From owner-freebsd-questions Tue Jun 27 23:26:41 2000 Delivered-To: freebsd-questions@freebsd.org Received: from mail1.noc0.hsacorp.net (mail1.noc0.hsacorp.net [208.247.171.140]) by hub.freebsd.org (Postfix) with ESMTP id AAA7837B7CD for ; Tue, 27 Jun 2000 23:26:34 -0700 (PDT) (envelope-from jconner@enterit.com) Received: from [24.216.177.145] (HELO CONCON.enterit.com) by mail1.noc0.hsacorp.net (CommuniGate Pro SMTP 3.2.4) with ESMTP id 14844981 for freebsd-questions@FreeBSD.ORG; Wed, 28 Jun 2000 02:26:33 -0400 Message-Id: <4.3.2.7.2.20000628023139.026784a0@mail.enterit.com> X-Sender: jconner@mail.enterit.com X-Mailer: QUALCOMM Windows Eudora Version 4.3.2 Date: Wed, 28 Jun 2000 02:37:03 -0400 To: freebsd-questions@FreeBSD.ORG From: Jim Conner Subject: ARGH! :) Ongoing bandwidth throttling issue...need help! Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed Sender: owner-freebsd-questions@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG Is there anything or any reason anyone can think of that would keep my machine from using its full capacity bandwidth? Its a 3.4REL machine using a 10/100 BT NIC plugged into a 10/100 switch and it transfers almost like its on a 1 BT connection =P It is absolutely driving me crazy! Im using the Via Rhine driver (DLink card) and no NATD or ipfw. Here is what systeat -tcp gives me: /0 /1 /2 /3 /4 /5 /6 /7 /8 /9 /10 Load Average ||| TCP Connections TCP Packets 415 connections initiated 164407 total packets sent 2553 connections accepted 77256 - data 2904 connections established 4458 - data (retransmit) 1909 connections dropped 61361 - ack-only 36 - in embryonic state 8 - window probes 4 - on retransmit timeout 18552 - window updates 2 - by keepalive 1 - urgent data only 0 - from listen queue 2769 - control 0 - resends by PMTU discovery TCP Timers 271346 total packets received 57225 potential rtt updates 208681 - in sequence 54477 - successful 1504 - completely duplicate 54575 delayed acks sent 109 - with some duplicate data 2925 retransmit timeouts 2835 - out-of-order 0 persist timeouts 7246 - duplicate acks 16 keepalive probes 65256 - acks 109 - timeouts 2 - window probes (hist 516)# sysctl -a | grep net.inet.tcp net.inet.tcp.rfc1323: 1 net.inet.tcp.rfc1644: 0 net.inet.tcp.mssdflt: 512 net.inet.tcp.rttdflt: 3 net.inet.tcp.keepidle: 14400 net.inet.tcp.keepintvl: 150 net.inet.tcp.sendspace: 16384 net.inet.tcp.recvspace: 16384 net.inet.tcp.keepinit: 150 net.inet.tcp.log_in_vain: 0 net.inet.tcp.delayed_ack: 1 net.inet.tcp.pcbcount: 16 net.inet.tcp.always_keepalive: 0 Is there a way for the ftp daemon to throttle its throughput? Because this problem is *most* apparent on incoming ftp sessions for my users. - Jim - Jim ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Today's errors, in contrast: Windows - "Invalid page fault in module kernel32.dll at 0032:A16F2935" UNIX - "segmentation fault - core dumped" Humanous Beingsus - "OOPS, I've fallen and I can't get up" ------------------------------- Jim Conner NOTJames jconner@enterit.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message