BF: CS-676: Improve qmaster shutdown performance for scenarios where the master has more that 128 threads

Author: ernst-bablick

source/daemons/qmaster/sge_c_gdi.cc

@@ -269,23 +269,17 @@ sge_c_gdi_process_in_listener(sge_gdi_packet_class_t *packet, sge_gdi_task_class
    sge_pack_buffer *pb = &(packet->pb);
    switch (operation) {
       case SGE_GDI_TRIGGER:
-#if 0
-         MONITOR_GDI_TRIG(monitor);
-#endif
+         MONITOR_LIS_GDI_TRIG(monitor);
          sge_c_gdi_trigger_in_listener(packet, task, monitor);
          sge_gdi_packet_pack_task(packet, task, answer_list, pb);
          DRETURN(true);
       case SGE_GDI_PERMCHECK:
-#if 0
-         MONITOR_GDI_PERM(monitor);
-#endif
+         MONITOR_LIS_GDI_PERM(monitor);
          sge_c_gdi_permcheck(packet, task, monitor);
          sge_gdi_packet_pack_task(packet, task, answer_list, pb);
          DRETURN(true);
       case SGE_GDI_GET:
-#if 0
-         MONITOR_GDI_GET(monitor);
-#endif
+         MONITOR_LIS_GDI_GET(monitor);
          sge_c_gdi_get_in_listener(ao, packet, task, monitor);
          sge_gdi_packet_pack_task(packet, task, answer_list, pb);
          DRETURN(true);

source/daemons/qmaster/sge_thread_reader.cc

@@ -233,6 +233,7 @@ sge_reader_main(void *arg) {
             sge_c_report(packet->host, packet->commproc, packet->commproc_id, task->data_list, p_monitor);
          } else if (packet->request_type == PACKET_ACK_REQUEST) {
             task = packet->first_task;
+            // @TODO: This could be done by listener already?
             sge_c_ack(packet, task, p_monitor);
          } else {
             DPRINTF("unknown request type %d\n", packet->request_type);

source/daemons/qmaster/sge_thread_worker.cc

@@ -218,7 +218,7 @@ sge_worker_main(void *arg) {
       MONITOR_SET_QLEN(p_monitor, sge_tq_get_task_count(GlobalRequestQueue));
 
       // handle the packet only if it is not nullptr and the shutdown has not started
-      if (packet != nullptr && !sge_thread_has_shutdown_started()) {
+      if (packet != nullptr) {
          sge_gdi_task_class_t *task;
          bool is_only_read_request = true;
 
@@ -352,23 +352,11 @@ sge_worker_main(void *arg) {
          sge_monitor_output(p_monitor);
       }
 
-      // pass the cancellation point at least once or stay here if shutdown was triggered
-      bool shutdown_started = false;
-      do {
-         // pthread cancellation point
-         int execute = 0;
-         pthread_cleanup_push(sge_worker_cleanup_monitor, static_cast<void *>(p_monitor));
-         cl_thread_func_testcancel(thread_config);
-         pthread_cleanup_pop(execute); // cleanup monitor
-
-         // shutdown in process?
-         shutdown_started = sge_thread_has_shutdown_started();
-
-         // if we will wait here than do not eat up all cpu time
-         if (shutdown_started) {
-            sge_usleep(25000);
-         }
-      } while (shutdown_started);
+      // pthread cancellation point
+      int execute = 0;
+      pthread_cleanup_push(sge_worker_cleanup_monitor, static_cast<void *>(p_monitor));
+      cl_thread_func_testcancel(thread_config);
+      pthread_cleanup_pop(execute); // cleanup monitor
    }
 
    // Don't add cleanup code here. It will never be executed. Instead, register a cleanup function with