From owner-freebsd-net@FreeBSD.ORG Wed Oct 1 21:21:02 2014 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 07145631; Wed, 1 Oct 2014 21:21:02 +0000 (UTC) Received: from mail.westryn.net (mail.westryn.net [199.48.135.251]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id C5CF0B56; Wed, 1 Oct 2014 21:21:01 +0000 (UTC) Received: from sneffels.westryn.net (225x169.ouraynet.com [204.16.225.169]) (using TLSv1 with cipher ECDHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.westryn.net (Postfix) with ESMTPSA id 0C8319432A1; Wed, 1 Oct 2014 15:13:54 -0600 (MDT) Content-Type: text/plain; charset=windows-1252 Mime-Version: 1.0 (Mac OS X Mail 7.3 \(1878.6\)) Subject: Re: individual queue blocking entire rx unit on ixgbe (Re: How do I balance bandwidth over several virtual NICs?) From: Kim Shrier In-Reply-To: Date: Wed, 1 Oct 2014 15:12:30 -0600 Content-Transfer-Encoding: quoted-printable Message-Id: <2FAAD083-7EAF-4E5F-A3D5-0AFB08C4ED9D@westryn.net> References: To: Luigi Rizzo X-Mailer: Apple Mail (2.1878.6) Cc: "freebsd-net@freebsd.org" , Adrian Chadd , Elof Ofel , "Alexander V. Chernikov" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 01 Oct 2014 21:21:02 -0000 Not sure if this is related. I was testing on 10.1 beta3 and I was = copying approximately 250 GB of data to the test machine, I noticed that the network would periodically slow down to about 4 mbits/sec or it would pause for about 20 seconds and then continue at full speed. The ethernet interface on the test machine is: bge0: mem 0xa0400000-0xa040ffff,0xa0410000-0xa041ffff irq 16 at = device 0.0 on pci1 bge0: CHIP ID 0x57766001; ASIC REV 0x57766; CHIP REV 0x577660; PCI-E The machine I am transferring from is using the em0 interface: em0: port 0xdc00-0xdc1f mem = 0xfb5e0000-0xfb5fffff,0xfb5dc000-0xfb5dffff irq 16 at device 0.0 on pci2 I haven=92t noticed any slow down when transferring between machines = where both sides are using the em driver. During the slow downs and pauses, when I had a top command running, the process state would show up as =93dp->dp=94 or =93rl->l_=94 instead = of something normal like =93select=94 or CPUn. If this is related, then maybe the problem is somewhere other than the = device driver. Kim On Oct 1, 2014, at 3:48 AM, Luigi Rizzo wrote: > reviving this thread: >=20 > i am just running experiments on 10.1 beta3 and even > setting dev.ix.*.fc=3D0 and flipping the interface up and down > does not seem to help: if i read only from a subset of the > queues, the entire rx unit stalls eventually. >=20 > I need to drain all queues to keep moving. >=20 > Just tested this with 8 instances of netmap-ipfw running > on an 8-core machine (8 queues enabled). >=20 > netmap-ipfw netmap:ix0-0 netmap:ix1-0 > netmap-ipfw netmap:ix0-1 netmap:ix1-1 > ... >=20 > and the source on another box is blasting on multiple queues with >=20 > pkt-gen -f tx -i ix0 -d 10.0.10.0-10.0.10.255 >=20 >=20 > I going to look at the driver's code now to see if/how > this issue can be addressed. >=20 > cheers > luigi >=20 >=20 > On Tue, Sep 23, 2014 at 6:00 PM, Adrian Chadd = wrote: >=20 >> Ah, this behaviour. >>=20 >> It's called DROP_EN on the intel igb / ixgbe hardware. Grep the >> drivers for that particular register bit/setting. >>=20 >> Set that bit for an RX queue and it'll instruct the MAC to drop = frames >> destined if that RX ring is full to it and keep receiving on the = other >> rings. Otherwise yes, receiving on that ring with the ring full = cuases >> the MAC to stop receiving on all rings until that ring has free = space. >>=20 >> You flip this on with ixgbe and igb by disabling tx/rx flowcontrol >> (sysctl dev.ix|igb.X.fc=3D0) before configuring the interface. >>=20 >>=20 >>=20 >> -a >>=20 >=20 >=20 >=20 > --=20 > = -----------------------------------------+------------------------------- > Prof. Luigi RIZZO, rizzo@iet.unipi.it . Dip. di Ing. = dell'Informazione > http://www.iet.unipi.it/~luigi/ . Universita` di Pisa > TEL +39-050-2211611 . via Diotisalvi 2 > Mobile +39-338-6809875 . 56122 PISA (Italy) > = -----------------------------------------+------------------------------- > _______________________________________________ > freebsd-net@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org"