From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 1/2] manifest.js.gz: avoid long-lived per-epoch cat-file processes
Date: Sat, 11 Sep 2021 23:30:45 +0000 [thread overview]
Message-ID: <20210911233046.23862-2-e@80x24.org> (raw)
In-Reply-To: <20210911233046.23862-1-e@80x24.org>
When generating per-inbox manifests, we were forgetting to
cleanup per-epoch "git cat-file --batch" processes. Our
previous method of generating modified times was also stupidly
inefficient, so replace the pipeline with a single
"git for-each-ref" invocation.
---
lib/PublicInbox/Git.pm | 25 +++++--------------------
lib/PublicInbox/ManifestJsGz.pm | 2 +-
2 files changed, 6 insertions(+), 21 deletions(-)
diff --git a/lib/PublicInbox/Git.pm b/lib/PublicInbox/Git.pm
index e557f6d6..219a1732 100644
--- a/lib/PublicInbox/Git.pm
+++ b/lib/PublicInbox/Git.pm
@@ -16,7 +16,7 @@ use Errno qw(EINTR EAGAIN);
use File::Glob qw(bsd_glob GLOB_NOSORT);
use File::Spec ();
use Time::HiRes qw(stat);
-use PublicInbox::Spawn qw(popen_rd);
+use PublicInbox::Spawn qw(popen_rd spawn);
use PublicInbox::Tmpfile;
use IO::Poll qw(POLLIN);
use Carp qw(croak);
@@ -466,28 +466,13 @@ sub cat_async ($$$;$) {
push(@$inflight, $oid, $cb, $arg);
}
-sub extract_cmt_time {
- my ($bref, undef, undef, undef, $modified) = @_;
-
- if ($$bref =~ /^committer .*?> ([0-9]+) [\+\-]?[0-9]+/sm) {
- my $cmt_time = $1 + 0;
- $$modified = $cmt_time if $cmt_time > $$modified;
- }
-}
-
# returns the modified time of a git repo, same as the "modified" field
# of a grokmirror manifest
sub modified ($) {
- my ($self) = @_;
- my $modified = 0;
- my $fh = popen($self, qw(rev-parse --branches));
- local $/ = "\n";
- while (my $oid = <$fh>) {
- chomp $oid;
- cat_async($self, $oid, \&extract_cmt_time, \$modified);
- }
- cat_async_wait($self);
- $modified || time;
+ # committerdate:unix is git 2.9.4+ (2017-05-05), so using raw instead
+ my $fh = popen($_[0], qw[for-each-ref --sort=-committerdate
+ --format=%(committerdate:raw) --count=1]);
+ (split(/ /, <$fh> // time))[0] + 0; # integerize for JSON
}
# for grokmirror, which doesn't read gitweb.description
diff --git a/lib/PublicInbox/ManifestJsGz.pm b/lib/PublicInbox/ManifestJsGz.pm
index 69d81fa1..cde60245 100644
--- a/lib/PublicInbox/ManifestJsGz.pm
+++ b/lib/PublicInbox/ManifestJsGz.pm
@@ -27,7 +27,7 @@ sub inject_entry ($$$;$) {
$ctx->{manifest}->{$url_path} = $ent;
}
-sub manifest_add ($$;$$) { # slow path w/o extindex "all"
+sub manifest_add ($$;$$) { # slow path w/o extindex "all" (or per-inbox)
my ($ctx, $ibx, $epoch, $default_desc) = @_;
my $url_path = "/$ibx->{name}";
my $git;
next prev parent reply other threads:[~2021-09-11 23:30 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-11 23:30 [PATCH 0/2] www: per-inbox manifest.js.gz improvements Eric Wong
2021-09-11 23:30 ` Eric Wong [this message]
2021-09-11 23:30 ` [PATCH 2/2] www: use ->ALL for per-inbox manifest.js.gz, too 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=20210911233046.23862-2-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.
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).