From owner-freebsd-performance@FreeBSD.ORG Sun Aug 22 21:35:20 2004 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 800D416A4CE; Sun, 22 Aug 2004 21:35:20 +0000 (GMT) Received: from darkness.comp.waw.pl (darkness.comp.waw.pl [195.117.238.236]) by mx1.FreeBSD.org (Postfix) with ESMTP id 30A3143D2F; Sun, 22 Aug 2004 21:35:20 +0000 (GMT) (envelope-from pjd@darkness.comp.waw.pl) Received: by darkness.comp.waw.pl (Postfix, from userid 1009) id 180A1ACAE3; Sun, 22 Aug 2004 23:35:18 +0200 (CEST) Date: Sun, 22 Aug 2004 23:35:18 +0200 From: Pawel Jakub Dawidek To: Poul-Henning Kamp Message-ID: <20040822213518.GN30151@darkness.comp.waw.pl> References: <20040820193547.GZ30151@darkness.comp.waw.pl> <24879.1093031928@critter.freebsd.dk> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="krEeKW19zDoEvn6D" Content-Disposition: inline In-Reply-To: <24879.1093031928@critter.freebsd.dk> User-Agent: Mutt/1.4.2i X-PGP-Key-URL: http://people.freebsd.org/~pjd/pjd.asc X-OS: FreeBSD 5.2.1-RC2 i386 cc: Greg 'groggy' Lehey cc: Wilko Bulte cc: freebsd-performance@FreeBSD.org Subject: Re: RAID-3? (was: cvs commit: src MAINTAINERS) X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 22 Aug 2004 21:35:20 -0000 --krEeKW19zDoEvn6D Content-Type: text/plain; charset=iso-8859-2 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Fri, Aug 20, 2004 at 09:58:48PM +0200, Poul-Henning Kamp wrote: +> In message <20040820193547.GZ30151@darkness.comp.waw.pl>, Pawel Jakub Da= widek w +> rites: +>=20 +> >As you can see RAID5 is only faster in READ tests for 15 and 100 proces= ses +> >working in parallel. As I can see, RAID3 is faster in all the rest test= s. +> > +> >PS. I wonder about read optimization, so parity component can be also +> > used for reading in round-robin fashion... +>=20 +> I would far rather have an option to give me data-integrity checking ? =2E..Just want to note, that I implemented both algorithms ("round-robin reading" and "verify reading") and committed to HEAD. Enjoy:) --=20 Pawel Jakub Dawidek http://www.FreeBSD.org pjd@FreeBSD.org http://garage.freebsd.pl FreeBSD committer Am I Evil? Yes, I Am! --krEeKW19zDoEvn6D Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.4 (FreeBSD) iD8DBQFBKRGWForvXbEpPzQRAh2SAKCBGjt/+Z5GTygygmWQ1B8hB7VWowCguUNm OZ2Ab4kQvbVQTh1cSel9NHA= =8aS6 -----END PGP SIGNATURE----- --krEeKW19zDoEvn6D-- From owner-freebsd-performance@FreeBSD.ORG Mon Aug 23 09:55:08 2004 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id AD3F316A4CE; Mon, 23 Aug 2004 09:55:08 +0000 (GMT) Received: from pathfinder.roks.biz (roks.biz [82.207.80.37]) by mx1.FreeBSD.org (Postfix) with ESMTP id F3D5E43D41; Mon, 23 Aug 2004 09:55:05 +0000 (GMT) (envelope-from padla@roks.biz) Received: from admin.office.roks.biz (admin.office.roks.biz [192.168.100.103]) by pathfinder.roks.biz (8.12.11/8.12.11) with ESMTP id i7N9t1Uh072799; Mon, 23 Aug 2004 12:55:01 +0300 (EEST) (envelope-from padla@pathfinder.roks.biz) Received: from admin.office.roks.biz (localhost.roks.biz [127.0.0.1]) i7N9t2oO001089; Mon, 23 Aug 2004 12:55:02 +0300 (EEST) (envelope-from padla@admin.office.roks.biz) Received: (from padla@localhost) by admin.office.roks.biz (8.12.11/8.12.11/Submit) id i7N9t28Z001088; Mon, 23 Aug 2004 12:55:02 +0300 (EEST) (envelope-from padla) Date: Mon, 23 Aug 2004 12:55:02 +0300 From: Nikolay Pavlov To: freebsd-performance@freebsd.org Message-ID: <20040823095502.GA757@roks.biz> Mail-Followup-To: Nikolay Pavlov , freebsd-performance@freebsd.org, freebsd-current@freebsd.org Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.4.2.1i cc: freebsd-current@freebsd.org Subject: Poor results of network perfomance with 5.2.1-p9. X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 23 Aug 2004 09:55:08 -0000 Hi, FreeBSD users. I have made a smimple test of my network connection and have received rather modest results of network perfomance. Here is my test conditions: ------------------------------ |FreeBSD4.10-p2 CUSTOM kernel| |LANRealTek100Mb/s | |192.168.35.3 | ------------------------------ | | ------------------------------ |D-Link DWL-900AP+ | |Wireless11Mb/s | ------------------------------ | | ------------------------------ |Wireless11Mb/s | |D-Link DWL-900AP+ | ------------------------------ | | ------------------------------- |192.168.35.4 | |LANRealTek100Mb/s | |FreeBSD5.2.1-p9 CUSTOM kernel| ------------------------------- For my tests I use benchmarks/netperf (TCP client-server model) and net/pchar (don't need special server on the other side, test based on UDP/ICMP rtt). Results: 1. From 4.10 side: 1.1. pchar test using UDP ============================================================================= pathfinder# pchar 192.168.35.4 pchar to 192.168.35.4 (192.168.35.4) using UDP/IPv4 Using raw socket input Packet size increments from 32 to 1500 by 32 46 test(s) per repetition 32 repetition(s) per hop 0: 192.168.35.3 (pathfinder) Partial loss: 0 / 1472 (0%) Partial char: rtt = 1.678817 ms, (b = 0.002133 ms/B), r2 = 0.999667 stddev rtt = 0.004743, stddev b = 0.000006 Partial queueing: avg = 0.000310 ms (145 bytes) Hop char: rtt = 1.678817 ms, bw = 3750.725109 Kbps Hop queueing: avg = 0.000310 ms (145 bytes) 1: 192.168.35.4 (pioneer) Path length: 1 hops Path char: rtt = 1.678817 ms r2 = 0.999667 Path bottleneck: 3750.725109 Kbps ^^^^^^^^^^^^^^^^ Path pipe: 787 bytes Path queueing: average = 0.000310 ms (145 bytes) Start time: Mon Aug 23 11:34:40 2004 End time: Mon Aug 23 11:40:54 2004 1.2. netperf test using TCP_STREAM ============================================================================ pathfinder# /usr/local/netperf/netperf -v 2 -H 192.168.35.4 TCP STREAM TEST to 192.168.35.4 : histogram Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 131072 131072 131072 10.23 4.25 ^^^^^^^^^^^^ Alignment Offset Bytes Bytes Sends Bytes Recvs Local Remote Local Remote Xfered Per Per Send Recv Send Recv Send (avg) Recv (avg) 8 8 0 0 5.436e+06 132580.29 41 1492.12 3643 Maximum Segment Size (bytes) 1448 Histogram of time spent in send() call. TENTH_MSEC : 0: 0: 0: 0: 0: 0: 1: 0: 0: 0 UNIT_MSEC : 0: 0: 0: 0: 0: 0: 0: 0: 0: 0 TEN_MSEC : 0: 0: 0: 0: 0: 0: 0: 0: 0: 0 HUNDRED_MSEC : 0: 2: 34: 4: 0: 0: 0: 0: 0: 0 UNIT_SEC : 0: 0: 0: 0: 0: 0: 0: 0: 0: 0 TEN_SEC : 0: 0: 0: 0: 0: 0: 0: 0: 0: 0 >100_SECS: 0 HIST_TOTAL: 41 2. From 5.2.1 side: 2.1. pchar test using UDP ============================================================================ pioneer# pchar 192.168.35.3 pchar to 192.168.35.3 (192.168.35.3) using UDP/IPv4 Using raw socket input Packet size increments from 32 to 1500 by 32 46 test(s) per repetition 32 repetition(s) per hop 0: 192.168.35.4 (pioneer) Partial loss: 84 / 1472 (5%) Partial char: rtt = 1.621225 ms, (b = 0.002300 ms/B), r2 = 0.946789 stddev rtt = 0.066426, stddev b = 0.000082 Partial queueing: avg = 0.002433 ms (1057 bytes) Hop char: rtt = 1.621225 ms, bw = 3477.844143 Kbps Hop queueing: avg = 0.002433 ms (1057 bytes) 1: 192.168.35.3 (pathfinder) Path length: 1 hops Path char: rtt = 1.621225 ms r2 = 0.946789 Path bottleneck: 3477.844143 Kbps Path pipe: 704 bytes Path queueing: average = 0.002433 ms (1057 bytes) Start time: Mon Aug 23 11:20:24 2004 End time: Mon Aug 23 11:30:39 2004 2.2. netperf test using TCP_STREAM ============================================================================ pioneer# /usr/local/netperf/netperf -v 2 -H 192.168.35.3 TCP STREAM TEST to 192.168.35.3 : histogram Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 131072 131072 131072 10.75 0.64 ^^^^^^^^^^^^^ Alignment Offset Bytes Bytes Sends Bytes Recvs Local Remote Local Remote Xfered Per Per Send Recv Send Recv Send (avg) Recv (avg) 8 8 0 0 8.601e+05 143352.00 6 1455.35 591 Maximum Segment Size (bytes) 1448 Histogram of time spent in send() call. TENTH_MSEC : 0: 0: 0: 0: 0: 0: 1: 0: 0: 0 UNIT_MSEC : 0: 0: 0: 0: 0: 0: 0: 0: 0: 0 TEN_MSEC : 0: 0: 0: 0: 0: 0: 0: 0: 0: 0 HUNDRED_MSEC : 0: 0: 0: 0: 0: 0: 0: 1: 3: 0 UNIT_SEC : 0: 0: 0: 0: 0: 0: 1: 0: 0: 0 TEN_SEC : 0: 0: 0: 0: 0: 0: 0: 0: 0: 0 >100_SECS: 0 HIST_TOTAL: 6 As you can see there is almost no diffrence between pchar udp tests (3750.725109 Kbps against 3477.844143 Kbps), but in netperf test 4.10 in 10.23 sec has made 41 send() (4.25Mb/s) against 6! send() in 10.75 sec (0.64Mb/s). What is the secret of so poor perfomance? Could you please help me in correct understanding of this test? P.S. Some additional information: There is no WITNESS, INVARIANTS, INVARIANT_SUPPORT, SMP in 5.2.1 kernel. ipfw_type=OPEN in 5.2.1 and corresponding pass rule in top off firewall ruleset in 4.10. tcp.sendspace and recvspace = 131072 in both OS. In test I use "clear" conditions, but in real work this connection is ecrypted by IPsec so my working productivity is much more slower. If you need more info just let me know. Best regards and sorry for my english, Nikolay Pavlov. From owner-freebsd-performance@FreeBSD.ORG Mon Aug 23 16:43:17 2004 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 791F716A4D7; Mon, 23 Aug 2004 16:43:17 +0000 (GMT) Received: from ylpvm43.prodigy.net (ylpvm43-ext.prodigy.net [207.115.57.74]) by mx1.FreeBSD.org (Postfix) with ESMTP id 397C643D5A; Mon, 23 Aug 2004 16:43:17 +0000 (GMT) (envelope-from kris@obsecurity.org) Received: from obsecurity.dyndns.org (adsl-67-115-74-195.dsl.lsan03.pacbell.net [67.115.74.195]) i7NGhHnA030858; Mon, 23 Aug 2004 12:43:20 -0400 Received: by obsecurity.dyndns.org (Postfix, from userid 1000) id ECF7653631; Mon, 23 Aug 2004 09:43:09 -0700 (PDT) Date: Mon, 23 Aug 2004 09:43:09 -0700 From: Kris Kennaway To: Nikolay Pavlov , freebsd-performance@freebsd.org, freebsd-current@freebsd.org Message-ID: <20040823164309.GA11331@xor.obsecurity.org> References: <20040823095502.GA757@roks.biz> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="Nq2Wo0NMKNjxTN9z" Content-Disposition: inline In-Reply-To: <20040823095502.GA757@roks.biz> User-Agent: Mutt/1.4.2.1i Subject: Re: Poor results of network perfomance with 5.2.1-p9. X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 23 Aug 2004 16:43:17 -0000 --Nq2Wo0NMKNjxTN9z Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Mon, Aug 23, 2004 at 12:55:02PM +0300, Nikolay Pavlov wrote: > Hi, FreeBSD users. > I have made a smimple test of my network connection and have=20 > received rather modest results of network perfomance. Here is my=20 > test conditions: [...] Try again with 5.3-BETA, network performance has been an area of major work. Kris --Nq2Wo0NMKNjxTN9z Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.5 (FreeBSD) iD8DBQFBKh6cWry0BWjoQKURAttUAKCHcx7TfFnsW+4CsfJHp1pFO3u3NgCgwDxf TWJW8bcRdXN4WMQZW8sPxqM= =LpTQ -----END PGP SIGNATURE----- --Nq2Wo0NMKNjxTN9z-- From owner-freebsd-performance@FreeBSD.ORG Mon Aug 23 17:12:19 2004 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D019916A4CE for ; Mon, 23 Aug 2004 17:12:19 +0000 (GMT) Received: from web.matik.com.br (web.matik.com.br [200.208.167.3]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8986843D48 for ; Mon, 23 Aug 2004 17:12:18 +0000 (GMT) (envelope-from tec@mega.net.br) Received: from wsrv.matik.com.br (201-0-9-226.dsl.telesp.net.br [201.0.9.226] (may be forged)) by web.matik.com.br (8.12.11/8.12.11) with ESMTP id i7NHDtXm092319 for ; Mon, 23 Aug 2004 14:13:56 -0300 (BRT) (envelope-from tec@mega.net.br) Received: from bon04.mega.net.br (bon04.mega.net.br [200.152.81.44]) by wsrv.matik.com.br (8.12.11/8.12.11) with ESMTP id i7NHD6c5057141 for ; Mon, 23 Aug 2004 14:13:06 -0300 (BRT) (envelope-from tec@mega.net.br) From: Tec Meganet Date: Mon, 23 Aug 2004 14:12:00 -0300 User-Agent: KMail/1.6.2 To: freebsd-performance@freebsd.org MIME-Version: 1.0 Content-Disposition: inline Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Message-Id: <200408231412.00327.tec@mega.net.br> X-Virus-Scanned: clamd / ClamAV version devel-20040712, clamav-milter version 0.70k X-Virus-Scanned: clamd / ClamAV version 0.73, clamav-milter version 0.73a on wsrv.matik.com.br X-Virus-Status: Clean Subject: Fwd: Re: Poor results of network perfomance with 5.2.1-p9. X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 23 Aug 2004 17:12:19 -0000 ---------- Forwarded Message ---------- Subject: Re: Poor results of network perfomance with 5.2.1-p9. Date: Monday 23 August 2004 14:10 From: Infomatik To: Nikolay Pavlov , freebsd-performance@freebsd.org, freebsd-current@freebsd.org I am not so sure if your test is giving any usable result for FreeBSD. It seems you are using some wireless equipment between both servers what means that the throuput depends on this APs first. Any correctly cabled 10/100 NIC should give higher throughput than any available 802.11b network equipment. Even if you have a clean radio connection (> 25Db SNR on each side) between both APs, low(est) noise and a PP correctly configured you never get full duplex , one direction ever is slower. Also it depends on the distance between both points I believe. There are also several issues with the wireless equipments, may be you never get some usable cicles from an AP when it is highly used by another connection already. May be you first check your radio connection and before running a test between both server you check pinging the remote AP (even flooding) to see how capable your radio is. I guess you never get more than 1-1.5MB/s bi-directional between both servers. You may get sustained transfer rates of 3-6MB/s in one direction only but I do not know this APs enough to say it exactly. If you need higher traffic you should use Tsunami WL-PP-bridges or 802.11a/b/g cards configured as adhoc instead of this cheap APs connected to your NICs H On Monday 23 August 2004 06:55, Nikolay Pavlov wrote: > Hi, FreeBSD users. > I have made a smimple test of my network connection and have > received rather modest results of network perfomance. Here is my > test conditions: > ------------------------------ > > |FreeBSD4.10-p2 CUSTOM kernel| > |LANRealTek100Mb/s | > |192.168.35.3 | > > ------------------------------ > ------------------------------ > > |D-Link DWL-900AP+ | > |Wireless11Mb/s | > > ------------------------------ ------------------------------------------------------- From owner-freebsd-performance@FreeBSD.ORG Mon Aug 23 17:11:12 2004 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 2217B16A4CE; Mon, 23 Aug 2004 17:11:12 +0000 (GMT) Received: from web.matik.com.br (web.matik.com.br [200.208.167.3]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7830843D1F; Mon, 23 Aug 2004 17:11:03 +0000 (GMT) (envelope-from info@matik.com.br) Received: from wsrv.matik.com.br (201-0-9-226.dsl.telesp.net.br [201.0.9.226] (may be forged)) by web.matik.com.br (8.12.11/8.12.11) with ESMTP id i7NHCYJb092310; Mon, 23 Aug 2004 14:12:36 -0300 (BRT) (envelope-from info@matik.com.br) Received: from bon04.mega.net.br (bon04.mega.net.br [200.152.81.44]) by wsrv.matik.com.br (8.12.11/8.12.11) with ESMTP id i7NHBgbI057117; Mon, 23 Aug 2004 14:11:42 -0300 (BRT) (envelope-from info@matik.com.br) From: Infomatik Organization: Infomatik To: Nikolay Pavlov , freebsd-performance@freebsd.org, freebsd-current@freebsd.org Date: Mon, 23 Aug 2004 14:10:36 -0300 User-Agent: KMail/1.6.2 References: <20040823095502.GA757@roks.biz> In-Reply-To: <20040823095502.GA757@roks.biz> MIME-Version: 1.0 Content-Disposition: inline Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Message-Id: <200408231410.36111.info@matik.com.br> X-Virus-Scanned: clamd / ClamAV version devel-20040712, clamav-milter version 0.70k X-Virus-Scanned: clamd / ClamAV version 0.73, clamav-milter version 0.73a on wsrv.matik.com.br X-Virus-Status: Clean X-Mailman-Approved-At: Mon, 23 Aug 2004 18:12:13 +0000 Subject: Re: Poor results of network perfomance with 5.2.1-p9. X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 23 Aug 2004 17:11:12 -0000 I am not so sure if your test is giving any usable result for FreeBSD. It seems you are using some wireless equipment between both servers what means that the throuput depends on this APs first. Any correctly cabled 10/100 NIC should give higher throughput than any available 802.11b network equipment. Even if you have a clean radio connection (> 25Db SNR on each side) between both APs, low(est) noise and a PP correctly configured you never get full duplex , one direction ever is slower. Also it depends on the distance between both points I believe. There are also several issues with the wireless equipments, may be you never get some usable cicles from an AP when it is highly used by another connection already. May be you first check your radio connection and before running a test between both server you check pinging the remote AP (even flooding) to see how capable your radio is. I guess you never get more than 1-1.5MB/s bi-directional between both servers. You may get sustained transfer rates of 3-6MB/s in one direction only but I do not know this APs enough to say it exactly. If you need higher traffic you should use Tsunami WL-PP-bridges or 802.11a/b/g cards configured as adhoc instead of this cheap APs connected to your NICs H On Monday 23 August 2004 06:55, Nikolay Pavlov wrote: > Hi, FreeBSD users. > I have made a smimple test of my network connection and have > received rather modest results of network perfomance. Here is my > test conditions: > ------------------------------ > > |FreeBSD4.10-p2 CUSTOM kernel| > |LANRealTek100Mb/s | > |192.168.35.3 | > > ------------------------------ > ------------------------------ > > |D-Link DWL-900AP+ | > |Wireless11Mb/s | > > ------------------------------ > From owner-freebsd-performance@FreeBSD.ORG Tue Aug 24 07:04:11 2004 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 9C5A516A4CE; Tue, 24 Aug 2004 07:04:11 +0000 (GMT) Received: from pathfinder.roks.biz (roks.biz [82.207.80.37]) by mx1.FreeBSD.org (Postfix) with ESMTP id B20C043D1D; Tue, 24 Aug 2004 07:04:09 +0000 (GMT) (envelope-from padla@roks.biz) Received: from admin.office.roks.biz (admin.office.roks.biz [192.168.100.103]) by pathfinder.roks.biz (8.12.11/8.12.11) with ESMTP id i7O746uq082266; Tue, 24 Aug 2004 10:04:07 +0300 (EEST) (envelope-from padla@pathfinder.roks.biz) Received: from admin.office.roks.biz (localhost.roks.biz [127.0.0.1]) i7O746BS000500; Tue, 24 Aug 2004 10:04:06 +0300 (EEST) (envelope-from padla@admin.office.roks.biz) Received: (from padla@localhost) by admin.office.roks.biz (8.12.11/8.12.11/Submit) id i7O744HY000499; Tue, 24 Aug 2004 10:04:05 +0300 (EEST) (envelope-from padla) Date: Tue, 24 Aug 2004 10:04:04 +0300 From: Nikolay Pavlov To: Infomatik Message-ID: <20040824070404.GA218@roks.biz> Mail-Followup-To: Nikolay Pavlov , Infomatik , freebsd-performance@freebsd.org, freebsd-current@freebsd.org References: <20040823095502.GA757@roks.biz> <200408231410.36111.info@matik.com.br> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <200408231410.36111.info@matik.com.br> User-Agent: Mutt/1.4.2.1i cc: freebsd-performance@freebsd.org cc: freebsd-current@freebsd.org Subject: Re: Poor results of network perfomance with 5.2.1-p9. X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Aug 2004 07:04:11 -0000 Hi, FreeBSD users. On Monday, 23 August 2004 at 14:10:36 -0300, Infomatik wrote: > I am not so sure if your test is giving any usable result for FreeBSD. > > It seems you are using some wireless equipment between both servers what means > that the throuput depends on this APs first. > Any correctly cabled 10/100 NIC should give higher throughput than any > available 802.11b network equipment. > Even if you have a clean radio connection (> 25Db SNR on each side) between > both APs, low(est) noise and a PP correctly configured you never get full > duplex , one direction ever is slower. Also it depends on the distance > between both points I believe. > There are also several issues with the wireless equipments, may be you never > get some usable cicles from an AP when it is highly used by another > connection already. > > May be you first check your radio connection and before running a test between > both server you check pinging the remote AP (even flooding) to see how > capable your radio is. I guess you never get more than 1-1.5MB/s > bi-directional between both servers. You may get sustained transfer rates of > 3-6MB/s in one direction only but I do not know this APs enough to say it > exactly. > > If you need higher traffic you should use Tsunami WL-PP-bridges or 802.11a/b/g > cards configured as adhoc instead of this cheap APs connected to your NICs You are right. This damned chinese AP again and again let down me. I have found a huge amount of drops on send queue in 5.2.1 side. When I have drop speed down to 2 Mb/s on both AP results of test were leveled on a mark 1.35 Mb/s. Sorry for that noise and thank's for your time. Best regards, Nikolay Pavlov.