diff --git a/core/src/main/resources/crawler-default.yaml b/core/src/main/resources/crawler-default.yaml index 204b77007..ed5046056 100644 --- a/core/src/main/resources/crawler-default.yaml +++ b/core/src/main/resources/crawler-default.yaml @@ -467,7 +467,7 @@ config: # Guava cache use by AbstractStatusUpdaterBolt for DISCOVERED URLs status.updater.use.cache: true - status.updater.cache.spec: "expireAfterAccess=1h,softValues" + status.updater.cache.spec: "maximumSize=1000000,expireAfterAccess=1h" # Normalise the host component of DISCOVERED URLs before they are stored, # so that aliases of one server (percent-escaping, case, trailing dot)