* [PATCH 79/95] lei_mirror: update fingerprints when writing local manifest.js.gz
2022-11-28 5:30 7% [PATCH 00/95] clone: multi-inbox/repo support Eric Wong
@ 2022-11-28 5:32 6% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2022-11-28 5:32 UTC (permalink / raw)
To: meta
We need our local manifest to match the actual data we store,
not what we're mirroring.
---
lib/PublicInbox/LeiMirror.pm | 70 +++++++++++++++++++++++++++++-------
1 file changed, 58 insertions(+), 12 deletions(-)
diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm
index 2e94a2fa..b982f919 100644
--- a/lib/PublicInbox/LeiMirror.pm
+++ b/lib/PublicInbox/LeiMirror.pm
@@ -692,17 +692,46 @@ sub reap_cmd { # async, called via SIGCHLD
$self->{lei}->child_error($cerr, "@$cmd failed (\$?=$cerr)") if $cerr;
}
+sub up_fp_done {
+ my ($self) = @_;
+ return if !keep_going($self);
+ my $fh = delete $self->{-show_ref_up} // die 'BUG: no show-ref output';
+ seek($fh, SEEK_SET, 0) or die "seek(show_ref): $!";
+ $self->{-ent} // die 'BUG: no -ent';
+ my $A = $self->{-ent}->{fingerprint} // die 'BUG: no fingerprint';
+ my $B = sha1_hex(do { local $/; <$fh> } // die("read(show_ref): $!"));
+ return if $A eq $B;
+ $self->{-ent}->{fingerprint} = $B;
+ push @{$self->{chg}->{fp_mismatch}}, $self->{-key};
+}
+
+sub update_ent {
+ my ($self) = @_;
+ my $key = $self->{-key} // die 'BUG: no -key';
+ my $new = $self->{-ent}->{fingerprint};
+ my $cur = $self->{-local_manifest}->{$key}->{fingerprint} // "\0";
+ my $dst = $self->{cur_dst} // $self->{dst};
+ if (defined($new) && $new ne $cur) {
+ my $cmd = ['git', "--git-dir=$dst", 'show-ref'];
+ my $opt = { 2 => $self->{lei}->{2} };
+ open($opt->{1}, '+>', undef) or die "open(tmp): $!";
+ $self->{-show_ref_up} = $opt->{1};
+ my $done = PublicInbox::OnDestroy->new($$, \&up_fp_done, $self);
+ start_cmd($self, $cmd, $opt, $done);
+ }
+ $new = $self->{-ent}->{owner} // return;
+ $cur = $self->{-local_manifest}->{$key}->{owner} // "\0";
+ return if $cur eq $new;
+ my $cmd = [ qw(git config -f), "$dst/config", 'gitweb.owner', $new ];
+ start_cmd($self, $cmd, { 2 => $self->{lei}->{2} });
+}
+
sub v1_done { # called via OnDestroy
my ($self) = @_;
return if $self->{dry_run} || !keep_going($self);
_write_inbox_config($self);
my $dst = $self->{cur_dst} // $self->{dst};
- if (defined(my $o = $self->{-ent} ? $self->{-ent}->{owner} : undef)) {
- my $key = $self->{-key} // die 'BUG: no -key';
- my $cur = $self->{-local_manifest}->{$key}->{owner} // "\0";
- $cur eq $o or run_die([qw(git config -f),
- "$dst/config", 'gitweb.owner', $o]);
- }
+ update_ent($self) if $self->{-ent};
my $o = "$dst/objects";
if (open(my $fh, '<', my $fn = "$o/info/alternates")) {;
my $base = File::Spec->rel2abs($o);
@@ -797,7 +826,7 @@ failed to extract epoch number from $src
}
}
# filter out the epochs we skipped
- $self->{-culled_manifest} = 1 if $m && delete(@$m{@skip});
+ $self->{chg}->{manifest} = 1 if $m && delete(@$m{@skip});
(!$self->{dry_run} && !-d $dst) and File::Path::mkpath($dst);
@@ -854,8 +883,8 @@ sub multi_inbox ($$$) {
$self->{lei}->glob2re($_) // qr/\A\Q$_\E/
} @$incl).'\\z)';
my @gone = delete @$v2{grep(!/$re/, keys %$v2)};
- delete @$m{map { @$_ } @gone} and $self->{-culled_manifest} = 1;
- delete @$m{grep(!/$re/, @v1)} and $self->{-culled_manifest} = 1;
+ delete @$m{map { @$_ } @gone} and $self->{chg}->{manifest} = 1;
+ delete @$m{grep(!/$re/, @v1)} and $self->{chg}->{manifest} = 1;
@v1 = grep(/$re/, @v1);
}
if (defined $excl) {
@@ -863,8 +892,8 @@ sub multi_inbox ($$$) {
$self->{lei}->glob2re($_) // qr/\A\Q$_\E/
} @$excl).'\\z)';
my @gone = delete @$v2{grep(/$re/, keys %$v2)};
- delete @$m{map { @$_ } @gone} and $self->{-culled_manifest} = 1;
- delete @$m{grep(/$re/, @v1)} and $self->{-culled_manifest} = 1;
+ delete @$m{map { @$_ } @gone} and $self->{chg}->{manifest} = 1;
+ delete @$m{grep(/$re/, @v1)} and $self->{chg}->{manifest} = 1;
@v1 = grep(!/$re/, @v1);
}
my $ret; # { v1 => [ ... ], v2 => { "/$inbox_name" => [ epochs ] }}
@@ -963,6 +992,7 @@ sub try_manifest {
}
my $ft = File::Temp->new(TEMPLATE => '.manifest-XXXX', %opt);
my $cmd = $curl->for_uri($lei, $uri, qw(-f -R -o), $ft->filename);
+ my $mf_url = "$uri";
%opt = map { $_ => $lei->{$_} } (0..2);
my $cerr = run_reap($lei, $cmd, \%opt);
if ($cerr) {
@@ -974,6 +1004,7 @@ sub try_manifest {
warn $@;
return try_scrape($self);
}
+ local $self->{chg} = {};
local $self->{-local_manifest} = load_current_manifest($self);
my ($path_pfx, $n, $multi) = multi_inbox($self, \$path, $m);
return $lei->child_error(1, $multi) if !ref($multi);
@@ -1034,7 +1065,22 @@ EOM
return if $self->{dry_run} || !keep_going($self);
# set by clone_v2_prep/-I/--exclude
- dump_manifest($m => $ft) if delete $self->{-culled_manifest};
+ my $mis = delete $self->{chg}->{fp_mismatch};
+ if ($mis) {
+ my $t = (stat($ft))[9];
+ require POSIX;
+ $t = POSIX::strftime('%Y-%m-%d %k:%M:%S %z', localtime($t));
+ warn <<EOM;
+W: Fingerprints for the following repositories do not match
+W: $mf_url @ $t:
+W: These repositories may have updated since $t:
+EOM
+ warn "\t", $_, "\n" for @$mis;
+ warn <<EOM if !$self->{lei}->{opt}->{prune};
+W: The above fingerprints may never match without --prune
+EOM
+ }
+ dump_manifest($m => $ft) if delete($self->{chg}->{manifest}) || $mis;
ft_rename($ft, $manifest, 0666);
open my $x, '>', "$self->{dst}/mirror.done"; # for _wq_done_wait
}
^ permalink raw reply related [relevance 6%]
* [PATCH 00/95] clone: multi-inbox/repo support...
@ 2022-11-28 5:30 7% Eric Wong
2022-11-28 5:32 6% ` [PATCH 79/95] lei_mirror: update fingerprints when writing local manifest.js.gz 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 7%]
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 7% [PATCH 00/95] clone: multi-inbox/repo support Eric Wong
2022-11-28 5:32 6% ` [PATCH 79/95] lei_mirror: update fingerprints when writing local manifest.js.gz 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).