From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@80x24.org>
X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,BAYES_00,
	URIBL_BLOCKED shortcircuit=no autolearn=ham autolearn_force=no
	version=3.4.2
Received: from localhost (dcvr.yhbt.net [127.0.0.1])
	by dcvr.yhbt.net (Postfix) with ESMTP id CF3711F66F;
	Mon, 31 Aug 2020 04:41:40 +0000 (UTC)
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Cc: Eric Wong <e@yhbt.net>
Subject: [PATCH 01/11] watch: limit batch size of NNTP and IMAP workers, too
Date: Mon, 31 Aug 2020 04:41:30 +0000
Message-Id: <20200831044140.17027-2-e@80x24.org>
In-Reply-To: <20200831044140.17027-1-e@80x24.org>
References: <20200831044140.17027-1-e@80x24.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
List-Id: <meta.public-inbox.org>

From: Eric Wong <e@yhbt.net>

We don't want to monopolize locks because processes can easily
block each other if using `watchspam' on a Maildir while a big
NNTP or IMAP import is happening.

This can also happen if somebody configured a single inbox to
watch from several sources to merge several mailboxes into one
(e.g. both an IMAP and Maildir are watched).
---
 lib/PublicInbox/WatchMaildir.pm | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/lib/PublicInbox/WatchMaildir.pm b/lib/PublicInbox/WatchMaildir.pm
index a227a6fd..5176ef69 100644
--- a/lib/PublicInbox/WatchMaildir.pm
+++ b/lib/PublicInbox/WatchMaildir.pm
@@ -108,6 +108,7 @@ sub new {
 	return unless $mdre || scalar(keys %imap) || scalar(keys %nntp);
 
 	bless {
+		max_batch => 10, # avoid hogging locks for too long
 		spamcheck => $spamcheck,
 		mdmap => \%mdmap,
 		mdre => $mdre,
@@ -472,8 +473,14 @@ sub imap_fetch_all ($$$) {
 
 		$l_uid = $uids->[-1] + 1; # for next search
 		my $last_uid;
+		my $n = $self->{max_batch};
 
 		while (scalar @$uids) {
+			if (--$n < 0) {
+				_done_for_now($self);
+				$itrk->update_last($r_uidval, $last_uid);
+				$n = $self->{max_batch};
+			}
 			my @batch = splice(@$uids, 0, $bs);
 			$batch = join(',', @batch);
 			local $0 = "UID:$batch $mbx $sec";
@@ -888,9 +895,15 @@ sub nntp_fetch_all ($$$) {
 	};
 	my $inboxes = $self->{nntp}->{$url};
 	my $last_art;
+	my $n = $self->{max_batch};
 	for ($beg..$end) {
 		last if $self->{quit};
 		$art = $_;
+		if (--$n < 0) {
+			_done_for_now($self);
+			$itrk->update_last(0, $last_art);
+			$n = $self->{max_batch};
+		}
 		my $raw = $nn->article($art);
 		unless (defined($raw)) {
 			my $msg = $nn->message;
@@ -976,12 +989,11 @@ sub fs_scan_step {
 	local $PublicInbox::DS::in_loop = 0; # waitpid() synchronously
 
 	# continue existing scan
-	my $max = 10;
 	my $opendirs = $self->{opendirs};
 	my @dirnames = keys %$opendirs;
 	foreach my $dir (@dirnames) {
 		my $dh = delete $opendirs->{$dir};
-		my $n = $max;
+		my $n = $self->{max_batch};
 		while (my $fn = readdir($dh)) {
 			_try_path($self, "$dir/$fn");
 			last if --$n < 0;
@@ -996,7 +1008,7 @@ sub fs_scan_step {
 				warn "failed to open $dir: $!\n";
 				next;
 			}
-			my $n = $max;
+			my $n = $self->{max_batch};
 			while (my $fn = readdir($dh)) {
 				_try_path($self, "$dir/$fn");
 				last if --$n < 0;