From owner-freebsd-stable@FreeBSD.ORG Tue Jul 6 06:06:34 2010 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 6D605106564A for ; Tue, 6 Jul 2010 06:06:34 +0000 (UTC) (envelope-from davideugenewarren@gmail.com) Received: from mail-vw0-f54.google.com (mail-vw0-f54.google.com [209.85.212.54]) by mx1.freebsd.org (Postfix) with ESMTP id D1BD68FC08 for ; Tue, 6 Jul 2010 06:06:33 +0000 (UTC) Received: by vws6 with SMTP id 6so7276233vws.13 for ; Mon, 05 Jul 2010 23:06:25 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:received:in-reply-to :references:date:message-id:subject:from:to:content-type; bh=OUsA5h5ca4+dpWTI7WV/xsDamBkkqLSvocxbivFb/2s=; b=K1rbxFHCuX26k0bqEBdWXXLU9kgPXb/+I+HvIsZtYb9TqM5ifsRntPIVEDdUi5jooP WKAWuMvDuXK08jRTNgoY9n1VIESA4vST2q5ZbzVfdtfzSAqyKnkiuJ7KUZEU5mQhHBYq 8z7jmKAx1LRIjylqEtX6ccbFzbwBPtZR+z9Fo= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :content-type; b=kRxo+v4bVAx38n3eBNdEUVuOU/ghW0bBJcFjtVEoOeRRI/fPTDAr/D32tcsIYFL1do nu5aEysfB3H05IZHsPehFqrnUrRGlnYP5GDOhC0n+NoklouCCy7QTpkAW7R4Za7R1OFF oxiS0ggtv2dDRGS0dtKsxHXPBwLV+E+JKxKSg= MIME-Version: 1.0 Received: by 10.220.157.139 with SMTP id b11mr2167738vcx.180.1278396385485; Mon, 05 Jul 2010 23:06:25 -0700 (PDT) Received: by 10.220.190.1 with HTTP; Mon, 5 Jul 2010 23:06:25 -0700 (PDT) In-Reply-To: References: <20100705055105.GA21681@icarus.home.lan> Date: Tue, 6 Jul 2010 01:06:25 -0500 Message-ID: From: David Warren To: freebsd-stable@freebsd.org Content-Type: text/plain; charset=ISO-8859-1 X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Subject: Re: 8.0 network problem X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 06 Jul 2010 06:06:34 -0000 Hi again, Disabling pf definitely makes samba file transfers move faster (the speed varies quite a bit, but everything's faster than the single kilobytes per second I was seeing previously), but I'm perplexed about what's causing the slowdown. There's certainly some cruft in my pf.conf (below), but I'm not sure what might be strangling my LAN. Can anyone set me straight? /etc/pf.conf: # macros int_if = "em0" wifi_if = "wlan0" ext_if = "nfe0" nat_opt = "192.168.0.5" # Windows box nat_cu = "192.168.0.1" # server tcp_services = "{ 22 }" icmp_types = "echoreq" priv_nets = "{ 127.0.0.0/8, 192.168.0.0/16, 172.16.0.0/12, 10.0.0.0/8 }" # options set block-policy return set loginterface $ext_if set skip on lo # scrub scrub in # nat/rdr nat on $ext_if from !($ext_if) -> ($ext_if:0) nat on $ext_if from $wifi_if:network to any -> ($ext_if) rdr on $ext_if proto tcp from any to any port 22 -> $nat_cu rdr on $ext_if proto tcp from any to any port 6881:6999 -> $nat_opt rdr on $ext_if proto tcp from any to any port 34567:34575 -> $nat_cu rdr on $ext_if proto tcp from any to any port 993 -> $nat_opt # filter rules block in log pass out keep state antispoof quick for { lo $int_if } pass in on $ext_if inet proto tcp from any to ($ext_if) port $tcp_services flags S/SA keep state block drop in quick on $ext_if from $priv_nets to any block drop out quick on $ext_if from any to $priv_nets pass in inet proto icmp all icmp-type $icmp_types keep state #pass in on $int_if from $int_if:network to any keep state #pass out on $int_if from any to $int_if:network keep state #pass in on $wifi_if from $wifi_if:network to any keep state #pass out on $wifi_if from any to $wifi_if:network keep state pass in on $ext_if inet proto tcp from any to $nat_cu port $tcp_services flags S/SA synproxy state pass in on $ext_if inet proto tcp from any to $nat_cu port 34567:34575 flags S/SA synproxy state pass in on $ext_if inet proto tcp from any to $nat_opt port 6881:6999 flags S/SA synproxy state pass in on $ext_if inet proto tcp from any to $nat_opt port 993 flags S/SA synproxy state pass in quick on $int_if pass in quick on $wifi_if Many thanks, Dave On Mon, Jul 5, 2010 at 5:49 PM, David Warren wrote: > Hi all, > > As several people have noted, I should have been more specific about > the problem. As far as I can tell, it's limited to the wired portion of my > network involving the em0 interface. Samba and scp transfers to and from > computers on the ral0 interface seem unaffected. Even at the relatively > slow speeds of wireless, those transfers are substantially faster than the > degraded speeds I'm seeing on the wired network. I should also have noted > that the main computer on the wired network is a Windows box, while I use > the wireless with my MacBook. I'm using pf for my firewall on the FreeBSD > box, and having tried a bunch of the suggested tests I'm thinking that's the > most likely culprit. I'm going to try a few things out to test that idea. > However, for completeness, here's are the results of the various tests and > diagnostics that were requested. > > My pciconf output: > > > pciconf -lvc > nfe0@pci0:0:20:0: class=0x068000 card=0x816a1043 chip=0x026910de > rev=0xa3 hdr=0x00 > vendor = 'Nvidia Corp' > device = 'MCP51 Ethernet Controller (2A34103C)' > class = bridge > cap 01[44] = powerspec 2 supports D0 D1 D2 D3 current D0 > em0@pci0:4:8:0: class=0x020000 card=0x13768086 chip=0x107c8086 rev=0x05 > hdr=0x00 > vendor = 'Intel Corporation' > device = 'Gigabit Ethernet Controller (Copper) rev 5 (82541PI)' > class = network > subclass = ethernet > cap 01[dc] = powerspec 2 supports D0 D3 current D0 > cap 07[e4] = PCI-X supports 2048 burst read, 1 split transaction > ral0@pci0:4:9:0: class=0x028000 card=0x71281432 chip=0x03011814 > rev=0x00 hdr=0x00 > vendor = 'Ralink Technology, Corp' > device = 'Edimax 54 MBit WLan 802.11g rt 2500 (b8341462)' > class = network > cap 01[40] = powerspec 2 supports D0 D3 current D0 > > > dmesg isn't reporting anything new when this happens. Disabling > rxcsum and txcsum doesn't seem to have an effect. Here's a quick overview > of what I've tried: > > pscp works from .13 to .1 (pscp because I'm using key-based > identification). > samba fast then slow from .1 to .13 > samba fast then slow from .13 to .1 > netcat fast then slow from .13 to .1 > netcat not working from .1 to .13 (I need to figure out how to get netcat > input into the Windows box on .13) > > While the problem was evident, I collected the following netstat: > > > netstat -i > Name Mtu Network Address Ipkts Ierrs Opkts Oerrs > Coll > em0 1500 00:0e:0c:b7:71:44 4840841 0 3791658 > 0 0 > em0 1500 192.168.0.0 192.168.0.1 5496050 - 3687095 > - - > ral0 2290 00:1f:1f:3f:76:f3 0 0 965271 > 1156 0 > nfe0 1500 00:01:29:d4:2d:6b 349488 0 83833 > 0 0 > nfe0 1500 173.19.224.0/ 173-19-224-254.cl 3260 - 7725 > - - > plip0 1500 0 0 0 > 0 0 > lo0 16384 758 0 758 > 0 0 > lo0 16384 fe80:5::1 fe80:5::1 0 - 0 > - - > lo0 16384 localhost ::1 0 - 0 > - - > lo0 16384 your-net localhost 74 - 758 > - - > wlan0 1500 00:1f:1f:3f:76:f3 873552 64 950672 > 7 0 > wlan0 1500 192.168.1.0 192.168.1.1 142745 - 937938 > - - > pflog 33152 0 0 242 > 0 0 > > which appears to be free of errors for em0. I also got the following > vmstat -i: > > > vmstat -i > interrupt total rate > irq1: atkbd0 8 0 > irq6: fdc0 7 0 > irq15: ata1 144 0 > irq16: em0 2456436 52 > irq17: ral0 3782116 80 > irq20: atapci2 217325 4 > irq21: hdac0 ohci0 11 0 > irq22: nfe0 ehci0 436597 9 > irq23: atapci1 206722 4 > cpu0: timer 94022466 2000 > cpu1: timer 94022098 2000 > Total 195143930 4151 > > And the following netstat: > > > sudo netstat -I em0 -indb > Name Mtu Network Address Ipkts Ierrs Ibytes > Opkts Oerrs Obytes Coll Drop > em0 1500 00:0e:0c:b7:71:44 5023101 0 3770654334 > 3978181 0 925661555 0 0 > em0 1500 192.168.0.0/2 192.168.0.1 5677843 - 4600314279 > 3873061 - 739695560 - - > > After starting a netcat transfer from .13 to .1, .13's system monitor > indicates that transfer over the local (outbound) interface starts out very > fast for a few seconds and then bottoms out. This iostat captures the same > pattern. ad4, ad6, ad8, and ad10 are the four disks sharing the base system > (geom mirror) and ZFS bulk filesystem. > > > iostat -n 5 -w 1 -c 30 > tty ad4 ad6 ad8 > ad10 da0 cpu > tin tout KB/t tps MB/s KB/t tps MB/s KB/t tps MB/s KB/t tps > MB/s KB/t tps MB/s us ni sy in id > 1 237 27.06 2 0.06 27.06 2 0.06 27.84 2 0.07 28.29 2 > 0.06 61.23 0 0.03 0 0 1 0 99 > 0 671 0.00 0 0.00 0.00 0 0.00 0.00 0 0.00 0.00 0 > 0.00 0.00 0 0.00 0 0 7 0 93 > 0 224 0.00 0 0.00 0.00 0 0.00 0.00 0 0.00 0.00 0 > 0.00 0.00 0 0.00 2 0 70 0 29 > 0 224 0.00 0 0.00 0.00 0 0.00 64.00 1 0.06 0.00 0 > 0.00 0.00 0 0.00 2 0 63 0 36 > 0 224 64.00 1 0.06 0.00 0 0.00 0.00 0 0.00 64.00 1 > 0.06 0.00 0 0.00 2 0 57 0 41 > 0 224 0.00 0 0.00 0.00 0 0.00 0.00 0 0.00 0.00 0 > 0.00 0.00 0 0.00 3 0 55 0 42 > 0 224 0.00 0 0.00 0.00 0 0.00 0.00 0 0.00 0.00 0 > 0.00 0.00 0 0.00 2 0 51 0 48 > 0 224 0.00 0 0.00 0.00 0 0.00 0.00 0 0.00 0.00 0 > 0.00 0.00 0 0.00 5 0 50 0 45 > 0 224 0.00 0 0.00 0.00 0 0.00 0.00 0 0.00 0.00 0 > 0.00 0.00 0 0.00 4 0 57 0 39 > 0 224 0.50 14 0.01 0.50 15 0.01 0.50 29 0.01 0.00 0 > 0.00 0.00 0 0.00 1 0 4 0 95 > 0 224 1.23 87 0.10 0.50 84 0.04 0.50 158 0.08 0.50 5 > 0.00 0.00 0 0.00 2 0 7 0 91 > 0 224 3.18 84 0.26 3.03 89 0.26 1.64 160 0.26 18.33 15 > 0.27 0.00 0 0.00 2 0 12 1 85 > 0 224 42.66 1167 48.63 42.70 1198 49.97 42.69 1870 77.96 42.66 1238 > 51.59 0.00 0 0.00 0 0 46 3 51 > 0 232 37.66 798 29.36 38.95 737 28.01 1.60 99 0.15 38.41 703 > 26.35 0.00 0 0.00 1 0 20 1 78 > 0 224 59.19 13 0.75 58.79 12 0.69 64.00 17 1.06 59.23 13 > 0.75 0.00 0 0.00 4 0 13 0 82 > 0 224 45.14 11 0.48 40.94 9 0.36 49.18 14 0.67 46.71 12 > 0.55 0.00 0 0.00 3 0 17 0 79 > 0 224 64.00 15 0.94 64.00 20 1.25 64.00 27 1.68 64.00 13 > 0.81 0.00 0 0.00 1 0 13 0 85 > 0 224 64.00 18 1.12 64.00 16 1.00 64.00 27 1.68 64.00 14 > 0.87 0.00 0 0.00 3 0 13 0 84 > 0 224 64.00 14 0.87 64.00 13 0.81 64.00 21 1.31 64.00 16 > 1.00 0.00 0 0.00 3 0 6 0 91 > 0 224 64.00 11 0.69 64.00 16 1.00 64.00 20 1.25 64.00 14 > 0.87 0.00 0 0.00 2 0 11 0 86 > 0 224 59.77 15 0.87 56.94 9 0.50 60.83 20 1.19 59.77 15 > 0.87 0.00 0 0.00 2 0 11 0 87 > 0 224 64.00 12 0.75 64.00 9 0.56 64.00 15 0.94 64.00 9 > 0.56 0.00 0 0.00 2 0 14 0 83 > 0 671 64.00 8 0.50 64.00 8 0.50 64.00 15 0.94 64.00 8 > 0.50 0.00 0 0.00 2 0 13 0 84 > 0 224 64.00 12 0.75 64.00 13 0.81 64.00 28 1.75 64.00 14 > 0.87 0.00 0 0.00 3 0 12 0 85 > 0 224 64.00 15 0.94 64.00 15 0.94 64.00 26 1.62 64.00 13 > 0.81 0.00 0 0.00 2 0 12 0 85 > 0 224 59.42 18 1.04 61.38 8 0.48 59.85 20 1.17 57.04 12 > 0.67 0.00 0 0.00 3 0 10 0 87 > 0 224 64.00 16 1.00 64.00 15 0.94 64.00 22 1.37 64.00 14 > 0.87 0.00 0 0.00 1 0 10 0 89 > 0 224 64.00 14 0.87 64.00 9 0.56 64.00 28 1.75 64.00 15 > 0.94 0.00 0 0.00 4 0 10 0 86 > 0 224 64.00 11 0.69 64.00 6 0.37 64.00 23 1.43 64.00 10 > 0.62 0.00 0 0.00 2 0 9 0 89 > 0 224 64.00 11 0.69 64.00 8 0.50 64.00 20 1.25 64.00 11 > 0.69 0.00 0 0.00 2 0 12 0 86 > > > Here's the iostat output during the transfer of a file from the ZFS > volume to an external HDD (da0): > > > iostat -n 5 -w 1 -c 30 > tty ad4 ad6 ad8 > ad10 da0 cpu > tin tout KB/t tps MB/s KB/t tps MB/s KB/t tps MB/s KB/t tps > MB/s KB/t tps MB/s us ni sy in id > 1 241 29.20 3 0.08 29.21 3 0.08 30.03 3 0.09 30.35 3 > 0.08 61.97 1 0.06 0 0 1 0 99 > 10 2167 64.00 2 0.12 0.00 0 0.00 64.00 1 0.06 0.00 0 > 0.00 0.00 0 0.00 1 0 7 0 92 > 0 224 0.00 0 0.00 64.00 2 0.12 0.00 0 0.00 64.00 3 > 0.19 0.00 0 0.00 2 0 13 0 85 > 12 961 44.45 144 6.24 43.24 150 6.32 42.81 152 6.34 45.06 143 > 6.28 62.21 382 23.22 2 0 19 1 78 > 0 335 45.67 163 7.26 43.89 174 7.44 43.28 175 7.38 46.06 170 > 7.63 63.07 453 27.91 3 0 32 1 64 > 0 335 32.70 209 6.66 32.09 213 6.66 32.66 221 7.03 32.85 211 > 6.75 63.10 398 24.53 6 0 24 2 68 > 0 335 45.22 167 7.36 43.16 172 7.23 45.68 170 7.57 43.88 176 > 7.53 63.08 457 28.15 4 0 38 1 57 > 0 335 45.25 157 6.93 43.95 166 7.11 45.94 163 7.30 43.69 167 > 7.11 62.88 433 26.61 4 0 35 1 60 > 0 335 44.04 171 7.34 45.36 174 7.69 46.46 169 7.65 43.66 172 > 7.32 63.09 462 28.47 2 0 36 3 60 > 0 335 43.38 179 7.57 44.68 170 7.40 45.68 170 7.57 43.39 178 > 7.53 63.08 455 28.03 3 0 44 1 52 > 0 335 43.53 173 7.34 45.01 164 7.19 44.18 169 7.28 44.73 165 > 7.19 63.10 465 28.66 1 0 24 4 70 > 0 335 43.26 178 7.50 45.27 172 7.59 43.85 181 7.73 45.40 172 > 7.61 62.98 468 28.78 7 0 37 1 55 > 0 335 45.18 170 7.49 44.54 171 7.42 44.66 182 7.92 45.71 175 > 7.80 62.94 455 27.97 2 0 30 2 66 > 0 335 44.25 171 7.38 44.52 169 7.33 45.94 174 7.79 43.35 178 > 7.52 63.07 449 27.66 3 0 37 1 59 > 0 335 45.77 165 7.36 43.42 171 7.24 45.62 166 7.38 43.86 179 > 7.65 63.08 458 28.22 4 0 36 1 59 > 0 349 46.11 99 4.45 43.89 105 4.49 47.30 106 4.89 44.82 109 > 4.76 63.17 287 17.73 3 0 35 1 61 > 0 335 64.00 5 0.31 64.00 9 0.56 64.00 8 0.50 64.00 7 > 0.44 0.00 0 0.00 3 0 29 0 69 > 0 335 64.00 10 0.62 64.00 3 0.19 64.00 15 0.94 64.00 12 > 0.75 0.00 0 0.00 3 0 22 0 75 > 0 335 64.00 2 0.12 64.00 4 0.25 64.00 6 0.37 64.00 6 > 0.37 0.00 0 0.00 6 0 30 0 64 > 0 335 0.00 0 0.00 0.00 0 0.00 0.00 0 0.00 64.00 1 > 0.06 0.00 0 0.00 4 0 36 0 60 > 0 335 64.00 2 0.12 64.00 4 0.25 64.00 10 0.62 64.00 6 > 0.37 0.00 0 0.00 4 0 20 0 75 > > and from the external HDD to the ZFS pool: > > > iostat -n 5 -w 1 -c 40 > tty ad4 ad6 ad8 > ad10 da0 cpu > tin tout KB/t tps MB/s KB/t tps MB/s KB/t tps MB/s KB/t tps > MB/s KB/t tps MB/s us ni sy in id > 1 241 28.86 3 0.07 28.87 3 0.07 29.70 3 0.08 30.03 3 > 0.08 61.79 1 0.05 0 0 1 0 99 > 16 2391 64.00 6 0.37 64.00 7 0.44 64.00 8 0.50 64.00 6 > 0.37 0.00 0 0.00 2 0 14 0 84 > 8 277 64.00 2 0.12 0.00 0 0.00 64.00 3 0.19 64.00 2 > 0.12 58.15 13 0.74 6 0 17 0 76 > 10 957 30.35 139 4.11 31.93 138 4.29 32.62 141 4.48 32.65 138 > 4.39 63.03 246 15.17 2 0 13 2 84 > 0 335 7.17 29 0.20 4.82 31 0.15 10.24 33 0.33 11.64 33 > 0.37 63.04 248 15.30 2 0 30 0 67 > 0 335 64.00 7 0.44 64.00 5 0.31 64.00 10 0.62 64.00 8 > 0.50 63.04 249 15.30 5 0 23 0 72 > 0 335 43.29 317 13.42 43.22 316 13.35 43.47 323 13.73 43.34 321 > 13.60 63.00 241 14.80 2 0 31 2 65 > 0 335 64.00 4 0.25 58.79 12 0.69 58.79 12 0.69 58.79 12 > 0.69 63.04 250 15.36 5 0 27 0 68 > 0 335 64.00 5 0.31 64.00 5 0.31 64.00 11 0.69 64.00 8 > 0.50 63.04 249 15.30 3 0 28 0 69 > 0 335 64.00 13 0.81 64.00 4 0.25 64.00 14 0.87 64.00 11 > 0.69 63.27 248 15.29 3 0 24 0 73 > 0 335 64.00 2 0.12 53.58 6 0.31 55.00 7 0.38 55.00 7 > 0.38 62.78 250 15.30 6 0 26 0 68 > 0 335 0.00 0 0.00 0.00 0 0.00 0.00 0 0.00 0.00 0 > 0.00 63.04 248 15.30 6 0 29 0 64 > 0 335 64.00 2 0.12 64.00 2 0.12 64.00 2 0.12 64.00 1 > 0.06 63.04 250 15.36 6 0 23 0 71 > 0 335 48.38 4 0.19 64.00 4 0.25 43.00 3 0.13 48.25 4 > 0.19 63.04 248 15.30 3 0 32 0 65 > 0 335 0.00 0 0.00 0.00 0 0.00 0.00 0 0.00 0.00 0 > 0.00 63.04 250 15.36 5 0 29 0 66 > 0 335 64.00 1 0.06 64.00 2 0.12 64.00 4 0.25 64.00 3 > 0.19 63.28 248 15.35 4 0 27 0 68 > 0 335 64.00 5 0.31 64.00 6 0.37 64.00 6 0.37 64.00 5 > 0.31 63.04 249 15.30 4 0 29 0 67 > 0 335 0.00 0 0.00 64.00 1 0.06 64.00 1 0.06 64.00 1 > 0.06 63.04 250 15.36 2 0 38 0 60 > 0 335 64.00 1 0.06 0.00 0 0.00 64.00 3 0.19 64.00 2 > 0.12 62.78 249 15.24 5 0 32 0 62 > 0 335 21.42 6 0.13 35.61 9 0.31 35.61 9 0.31 32.06 8 > 0.25 63.04 250 15.36 3 0 34 0 62 > 0 335 55.07 7 0.38 64.00 1 0.06 56.19 8 0.44 43.17 3 > 0.13 63.04 248 15.30 6 0 28 0 67 > 0 335 51.50 10 0.50 64.00 13 0.81 58.32 22 1.25 61.14 22 > 1.31 63.28 249 15.36 3 0 26 0 71 > 0 1006 55.91 11 0.60 54.00 15 0.79 59.32 19 1.10 56.50 20 > 1.10 63.04 250 15.36 4 0 27 0 69 > 0 335 60.25 10 0.59 61.66 16 0.96 62.46 24 1.46 62.39 23 > 1.40 63.04 249 15.30 1 0 27 0 72 > 0 335 57.65 10 0.56 57.65 10 0.56 60.26 17 1.00 60.03 16 > 0.94 63.04 250 15.36 3 0 24 0 73 > 0 335 64.00 8 0.50 64.00 7 0.44 64.00 14 0.87 64.00 16 > 1.00 63.04 249 15.30 3 0 29 0 68 > 0 335 64.00 10 0.62 64.00 8 0.50 64.00 16 1.00 64.00 15 > 0.94 62.78 249 15.30 1 0 29 0 70 > 0 335 64.00 6 0.37 64.00 14 0.87 64.00 21 1.31 64.00 20 > 1.25 63.28 248 15.35 3 0 25 0 72 > 0 335 64.00 10 0.62 64.00 8 0.50 64.00 17 1.06 64.00 17 > 1.06 63.04 250 15.36 1 0 27 0 71 > 0 335 64.00 9 0.56 64.00 13 0.81 64.00 23 1.43 64.00 22 > 1.37 63.04 249 15.30 4 0 24 0 71 > 0 335 64.00 9 0.56 64.00 11 0.69 64.00 20 1.25 64.00 21 > 1.31 63.04 250 15.36 2 0 25 0 72 > 0 419 64.00 9 0.56 64.00 7 0.44 64.00 15 0.94 64.00 13 > 0.81 62.68 197 12.03 3 0 23 0 74 > 0 335 59.54 14 0.81 64.00 3 0.19 60.32 17 1.00 64.00 18 > 1.12 0.00 0 0.00 4 0 25 0 71 > 0 335 44.50 63 2.73 45.35 75 3.31 46.15 76 3.42 44.82 69 > 3.01 0.00 0 0.00 4 0 48 0 48 > 0 335 42.74 1560 65.11 42.75 1651 68.93 42.74 2466 102.95 42.74 > 1634 68.20 0.00 0 0.00 1 0 53 5 40 > 0 350 42.69 1519 63.32 42.40 1431 59.25 41.90 623 25.48 42.24 1468 > 60.55 0.00 0 0.00 0 0 27 4 69 > 0 344 11.20 88 0.96 11.31 67 0.74 18.38 82 1.47 19.02 81 > 1.50 0.00 0 0.00 3 0 12 0 85 > 0 335 64.00 7 0.44 64.00 7 0.44 64.00 12 0.75 64.00 11 > 0.69 0.00 0 0.00 3 0 23 0 73 > 0 335 64.00 7 0.44 64.00 9 0.56 64.00 14 0.87 64.00 14 > 0.87 0.00 0 0.00 3 0 23 0 74 > 0 335 64.00 8 0.50 64.00 6 0.37 64.00 12 0.75 64.00 7 > 0.44 0.00 0 0.00 2 0 19 1 78 > > Many thanks for all the ideas, and I'll report back after a bit more > testing. > > Dave > > > On Mon, Jul 5, 2010 at 12:51 AM, Jeremy Chadwick > wrote: > >> On Sun, Jul 04, 2010 at 07:52:11PM -0500, David Warren wrote: >> > I've got a persistent problem with my LAN. I'm running a FreeBSD >> 8.0 >> > box as a home server performing the following functions for wired and >> > wireless networks: router; firewall; DHCP server; and file server. For >> what >> > it's worth, I've got ZFS up and running as the main filesystem. The >> > recurring issue is that file transfers from the FreeBSD box to computers >> on >> > the wired network (gigabit) start out fast and then become agonizingly >> > slow. I'm sharing home directories over Samba, and those transfers work >> > briefly and then tail off to a few kilobytes per second. The failure is >> > somewhat predicatable in that it tends to happen once a few hundred >> > megabytes have been transferred. >> >> Your system has 3 different network interfaces on it (em, ral, nfe), but >> you don't tell us across which interface the slow transfers happen. You >> also don't tell us which firewalling stack you're using (ipfw, ipfilter, >> pf). Let us know. >> >> I'm going to make the assumption that based on your "...on the wired >> network (gigabit)..." statement that the transfers are going across the >> em0 interface, but again, I'm not sure. >> >> Relevant interfaces (wlan0 is tied to ral0): >> >> > em0: flags=8843 metric 0 mtu >> 1500 >> > options=9b >> > ether 00:0e:0c:b7:71:44 >> > inet 192.168.0.1 netmask 0xffffff00 broadcast 192.168.0.255 >> > media: Ethernet autoselect (1000baseT ) >> > status: active >> > ral0: flags=8843 metric 0 mtu >> 2290 >> > ether 00:1f:1f:3f:76:f3 >> > media: IEEE 802.11 Wireless Ethernet autoselect mode 11g >> >> > status: running >> > nfe0: flags=8843 metric 0 mtu >> 1500 >> > options=8 >> > ether 00:01:29:d4:2d:6b >> > inet XXX.XXX.XXX.XXX netmask 0xfffffc00 broadcast >> 255.255.255.255 >> > media: Ethernet autoselect (100baseTX ) >> > status: active >> > [...] >> > wlan0: flags=8843 metric 0 mtu >> 1500 >> > ether 00:1f:1f:3f:76:f3 >> > inet 192.168.1.1 netmask 0xffffff00 broadcast 192.168.1.255 >> > media: IEEE 802.11 Wireless Ethernet autoselect mode 11g >> >> > status: running >> > ssid FreeBSD_AP channel 7 (2442 Mhz 11g) bssid 00:1f:1f:3f:76:f3 >> > country US authmode WPA privacy MIXED deftxkey 2 TKIP 2:128-bit >> > txpower 0 scanvalid 60 protmode CTS dtimperiod 1 -dfs >> >> First and foremost: is the problem specific to Samba? Can you reproduce >> the problem when using the FTP protocol? >> >> Are there any indications of problems in "dmesg" when the issue is >> happening? >> >> Can you provide output from "vmstat -i" while the problem is happening? >> >> Can you provide output from "pciconf -lvc"? Only interested in the >> sections relevant to the above devices. >> >> Can you provide contents of /etc/make.conf, /etc/sysctl.conf, and >> /boot/loader.conf? >> >> Have you looked at "netstat -I -indb" output during the slow >> transfers to see if there's any indication of problems, or some sort of >> "common rate" (transfer, etc.) >> >> Does disabling the firewalling stack improve things at all? >> >> Can the slowness be reproduced using benchmarks/netperf or only when >> using something that involves actual disk I/O? (To use netperf you'll >> need two FreeBSD boxes). If only disk I/O, then ZFS analysis might be >> needed (there are some performance adjustments that are often required). >> >> Focusing more on em0: >> >> Have you tried disabling rxcsum and txcsum (using ifconfig) to see if >> there's any improvement? I don't see TSO used by your interface, so >> that should rule out any problems with that feature. >> >> -- >> | Jeremy Chadwick jdc@parodius.com | >> | Parodius Networking http://www.parodius.com/ | >> | UNIX Systems Administrator Mountain View, CA, USA | >> | Making life hard for others since 1977. PGP: 4BD6C0CB | >> >> > > > -- > Post-doctoral Fellow > Neurology Department > University of Iowa Hospitals and Clinics > davideugenewarren@gmail.com > -- Post-doctoral Fellow Neurology Department University of Iowa Hospitals and Clinics davideugenewarren@gmail.com