pktgen: avoid expensive set_current_state() call in loop
Avoid calling set_current_state() inside the busy-loop in
pktgen_thread_worker(). In case of pkt_dev->delay, then it is still
used/enabled in pktgen_xmit() via the spin() call.
The set_current_state(TASK_INTERRUPTIBLE) uses a xchg, which implicit
is LOCK prefixed. I've measured the asm LOCK operation to take approx
8ns on this E5-2630 CPU. Performance increase corrolate with this
measurement.
Performance data with CLONE_SKB==100000, rx-usecs=30:
(single CPU performance, ixgbe 10Gbit/s, E5-2630)
* Prev: 5454050 pps --> 183.35ns (1/5454050*10^9)
* Now: 5684009 pps --> 175.93ns (1/5684009*10^9)
* Diff: +229959 pps --> -7.42ns
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index fc17a9d..b61f553 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3407,10 +3407,10 @@
pr_debug("starting pktgen/%d: pid=%d\n", cpu, task_pid_nr(current));
- set_current_state(TASK_INTERRUPTIBLE);
-
set_freezable();
+ __set_current_state(TASK_RUNNING);
+
while (!kthread_should_stop()) {
pkt_dev = next_to_run(t);
@@ -3424,8 +3424,6 @@
continue;
}
- __set_current_state(TASK_RUNNING);
-
if (likely(pkt_dev)) {
pktgen_xmit(pkt_dev);
@@ -3456,9 +3454,8 @@
}
try_to_freeze();
-
- set_current_state(TASK_INTERRUPTIBLE);
}
+ set_current_state(TASK_INTERRUPTIBLE);
pr_debug("%s stopping all device\n", t->tsk->comm);
pktgen_stop(t);