From owner-freebsd-performance@FreeBSD.ORG Wed Jan 17 00:26:05 2007 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id CD98A16A412; Wed, 17 Jan 2007 00:26:05 +0000 (UTC) (envelope-from ivoras@fer.hr) Received: from ls405.t-com.hr (ls405.t-com.hr [195.29.150.135]) by mx1.freebsd.org (Postfix) with ESMTP id 566E513C448; Wed, 17 Jan 2007 00:26:05 +0000 (UTC) (envelope-from ivoras@fer.hr) Received: from ls242.t-com.hr (ls242.t-com.hr [195.29.150.134]) by ls405.t-com.hr (Postfix) with ESMTP id D4601143AB7; Wed, 17 Jan 2007 00:53:18 +0100 (CET) Received: from ls242.t-com.hr (localhost.localdomain [127.0.0.1]) by ls242.t-com.hr (Qmlai) with ESMTP id BC72310F805B; Wed, 17 Jan 2007 00:53:18 +0100 (CET) Received: from ls242.t-com.hr (localhost.localdomain [127.0.0.1]) by ls242.t-com.hr (Qmlai) with ESMTP id A654510F8059; Wed, 17 Jan 2007 00:53:18 +0100 (CET) X-Envelope-Sender-Info: qNMqIwJL6pMxrLsv6Bv6QwbAS50Yr5Qqas2jRir/hsbKYW+NL8qJhtwp0O8kWM3b X-Envelope-Sender: ivoras@fer.hr Received: from [10.0.0.101] (83-131-108-141.adsl.net.t-com.hr [83.131.108.141]) by ls242.t-com.hr (Qmali) with ESMTP id 4443C6C003C; Wed, 17 Jan 2007 00:53:17 +0100 (CET) Message-ID: <45AD6651.5010107@fer.hr> Date: Wed, 17 Jan 2007 00:57:05 +0100 From: Ivan Voras User-Agent: Thunderbird 1.5.0.9 (Windows/20061207) MIME-Version: 1.0 To: "Wood, Russell" References: In-Reply-To: X-Enigmail-Version: 0.94.1.2 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig21B123D9444D806EC45519D7" Cc: freebsd-performance@freebsd.org, freebsd-questions@freebsd.org Subject: Re: Very Poor Raid Card Performance X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 17 Jan 2007 00:26:06 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig21B123D9444D806EC45519D7 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Wood, Russell wrote: > I have an LSI MegaRaid with three drives at RAID 5: works a > god-damn-treat. I don't know what my throughput is on RAID 5 but RAID 0= > was fast (70MB/s+). Mine was RAID5. Hmm, oops, it wasn't LSI but HP/Compaq CISS, battery backed, SATA on SAS. da0 at ciss0 bus 0 target 0 lun 0 da0: Fixed Direct Access SCSI-0 device da0: 135.168MB/s transfers da0: 476886MB (976662896 512 byte sectors: 255H 32S/T 65535C) > Were you doing these tests a few hours after initializing the array, by= > any chance? If so, then the poor performance could be because the array= > was `in build' while you were using it, and therefore you'd get very > poor performance. Yes, I observed BIOS status. Here's a typical run of bonnie++: Version 1.93c ------Sequential Output------ --Sequential Input- --Random- Concurrency 1 -Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks-- Machine Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP /sec %CP xxx.com 2500M 358 99 13446 4 7068 2 559 96 97548 23 300.0 10 Latency 23236us 848ms 488ms 191ms 214ms 175ms My reading of iostat during 'dd' is that writes perform good until the on-controller cache gets filled, then it slows down: tty da0 pass0 cpu tin tout KB/t tps MB/s KB/t tps MB/s us ni sy in id =2E.. 0 60 0.00 0 0.00 0.00 0 0.00 0 0 0 0 100 1 64 127.93 217 27.08 0.00 0 0.00 0 0 5 0 95 0 61 125.92 400 49.14 0.00 0 0.00 0 0 2 1 98 0 61 128.00 107 13.36 0.00 0 0.00 0 0 2 0 98 0 61 128.00 107 13.36 0.00 0 0.00 0 0 2 0 98 0 61 128.00 104 12.99 0.00 0 0.00 0 0 2 0 98 Cache size is 128MB, 75% dedicated to write caching. --------------enig21B123D9444D806EC45519D7 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.4 (MingW32) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org iD8DBQFFrWZYldnAQVacBcgRAnHEAJ4vXIxQL0kUSVnhyCCWH47HTisKjQCdFLBx LLKpARmf0xI5udqqNOznODg= =ajTN -----END PGP SIGNATURE----- --------------enig21B123D9444D806EC45519D7-- From owner-freebsd-performance@FreeBSD.ORG Fri Jan 19 11:38:12 2007 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 1208616A416 for ; Fri, 19 Jan 2007 11:38:12 +0000 (UTC) (envelope-from garcol@postino.it) Received: from abraham.elitel.it (vdisk2.elitel.it [212.34.224.151]) by mx1.freebsd.org (Postfix) with SMTP id 6DBD813C448 for ; Fri, 19 Jan 2007 11:38:09 +0000 (UTC) (envelope-from garcol@postino.it) Received: (qmail 4021 invoked by uid 65534); 19 Jan 2007 11:11:08 -0000 X-Spam-Checker-Version: SpamAssassin on abraham.elitel.it X-Spam-Level: X-Spam-Status: No, score=-1.6 required=5.2 tests=BAYES_00,NO_REAL_NAME autolearn=no Received: from 212.63.96.97 ([212.63.96.97]) by www.postino.punto.it (IMP) with HTTP for ; Fri, 19 Jan 2007 12:11:08 +0100 Message-ID: <1169205068.45b0a74c17e88@www.postino.punto.it> Date: Fri, 19 Jan 2007 12:11:08 +0100 From: garcol@postino.it To: freebsd-performance@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit User-Agent: Internet Messaging Program (IMP) 3.2.2 X-Originating-IP: 212.63.96.97 Subject: Performance on udp socket X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 19 Jan 2007 11:38:12 -0000 Hi, I've seen a packets drop with high rate of radius authentication request (UDP 150 byte) The software is radiator (perl), and it seems not to be dependent on CPU speed. How is possible to avoid this with a more accurate tuning? #netstat -s -p udp udp: 1917 datagrams received 0 with incomplete header 0 with bad data length field 0 with bad checksum 0 with no checksum 0 dropped due to no socket 0 broadcast/multicast datagrams dropped due to no socket 557 dropped due to full socket buffers 0 not for hashed pcb 1360 delivered 1226 datagrams output #netstat -na Active Internet connections (including servers) Proto Recv-Q Send-Q Local Address Foreign Address (state) udp4 5162 0 *.1813 *.* udp4 13615 0 *.1812 *.* #sysctl -a ... udpcb: 192, 1992, 8, 34, 26713 ... net.inet.udp.maxdgram: 9216 net.inet.udp.recvspace: 42080 ... kern.ipc.maxsockbuf: 1048576 kern.ipc.nmbclusters: 1488 #netstat -s -p udp udp: 4333 datagrams received 0 with incomplete header 0 with bad data length field 0 with bad checksum 0 with no checksum 0 dropped due to no socket 0 broadcast/multicast datagrams dropped due to no socket 724 dropped due to full socket buffers 0 not for hashed pcb 3609 delivered 3582 datagrams output udp: 6366 datagrams received 0 with incomplete header 0 with bad data length field 0 with bad checksum 1 with no checksum 4 dropped due to no socket 8 broadcast/multicast datagrams dropped due to no socket 724 dropped due to full socket buffers 0 not for hashed pcb 6293 delivered 6315 datagrams output netstat -m 158/720/5952 mbufs in use (current/peak/max): 135 mbufs allocated to data 23 mbufs allocated to packet headers 128/368/1488 mbuf clusters in use (current/peak/max) 916 Kbytes allocated to network (20% of mb_map in use) 0 requests for memory denied 0 requests for memory delayed 0 calls to protocol drain routines