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>
This commit is contained in:
parent
9ceb87fcea
commit
baac167b70
|
@ -3407,10 +3407,10 @@ static int pktgen_thread_worker(void *arg)
|
|||
|
||||
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 @@ static int pktgen_thread_worker(void *arg)
|
|||
continue;
|
||||
}
|
||||
|
||||
__set_current_state(TASK_RUNNING);
|
||||
|
||||
if (likely(pkt_dev)) {
|
||||
pktgen_xmit(pkt_dev);
|
||||
|
||||
|
@ -3456,9 +3454,8 @@ static int pktgen_thread_worker(void *arg)
|
|||
}
|
||||
|
||||
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);
|
||||
|
|
Loading…
Reference in a new issue