sched: poll for longer before HLTing

Increasing the poll time increases the chances that we can avoid the IPI. Idle host load increase is negligible.
cloudius-systems · Aug 5, 2013 · 4e3177e · 4e3177e
1 parent 032aa93
commit 4e3177e
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/core/sched.cc b/core/sched.cc
@@ -200,7 +200,7 @@ void cpu::do_idle()
         idle_poll_lock_type idle_poll_lock{*this};
         WITH_LOCK(idle_poll_lock) {
             // spin for a bit before halting
-            for (unsigned ctr = 0; ctr < 100; ++ctr) {
+            for (unsigned ctr = 0; ctr < 10000; ++ctr) {
                 // FIXME: can we pull threads from loaded cpus?
                 handle_incoming_wakeups();
                 if (!runqueue.empty()) {