From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: HTB accuracy for high speed Date: Mon, 18 May 2009 18:40:56 +0200 Message-ID: <4A118F98.60101@cosmosbay.com> References: <298f5c050905150745p13dc226eia1ff50ffa8c4b300@mail.gmail.com> <298f5c050905150749s3597328dr8dd15adbd7a37532@mail.gmail.com> <20090516141430.GB3013@ami.dom.local> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Antonio Almeida , netdev@vger.kernel.org, kaber@trash.net, davem@davemloft.net, devik@cdi.cz To: Jarek Poplawski Return-path: Received: from gw1.cosmosbay.com ([212.99.114.194]:46901 "EHLO gw1.cosmosbay.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752164AbZERQlI convert rfc822-to-8bit (ORCPT ); Mon, 18 May 2009 12:41:08 -0400 In-Reply-To: <20090516141430.GB3013@ami.dom.local> Sender: netdev-owner@vger.kernel.org List-ID: Jarek Poplawski a =E9crit : > On Fri, May 15, 2009 at 03:49:31PM +0100, Antonio Almeida wrote: > ... >> I also note that, for HTB rate configurations over 500Mbit/s on leaf >> class, when I stop the traffic, in the output of "tc -s -d class ls >> dev eth1" command, I see that leaf's rate (in bits/s) is growing >> instead of decreasing (as expected since I've stopped the traffic). >> Rate in pps is ok and decreases until 0pps. Rate in bits/s increases >> above 1000Mbit and stays there for a few minutes. After two or three >> minutes it becomes 0bit. The same happens for it's ancestors (also f= or >> root class).Here's tc output of my leaf class for this situation: >> >> class htb 1:108 parent 1:10 leaf 108: prio 7 quantum 1514 rate >> 555000Kbit ceil 555000Kbit burst 70901b/8 mpu 0b overhead 0b cburst >> 70901b/8 mpu 0b overhead 0b level 0 >> Sent 120267768144 bytes 242475339 pkt (dropped 62272599, overlimits= 0 >> requeues 0) >> rate 1074Mbit 0pps backlog 0b 0p requeues 0 >> lended: 242475339 borrowed: 0 giants: 0 >> tokens: 8 ctokens: 8 >=20 > This looks like a regular bug. I guess it's an overflow in > gen_estimator(), but I'm not sure there is nothing more. Could you > try the patch below? (An offset warning when patching 2.6.25 is OK) >=20 > Thanks, > Jarek P. > --- >=20 > net/core/gen_estimator.c | 6 +++++- > 1 files changed, 5 insertions(+), 1 deletions(-) >=20 > diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c > index 9cc9f95..87f0ced 100644 > --- a/net/core/gen_estimator.c > +++ b/net/core/gen_estimator.c > @@ -127,7 +127,11 @@ static void est_timer(unsigned long arg) > npackets =3D e->bstats->packets; > rate =3D (nbytes - e->last_bytes)<<(7 - idx); > e->last_bytes =3D nbytes; > - e->avbps +=3D ((long)rate - (long)e->avbps) >> e->ewma_log; > + if (rate > e->avbps) > + e->avbps +=3D (rate - e->avbps) >> e->ewma_log; > + else > + e->avbps -=3D (e->avbps - rate) >> e->ewma_log; > + > e->rate_est->bps =3D (e->avbps+0xF)>>5; > =20 > rate =3D (npackets - e->last_packets)<<(12 - idx); With a typical estimator "1sec 8sec", ewma_log value is 3 At gigabit speeds, we are very close to overflow yes, since we only have 27 bits available, so 134217728 bytes per second or 1073741824 bits per second. So formula : e->avbps +=3D ((long)rate - (long)e->avbps) >> e->ewma_log; is going to overflow. One way to avoid the overflow would be to use a smaller estimator, like= "500ms 4sec"=20 Or use a 64bits rate & avbps, this is needed fo 10Gb speeds I suppose..= =2E diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 9cc9f95..150e2f5 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -86,9 +86,9 @@ struct gen_estimator spinlock_t *stats_lock; int ewma_log; u64 last_bytes; + u64 avbps; u32 last_packets; u32 avpps; - u32 avbps; struct rcu_head e_rcu; struct rb_node node; }; @@ -115,6 +115,7 @@ static void est_timer(unsigned long arg) rcu_read_lock(); list_for_each_entry_rcu(e, &elist[idx].list, list) { u64 nbytes; + u64 brate; u32 npackets; u32 rate; =20 @@ -125,9 +126,9 @@ static void est_timer(unsigned long arg) =20 nbytes =3D e->bstats->bytes; npackets =3D e->bstats->packets; - rate =3D (nbytes - e->last_bytes)<<(7 - idx); + brate =3D (nbytes - e->last_bytes)<<(7 - idx); e->last_bytes =3D nbytes; - e->avbps +=3D ((long)rate - (long)e->avbps) >> e->ewma_log; + e->avbps +=3D ((s64)(brate - e->avbps)) >> e->ewma_log; e->rate_est->bps =3D (e->avbps+0xF)>>5; =20 rate =3D (npackets - e->last_packets)<<(12 - idx);