[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1378344185.11205.3.camel@edumazet-glaptop>
Date: Wed, 04 Sep 2013 18:23:05 -0700
From: Eric Dumazet <eric.dumazet@...il.com>
To: Jason Wang <jasowang@...hat.com>
Cc: David Miller <davem@...emloft.net>,
netdev <netdev@...r.kernel.org>,
Yuchung Cheng <ycheng@...gle.com>,
Neal Cardwell <ncardwell@...gle.com>,
"Michael S. Tsirkin" <mst@...hat.com>
Subject: Re: [PATCH v2 net-next] pkt_sched: fq: Fair Queue packet scheduler
On Wed, 2013-09-04 at 17:50 -0700, Eric Dumazet wrote:
>
> BTW what is your HZ value ?
>
> We have a problem in TCP stack, because srtt is in HZ units.
>
> Before we change to us units, I guess tcp_update_pacing_rate() should be
> changed a bit if HZ=250
Oh well, I feel dumb, please try this fix (If you have HZ != 1000) :
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 93d7e9d..fd96d8e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -700,7 +700,7 @@ static void tcp_update_pacing_rate(struct sock *sk)
u64 rate;
/* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */
- rate = (u64)tp->mss_cache * 2 * (HZ << 3);
+ rate = (u64)tp->mss_cache * 2 * ((USEC_PER_SEC/HZ) << 3);
rate *= max(tp->snd_cwnd, tp->packets_out);
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists