diff options
author | Eric Dumazet <edumazet@google.com> | 2013-10-27 16:26:43 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2013-10-28 00:18:31 -0400 |
commit | fc59d5bdf1e3dca0336d155e55d812286db075ad (patch) | |
tree | 647350005b677b64cdfbea97d396245c74f9514a | |
parent | ad86de802d0ea6776eccd0a2526ba31101d89267 (diff) | |
download | linux-fc59d5bdf1e3dca0336d155e55d812286db075ad.tar.bz2 |
pkt_sched: fq: clear time_next_packet for reused flows
When a socket is freed/reallocated, we need to clear time_next_packet
or else we can inherit a prior value and delay first packets of the
new flow.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r-- | net/sched/sch_fq.c | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index a9dfdda9ed1d..fdc041c57853 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -255,6 +255,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) f->socket_hash != sk->sk_hash)) { f->credit = q->initial_quantum; f->socket_hash = sk->sk_hash; + f->time_next_packet = 0ULL; } return f; } |