user/dev discussion of public-inbox itself
 help / color / mirror / code / Atom feed
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 35/95] lei_mirror: simplify v2 code paths
Date: Mon, 28 Nov 2022 05:31:32 +0000	[thread overview]
Message-ID: <20221128053232.291618-36-e@80x24.org> (raw)
In-Reply-To: <20221128053232.291618-1-e@80x24.org>

We can simply reuse the parallelization of the manifest
code path for non-manifest v2 clones, now.
---
 lib/PublicInbox/LeiMirror.pm | 86 ++++++++++++++----------------------
 1 file changed, 34 insertions(+), 52 deletions(-)

diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm
index 20ae3ac8..18c825d3 100644
--- a/lib/PublicInbox/LeiMirror.pm
+++ b/lib/PublicInbox/LeiMirror.pm
@@ -67,8 +67,9 @@ sub try_scrape {
 			my ($n) = (m!/([0-9]+)\z!);
 			$n => [ URI->new($_), '' ]
 		} @v2_urls; # uniq
-		clone_v2($self, \%v2_epochs);
-		reap_live() while keys(%$LIVE);
+		clone_v2_prep($self, \%v2_epochs);
+		delete local $lei->{opt}->{epoch};
+		clone_all($self);
 		return;
 	}
 
@@ -223,7 +224,7 @@ sub index_cloned_inbox {
 		PublicInbox::Admin::progress_prepare($opt, $lei->{2});
 		PublicInbox::Admin::index_inbox($ibx, undef, $opt);
 	}
-	return if defined $self->{cur_dst};
+	return if defined $self->{cur_dst}; # one of many repos to clone
 	open my $x, '>', "$self->{dst}/mirror.done"; # for _wq_done_wait
 }
 
@@ -396,19 +397,6 @@ sub v2_done { # called via OnDestroy
 	my $mg = PublicInbox::MultiGit->new($dst, 'all.git', 'git');
 	$mg->fill_alternates;
 	for my $i ($mg->git_epochs) { $mg->epoch_cfg_set($i) }
-	my $entries = delete($self->{-entv}) // [];
-	while (@$entries) {
-		my ($edst, $ent) = splice(@$entries);
-		if (defined(my $o = $ent->{owner})) {
-			run_die [qw(git config -f), "$edst/config",
-				'gitweb.owner', $o];
-		}
-		my $d = $ent->{description} // next;
-		my $fn = "$edst/description";
-		open my $fh, '>', $fn or die "open($fn): $!";
-		print $fh $d, "\n" or die "print($fn): $!";
-		close $fh or die "close($fn): $!";
-	}
 	for my $edst (@{delete($self->{-read_only}) // []}) {
 		my @st = stat($edst) or die "stat($edst): $!";
 		chmod($st[2] & 0555, $edst) or die "chmod(a-w, $edst): $!";
@@ -428,7 +416,7 @@ sub reap_live {
 	}
 }
 
-sub clone_v2 ($$;$) {
+sub clone_v2_prep ($$;$) {
 	my ($self, $v2_epochs, $m) = @_; # $m => manifest.js.gz hashref
 	my $lei = $self->{lei};
 	my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return;
@@ -438,7 +426,7 @@ sub clone_v2 ($$;$) {
 	my $want = parse_epochs($lei->{opt}->{epoch}, $v2_epochs);
 	my $task = $m ? bless { %$self }, __PACKAGE__ : $self;
 	delete $task->{todo}; # $self->{todo} still exists
-	my (@src_edst, @skip, $desc);
+	my (@src_edst, @skip, $desc, @entv);
 	for my $nr (sort { $a <=> $b } keys %$v2_epochs) {
 		my ($uri, $key) = @{$v2_epochs->{$nr}};
 		my $src = $uri->as_string;
@@ -448,14 +436,18 @@ failed to extract epoch number from $src
 
 		$1 + 0 == $nr or die "BUG: <$uri> miskeyed $1 != $nr";
 		$edst .= "/git/$nr.git";
-		my $ent = $m->{$key} // die "BUG: `$key' not in manifest.js.gz";
-		if (defined(my $d = $ent->{description})) {
-			$d =~ s/ \[epoch [0-9]+\]\z//s;
-			$desc = $d;
+		my $ent;
+		if ($m) {
+			$ent = $m->{$key} //
+				die("BUG: `$key' not in manifest.js.gz");
+			if (defined(my $d = $ent->{description})) {
+				$d =~ s/ \[epoch [0-9]+\]\z//s;
+				$desc = $d;
+			}
 		}
 		if (!$want || $want->{$nr}) {
 			push @src_edst, $src, $edst;
-			push @{$task->{-entv}}, $edst, $ent;
+			push @entv, $edst, $ent;
 			$self->{any_want}->{$key} = 1;
 		} else { # create a placeholder so users only need to chmod +w
 			init_placeholder($src, $edst, $ent);
@@ -464,7 +456,7 @@ failed to extract epoch number from $src
 		}
 	}
 	# filter out the epochs we skipped
-	$self->{-culled_manifest} = 1 if delete(@$m{@skip});
+	$self->{-culled_manifest} = 1 if $m && delete(@$m{@skip});
 
 	(!$self->{dry_run} && !-d $dst) and File::Path::mkpath($dst);
 
@@ -475,27 +467,16 @@ failed to extract epoch number from $src
 
 	defined($desc) ? ($task->{'txt.description'} = $desc) :
 		_get_txt_start($task, 'description', $fini);
-	if (my $todo = $self->{todo}) {  # manifest clone, deal with references
-		my $entv = delete $task->{-entv};
-		while (@$entv) {
-			my ($edst, $ent) = splice(@$entv, 0, 2);
-			my $etask = bless { %$task }, __PACKAGE__;
-			$etask->{-ent} = $ent; # may have {reference}
-			$etask->{cur_src} = shift @src_edst //
-				die 'BUG: no cur_src';
-			$etask->{cur_dst} = shift @src_edst //
-				die 'BUG: no cur_dst';
-			$etask->{cur_dst} eq $edst or
-				die "BUG: `$etask->{cur_dst}' != `$edst'";
-			$etask->{-is_epoch} = $fini;
-			push @{$todo->{($ent->{reference} // '')}}, $etask;
-		}
-	} else {
-		my @cmd = clone_cmd($lei, my $opt = {});
-		while (@src_edst && !$lei->{child_error}) {
-			my $cmd = [ @$pfx, @cmd, splice(@src_edst, 0, 2) ];
-			start_clone($self, $cmd, $opt, $fini);
-		}
+	while (@entv) {
+		my ($edst, $ent) = splice(@entv, 0, 2);
+		my $etask = bless { %$task }, __PACKAGE__;
+		$etask->{-ent} = $ent; # may have {reference}
+		$etask->{cur_src} = shift @src_edst // die 'BUG: no cur_src';
+		$etask->{cur_dst} = shift @src_edst // die 'BUG: no cur_dst';
+		$etask->{cur_dst} eq $edst or
+			die "BUG: `$etask->{cur_dst}' != `$edst'";
+		$etask->{-is_epoch} = $fini;
+		push @{$self->{todo}->{($ent->{reference} // '')}}, $etask;
 	}
 }
 
@@ -568,7 +549,7 @@ sub multi_inbox ($$$) {
 	($path_pfx, $n, $ret);
 }
 
-sub clone_all ($$) {
+sub clone_all {
 	my ($self, $m) = @_;
 	my $todo = delete $self->{todo};
 	my $nodep = delete $todo->{''};
@@ -587,9 +568,9 @@ sub clone_all ($$) {
 	# resolve references, deepest, first:
 	while (scalar keys %$todo) {
 		for my $x (keys %$todo) {
-			my $nr;
+			my ($nr, $nxt);
 			# resolve multi-level references
-			while (defined(my $nxt = $m->{$x}->{reference})) {
+			while ($m && defined($nxt = $m->{$x}->{reference})) {
 				exists($todo->{$nxt}) or last;
 				die <<EOM if ++$nr > 1000;
 E: dependency loop detected (`$x' => `$nxt')
@@ -604,6 +585,7 @@ EOM
 			last; # restart %$todo iteration
 		}
 	}
+	reap_live() while keys(%$LIVE);
 }
 
 # FIXME: this gets confused by single inbox instance w/ global manifest.js.gz
@@ -656,7 +638,7 @@ sub try_manifest {
 			index($self->{cur_dst}, "\n") >= 0 and die <<EOM;
 E: `$self->{cur_dst}' must not contain newline
 EOM
-			clone_v2($self, \%v2_epochs, $m);
+			clone_v2_prep($self, \%v2_epochs, $m);
 			return if $self->{lei}->{child_error};
 		}
 	}
@@ -679,16 +661,16 @@ E: `$task->{cur_dst}' must not contain newline
 EOM
 			$task->{cur_src} .= '/';
 			my $dep = $task->{-ent}->{reference} // '';
-			push @{$self->{todo}->{$dep}}, $task;
+			push @{$self->{todo}->{$dep}}, $task; # for clone_all
 			$self->{any_want}->{$name} = 1;
 		}
 	}
 	delete local $lei->{opt}->{epoch} if defined($v2);
 	clone_all($self, $m);
-	reap_live() while keys(%$LIVE);
 	return if $self->{lei}->{child_error} || $self->{dry_run};
 
-	if (delete $self->{-culled_manifest}) { # set by clone_v2/-I/--exclude
+	# set by clone_v2_prep/-I/--exclude
+	if (delete $self->{-culled_manifest}) {
 		# write the smaller manifest if epochs were skipped so
 		# users won't have to delete manifest if they +w an
 		# epoch they no longer want to skip

  parent reply	other threads:[~2022-11-28  5:32 UTC|newest]

Thread overview: 96+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-11-28  5:30 [PATCH 00/95] clone: multi-inbox/repo support Eric Wong
2022-11-28  5:30 ` [PATCH 01/95] clone: support multi-inbox clone Eric Wong
2022-11-28  5:30 ` [PATCH 02/95] clone: support --include and --exclude with multi-clone Eric Wong
2022-11-28  5:31 ` [PATCH 03/95] clone: parallelize v2 epoch clones Eric Wong
2022-11-28  5:31 ` [PATCH 04/95] lei_mirror: async config retrieval for v2 w/ manifest Eric Wong
2022-11-28  5:31 ` [PATCH 05/95] lei_mirror: rely on DESTROY to index v2 inbox Eric Wong
2022-11-28  5:31 ` [PATCH 06/95] lei_mirror: rely on global process reaper Eric Wong
2022-11-28  5:31 ` [PATCH 07/95] clone: support parallel v1 clones Eric Wong
2022-11-28  5:31 ` [PATCH 08/95] lei_mirror: default to single job by default Eric Wong
2022-11-28  5:31 ` [PATCH 09/95] lei_mirror: move directory creation to v2-only path Eric Wong
2022-11-28  5:31 ` [PATCH 10/95] lei_mirror: retrieve description text asynchronously, too Eric Wong
2022-11-28  5:31 ` [PATCH 11/95] switch inotify/kevent stuff to v5.12 Eric Wong
2022-11-28  5:31 ` [PATCH 12/95] manifest: update module blurb + v5.12 Eric Wong
2022-11-28  5:31 ` [PATCH 13/95] lei_mirror: simplify _get_txt_start callers Eric Wong
2022-11-28  5:31 ` [PATCH 14/95] lei_mirror: elide description retrieval for v1|coderepo Eric Wong
2022-11-28  5:31 ` [PATCH 15/95] lei_mirror: add a hint for skipped epoch permissions Eric Wong
2022-11-28  5:31 ` [PATCH 16/95] lei_mirror: consolidate clone process management Eric Wong
2022-11-28  5:31 ` [PATCH 17/95] lei_mirror: load File::Path unconditionally Eric Wong
2022-11-28  5:31 ` [PATCH 18/95] lei_mirror: load most modules up-front Eric Wong
2022-11-28  5:31 ` [PATCH 19/95] lei_mirror: set gitweb.owner from manifest Eric Wong
2022-11-28  5:31 ` [PATCH 20/95] clone: support --dry-run / -n flag Eric Wong
2022-11-28  5:31 ` [PATCH 21/95] lei_mirror: initialize placeholders with "head" from manifest Eric Wong
2022-11-28  5:31 ` [PATCH 22/95] lei_mirror: support {reference} for v1 manifest clones Eric Wong
2022-11-28  5:31 ` [PATCH 23/95] lei_mirror: reduce noise on interrupted clones Eric Wong
2022-11-28  5:31 ` [PATCH 24/95] clone: support --inbox-config option Eric Wong
2022-11-28  5:31 ` [PATCH 25/95] lei_mirror: retrieve v2 description properly Eric Wong
2022-11-28  5:31 ` [PATCH 26/95] lei_mirror: reduce scope of v2 lock Eric Wong
2022-11-28  5:31 ` [PATCH 27/95] lei_mirror: allow --epoch on mixed v1/v2 clones Eric Wong
2022-11-28  5:31 ` [PATCH 28/95] lei_mirror: fix infinite loop in dependency resolution Eric Wong
2022-11-28  5:31 ` [PATCH 29/95] lei_mirror: defend against infinite loops Eric Wong
2022-11-28  5:31 ` [PATCH 30/95] lei_mirror: do not fetch descriptions if using manifest Eric Wong
2022-11-28  5:31 ` [PATCH 31/95] lei_mirror: require PublicInbox::Lock at use Eric Wong
2022-11-28  5:31 ` [PATCH 32/95] lei_mirror: fix glob semantics to match end-of-path Eric Wong
2022-11-28  5:31 ` [PATCH 33/95] lei_mirror: differentiate -entv vs -ent Eric Wong
2022-11-28  5:31 ` [PATCH 34/95] lei_mirror: support manifest {references} for v2 epochs Eric Wong
2022-11-28  5:31 ` Eric Wong [this message]
2022-11-28  5:31 ` [PATCH 36/95] clone: support --inbox-version Eric Wong
2022-11-28  5:31 ` [PATCH 37/95] lei_mirror: require Perl v5.12+ Eric Wong
2022-11-28  5:31 ` [PATCH 38/95] lei_mirror: ensure curl exits 22 on HTTP 404 responses Eric Wong
2022-11-28  5:31 ` [PATCH 39/95] lei_mirror: cleanup File::Temp OO usage Eric Wong
2022-11-28  5:31 ` [PATCH 40/95] lei_mirror: add `index' target to generated Makefile Eric Wong
2022-11-28  5:31 ` [PATCH 41/95] lei_mirror: do not write Makefile for --inbox-config=never Eric Wong
2022-11-28  5:31 ` [PATCH 42/95] lei_mirror: hoist out dump_manifest sub Eric Wong
2022-11-28  5:31 ` [PATCH 43/95] lei_mirror: avoid convoluted lazy_cb usage Eric Wong
2022-11-28  5:31 ` [PATCH 44/95] lei_mirror: simplify clone_v2_prep Eric Wong
2022-11-28  5:31 ` [PATCH 45/95] lei_mirror: support --objstore and forkgroups Eric Wong
2022-11-28  5:31 ` [PATCH 46/95] lei_mirror: cleanup process reaping logic Eric Wong
2022-11-28  5:31 ` [PATCH 47/95] lei_mirror: ensure git <1.8.5 fallback can use torsocks Eric Wong
2022-11-28  5:31 ` [PATCH 48/95] clone: flesh out --objstore behavior and document Eric Wong
2022-11-28  5:31 ` [PATCH 49/95] lei_mirror: always pack refs for coderepos Eric Wong
2022-11-28  5:31 ` [PATCH 50/95] lei_mirror: set description for non-inboxes, too Eric Wong
2022-11-28  5:31 ` [PATCH 51/95] lei_mirror: force --no-tags when fetching forkgroups Eric Wong
2022-11-28  5:31 ` [PATCH 52/95] lei_mirror: preserve permissions of existing alternates file Eric Wong
2022-11-28  5:31 ` [PATCH 53/95] lei_mirror: do not show ref updates w/o --verbose Eric Wong
2022-11-28  5:31 ` [PATCH 54/95] lei_mirror: drop git <1.8.5 support Eric Wong
2022-11-28  5:31 ` [PATCH 55/95] lei_mirror: make basename more descriptive Eric Wong
2022-11-28  5:31 ` [PATCH 56/95] lei_mirror: fix --dry-run for forkgroups Eric Wong
2022-11-28  5:31 ` [PATCH 57/95] lei_mirror: forkgroups use `git fetch --multiple' Eric Wong
2022-11-28  5:31 ` [PATCH 58/95] clone: move --dry-run handling to lei_mirror Eric Wong
2022-11-28  5:31 ` [PATCH 59/95] clone: drop unnecessary requires Eric Wong
2022-11-28  5:31 ` [PATCH 60/95] clone: use v5.12 Eric Wong
2022-11-28  5:31 ` [PATCH 61/95] clone: require `--objstore=' for default location Eric Wong
2022-11-28  5:31 ` [PATCH 62/95] lei_mirror: shorten remote names Eric Wong
2022-11-28  5:32 ` [PATCH 63/95] fetch: use v5.12 Eric Wong
2022-11-28  5:32 ` [PATCH 64/95] fetch: eliminate File::Temp->filename var Eric Wong
2022-11-28  5:32 ` [PATCH 65/95] lei_mirror: properly pack-refs in non-forkgroup repos Eric Wong
2022-11-28  5:32 ` [PATCH 66/95] lei_mirror: show child error error code Eric Wong
2022-11-28  5:32 ` [PATCH 67/95] on_destroy: support ->cancel callback Eric Wong
2022-11-28  5:32 ` [PATCH 68/95] lei_mirror: support resuming multi-repo clones Eric Wong
2022-11-28  5:32 ` [PATCH 69/95] lei_mirror: check fingerprints before fetching Eric Wong
2022-11-28  5:32 ` [PATCH 70/95] clone: support loading manifest.js.gz from destination Eric Wong
2022-11-28  5:32 ` [PATCH 71/95] lei_mirror: delay configuring forkgroups Eric Wong
2022-11-28  5:32 ` [PATCH 72/95] clone: canonicalize destination path from CLI Eric Wong
2022-11-28  5:32 ` [PATCH 73/95] clone|fetch: support passing --prune(-tags) to `git fetch' Eric Wong
2022-11-28  5:32 ` [PATCH 74/95] lei_mirror: avoid needless FD passing Eric Wong
2022-11-28  5:32 ` [PATCH 75/95] clone: support --keep-going/-k like make(1) Eric Wong
2022-11-28  5:32 ` [PATCH 76/95] lei_mirror: don't warn on missing manifest on initial clone Eric Wong
2022-11-28  5:32 ` [PATCH 77/95] lei_mirror: respect `./' and `../' prefixes for CLI args Eric Wong
2022-11-28  5:32 ` [PATCH 78/95] lei_mirror: --manifest= affects destination, too Eric Wong
2022-11-28  5:32 ` [PATCH 79/95] lei_mirror: update fingerprints when writing local manifest.js.gz Eric Wong
2022-11-28  5:32 ` [PATCH 80/95] lei_mirror: remove janky mirror.done stamp file Eric Wong
2022-11-28  5:32 ` [PATCH 81/95] lei_mirror: simplify most process spawning Eric Wong
2022-11-28  5:32 ` [PATCH 82/95] lei_mirror: run v1_done earlier on forkgroup done Eric Wong
2022-11-28  5:32 ` [PATCH 83/95] lei_mirror: simplify forkgroup-related subs Eric Wong
2022-11-28  5:32 ` [PATCH 84/95] lei_mirror: shorten scope mirror objects Eric Wong
2022-11-28  5:32 ` [PATCH 85/95] lei_mirror: set {head} from manifest Eric Wong
2022-11-28  5:32 ` [PATCH 86/95] lei_mirror: support {symlinks} " Eric Wong
2022-11-28  5:32 ` [PATCH 87/95] lei_mirror: eliminate circular references Eric Wong
2022-11-28  5:32 ` [PATCH 88/95] lei_mirror: use curl -z/--timecond if manifest exists Eric Wong
2022-11-28  5:32 ` [PATCH 89/95] lei_mirror: avoid redundant curl `-f' use Eric Wong
2022-11-28  5:32 ` [PATCH 90/95] lei_mirror: omit trailing slash for git remote.*.url Eric Wong
2022-11-28  5:32 ` [PATCH 91/95] lei_mirror: set info/web/last-modified from manifest Eric Wong
2022-11-28  5:32 ` [PATCH 92/95] lei_mirror: don't clobber inbox.config.example if it exists Eric Wong
2022-11-28  5:32 ` [PATCH 93/95] lei_mirror: break out of fgrp fetch iteration early Eric Wong
2022-11-28  5:32 ` [PATCH 94/95] clone: support --project-list= for cgit Eric Wong
2022-11-28  5:32 ` [PATCH 95/95] lei_mirror: handle forkgroup changes 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=20221128053232.291618-36-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.
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).