diff options
author | Eric Dumazet <edumazet@google.com> | 2013-07-31 00:55:08 (GMT) |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2013-07-31 21:59:49 (GMT) |
commit | f2f872f9272a79a1048877ea14c15576f46c225e (patch) | |
tree | 22af2e425ac96068c2d383c052e1d287db867211 /net/sched/sch_netem.c | |
parent | ca4c3fc24e293719fe7410c4e63da9b6bc633b83 (diff) | |
download | linux-fsl-qoriq-f2f872f9272a79a1048877ea14c15576f46c225e.tar.xz |
netem: Introduce skb_orphan_partial() helper
Commit 547669d483e578 ("tcp: xps: fix reordering issues") added
unexpected reorders in case netem is used in a MQ setup for high
performance test bed.
ETH=eth0
tc qd del dev $ETH root 2>/dev/null
tc qd add dev $ETH root handle 1: mq
for i in `seq 1 32`
do
tc qd add dev $ETH parent 1:$i netem delay 100ms
done
As all tcp packets are orphaned by netem, TCP stack believes it can
set skb->ooo_okay on all packets.
In order to allow producers to send more packets, we want to
keep sk_wmem_alloc from reaching sk_sndbuf limit.
We can do that by accounting one byte per skb in netem queues,
so that TCP stack is not fooled too much.
Tested:
With above MQ/netem setup, scaling number of concurrent flows gives
linear results and no reorders/retransmits
lpq83:~# for n in 1 10 20 30 40 50 60 70 80 90 100
do echo -n "n:$n " ; ./super_netperf $n -H 10.7.7.84; done
n:1 198.46
n:10 2002.69
n:20 4000.98
n:30 6006.35
n:40 8020.93
n:50 10032.3
n:60 12081.9
n:70 13971.3
n:80 16009.7
n:90 17117.3
n:100 17425.5
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/sched/sch_netem.c')
-rw-r--r-- | net/sched/sch_netem.c | 5 |
1 files changed, 1 insertions, 4 deletions
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 82f6016..a6d788d 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -412,12 +412,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) /* If a delay is expected, orphan the skb. (orphaning usually takes * place at TX completion time, so _before_ the link transit delay) - * Ideally, this orphaning should be done after the rate limiting - * module, because this breaks TCP Small Queue, and other mechanisms - * based on socket sk_wmem_alloc. */ if (q->latency || q->jitter) - skb_orphan(skb); + skb_orphan_partial(skb); /* * If we need to duplicate packet, then re-insert at top of the |