* [PATCH 46/95] lei_mirror: cleanup process reaping logic
2022-11-28 5:30 7% [PATCH 00/95] clone: multi-inbox/repo support Eric Wong
@ 2022-11-28 5:31 5% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2022-11-28 5:31 UTC (permalink / raw)
To: meta
We can put more of the default --jobs logic and loop handling
inside a sub to simplify callers.
---
lib/PublicInbox/LeiMirror.pm | 51 ++++++++++++++++++------------------
1 file changed, 25 insertions(+), 26 deletions(-)
diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm
index 799939b5..163f45ee 100644
--- a/lib/PublicInbox/LeiMirror.pm
+++ b/lib/PublicInbox/LeiMirror.pm
@@ -123,6 +123,21 @@ sub ft_rename ($$$) {
$ft->unlink_on_destroy(0);
}
+sub do_reap ($;$) {
+ my ($self, $jobs) = @_;
+ $jobs //= $self->{-jobs} //= $self->{lei}->{opt}->{jobs} // 1;
+ $jobs = 1 if $jobs < 1;
+ while (keys(%$LIVE) >= $jobs) {
+ my $pid = waitpid(-1, 0) // die "waitpid(-1): $!";
+ if (my $x = delete $LIVE->{$pid}) {
+ my $cb = shift @$x;
+ $cb->(@$x) if $cb;
+ } else {
+ warn "reaped unknown PID=$pid ($?)\n";
+ }
+ }
+}
+
sub _get_txt_start { # non-fatal
my ($self, $endpoint, $fini) = @_;
my $uri = URI->new($self->{cur_src} // $self->{src});
@@ -135,8 +150,7 @@ sub _get_txt_start { # non-fatal
my $opt = { 0 => $lei->{0}, 1 => $lei->{1}, 2 => $lei->{2} };
my $cmd = $self->{curl}->for_uri($lei, $uri, qw(-f --compressed -R -o),
$ft->filename);
- my $jobs = $lei->{opt}->{jobs} // 1;
- reap_live() while keys(%$LIVE) >= $jobs;
+ do_reap($self);
$lei->qerr("# @$cmd");
return if $self->{dry_run};
$self->{"-get_txt.$endpoint"} = [ $ft, $cmd, $uri ];
@@ -247,8 +261,7 @@ sub run_reap {
sub start_clone {
my ($self, $cmd, $opt, $fini) = @_;
- my $jobs = $self->{lei}->{opt}->{jobs} // 1;
- reap_live() while keys(%$LIVE) >= $jobs;
+ do_reap($self);
$self->{lei}->qerr("# @$cmd");
return if $self->{dry_run};
$LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_cmd, $self, $cmd, $fini ]
@@ -273,9 +286,8 @@ sub fgrp_update_old ($) { # for git <1.8.5
my $cmd = [ 'git', "--git-dir=$fgrp->{cur_dst}",
fetch_args($fgrp->{lei}, my $opt = {}) ];
$fgrp->{lei}->qerr("# @$cmd");
+ do_reap($fgrp);
$LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_cmd, $fgrp, $cmd ];
- my $jobs = $fgrp->{lei}->{opt}->{jobs} // 1;
- reap_live() while keys(%$LIVE) >= $jobs;
}
sub upr { # feed `git update-ref --stdin -z' verbosely
@@ -315,8 +327,7 @@ sub fgrp_update {
}
if (close($w)) { # git >= 1.8.5
$LIVE->{$pid} = [ \&reap_cmd, $fgrp, $cmd ];
- my $jobs = $fgrp->{lei}->{opt}->{jobs} // 1;
- reap_live() while keys(%$LIVE) >= $jobs;
+ do_reap($fgrp);
} else { # git <1.8.5 w/o update-ref --stdin
warn "E: close(update-ref --stdin): $!\n";
$update_ref_stdin = 0;
@@ -332,10 +343,9 @@ sub fgrp_fetched {
my %opt = map { $_ => $fgrp->{lei}->{$_} } (0..2);
my $cmd = [ 'git', "--git-dir=$fgrp->{-osdir}",
qw(pack-refs --all --prune) ];
+ do_reap($fgrp);
$fgrp->{lei}->qerr("# @$cmd");
$LIVE->{spawn($cmd, undef, \%opt)} = [ \&reap_cmd, $fgrp, $cmd ];
- my $jobs = $fgrp->{lei}->{opt}->{jobs} // 1;
- reap_live() while keys(%$LIVE) >= $jobs;
$update_ref_stdin or return fgrp_update_old($fgrp);
@@ -344,19 +354,19 @@ sub fgrp_fetched {
my $src = [ 'git', "--git-dir=$fgrp->{-osdir}", 'for-each-ref',
"--format=refs/%(refname:lstrip=3)%00%(objectname)",
"refs/remotes/$rn/" ];
+ do_reap($fgrp);
open($fgrp->{srcfh}, '+>', undef) or die "open(src): $!";
$fgrp->{lei}->qerr("# @$src >SRC");
my $pid = spawn($src, undef, { %opt, 1 => $fgrp->{srcfh} });
$LIVE->{$pid} = [ \&reap_cmd, $fgrp, $src, $update_ref ];
- reap_live() while keys(%$LIVE) >= $jobs;
my $dst = [ 'git', "--git-dir=$fgrp->{cur_dst}", 'for-each-ref',
'--format=%(refname)%00%(objectname)' ];
+ do_reap($fgrp);
open($fgrp->{dstfh}, '+>', undef) or die "open(dst): $!";
$fgrp->{lei}->qerr("# @$dst >DST");
$pid = spawn($dst, undef, { %opt, 1 => $fgrp->{dstfh} });
$LIVE->{$pid} = [ \&reap_cmd, $fgrp, $dst, $update_ref ];
- reap_live() while keys(%$LIVE) >= $jobs;
}
sub fgrp_fetch {
@@ -365,8 +375,7 @@ sub fgrp_fetch {
fetch_args($fgrp->{lei}, my $opt = {}),
$fgrp->{-remote} ];
$fgrp->{-fini} = $fini;
- my $jobs = $fgrp->{lei}->{opt}->{jobs} // 1;
- reap_live() while keys(%$LIVE) >= $jobs;
+ do_reap($fgrp);
$fgrp->{lei}->qerr("# @$cmd");
return if $fgrp->{dry_run};
my $fgrp_fini = PublicInbox::OnDestroy->new($$, \&fgrp_fetched, $fgrp);
@@ -451,7 +460,7 @@ sub clone_v1 {
(!defined($d) && !$nohang) and
_get_txt_start($self, 'description', $fini);
- reap_live() until ($nohang || !keys(%$LIVE)); # for non-manifest clone
+ $nohang or do_reap($self, 1); # for non-manifest clone
}
sub parse_epochs ($$) {
@@ -590,16 +599,6 @@ sub v2_done { # called via OnDestroy
index_cloned_inbox($self, 2);
}
-sub reap_live {
- my $pid = waitpid(-1, 0) // die "waitpid(-1): $!";
- if (my $x = delete $LIVE->{$pid}) {
- my $cb = shift @$x;
- $cb->(@$x) if $cb;
- } else {
- warn "reaped unknown PID=$pid ($?)\n";
- }
-}
-
sub clone_v2_prep ($$;$) {
my ($self, $v2_epochs, $m) = @_; # $m => manifest.js.gz hashref
my $lei = $self->{lei};
@@ -762,7 +761,7 @@ EOM
last; # restart %$todo iteration
}
}
- reap_live() while keys(%$LIVE);
+ do_reap($self, 1);
}
sub dump_manifest ($$) {
^ permalink raw reply related [relevance 5%]
* [PATCH 00/95] clone: multi-inbox/repo support...
@ 2022-11-28 5:30 7% Eric Wong
2022-11-28 5:31 5% ` [PATCH 46/95] lei_mirror: cleanup process reaping logic 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 5:31 5% ` [PATCH 46/95] lei_mirror: cleanup process reaping logic 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).