On Thu, 2014-09-25 at 16:57 +0200, Jesper Dangaard Brouer wrote:

We are saving 3% CPU, as I described in my post with subject:
"qdisc/UDP_STREAM: measuring effect of qdisc bulk dequeue":
 http://thread.gmane.org/gmane.linux.network/331152/focus=331154

Using UDP_STREAM on 1Gbit/s driver igb, I can show that the
_raw_spin_lock calls are reduced with approx 3%, when enabling
bulking of just 2 packets.

This test can only demonstrates a CPU usage reduction, as the
throughput is already at maximum link (bandwidth) capacity.

Notice netperf option "-m 1472" which makes sure we are not sending
UDP IP-fragments::

 netperf -H 192.168.111.2 -t UDP_STREAM -l 120 -- -m 1472

Results from perf diff::

 # Command: perf diff
 # Event 'cycles'
 # Baseline  Delta    Symbol
 # no-bulk   bulk(1)
 # ........  .......  .........................................
 #
     7.05%   -3.03%  [k] _raw_spin_lock
     6.34%   +0.23%  [k] copy_user_enhanced_fast_string
     6.30%   +0.26%  [k] fib_table_lookup
     3.03%   +0.01%  [k] __slab_free
     3.00%   +0.08%  [k] intel_idle
     2.49%   +0.05%  [k] sock_alloc_send_pskb
     2.31%   +0.30%  netperf  [.] send_omni_inner
     2.12%   +0.12%  netperf  [.] send_data
     2.11%   +0.10%  [k] udp_sendmsg
     1.96%   +0.02%  [k] __ip_append_data
     1.48%   -0.01%  [k] __alloc_skb
     1.46%   +0.07%  [k] __mkroute_output
     1.34%   +0.05%  [k] __ip_select_ident
     1.29%   +0.03%  [k] check_leaf
     1.27%   +0.09%  [k] __skb_get_hash

A nitpick is that, this testing were done on V2 of the patchset.

You could avoid the fib_table_lookup() cost by using netperf -- -N -n

(connected UDP sockets)

And of course reduce message sizes to increase pps