Re: [patch 0/6] mm: alloc_percpu and bigrefs

[Eric Dumazet <dada1@cosmosbay.com>]

Andrew Morton a écrit :
 > Eric Dumazet <dada1@cosmosbay.com> wrote:
 >
 >> Please (re)consider this patch since it really reduce CPU load and/or memory
 >> bus trafic between CPUS.
 >
 >
 > Did you actually measure this?   If so, you should publish the results.
 >
 >

Hi Andrew

Well yes I did.

Here is part of the mail sent on netdev one month ago :



Hi David

I played and I have very good results with the following patches.

# tc -s -d qdisc show dev eth0 ; sleep 10 ; tc -s -d qdisc show dev eth0
qdisc pfifo_fast 0: bands 3 priomap  1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1
  Sent 440173135511 bytes 3211378293 pkt (dropped 240817, overlimits 0 
requeues 27028035)
  backlog 0b 0p requeues 27028035
qdisc pfifo_fast 0: bands 3 priomap  1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1
  Sent 440216655667 bytes 3211730812 pkt (dropped 240904, overlimits 0 
requeues 27031668)
  backlog 0b 0p requeues 27031668

(So about 360 requeues per second, much better than before (12000 / second))

oprofile results give
0.6257  %    qdisc_restart  (instead of 2.6452 %)


thread is archived here :

http://marc.theaimsgroup.com/?l=linux-netdev&m=112521684415443&w=2

Thank you

Eric