From owner-freebsd-net@freebsd.org Sat Oct 19 17:23:30 2019 Return-Path: Delivered-To: freebsd-net@mailman.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.nyi.freebsd.org (Postfix) with ESMTP id E56D41521F2 for ; Sat, 19 Oct 2019 17:23:30 +0000 (UTC) (envelope-from devgs@ukr.net) Received: from frv190.fwdcdn.com (frv190.fwdcdn.com [212.42.77.190]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) server-signature RSA-PSS (4096 bits) client-signature RSA-PSS (2048 bits) client-digest SHA256) (Client CN "*.ukr.net", Issuer "Thawte RSA CA 2018" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 46wV9Z0GJXz4Rl2 for ; Sat, 19 Oct 2019 17:23:29 +0000 (UTC) (envelope-from devgs@ukr.net) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=ukr.net; s=ffe; h=Content-Transfer-Encoding:Content-Type:MIME-Version:Message-Id: References:In-Reply-To:Cc:To:Subject:From:Date:Sender:Reply-To:Content-ID: Content-Description:Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc :Resent-Message-ID:List-Id:List-Help:List-Unsubscribe:List-Subscribe: List-Post:List-Owner:List-Archive; bh=DvRKeAf5fANH4zVjuMX05802peHFxaHZejyCrlcodjw=; b=KOtlZIxw5/0mqWqqShIEI0ETDL 1wYdJky4xV2iUgmhnjzsxvO98+vDj13OG28QGZlfKBOT84NosEQ0I5JS2jRBZYIwHIWOLvIQbpCuS w3MKJyI3t2J9/O2YgTDnHAmb1MrIv+04eoGS7i/hvChpqWZvD9zJzaC+owPCbZNCXnFY=; Received: from [10.10.10.39] (helo=frv39.fwdcdn.com) by frv190.fwdcdn.com with smtp ID 1iLsRp-000EQo-RK for freebsd-net@freebsd.org; Sat, 19 Oct 2019 20:23:25 +0300 Date: Sat, 19 Oct 2019 20:23:25 +0300 From: Paul Subject: Re[2]: Network anomalies after update from 11.2 STABLE to 12.1 STABLE To: Michael Tuexen Cc: freebsd-net@freebsd.org, freebsd-stable@freebsd.org Received: from devgs@ukr.net by frv39.fwdcdn.com; Sat, 19 Oct 2019 20:23:25 +0300 In-Reply-To: References: <1571499556.409350000.a1ewtyar@frv39.fwdcdn.com> X-Reply-Action: reply Message-Id: <1571505335.800858000.sqrselsr@frv39.fwdcdn.com> X-Mailer: mail.ukr.net 5.0 MIME-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: binary X-Rspamd-Queue-Id: 46wV9Z0GJXz4Rl2 X-Spamd-Bar: --- Authentication-Results: mx1.freebsd.org; dkim=pass header.d=ukr.net header.s=ffe header.b=KOtlZIxw; dmarc=pass (policy=none) header.from=ukr.net; spf=pass (mx1.freebsd.org: domain of devgs@ukr.net designates 212.42.77.190 as permitted sender) smtp.mailfrom=devgs@ukr.net X-Spamd-Result: default: False [-4.00 / 15.00]; ARC_NA(0.00)[]; NEURAL_HAM_MEDIUM(-1.00)[-1.000,0]; R_DKIM_ALLOW(-0.20)[ukr.net:s=ffe]; FROM_HAS_DN(0.00)[]; RCPT_COUNT_THREE(0.00)[3]; R_SPF_ALLOW(-0.20)[+ip4:212.42.77.0/24:c]; FREEMAIL_FROM(0.00)[ukr.net]; MIME_GOOD(-0.10)[text/plain]; IP_SCORE(0.00)[ipnet: 212.42.77.0/24(-4.82), asn: 8856(-3.87), country: UA(0.08)]; NEURAL_HAM_LONG(-1.00)[-1.000,0]; TO_DN_SOME(0.00)[]; DWL_DNSWL_LOW(-1.00)[ukr.net.dwl.dnswl.org : 127.0.5.1]; RCVD_COUNT_THREE(0.00)[3]; TO_MATCH_ENVRCPT_SOME(0.00)[]; DKIM_TRACE(0.00)[ukr.net:+]; DMARC_POLICY_ALLOW(-0.50)[ukr.net,none]; IP_SCORE_FREEMAIL(0.00)[]; FROM_EQ_ENVFROM(0.00)[]; MIME_TRACE(0.00)[0:+]; FREEMAIL_ENVFROM(0.00)[ukr.net]; ASN(0.00)[asn:8856, ipnet:212.42.77.0/24, country:UA]; RCVD_TLS_LAST(0.00)[] X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 19 Oct 2019 17:23:31 -0000 19 October 2019, 19:35:24, by "Michael Tuexen" : > > On 19. Oct 2019, at 18:09, Paul wrote: > > > > Hi Michael, > > > > Thank you, for taking your time! > > > > We use physical machines. We don not have any special `pf` rules. > > Both sides ran `pfctl -d` before testing. > Hi Paul, > > OK. How are the physical machines connected to each other? We have tested different connections. The old, copper ethernet, cable, as well as optics connection with an identical outcome. Machines are connected through Juniper QFX5100. > > What happens when you don't use a lagg interface, but the physical ones? > > (Trying to localise the problem...) Same thing, lagg does not change anything. Originally, the problem was observed on a regular interface. We have tested a on different hardware. Results are consistently stable on 11.2-STABLE and consistently unstable on 12.1-STABLE. The only unchanged thing is the network card vendor, it's Intel. > > Best regards > Michael > > > > > > `nginx` config is primitive, no secrets there: > > > > ------------------------------------------------------------------- > > user www; > > worker_processes auto; > > > > error_log /var/log/nginx/error.log warn; > > > > events { > > worker_connections 81920; > > kqueue_changes 4096; > > use kqueue; > > } > > > > http { > > include mime.types; > > default_type application/octet-stream; > > > > sendfile off; > > keepalive_timeout 65; > > tcp_nopush on; > > tcp_nodelay on; > > > > # Logging > > log_format main '$remote_addr - $remote_user [$time_local] "$request" ' > > '$status $request_length $body_bytes_sent "$http_referer" ' > > '"$http_user_agent" "$http_x_real_ip" "$realip_remote_addr" "$request_completion" "$request_time" ' > > '"$request_body"'; > > > > access_log /var/log/nginx/access.log main; > > > > server { > > listen 80 default; > > > > server_name localhost _; > > > > location / { > > return 404; > > } > > } > > } > > ------------------------------------------------------------------- > > > > > > `wrk` is compiled with a default configuration. We test like this: > > > > `wrk -c 10 --header "Connection: close" -d 10 -t 1 --latency http://10.10.10.92:80/missing` > > > > > > Also, it seems that our issue, and the one described in this thread, are identical: > > > > https://lists.freebsd.org/pipermail/freebsd-net/2019-June/053667.html > > > > We both have the Intel network cards, BTW. Our network cards are these: > > > > em0 at pci0:10:0:0: class=0x020000 card=0x000015d9 chip=0x10d38086 rev=0x00 hdr=0x00 > > vendor = 'Intel Corporation' > > device = '82574L Gigabit Network Connection' > > > > ixl0 at pci0:4:0:0: class=0x020000 card=0x00078086 chip=0x15728086 rev=0x01 hdr=0x00 > > vendor = 'Intel Corporation' > > device = 'Ethernet Controller X710 for 10GbE SFP+' > > > > > > ============================== > > > > Additional info: > > > > During the tests, we have bonded two interfaces into a lagg: > > > > ixl0: flags=8843 metric 0 mtu 1500 > > options=c500b8 > > ether 3c:fd:fe:aa:60:20 > > media: Ethernet autoselect (10Gbase-SR ) > > status: active > > nd6 options=29 > > ixl1: flags=8843 metric 0 mtu 1500 > > options=c500b8 > > ether 3c:fd:fe:aa:60:20 > > hwaddr 3c:fd:fe:aa:60:21 > > media: Ethernet autoselect (10Gbase-SR ) > > status: active > > nd6 options=29 > > > > > > lagg0: flags=8843 metric 0 mtu 1500 > > options=c500b8 > > ether 3c:fd:fe:aa:60:20 > > inet 10.10.10.92 netmask 0xffff0000 broadcast 10.10.255.255 > > laggproto failover lagghash l2,l3,l4 > > laggport: ixl0 flags=5 > > laggport: ixl1 flags=0<> > > groups: lagg > > media: Ethernet autoselect > > status: active > > nd6 options=29 > > > > using this config: > > > > ifconfig_ixl0="up -lro -tso -rxcsum -txcsum" (tried different options - got the same outcome) > > ifconfig_ixl1="up -lro -tso -rxcsum -txcsum" > > ifconfig_lagg0="laggproto failover laggport ixl0 laggport ixl1 10.10.10.92/24" > > > > > > We have randomly picked `ixl0` and restricted number of RX/TX queues to 1: > > /boot/loader.conf : > > dev.ixl.0.iflib.override_ntxqs=1 > > dev.ixl.0.iflib.override_nrxqs=1 > > > > leaving `ixl1` with a default number, matching number of cores (6). > > > > > > ixl0: mem 0xf8800000-0xf8ffffff,0xf9808000-0xf980ffff irq 40 at device 0.0 on pci4 > > ixl0: fw 5.0.40043 api 1.5 nvm 5.05 etid 80002927 oem 1.261.0 > > ixl0: PF-ID[0]: VFs 64, MSI-X 129, VF MSI-X 5, QPs 768, I2C > > ixl0: Using 1024 TX descriptors and 1024 RX descriptors > > ixl0: Using 1 RX queues 1 TX queues > > ixl0: Using MSI-X interrupts with 2 vectors > > ixl0: Ethernet address: 3c:fd:fe:aa:60:20 > > ixl0: Allocating 1 queues for PF LAN VSI; 1 queues active > > ixl0: PCI Express Bus: Speed 8.0GT/s Width x4 > > ixl0: SR-IOV ready > > ixl0: netmap queues/slots: TX 1/1024, RX 1/1024 > > ixl1: mem 0xf8000000-0xf87fffff,0xf9800000-0xf9807fff irq 40 at device 0.1 on pci4 > > ixl1: fw 5.0.40043 api 1.5 nvm 5.05 etid 80002927 oem 1.261.0 > > ixl1: PF-ID[1]: VFs 64, MSI-X 129, VF MSI-X 5, QPs 768, I2C > > ixl1: Using 1024 TX descriptors and 1024 RX descriptors > > ixl1: Using 6 RX queues 6 TX queues > > ixl1: Using MSI-X interrupts with 7 vectors > > ixl1: Ethernet address: 3c:fd:fe:aa:60:21 > > ixl1: Allocating 8 queues for PF LAN VSI; 6 queues active > > ixl1: PCI Express Bus: Speed 8.0GT/s Width x4 > > ixl1: SR-IOV ready > > ixl1: netmap queues/slots: TX 6/1024, RX 6/1024 > > > > > > This allowed us easy switch between different configurations without > > the need to reboot, by simply shutting down one interface or the other: > > > > `ifconfig XXX down` > > > > When testing `ixl0` that runs only a single queue: > > ixl0: Using 1 RX queues 1 TX queues > > ixl0: netmap queues/slots: TX 1/1024, RX 1/1024 > > > > we've got these results: > > > > `wrk -c 10 --header "Connection: close" -d 10 -t 1 --latency http://10.10.10.92:80/missing` > > Running 10s test @ http://10.10.10.92:80/missing > > 1 threads and 10 connections > > Thread Stats Avg Stdev Max +/- Stdev > > Latency 281.31us 297.74us 22.66ms 99.70% > > Req/Sec 19.91k 2.79k 21.25k 97.59% > > Latency Distribution > > 50% 266.00us > > 75% 309.00us > > 90% 374.00us > > 99% 490.00us > > 164440 requests in 10.02s, 47.52MB read > > Socket errors: read 0, write 0, timeout 0 > > Non-2xx or 3xx responses: 164440 > > Requests/sec: 16412.09 > > Transfer/sec: 4.74MB > > > > > > When testing `ixl1` that runs 6 queues: > > ixl1: Using 6 RX queues 6 TX queues > > ixl1: netmap queues/slots: TX 6/1024, RX 6/1024 > > > > we've got these results: > > > > `wrk -c 10 --header "Connection: close" -d 10 -t 1 --latency http://10.10.10.92:80/missing` > > Running 10s test @ http://10.10.10.92:80/missing > > 1 threads and 10 connections > > Thread Stats Avg Stdev Max +/- Stdev > > Latency 216.16us 71.97us 511.00us 47.56% > > Req/Sec 4.34k 2.76k 15.44k 83.17% > > Latency Distribution > > 50% 216.00us > > 75% 276.00us > > 90% 312.00us > > 99% 365.00us > > 43616 requests in 10.10s, 12.60MB read > > Socket errors: connect 0, read 24, write 8, timeout 0 > > Non-2xx or 3xx responses: 43616 > > Requests/sec: 4318.26 > > Transfer/sec: 1.25MB > > > > Do note, that, not only multiple queues cause issues they also dramatically > > decrease the performance of the network. > > > > Using `sysctl -w net.inet.tcp.ts_offset_per_conn=0` didn't help at all. > > > > Best regards, > > -Paul > > > > > >