From: Eric Wong <e@80x24.org>
Date: Sun, 12 Feb 2017 09:04:54 +0000 (+0000)
Subject: searchidx: switch to accounting by message bytes
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=eb0267592377e116c7184d206bff48413ae202fe;p=thirdparty%2Fpublic-inbox.git

searchidx: switch to accounting by message bytes

Xapian memory usage is tied to the size of the indexed
text, so take the raw message size into account when
deciding when to flush Xapian data.

More importantly, we now flush Xapian before we have it
buffer beyond our maximum; and we do it unconditionally
to prevent even high priority processes from OOM-ing.
---

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 2548ddf25..e2a0a5441 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -21,7 +21,10 @@ use Carp qw(croak);
 use POSIX qw(strftime);
 require PublicInbox::Git;
 
-use constant MAX_MID_SIZE => 244; # max term size - 1 in Xapian
+use constant {
+	MAX_MID_SIZE => 244, # max term size - 1 in Xapian
+	BATCH_BYTES => 1_000_000,
+};
 
 sub new {
 	my ($class, $inbox, $creat) = @_;
@@ -64,7 +67,6 @@ sub _xdb_acquire {
 		require File::Path;
 		_lock_acquire($self);
 		File::Path::mkpath($dir);
-		$self->{batch_size} = 100;
 		$flag = Search::Xapian::DB_CREATE_OR_OPEN;
 	}
 	$self->{xdb} = Search::Xapian::WritableDatabase->new($dir, $flag);
@@ -406,6 +408,15 @@ sub index_sync {
 	with_umask($self->{'umask'}, sub { $self->_index_sync($opts) });
 }
 
+sub batch_adjust ($$$$) {
+	my ($max, $bytes, $batch_cb, $latest) = @_;
+	$$max -= $bytes;
+	if ($$max <= 0) {
+		$$max = BATCH_BYTES;
+		$batch_cb->($latest, 1);
+	}
+}
+
 sub rlog {
 	my ($self, $log, $add_cb, $del_cb, $batch_cb) = @_;
 	my $hex = '[a-f0-9]';
@@ -415,23 +426,21 @@ sub rlog {
 	my $git = $self->{git};
 	my $latest;
 	my $bytes;
-	my $max = $self->{batch_size}; # may be undef
+	my $max = BATCH_BYTES;
 	local $/ = "\n";
 	my $line;
 	while (defined($line = <$log>)) {
 		if ($line =~ /$addmsg/o) {
 			my $blob = $1;
 			my $mime = do_cat_mail($git, $blob, \$bytes) or next;
+			batch_adjust(\$max, $bytes, $batch_cb, $latest);
 			$add_cb->($self, $mime, $bytes, $blob);
 		} elsif ($line =~ /$delmsg/o) {
 			my $blob = $1;
-			my $mime = do_cat_mail($git, $blob) or next;
+			my $mime = do_cat_mail($git, $blob, \$bytes) or next;
+			batch_adjust(\$max, $bytes, $batch_cb, $latest);
 			$del_cb->($self, $mime);
 		} elsif ($line =~ /^commit ($h40)/o) {
-			if (defined $max && --$max <= 0) {
-				$max = $self->{batch_size};
-				$batch_cb->($latest, 1);
-			}
 			$latest = $1;
 		}
 	}