diff --git a/common/ParallelFor.h b/common/ParallelFor.h
index e8dbb4e4d..be3241991 100644
--- a/common/ParallelFor.h
+++ b/common/ParallelFor.h
@@ -91,6 +91,7 @@ namespace parallel_detail {
                             std::lock_guard lock(m);
                             tids.push_back(static_cast<int>(syscall(SYS_gettid)));
                         }
+                        cv.notify_all();
 #endif
                         Loop();
                     });
@@ -101,6 +102,11 @@ namespace parallel_detail {
                 StopAndJoin();
                 throw;
             }
+#ifdef __linux__
+            // Every worker is in tids once the pool exists, so a SetNice right after reaches all of them.
+            std::unique_lock lock(m);
+            cv.wait(lock, [this] { return tids.size() == workers.size(); });
+#endif
         }
 
         ~WorkerPool() { StopAndJoin(); }
diff --git a/receiver/JFJochReceiverRugnux.cpp b/receiver/JFJochReceiverRugnux.cpp
index 25594a95a..e4337f7c4 100644
--- a/receiver/JFJochReceiverRugnux.cpp
+++ b/receiver/JFJochReceiverRugnux.cpp
@@ -123,6 +123,10 @@ JFJochReceiverRugnux::JFJochReceiverRugnux(const DiffractionExperiment &in_exper
       live_status(in_live_status),
       measurement_started(1),
       forward_started(forward_nthreads) {
+    // The ParallelFor pool is made by the first thread to use it and its workers take that thread's
+    // priority. Made here, at the broker's own priority, before the rugnux thread lowers its own - so
+    // the pool is lowered for the analysis only where it can be raised back (see RugnuxThread).
+    parallel_detail::WorkerPool::Instance();
     logger.Info("Starting {} forward threads; rugnux runs on {} threads while the images arrive",
                 forward_nthreads, rugnux_nthreads);
     for (int i = 0; i < forward_nthreads; i++)
@@ -264,7 +268,8 @@ void JFJochReceiverRugnux::StartRugnux(std::future<void> &rugnux_done, std::futu
 void JFJochReceiverRugnux::RugnuxThread() {
     // Below the forward threads: every thread rugnux starts inherits this, so an image arriving finds a
     // core however busy rugnux keeps the machine.
-    // The process-wide ParallelFor pool is not started by this thread, so it is lowered separately.
+    // The process-wide ParallelFor pool was made before (in the constructor), so it does not inherit
+    // this and is lowered separately.
     setpriority(PRIO_PROCESS, static_cast<id_t>(syscall(SYS_gettid)), 10);
     // Only where it can be raised back afterwards: the pool outlives the collection, and left at nice 10
     // it would slow every analysis the broker runs after it.