From nobody Sat Aug 6 19:04:11 2022 X-Original-To: stable@mlmmj.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mlmmj.nyi.freebsd.org (Postfix) with ESMTP id 4M0X2N50dgz4YYtQ for ; Sat, 6 Aug 2022 19:04:28 +0000 (UTC) (envelope-from jim@jimking.net) Received: from flounder.jimking.net (flounder.jimking.net [IPv6:2607:fc50:1:8b00:216:3eff:fe33:f0f9]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "flounder.jimking.net", Issuer "jimking.net CA" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id 4M0X2M3pdWz3kFH; Sat, 6 Aug 2022 19:04:27 +0000 (UTC) (envelope-from jim@jimking.net) Received: from [192.168.22.253] (c-98-199-170-72.hsd1.tx.comcast.net [98.199.170.72]) (authenticated bits=0) by flounder.jimking.net (8.15.2/8.15.2) with ESMTPSA id 276J4JJI032369 (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128 verify=NO); Sat, 6 Aug 2022 14:04:20 -0500 (CDT) (envelope-from jim@jimking.net) X-Authentication-Warning: flounder.jimking.net: Host c-98-199-170-72.hsd1.tx.comcast.net [98.199.170.72] claimed to be [192.168.22.253] Message-ID: Date: Sat, 6 Aug 2022 14:04:11 -0500 List-Id: Production branch of FreeBSD source code List-Archive: https://lists.freebsd.org/archives/freebsd-stable List-Help: List-Post: List-Subscribe: List-Unsubscribe: Sender: owner-freebsd-stable@freebsd.org X-BeenThere: freebsd-stable@freebsd.org MIME-Version: 1.0 User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:91.0) Gecko/20100101 Thunderbird/91.12.0 Subject: Re: igc problems with heavy traffic Content-Language: en-US To: mike tancsa , stable@freebsd.org, kbowling@FreeBSD.org References: <59b9cec0-d8c2-ce72-b5e9-99d1a1e807f8@sentex.net> <86995d10-af63-d053-972e-dd233029f3bf@jimking.net> <3d874f65-8ce2-8f06-f19a-14cd550166e3@sentex.net> From: Jim King In-Reply-To: Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 8bit X-Virus-Scanned: clamav-milter 0.99.4 at flounder.jimking.net X-Virus-Status: Clean X-Rspamd-Queue-Id: 4M0X2M3pdWz3kFH X-Spamd-Bar: --- Authentication-Results: mx1.freebsd.org; dkim=none; dmarc=none; spf=pass (mx1.freebsd.org: domain of jim@jimking.net designates 2607:fc50:1:8b00:216:3eff:fe33:f0f9 as permitted sender) smtp.mailfrom=jim@jimking.net X-Spamd-Result: default: False [-3.30 / 15.00]; NEURAL_HAM_LONG(-1.00)[-1.000]; NEURAL_HAM_MEDIUM(-1.00)[-1.000]; NEURAL_HAM_SHORT(-1.00)[-1.000]; R_SPF_ALLOW(-0.20)[+a:flounder.jimking.net]; MIME_GOOD(-0.10)[text/plain]; MIME_TRACE(0.00)[0:+]; ASN(0.00)[asn:36236, ipnet:2607:fc50::/36, country:US]; R_DKIM_NA(0.00)[]; FROM_EQ_ENVFROM(0.00)[]; TO_MATCH_ENVRCPT_SOME(0.00)[]; MLMMJ_DEST(0.00)[stable@freebsd.org]; RCVD_VIA_SMTP_AUTH(0.00)[]; MID_RHS_MATCH_FROM(0.00)[]; DMARC_NA(0.00)[jimking.net]; FREEFALL_USER(0.00)[jim]; ARC_NA(0.00)[]; RCVD_COUNT_TWO(0.00)[2]; RCPT_COUNT_THREE(0.00)[3]; FROM_HAS_DN(0.00)[]; TO_DN_SOME(0.00)[]; HAS_XAW(0.00)[]; RCVD_TLS_ALL(0.00)[] X-ThisMailContainsUnwantedMimeParts: N On 8/5/2022 12:47 PM, mike tancsa wrote: > On 8/5/2022 11:41 AM, Jim King wrote: >> If I fiddle with the Flow Control settings it seems to make a >> difference.  I can do it without bouncing the link.  I wonder what >> the Linux driver has as default ? >>> >>> ie. >>> >>> sysctl -w dev.igc.1.fc=1 >>> sysctl -w dev.igc.0.fc=1 >>> >>> Does it help in your case ? >>> >> Thanks for the suggestion.  Unfortunately it doesn't seem to help in >> my case.  All four values for flow control give pretty much the same >> results with my iperf test. >> >> > Are you able to boot a RELENG_13 stable kernel and test ? I am using a > stable kernel from a couple of days ago and setting the fc=0 (you set > that on all nics right ?) does work for me both at 2.5G and 1G. > Leaving the default causes the nic to bounce on my test boxes. I dont > see any obvious big changes in the driver itself since 13.1 came out > so I am guessing something else fixed or worked around this bug ? > I build stable/13 from yesterday and still haven't found a working configuration.  When I turn off Flow Control on both NICs my first iperf test always causes the NIC to bounce, and sometimes subsequent tests will work OK, but only sometimes.  Most of the time the subsequent iperf runs also cause the NIC to bounce. I also tried -rxcsum and -txcsum on the NIC, which had no effect. > Anything interesting come up in > > sysctl -a dev.igc > > ? > Nothing that catches my eye, but I don't have much experience with this kind of troubleshooting. Jim