Limit the size of the result caches
The neighbourhood, classic collocator and similar profile caches grew by one
entry per queried word and were never evicted, so a long running worker
eventually exhausted the machine's memory. They are size limited Mojo::Cache
instances now, configurable in the new cache section of the configuration
file.
The neighbourhood cache never hit anyway: the lookup used a comma inside the
hash subscript, i.e. a $; joined multidimensional key, the value was read with
a second key and stored under a third one that did not include
searchBaseVocabFirst at all.
Starting the server with -C now really bypasses the caches. It did not before,
because $opt_C was read in IDS::DeReKoVecs::Read but set in main.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Change-Id: I17b801df54137ea81b660229bf789725de5a2b1b
diff --git a/script/derekovecs-server b/script/derekovecs-server
index 1930381..b15341e 100755
--- a/script/derekovecs-server
+++ b/script/derekovecs-server
@@ -4,6 +4,7 @@
use IDS::DeReKoVecs::Read;
use Mojolicious::Lite;
+use Mojo::Cache;
use Mojo::JSON qw(decode_json encode_json to_json);
use base 'Mojolicious::Plugin';
@@ -57,12 +58,17 @@
our $opt_G;
our $mergedEnd=0;
-our %cache;
-our %cccache; # classic collocator cache
-our %spcache; # similar profile cache
our $opt_p = 5676;
our $opt_C;
+# Neighbourhood results are the biggest objects the server keeps around (one
+# hash plus one vector array per neighbour), so this cache is deliberately
+# small. It is per worker, i.e. the total footprint is
+# workers * max_keys * result size. Set cache => {max_keys => 0} to switch the
+# cache off.
+my $CACHE_MAX_KEYS = app->config->{cache}->{max_keys} // 50;
+my $cache = Mojo::Cache->new(max_keys => $CACHE_MAX_KEYS);
+
my %marked;
my $title="";
my $training_args="";
@@ -82,6 +88,12 @@
getopts('d:D:Gil:p:m:n:M:Ch') or usage();
+configure_cache(
+ no_cache => $opt_C,
+ collocators_max_keys => app->config->{cache}->{collocators_max_keys},
+ profiles_max_keys => app->config->{cache}->{profiles_max_keys}
+);
+
if($opt_M) {
open my $handle, '<:encoding(UTF-8)', $opt_M
or die "Can't open '$opt_M' for reading: $!";
@@ -359,9 +371,10 @@
$searchBaseVocabFirst=1;
}
}
- if ($cache{$w.$cutoff.$no_nbs.$sort.$dedupe,$searchBaseVocabFirst}) {
+ my $key = join("\x1c", $w, $cutoff, $no_nbs, $sort, $dedupe, $searchBaseVocabFirst, $nosp);
+ $res = $opt_C ? undef : $cache->get($key);
+ if (defined $res) {
$c->app->log->info("Getting $w results from cache");
- $res = $cache{$w.$cutoff.$no_nbs.$sort.$dedupe.$searchBaseVocabFirst}
} else {
$c->app->log->info('Looking for neighbours of '.$w);
if($opt_i) {
@@ -369,7 +382,7 @@
} else {
$res = get_neighbours($w, $no_nbs, $sort, $searchBaseVocabFirst, $cutoff, $dedupe, $nosp);
}
- $cache{$w.$cutoff.$no_nbs.$sort.$dedupe} = $res;
+ $cache->set($key => $res) unless $opt_C;
}
push(@lists, $res->{paradigmatic});
}