diff options
| author | Vasily Averin <vvs@parallels.com> | 2013-04-01 03:01:32 +0000 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2013-04-02 14:29:20 -0400 |
| commit | f0f6ee1f70c4eaab9d52cf7d255df4bd89f8d1c2 (patch) | |
| tree | 74e0b553a8853d7e4b574cb12de54a5e359952ab /net/sched | |
| parent | bab6a9eac05360db25c81b0090f6b1195dd986cc (diff) | |
| download | kernel_goldelico_gta04-f0f6ee1f70c4eaab9d52cf7d255df4bd89f8d1c2.zip kernel_goldelico_gta04-f0f6ee1f70c4eaab9d52cf7d255df4bd89f8d1c2.tar.gz kernel_goldelico_gta04-f0f6ee1f70c4eaab9d52cf7d255df4bd89f8d1c2.tar.bz2 | |
cbq: incorrect processing of high limits
currently cbq works incorrectly for limits > 10% real link bandwidth,
and practically does not work for limits > 50% real link bandwidth.
Below are results of experiments taken on 1 Gbit link
In shaper | Actual Result
-----------+---------------
100M | 108 Mbps
200M | 244 Mbps
300M | 412 Mbps
500M | 893 Mbps
This happen because of q->now changes incorrectly in cbq_dequeue():
when it is called before real end of packet transmitting,
L2T is greater than real time delay, q_now gets an extra boost
but never compensate it.
To fix this problem we prevent change of q->now until its synchronization
with real time.
Signed-off-by: Vasily Averin <vvs@openvz.org>
Reviewed-by: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/sched')
| -rw-r--r-- | net/sched/sch_cbq.c | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 13aa47a..1bc210f 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -962,8 +962,11 @@ cbq_dequeue(struct Qdisc *sch) cbq_update(q); if ((incr -= incr2) < 0) incr = 0; + q->now += incr; + } else { + if (now > q->now) + q->now = now; } - q->now += incr; q->now_rt = now; for (;;) { |