> +		print $fh "$dir\n" or die "print >> $alt: $!\n";
> +	}
>  	close $fh or die "close $alt: $!\n";
>  	$git_dir
>  }
> diff --git a/t/v2mirror.t b/t/v2mirror.t
> index 4cd369b..c0c329c 100644
> --- a/t/v2mirror.t
> +++ b/t/v2mirror.t
> @@ -45,11 +45,16 @@ To: You <you@example.com>
>  Subject: a
>  Date: Thu, 01 Jan 1970 00:00:00 +0000
>  
> +my $old_rotate_bytes = $v2w->{rotate_bytes};
> +$v2w->{rotate_bytes} = 500; # force rotating
>  for my $i (1..9) {
>  	$mime->header_set('Message-ID', "<$i\@example.com>");
>  	$mime->header_set('Subject', "subject = $i");
>  	ok($v2w->add($mime), "add msg $i OK");
>  }
> +
> +my $epoch_max = $v2w->{epoch_max};
> +ok($epoch_max > 0, "multiple epochs");
>  $v2w->done;
>  
>  my %opts = (
> @@ -79,11 +84,14 @@ ok(defined $pid, 'forked httpd process successfully');
>  my ($host, $port) = ($sock->sockhost, $sock->sockport);
>  $sock = undef;
>  
> -my @cmd = (qw(git clone --mirror -q), "http://$host:$port/v2/0",
> -	"$tmpdir/m/git/0.git");
> +my @cmd;
> +foreach my $i (0..$epoch_max) {
> +	@cmd = (qw(git clone --mirror -q), "http://$host:$port/v2/$i",
> +		"$tmpdir/m/git/$i.git");
>  
> -is(system(@cmd), 0, 'cloned OK');
> -ok(-d "$tmpdir/m/git/0.git", 'mirror OK');;
> +	is(system(@cmd), 0, 'cloned OK');
> +	ok(-d "$tmpdir/m/git/$i.git", 'mirror OK');
> +}
>  
>  @cmd = ("$script-init", '-V2', 'm', "$tmpdir/m", 'http://example.com/m',
>  	'alt@example.com');
> @@ -94,14 +102,23 @@ my $mibx = { mainrepo => "$tmpdir/m", address => 'alt@example.com' };
>  $mibx = PublicInbox::Inbox->new($mibx);
>  is_deeply([$mibx->mm->minmax], [$ibx->mm->minmax], 'index synched minmax');
>  
> +$v2w->{rotate_bytes} = $old_rotate_bytes;
>  for my $i (10..15) {
>  	$mime->header_set('Message-ID', "<$i\@example.com>");
>  	$mime->header_set('Subject', "subject = $i");
>  	ok($v2w->add($mime), "add msg $i OK");
>  }
>  $v2w->barrier;
> -is(system('git', "--git-dir=$tmpdir/m/git/0.git", 'fetch', '-q'), 0,
> -	'fetch successful');
> +
> +sub fetch_each_epoch {
> +	foreach my $i (0..$epoch_max) {
> +		my $dir = "$tmpdir/m/git/$i.git";
> +		is(system('git', "--git-dir=$dir", 'fetch', '-q'), 0,
> +			'fetch successful');
> +	}
> +}
> +
> +fetch_each_epoch();
>  
>  my $mset = $mibx->search->reopen->query('m:15@example.com', {mset => 1});
>  is(scalar($mset->items), 0, 'new message not found in mirror, yet');
> @@ -131,8 +148,7 @@ like($to_purge, qr/\A[a-f0-9]{40,}\z/, 'read blob to be purged');
>  $mset = $ibx->search->reopen->query('m:10@example.com', {mset => 1});
>  is(scalar($mset->items), 0, 'purged message gone from origin');
>  
> -is(system('git', "--git-dir=$tmpdir/m/git/0.git", 'fetch', '-q'), 0,
> -	'fetch successful');
> +fetch_each_epoch();
>  {
>  	open my $err, '+>', "$tmpdir/index-err" or die "open: $!";
>  	my $ipid = fork;