* [PATCH 75/95] clone: support --keep-going/-k like make(1)
2022-11-28 5:30 5% [PATCH 00/95] clone: multi-inbox/repo support Eric Wong
@ 2022-11-28 5:32 7% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2022-11-28 5:32 UTC (permalink / raw)
To: meta
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
^ permalink raw reply related [relevance 7%]
* [PATCH 00/95] clone: multi-inbox/repo support...
@ 2022-11-28 5:30 5% Eric Wong
2022-11-28 5:32 7% ` [PATCH 75/95] clone: support --keep-going/-k like make(1) Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2022-11-28 5:30 UTC (permalink / raw)
To: meta
A large patchset, and not done, yet :P It's only tested live,
but it seems to work reasonably well against live hosts...
Behavior changes to public-inbox-clone are NOT final; but
public-inbox-fetch|PublicInbox::Fetch will probably become
thin wrappers around LeiMirror.
--include=/--exclude= support now exists with glob support
--keep-going and --dry-run support added, too, since it's
make(1) influenced (more below)
It supports coderepos, too, using --inbox-config=never (default: always);
--project-list=, --manifest=, --objstore=, and --prune.
key differences from grok-pull (grokmirror) for coderepos:
* uses relative paths on the FS (dumb HTTP untested, but dumb
HTTP is a goal for memory-constrained hosts). This means
I can relocate coderepos freely within my FS or do sneakernet
transfers across machines without having to `perl -ipe s/x/y/'
on hundreds of info/alternates and config files.
* CLI-only, no extra config files (may generate a Makefile, like
individual inbox clones)
* objstore repos fetches from remotes directly
(does not need, use, nor benefit from hardlinks at all)
* no sleep states
It is not a full replacement for grokmirror
* reliant on default `git gc' behavior for repack. This is OK
since it's only one-way relationships between objstore and
non-objstore repos.
* no fsck support (probably will be in generated Makefile)
* doesn't generate forkgroups nor manifest.js.gz
(I may do this for coderepo Xapian indexing)
It relies on parallel git-fetch for objstores, so `-j $NUM'
calculations may end up being ($NUM * $NUM) in the worst case.
Not sure how to best approach this...
Maybe `-j $M,$N' similar to `lei q -j$M,$N` is a solution...
Design note:
This is an exercise in building make(1)-like parallelism using
->DESTROY callbacks for prerequisites; so it's a newish paradigm
for me. It forced me to fix a reference cycle, already.
TODO: repo|symlink pruning, --exit-code, retry/refetch, manpage updates
Eric Wong (95):
clone: support multi-inbox clone
clone: support --include and --exclude with multi-clone
clone: parallelize v2 epoch clones
lei_mirror: async config retrieval for v2 w/ manifest
lei_mirror: rely on DESTROY to index v2 inbox
lei_mirror: rely on global process reaper
clone: support parallel v1 clones
lei_mirror: default to single job by default
lei_mirror: move directory creation to v2-only path
lei_mirror: retrieve description text asynchronously, too
switch inotify/kevent stuff to v5.12
manifest: update module blurb + v5.12
lei_mirror: simplify _get_txt_start callers
lei_mirror: elide description retrieval for v1|coderepo
lei_mirror: add a hint for skipped epoch permissions
lei_mirror: consolidate clone process management
lei_mirror: load File::Path unconditionally
lei_mirror: load most modules up-front
lei_mirror: set gitweb.owner from manifest
clone: support --dry-run / -n flag
lei_mirror: initialize placeholders with "head" from manifest
lei_mirror: support {reference} for v1 manifest clones
lei_mirror: reduce noise on interrupted clones
clone: support --inbox-config option
lei_mirror: retrieve v2 description properly
lei_mirror: reduce scope of v2 lock
lei_mirror: allow --epoch on mixed v1/v2 clones
lei_mirror: fix infinite loop in dependency resolution
lei_mirror: defend against infinite loops
lei_mirror: do not fetch descriptions if using manifest
lei_mirror: require PublicInbox::Lock at use
lei_mirror: fix glob semantics to match end-of-path
lei_mirror: differentiate -entv vs -ent
lei_mirror: support manifest {references} for v2 epochs
lei_mirror: simplify v2 code paths
clone: support --inbox-version
lei_mirror: require Perl v5.12+
lei_mirror: ensure curl exits 22 on HTTP 404 responses
lei_mirror: cleanup File::Temp OO usage
lei_mirror: add `index' target to generated Makefile
lei_mirror: do not write Makefile for --inbox-config=never
lei_mirror: hoist out dump_manifest sub
lei_mirror: avoid convoluted lazy_cb usage
lei_mirror: simplify clone_v2_prep
lei_mirror: support --objstore and forkgroups
lei_mirror: cleanup process reaping logic
lei_mirror: ensure git <1.8.5 fallback can use torsocks
clone: flesh out --objstore behavior and document
lei_mirror: always pack refs for coderepos
lei_mirror: set description for non-inboxes, too
lei_mirror: force --no-tags when fetching forkgroups
lei_mirror: preserve permissions of existing alternates file
lei_mirror: do not show ref updates w/o --verbose
lei_mirror: drop git <1.8.5 support
lei_mirror: make basename more descriptive
lei_mirror: fix --dry-run for forkgroups
lei_mirror: forkgroups use `git fetch --multiple'
clone: move --dry-run handling to lei_mirror
clone: drop unnecessary requires
clone: use v5.12
clone: require `--objstore=' for default location
lei_mirror: shorten remote names
fetch: use v5.12
fetch: eliminate File::Temp->filename var
lei_mirror: properly pack-refs in non-forkgroup repos
lei_mirror: show child error error code
on_destroy: support ->cancel callback
lei_mirror: support resuming multi-repo clones
lei_mirror: check fingerprints before fetching
clone: support loading manifest.js.gz from destination
lei_mirror: delay configuring forkgroups
clone: canonicalize destination path from CLI
clone|fetch: support passing --prune(-tags) to `git fetch'
lei_mirror: avoid needless FD passing
clone: support --keep-going/-k like make(1)
lei_mirror: don't warn on missing manifest on initial clone
lei_mirror: respect `./' and `../' prefixes for CLI args
lei_mirror: --manifest= affects destination, too
lei_mirror: update fingerprints when writing local manifest.js.gz
lei_mirror: remove janky mirror.done stamp file
lei_mirror: simplify most process spawning
lei_mirror: run v1_done earlier on forkgroup done
lei_mirror: simplify forkgroup-related subs
lei_mirror: shorten scope mirror objects
lei_mirror: set {head} from manifest
lei_mirror: support {symlinks} from manifest
lei_mirror: eliminate circular references
lei_mirror: use curl -z/--timecond if manifest exists
lei_mirror: avoid redundant curl `-f' use
lei_mirror: omit trailing slash for git remote.*.url
lei_mirror: set info/web/last-modified from manifest
lei_mirror: don't clobber inbox.config.example if it exists
lei_mirror: break out of fgrp fetch iteration early
clone: support --project-list= for cgit
lei_mirror: handle forkgroup changes
Documentation/lei-add-external.pod | 4 +-
Documentation/public-inbox-clone.pod | 76 ++
Documentation/public-inbox-fetch.pod | 6 +
lib/PublicInbox/DSKQXS.pm | 5 +-
lib/PublicInbox/DirIdle.pm | 4 +-
lib/PublicInbox/FakeInotify.pm | 13 +-
lib/PublicInbox/Fetch.pm | 50 +-
lib/PublicInbox/In2Tie.pm | 4 +-
lib/PublicInbox/InboxIdle.pm | 2 +-
lib/PublicInbox/KQNotify.pm | 12 +-
lib/PublicInbox/LEI.pm | 5 +-
lib/PublicInbox/LeiMirror.pm | 1104 +++++++++++++++++++++-----
lib/PublicInbox/ManifestJsGz.pm | 8 +-
lib/PublicInbox/OnDestroy.pm | 5 +-
lib/PublicInbox/TestCommon.pm | 1 +
script/public-inbox-clone | 23 +-
script/public-inbox-fetch | 4 +-
t/on_destroy.t | 8 +-
t/www_listing.t | 71 +-
19 files changed, 1148 insertions(+), 257 deletions(-)
^ permalink raw reply [relevance 5%]
Results 1-2 of 2 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2022-11-28 5:30 5% [PATCH 00/95] clone: multi-inbox/repo support Eric Wong
2022-11-28 5:32 7% ` [PATCH 75/95] clone: support --keep-going/-k like make(1) Eric Wong
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).