diff --git a/doc/configuration.txt b/doc/configuration.txt
index 450d831..65aabd8 100644
--- a/doc/configuration.txt
+++ b/doc/configuration.txt
@@ -2493,10 +2493,12 @@
 
 tune.runqueue-depth <number>
   Sets the maximum amount of task that can be processed at once when running
-  tasks. The default value is 200. Increasing it may incur latency when
-  dealing with I/Os, making it too small can incur extra overhead. When
-  experimenting with much larger values, it may be useful to also enable
-  tune.sched.low-latency to limit the maximum latency to the lowest possible.
+  tasks. The default value is 40 which tends to show the highest request rates
+  and lowest latencies. Increasing it may incur latency when dealing with I/Os,
+  making it too small can incur extra overhead. When experimenting with much
+  larger values, it may be useful to also enable tune.sched.low-latency and
+  possibly tune.fd.edge-triggered to limit the maximum latency to the lowest
+  possible.
 
 tune.sched.low-latency { on | off }
   Enables ('on') or disables ('off') the low-latency task scheduler. By default
diff --git a/include/haproxy/defaults.h b/include/haproxy/defaults.h
index 6a8b03d..b023827 100644
--- a/include/haproxy/defaults.h
+++ b/include/haproxy/defaults.h
@@ -170,9 +170,19 @@
 #define MAX_POLL_EVENTS 200
 #endif
 
-// the max number of tasks to run at once
+// the max number of tasks to run at once. Tests have shown the following
+// number of requests/s for 1 to 16 threads (1c1t, 1c2t, 2c4t, 4c8t, 4c16t):
+//
+// rq\thr|    1     2     4     8    16
+// ------+------------------------------
+//     32|  120k  159k  276k  477k  698k
+//     40|  122k  160k  276k  478k  722k
+//     48|  121k  159k  274k  482k  720k
+//     64|  121k  160k  274k  469k  710k
+//    200|  114k  150k  247k  415k  613k
+//
 #ifndef RUNQUEUE_DEPTH
-#define RUNQUEUE_DEPTH 200
+#define RUNQUEUE_DEPTH 40
 #endif
 
 // cookie delimiter in "prefix" mode. This character is inserted between the