Gehel added a comment.
CLOSE_WAIT is whan the TCP stack is waiting for the application to acknowledge that the connection is terminated. So yes, a high number of CLOSE_WAIT is an indication of a problem. If blazegraph is frozen (or Jetty more precisely) that could explain. If I read the code / stacktraces correctly, blazegraph is using only async IO, so the reasons I see for a delay in acknowledging CLOSE_WAIT is if the HTTP thread pool is overloaded or if the JVM is completely frozen (GC going crazy?). There are probably other scenarios, but I can't think of any at the moment. TASK DETAIL https://phabricator.wikimedia.org/T134238 EMAIL PREFERENCES https://phabricator.wikimedia.org/settings/panel/emailpreferences/ To: Gehel Cc: Yurik, Smalyshev, Joe, Stashbot, Envlh, JanZerebecki, hoo, Frog23, Karima, Aklapper, Yair_rand, Zppix, Avner, debt, Gehel, D3r1ck01, FloNight, Izno, jkroll, Wikidata-bugs, Jdouglas, aude, Deskana, Manybubbles, Mbch331 _______________________________________________ Wikidata-bugs mailing list Wikidata-bugs@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/wikidata-bugs