Add check for stuck jobs in poll()

client/app.cpp

@@ -114,6 +114,9 @@ ACTIVE_TASK::ACTIVE_TASK() {
     fraction_done_elapsed_time = 0;
     first_fraction_done = 0;
     first_fraction_done_elapsed_time = 0;
+    stuck_check_fraction_done = 0;
+    stuck_check_elapsed_time = 0;
+    stuck_check_cpu_time = 0;
     scheduler_state = CPU_SCHED_UNINITIALIZED;
     next_scheduler_state = CPU_SCHED_UNINITIALIZED;
     signal = 0;

client/app.h

@@ -112,6 +112,12 @@ struct ACTIVE_TASK {
         // first frac done reported during this run of task
     double first_fraction_done_elapsed_time;
         // elapsed time when the above was reported
+    double stuck_check_fraction_done;
+        // fraction done since last check for stuck
+    double stuck_check_elapsed_time;
+        // elapsed time at last stuck check
+    double stuck_check_cpu_time;
+        // cpu time at last check
     SCHEDULER_STATE scheduler_state;
     SCHEDULER_STATE next_scheduler_state; // temp
     int signal;

client/app_control.cpp

@@ -149,6 +149,36 @@ bool ACTIVE_TASK_SET::poll() {
             }
         }
     }
+
+    // check if a job is "stuck" (did not make progress in the last hour)
+    // notify the user about the issue
+    // abort after some time
+    static double last_stuck_check_time = 0;
+    if (gstate.now - last_stuck_check_time > STUCK_CHECK_POLL_PERIOD) {
+        for (i=0; i<active_tasks.size(); i++){
+            ACTIVE_TASK* atp = active_tasks[i];
+            if (!atp->non_cpu_intensive()) continue;
+            if (atp->sporadic()) continue;
+            if (atp->stuck_check_elapsed_time == 0) {
+                // first pass
+                atp->stuck_check_elapsed_time = atp->elapsed_time;
+                atp->stuck_check_fraction_done = atp->fraction_done;
+                atp->stuck_check_cpu_time = atp->current_cpu_time;
+            }
+            // if fraction done does not change and cpu time is <10, message the user
+            if (atp->stuck_check_fraction_done == atp->fraction_done &&
+                    (atp->current_cpu_time - atp->stuck_check_cpu_time) < 10) {
+                msg_printf(atp->result->project, MSG_USER_ALERT,
+                    "Task has not made progress in last hour, consider aborting");
+            }
+            if (atp->elapsed_time < atp->stuck_check_elapsed_time + STUCK_CHECK_POLL_PERIOD) continue;
+            atp->stuck_check_elapsed_time = atp->elapsed_time;
+            atp->stuck_check_fraction_done = atp->fraction_done;
+            atp->stuck_check_cpu_time = atp->current_cpu_time;
+        }
+        last_stuck_check_time = gstate.now;
+    }
+
     if (action) {
         gstate.set_client_state_dirty("ACTIVE_TASK_SET::poll");
     }

client/client_state.h

@@ -601,6 +601,9 @@ extern THREAD throttle_thread;
 #define MEMORY_USAGE_PERIOD     10
     // computer memory usage and check for exclusive apps this often
 
+#define STUCK_CHECK_POLL_PERIOD 3600
+    // poll if a job is ever stuck
+
 //////// WORK FETCH
 
 #define WORK_FETCH_PERIOD   60