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 75/95] clone: support --keep-going/-k like make(1)
Date: Mon, 28 Nov 2022 05:32:12 +0000	[thread overview]
Message-ID: <20221128053232.291618-76-e@80x24.org> (raw)
In-Reply-To: <20221128053232.291618-1-e@80x24.org>

This can be useful for intermittent network errors,
and the required code changes makes it less dependent
on global state.
---
 Documentation/public-inbox-clone.pod |  6 ++++++
 lib/PublicInbox/LeiMirror.pm         | 30 ++++++++++++++++++----------
 script/public-inbox-clone            |  2 +-
 3 files changed, 26 insertions(+), 12 deletions(-)

diff --git a/Documentation/public-inbox-clone.pod b/Documentation/public-inbox-clone.pod
index bcf7dcc1..5e6a6fe9 100644
--- a/Documentation/public-inbox-clone.pod
+++ b/Documentation/public-inbox-clone.pod
@@ -111,6 +111,12 @@ where C<FILE > is an empty string (C<"">), then C<manifest.js.gz>
 Pass the C<--prune> and C<--prune-tags> flags to L<git-fetch(1)>
 calls on incremental clones.
 
+=item -k
+
+=item --keep-going
+
+Continue as much as possible after an error.
+
 =item -n
 
 =item --dry-run
diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm
index 7fcb4ebb..8cd64b65 100644
--- a/lib/PublicInbox/LeiMirror.pm
+++ b/lib/PublicInbox/LeiMirror.pm
@@ -22,6 +22,11 @@ use Digest::SHA qw(sha256_hex sha1_hex);
 
 our $LIVE; # pid => callback
 
+sub keep_going ($) {
+	$LIVE && (!$_[0]->{lei}->{child_error} ||
+		$_[0]->{lei}->{opt}->{'keep-going'});
+}
+
 sub _wq_done_wait { # dwaitpid callback (via wq_eof)
 	my ($arg, $pid) = @_;
 	my ($mrr, $lei) = @$arg;
@@ -287,6 +292,7 @@ sub upr { # feed `git update-ref --stdin -z' verbosely
 
 sub fgrp_update {
 	my ($fgrp) = @_;
+	return if !keep_going($fgrp);
 	my $srcfh = delete $fgrp->{srcfh} or return;
 	my $dstfh = delete $fgrp->{dstfh} or return;
 	seek($srcfh, SEEK_SET, 0) or die "seek(src): $!";
@@ -329,6 +335,7 @@ sub pack_dst { # packs lightweight satellite repos
 sub pack_refs {
 	my ($self, $git_dir) = @_;
 	do_reap($self);
+	return if !keep_going($self);
 	my $cmd = [ 'git', "--git-dir=$git_dir", qw(pack-refs --all --prune) ];
 	$self->{lei}->qerr("# @$cmd");
 	return if $self->{dry_run};
@@ -341,6 +348,7 @@ sub fgrpv_done {
 	return if !$LIVE;
 	my $pid;
 	my $first = $fgrpv->[0] // die 'BUG: no fgrpv->[0]';
+	return if !keep_going($first);
 	pack_refs($first, $first->{-osdir}); # objstore refs always packed
 	for my $fgrp (@$fgrpv) {
 		my $rn = $fgrp->{-remote};
@@ -479,6 +487,7 @@ EOM
 
 sub fp_done {
 	my ($self, $go_fetch) = @_;
+	return if !keep_going($self);
 	my $fh = delete $self->{-show_ref} // die 'BUG: no show-ref output';
 	seek($fh, SEEK_SET, 0) or die "seek(show_ref): $!";
 	$self->{-ent} // die 'BUG: no -ent';
@@ -516,6 +525,7 @@ sub resume_fetch_maybe {
 
 sub resume_fetch {
 	my ($self, $uri, $fini) = @_;
+	return if !keep_going($self);
 	my $dst = $self->{cur_dst} // $self->{dst};
 	my @git = ('git', "--git-dir=$dst");
 	my $opt = { 2 => $self->{lei}->{2} };
@@ -542,6 +552,7 @@ sub fgrp_enqueue_maybe {
 
 sub fgrp_enqueue {
 	my ($self, $fgrp) = @_;
+	return if !keep_going($self);
 	my $opt = { 2 => $self->{lei}->{2} };
 	# --no-tags is required to avoid conflicts
 	my $u = $fgrp->{-uri} // die 'BUG: no {-uri}';
@@ -678,15 +689,12 @@ sub reap_cmd { # async, called via SIGCHLD
 	my ($self, $cmd) = @_;
 	my $cerr = $?;
 	$? = 0; # don't let it influence normal exit
-	if ($cerr) {
-		kill('TERM', keys %$LIVE);
-		$self->{lei}->child_error($cerr, "@$cmd failed (\$?=$cerr)");
-	}
+	$self->{lei}->child_error($cerr, "@$cmd failed (\$?=$cerr)") if $cerr;
 }
 
 sub v1_done { # called via OnDestroy
 	my ($self) = @_;
-	return if $self->{dry_run} || !$LIVE;
+	return if $self->{dry_run} || !keep_going($self);
 	_write_inbox_config($self);
 	my $dst = $self->{cur_dst} // $self->{dst};
 	if (defined(my $o = $self->{-ent} ? $self->{-ent}->{owner} : undef)) {
@@ -722,7 +730,7 @@ sub v1_done { # called via OnDestroy
 
 sub v2_done { # called via OnDestroy
 	my ($self) = @_;
-	return if $self->{dry_run} || !$LIVE;
+	return if $self->{dry_run} || !keep_going($self);
 	my $dst = $self->{cur_dst} // $self->{dst};
 	require PublicInbox::Lock;
 	my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock';
@@ -896,7 +904,7 @@ sub clone_all {
 	# handle no-dependency repos, first
 	for (@$nodep) {
 		clone_v1($_, 1);
-		return if $self->{lei}->{child_error};
+		return if !keep_going($self);
 	}
 	# resolve references, deepest, first:
 	while (scalar keys %$todo) {
@@ -913,7 +921,7 @@ EOM
 			my $y = delete $todo->{$x} // next; # already done
 			for (@$y) {
 				clone_v1($_, 1);
-				return if $self->{lei}->{child_error};
+				return if !keep_going($self);
 			}
 			last; # restart %$todo iteration
 		}
@@ -989,7 +997,7 @@ sub try_manifest {
 E: `$self->{cur_dst}' must not contain newline
 EOM
 			clone_v2_prep($self, \%v2_epochs, $m);
-			return if $self->{lei}->{child_error};
+			return if !keep_going($self);
 		}
 	}
 	if (my $v1 = delete $multi->{v1}) {
@@ -1018,7 +1026,7 @@ EOM
 	}
 	delete local $lei->{opt}->{epoch} if defined($v2);
 	clone_all($self, $m);
-	return if $self->{lei}->{child_error} || $self->{dry_run};
+	return if $self->{dry_run} || !keep_going($self);
 
 	# set by clone_v2_prep/-I/--exclude
 	dump_manifest($m => $ft) if delete $self->{-culled_manifest};
@@ -1050,7 +1058,7 @@ sub do_mirror { # via wq_io_do or public-inbox-clone
 			$v = "$self->{dst}/$v" if $v !~ m!\A/!;
 			$self->{"-$k"} = $v;
 		}
-		local $LIVE;
+		local $LIVE = {};
 		my $iv = $lei->{opt}->{'inbox-version'} //
 			return start_clone_url($self);
 		return clone_v1($self) if $iv == 1;
diff --git a/script/public-inbox-clone b/script/public-inbox-clone
index df9ddd37..efe0cff6 100755
--- a/script/public-inbox-clone
+++ b/script/public-inbox-clone
@@ -24,7 +24,7 @@ options:
 EOF
 GetOptions($opt, qw(help|h quiet|q verbose|v+ C=s@ c=s@ include|I=s@ exclude=s@
 	inbox-config=s inbox-version=i objstore=s manifest=s
-	prune|p
+	prune|p keep-going|k
 	dry-run|n jobs|j=i no-torsocks torsocks=s epoch=s)) or die $help;
 if ($opt->{help}) { print $help; exit };
 require PublicInbox::Admin; # loads Config

  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 ` [PATCH 35/95] lei_mirror: simplify v2 code paths Eric Wong
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 ` Eric Wong [this message]
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=20221128053232.291618-76-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).