From: Eric Wong <e@yhbt.net>
To: meta@public-inbox.org
Subject: [PATCH 05/14] index+xcpdb: improve SIG{INT,TERM,HUP,PIPE} behavior
Date: Mon, 10 Aug 2020 02:11:56 +0000 [thread overview]
Message-ID: <20200810021205.18909-6-e@yhbt.net> (raw)
In-Reply-To: <20200810021205.18909-1-e@yhbt.net>
-index now invokes ->DESTROY like xcpdb does, which is necessary
to cleanup $INBOX_DIR/msgmap-XXXXXXX files. We'll also exit
with the expected values for various signals by adding 128
as described in <https://www.tldp.org/LDP/abs/html/exitcodes.html>
-xcpdb now terminates worker processes and xapian-compact(1)
invocations when prematurely killed, too.
---
lib/PublicInbox/Admin.pm | 29 +++++++++++++++++++++++++----
lib/PublicInbox/Xapcmd.pm | 28 +++++++++++++++++++---------
2 files changed, 44 insertions(+), 13 deletions(-)
diff --git a/lib/PublicInbox/Admin.pm b/lib/PublicInbox/Admin.pm
index e42b01e0..af2b3da9 100644
--- a/lib/PublicInbox/Admin.pm
+++ b/lib/PublicInbox/Admin.pm
@@ -5,14 +5,28 @@
# Unstable internal API
package PublicInbox::Admin;
use strict;
-use warnings;
-use Cwd 'abs_path';
-use base qw(Exporter);
-our @EXPORT_OK = qw(resolve_repo_dir);
+use parent qw(Exporter);
+use Cwd qw(abs_path);
+use POSIX ();
+our @EXPORT_OK = qw(resolve_repo_dir setup_signals);
use PublicInbox::Config;
use PublicInbox::Inbox;
use PublicInbox::Spawn qw(popen_rd);
+sub setup_signals {
+ my ($cb, $arg) = @_; # optional
+
+ # we call exit() here instead of _exit() so DESTROY methods
+ # get called (e.g. File::Temp::Dir and PublicInbox::Msgmap)
+ $SIG{INT} = $SIG{HUP} = $SIG{PIPE} = $SIG{TERM} = sub {
+ my ($sig) = @_;
+ # https://www.tldp.org/LDP/abs/html/exitcodes.html
+ eval { $cb->($sig, $arg) } if $cb;
+ $sig = 'SIG'.$sig;
+ exit(128 + POSIX->$sig);
+ };
+}
+
sub resolve_repo_dir {
my ($cd, $ver) = @_;
my $prefix = defined $cd ? $cd : './';
@@ -185,9 +199,16 @@ invalid indexlevel=$indexlevel (must be `basic', `medium', or `full')
die missing_mod_msg($err) ." required for indexlevel=$indexlevel\n";
}
+sub index_terminate {
+ my (undef, $ibx) = @_; # $_[0] = signal name
+ $ibx->git->cleanup;
+}
+
sub index_inbox {
my ($ibx, $im, $opt) = @_;
my $jobs = delete $opt->{jobs} if $opt;
+ local %SIG = %SIG;
+ setup_signals(\&index_terminate, $ibx);
if (ref($ibx) && $ibx->version == 2) {
eval { require PublicInbox::V2Writable };
die "v2 requirements not met: $@\n" if $@;
diff --git a/lib/PublicInbox/Xapcmd.pm b/lib/PublicInbox/Xapcmd.pm
index 714f6859..348621ce 100644
--- a/lib/PublicInbox/Xapcmd.pm
+++ b/lib/PublicInbox/Xapcmd.pm
@@ -2,8 +2,8 @@
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
package PublicInbox::Xapcmd;
use strict;
-use warnings;
use PublicInbox::Spawn qw(which popen_rd nodatacow_dir);
+use PublicInbox::Admin qw(setup_signals);
use PublicInbox::Over;
use PublicInbox::SearchIdx;
use File::Temp 0.19 (); # ->newdir
@@ -126,6 +126,11 @@ sub same_fs_or_die ($$) {
die "$x and $y reside on different filesystems\n";
}
+sub kill_pids {
+ my ($sig, $pids) = @_;
+ kill($sig, keys %$pids); # pids may be empty
+}
+
sub process_queue {
my ($queue, $cb, $opt) = @_;
my $max = $opt->{jobs} // scalar(@$queue);
@@ -138,6 +143,8 @@ sub process_queue {
# run in parallel:
my %pids;
+ local %SIG = %SIG;
+ setup_signals(\&kill_pids, \%pids);
while (@$queue) {
while (scalar(keys(%pids)) < $max && scalar(@$queue)) {
my $args = shift @$queue;
@@ -156,12 +163,6 @@ sub process_queue {
}
}
-sub setup_signals () {
- # http://www.tldp.org/LDP/abs/html/exitcodes.html
- $SIG{INT} = sub { exit(130) };
- $SIG{HUP} = $SIG{PIPE} = $SIG{TERM} = sub { exit(1) };
-}
-
sub prepare_run {
my ($ibx, $opt) = @_;
my $tmp = {}; # old shard dir => File::Temp->newdir object or undef
@@ -294,6 +295,11 @@ sub progress_pfx ($) {
($p[-1] =~ /\A([0-9]+)/) ? "$p[-2]/$1" : $p[-1];
}
+sub kill_compact { # setup_signals callback
+ my ($sig, $pidref) = @_;
+ kill($sig, $$pidref) if defined($$pidref);
+}
+
# xapian-compact wrapper
sub compact ($$) {
my ($args, $opt) = @_;
@@ -319,14 +325,18 @@ sub compact ($$) {
}
$pr->("$pfx `".join(' ', @$cmd)."'\n") if $pr;
push @$cmd, $src, $dst;
- my $rd = popen_rd($cmd, undef, $rdr);
+ my ($rd, $pid);
+ local %SIG = %SIG;
+ setup_signals(\&kill_compact, \$pid);
+ ($rd, $pid) = popen_rd($cmd, undef, $rdr);
while (<$rd>) {
if ($pr) {
s/\r/\r$pfx /g;
$pr->("$pfx $_");
}
}
- close $rd or die join(' ', @$cmd)." failed: $?n";
+ waitpid($pid, 0);
+ die "@$cmd failed: \$?=$?\n" if $?;
}
sub cpdb_loop ($$$;$$) {
next prev parent reply other threads:[~2020-08-10 2:12 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-08-10 2:11 [PATCH 00/14] more indexing related improvements Eric Wong
2020-08-10 2:11 ` [PATCH 01/14] index: require --reindex when using --xapian-only Eric Wong
2020-08-10 2:11 ` [PATCH 02/14] index: --sequential-shard works incrementally Eric Wong
2020-08-10 2:11 ` [PATCH 03/14] doc: index: more notes about latest changes Eric Wong
2020-08-10 2:38 ` Kyle Meyer
2020-08-10 6:29 ` Eric Wong
2020-08-10 2:11 ` [PATCH 04/14] doc: add some notes around -xcpdb / -edit / -purge Eric Wong
2020-08-10 2:11 ` Eric Wong [this message]
2020-08-10 2:11 ` [PATCH 06/14] msgmap: tmp_clone: simplify + meaningful filename Eric Wong
2020-08-10 2:11 ` [PATCH 07/14] avoid File::Temp::tempfile in more places Eric Wong
2020-08-10 2:11 ` [PATCH 08/14] admin: use a generic veriable name Eric Wong
2020-08-10 2:38 ` Kyle Meyer
2020-08-10 2:12 ` [PATCH 09/14] index: cleanup internal variables Eric Wong
2020-08-10 2:12 ` [PATCH 10/14] searchidx: use singular `$opt' for consistency with v2 Eric Wong
2020-08-10 2:12 ` [PATCH 11/14] convert: support new -index options Eric Wong
2020-08-10 2:12 ` [PATCH 12/14] convert: speed up --help Eric Wong
2020-08-10 2:12 ` [PATCH 13/14] convert: check ARGV more correctly Eric Wong
2020-08-10 2:12 ` [PATCH 14/14] convert: set No_COW on copied SQLite files 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=20200810021205.18909-6-e@yhbt.net \
--to=e@yhbt.net \
--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).