From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: NET_SCHED cbq dropping too many packets on a bonding interface Date: Thu, 15 May 2008 07:21:18 +0200 Message-ID: <482BC84E.3000401@cosmosbay.com> References: <20080514205604.e669a28f.akpm@linux-foundation.org> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Andrew Morton , linux-kernel@vger.kernel.org, netdev@vger.kernel.org To: Kingsley Foreman Return-path: Received: from smtp2e.orange.fr ([80.12.242.112]:27962 "EHLO smtp2e.orange.fr" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750751AbYEOFVi convert rfc822-to-8bit (ORCPT ); Thu, 15 May 2008 01:21:38 -0400 In-Reply-To: <20080514205604.e669a28f.akpm@linux-foundation.org> Sender: netdev-owner@vger.kernel.org List-ID: Andrew Morton a =E9crit : > (cc netdev) > > On Thu, 15 May 2008 12:25:19 +0930 "Kingsley Foreman" wrote: > > =20 >> Ive been using qdisc for quite a while without any problems, >> I just rebuilt a gentoo box with 2.6.25 kernel that does a lot of tr= affic >> ~1000mbits+ over a bonded interface >> >> Im however seeing a big problem with cbq class dropping packets for = no >> reason i can see, and it is causing a lot of speed issues. >> >> the basic config is this >> ____________________________________________________________________= _ >> /sbin/tc qdisc del dev bond0 root >> /sbin/tc qdisc add dev bond0 root handle 1 cbq bandwidth 2000Mbit av= pkt 1000 >> cell 8 >> /sbin/tc class change dev bond0 root cbq weight 200Mbit allot 1514 >> >> /sbin/tc class add dev bond0 parent 1: classid 1:1280 cbq bandwidth = 2000Mbit >> rate 1200Mbit weight 120Mbit prio 1 allot 1514 cell 8 maxburst 120 m= inburst >> 1 minidle 0 avpkt 1000 bounded >> /sbin/tc filter add dev bond0 parent 1:0 protocol ip prio 300 route = to 5 >> classid 1:1280 >> >> /sbin/tc class add dev bond0 parent 1: classid 1:1281 cbq bandwidth = 2000Mbit >> rate 400Mbit weight 40Mbit prio 6 allot 1514 cell 8 maxburst 120 min= burst 1 >> minidle 0 avpkt 1000 bounded >> /sbin/tc filter add dev bond0 parent 1:0 protocol ip prio 300 route = to 6 >> classid 1:1281 >> ____________________________________________________________________ >> >> So there is a lot of bandwidth handed out but it is still dropping a= lot of >> packets for very small ammounts of traffic eg 300mbits. >> >> However the biggest problem im seeing is if i just do this >> >> __________________________________________________________________ >> /sbin/tc qdisc del dev bond0 root >> /sbin/tc qdisc add dev bond0 root handle 1 cbq bandwidth 2000Mbit av= pkt 1000 >> cell 8 >> /sbin/tc class change dev bond0 root cbq weight 200Mbit allot 1514 >> ___________________________________________________________________ >> >> after 30sec I get results like >> ___________________________________________________________________ >> >> ### bond0: queueing disciplines >> >> qdisc cbq 1: root rate 2000Mbit (bounded,isolated) prio no-transmit >> Sent 574230043 bytes 407156 pkt (dropped 2524, overlimits 0 requeue= s 0) >> rate 0bit 0pps backlog 0b 0p requeues 0 >> borrowed 0 overactions 0 avgidle 3 undertime 0 >> >> ### bond0: traffic classes >> >> class cbq 1: root rate 2000Mbit (bounded,isolated) prio no-transmit >> Sent 574330783 bytes 407225 pkt (dropped 2525, overlimits 0 requeue= s 0) >> rate 0bit 0pps backlog 0b 0p requeues 0 >> borrowed 0 overactions 0 avgidle 3 undertime 0 >> __________________________________________________________________ >> >> I can't for the life if me work out why it is dropping so many packe= ts for=20 >> while doing so little traffic when i enable cbq the transfer rate d= rops by=20 >> approx 30%, any help would be great, and any improvements to my comm= and=20 >> lines would be good also. >> >> >> Kingsley Foreman >> =20 > > > > =20 Could you provide your linux-2.6.25 .config file please ? What kind of hardware is your box ? (CPU, network interfaces) CBQ and other packet schedulers depend on a fast ktime_get() interface,= =20 so maybe slowdown you notice has its root on core kernel facilities (CONFIG_HZ, SCHED_HRTICK, HIGH_RES_TIMERS, ...) If you remove CBQ, do you get same slowdown if you have a tcpdump=20 running on your machine ?