From jsomoza@pandasoftware.es Mon Feb 27 10:03:02 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id CF2119DC9E3 for ; Mon, 27 Feb 2006 06:03:02 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 92318-06 for ; Mon, 27 Feb 2006 06:03:03 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from bilbao.pandasoftware.es (unknown [62.14.249.71]) by postgresql.org (Postfix) with ESMTP id CB4989DC9DD for ; Mon, 27 Feb 2006 06:02:58 -0400 (AST) Received: from escorpexh05.pandasoftware.local (escorpext02 [192.168.100.182]) by bilbao.pandasoftware.es (Postfix) with ESMTP id AB9301B3708 for ; Mon, 27 Feb 2006 11:02:39 +0100 (CET) Received: from ESCORPEXH03.pandasoftware.local ([172.16.0.70]) by escorpexh05.pandasoftware.local with Microsoft SMTPSVC(6.0.3790.211); Mon, 27 Feb 2006 11:02:59 +0100 Received: escorpexh03.pandasoftware.local 172.16.0.73 from 172.16.128.4 172.16.128.4 via HTTP with MS-WebStorage 6.5.6944 Received: from pndsoft by escorpexh03.pandasoftware.local; 27 Feb 2006 11:03:43 +0100 Subject: fsync and battery-backed caches From: Javier Somoza To: pgsql-performance@postgresql.org Content-Type: multipart/alternative; boundary="=-CXS6MWlqw4nzwTflLotv" Message-Id: <1141034594.1556.15.camel@pndsoft> Mime-Version: 1.0 X-Mailer: Ximian Evolution 1.4.6 Date: Mon, 27 Feb 2006 11:03:14 +0100 X-OriginalArrivalTime: 27 Feb 2006 10:02:59.0817 (UTC) FILETIME=[FD4EF590:01C63B84] X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=2.502 required=5 tests=[HTML_MESSAGE=0.001, RAZOR2_CF_RANGE_51_100=0.5, RAZOR2_CF_RANGE_E8_51_100=1.5, RAZOR2_CHECK=0.5, UNPARSEABLE_RELAY=0.001] X-Spam-Score: 2.502 X-Spam-Level: ** X-Archive-Number: 200602/409 X-Sequence-Number: 17395 --=-CXS6MWlqw4nzwTflLotv Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable Hi all Is it secure to disable fsync havin battery-backed disk cache? =20 Thx Javier Somoza Oficina de Direcci=F3n Estrat=E9gica mailto:jsomoza@pandasoftware.es Panda Software Buenos Aires, 12 48001 BILBAO - ESPA=D1A Tel=E9fono: 902 24 365 4 Fax: 94 424 46 97 http://www.pandasoftware.es Panda Software, una de las principales compa=F1=EDas desarrolladoras de soluciones de protecci=F3n contra virus e intrusos, presenta su nueva familia de soluciones. Todos los usuarios de ordenadores, desde las redes m=E1s grandes a los dom=E9sticos, disponen ahora de nuevos productos con excelentes tecnolog=EDas de seguridad. M=E1s informaci=F3n en: http://www.pandasoftware.es/productos =20 =A1Prot=E9jase ahora contra virus e intrusos! Pruebe gratis nuestros productos en http://www.pandasoftware.es/descargas/ =20 =20 =20 =20 =20 =20 =20 =20 --=-CXS6MWlqw4nzwTflLotv Content-Type: text/html; charset=utf-8
        Hi all

        Is it secure to disable fsync havin battery-backed disk cache?
               
        Thx


Javier Somoza
Oficina de Dirección Estratégica

mailto:jsomoza@pandasoftware.es

Panda Software
Buenos Aires, 12
48001 BILBAO - ESPAÑA
Teléfono: 902 24 365 4
Fax:  94 424 46 97

http://www.pandasoftware.es
Panda Software, una de las principales compañías desarrolladoras de soluciones de protección contra virus e intrusos, presenta su nueva familia de soluciones. Todos los usuarios de ordenadores, desde las redes más grandes a los domésticos, disponen ahora de nuevos productos con excelentes tecnologías de seguridad. Más información en: http://www.pandasoftware.es/productos

¡Protéjase ahora contra virus e intrusos! Pruebe gratis nuestros productos en http://www.pandasoftware.es/descargas/








--=-CXS6MWlqw4nzwTflLotv-- From tino@wildenhain.de Mon Feb 27 10:13:09 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id D428C9DC9A8 for ; Mon, 27 Feb 2006 06:13:09 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 93836-05 for ; Mon, 27 Feb 2006 06:13:11 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from service-web.de (p15093784.pureserver.info [217.160.106.224]) by postgresql.org (Postfix) with ESMTP id CAB179DC825 for ; Mon, 27 Feb 2006 06:13:07 -0400 (AST) Received: from [10.100.1.50] (074-016-066-080.eggenet.de [80.66.16.74]) by service-web.de (Postfix) with ESMTP id 5463920002A; Mon, 27 Feb 2006 11:13:09 +0100 (CET) Message-ID: <4402D0A9.7080705@wildenhain.de> Date: Mon, 27 Feb 2006 11:12:57 +0100 From: Tino Wildenhain User-Agent: Mozilla Thunderbird 1.0.6 (X11/20050929) X-Accept-Language: de-DE, de, en-us, en MIME-Version: 1.0 To: Javier Somoza Cc: pgsql-performance@postgresql.org Subject: Re: fsync and battery-backed caches References: <1141034594.1556.15.camel@pndsoft> In-Reply-To: <1141034594.1556.15.camel@pndsoft> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.103 required=5 tests=[AWL=0.103] X-Spam-Score: 0.103 X-Spam-Level: X-Archive-Number: 200602/410 X-Sequence-Number: 17396 Javier Somoza schrieb: > > Hi all > > Is it secure to disable fsync havin battery-backed disk cache? > > Thx > No. fsync moves the data from OS memory cache to disk-adaptor cache which is required to benefit from battery backup. If this data is written to the plates immediately depends on settings of your disk adaptor card. Regards Tino From jnasby@pervasive.com Tue Feb 28 00:22:25 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id 52F139DC800 for ; Mon, 27 Feb 2006 20:22:25 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 39001-06 for ; Mon, 27 Feb 2006 20:22:28 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from noel.decibel.org (noel.decibel.org [67.100.216.10]) by postgresql.org (Postfix) with ESMTP id 1E9259DC8AA for ; Mon, 27 Feb 2006 20:22:22 -0400 (AST) Received: by noel.decibel.org (Postfix, from userid 1001) id 2B1C75645D; Mon, 27 Feb 2006 18:22:26 -0600 (CST) Received: (hashcash-sendmail, from uid 1001); Mon, 27 Feb 2006 18:22:23 -0600 Date: Mon, 27 Feb 2006 18:22:23 -0600 From: "Jim C. Nasby" To: Tino Wildenhain Cc: Javier Somoza , pgsql-performance@postgresql.org Subject: Re: fsync and battery-backed caches Message-ID: <20060228002223.GW82012@pervasive.com> References: <1141034594.1556.15.camel@pndsoft> <4402D0A9.7080705@wildenhain.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4402D0A9.7080705@wildenhain.de> X-Operating-System: FreeBSD 6.0-RELEASE-p4 amd64 X-Distributed: Join the Effort! http://www.distributed.net User-Agent: Mutt/1.5.11 X-Hashcash: 1:20:060228:tino@wildenhain.de::jfHX0Y3fAICZPhhb:0000000000000000000 000000000000000000000000AGSr X-Hashcash: 1:20:060228:jsomoza@pandasoftware.es::M7gJzIgtYVyEhNeP:0000000000000 0000000000000000000000002qCl X-Hashcash: 1:20:060228:pgsql-performance@postgresql.org::d9YObfzMqiiHPeUN:00000 00000000000000000000000099Cg X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.105 required=5 tests=[AWL=0.105] X-Spam-Score: 0.105 X-Spam-Level: X-Archive-Number: 200602/423 X-Sequence-Number: 17409 On Mon, Feb 27, 2006 at 11:12:57AM +0100, Tino Wildenhain wrote: > Javier Somoza schrieb: > > > > Hi all > > > > Is it secure to disable fsync havin battery-backed disk cache? > > > > Thx > > > No. fsync moves the data from OS memory cache to disk-adaptor > cache which is required to benefit from battery backup. More importantly, in guarantees that data is committed to non-volatile storage in such a way that PostgreSQL can recover from a crash without corruption. If you have a battery-backed controller and turn on write caching you shouldn't see much effect from fsync anyway. -- Jim C. Nasby, Sr. Engineering Consultant jnasby@pervasive.com Pervasive Software http://pervasive.com work: 512-231-6117 vcard: http://jim.nasby.net/pervasive.vcf cell: 512-569-9461 From pgman@candle.pha.pa.us Tue Feb 28 01:06:15 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id DCB689DC850 for ; Mon, 27 Feb 2006 21:06:15 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 44058-09 for ; Mon, 27 Feb 2006 21:06:18 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from candle.pha.pa.us (candle.pha.pa.us [70.90.9.53]) by postgresql.org (Postfix) with ESMTP id 3C0549DC823 for ; Mon, 27 Feb 2006 21:06:13 -0400 (AST) Received: (from pgman@localhost) by candle.pha.pa.us (8.11.6/8.11.6) id k1S16DK16068; Mon, 27 Feb 2006 20:06:13 -0500 (EST) From: Bruce Momjian Message-Id: <200602280106.k1S16DK16068@candle.pha.pa.us> Subject: Re: fsync and battery-backed caches In-Reply-To: <20060228002223.GW82012@pervasive.com> To: "Jim C. Nasby" Date: Mon, 27 Feb 2006 20:06:13 -0500 (EST) CC: Tino Wildenhain , Javier Somoza , pgsql-performance@postgresql.org X-Mailer: ELM [version 2.4ME+ PL121 (25)] MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset=US-ASCII X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.393 required=5 tests=[AWL=-0.107, RAZOR2_CHECK=0.5] X-Spam-Score: 0.393 X-Spam-Level: X-Archive-Number: 200602/424 X-Sequence-Number: 17410 Jim C. Nasby wrote: > On Mon, Feb 27, 2006 at 11:12:57AM +0100, Tino Wildenhain wrote: > > Javier Somoza schrieb: > > > > > > Hi all > > > > > > Is it secure to disable fsync havin battery-backed disk cache? > > > > > > Thx > > > > > No. fsync moves the data from OS memory cache to disk-adaptor > > cache which is required to benefit from battery backup. > > More importantly, in guarantees that data is committed to non-volatile > storage in such a way that PostgreSQL can recover from a crash without > corruption. > > If you have a battery-backed controller and turn on write caching you > shouldn't see much effect from fsync anyway. We do mention battery-backed cache in our docs: http://www.postgresql.org/docs/8.1/static/wal.html If it is unclear, please let us know. -- Bruce Momjian http://candle.pha.pa.us SRA OSS, Inc. http://www.sraoss.com + If your life is a hard drive, Christ can be your backup. + From jsomoza@pandasoftware.es Tue Feb 28 08:18:57 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id DF1E09DC881 for ; Tue, 28 Feb 2006 04:18:57 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 52176-10 for ; Tue, 28 Feb 2006 04:18:58 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from bilbao.pandasoftware.es (unknown [62.14.249.71]) by postgresql.org (Postfix) with ESMTP id C8C2B9DC832 for ; Tue, 28 Feb 2006 04:18:53 -0400 (AST) Received: from escorpexh05.pandasoftware.local (escorpext02 [192.168.100.182]) by bilbao.pandasoftware.es (Postfix) with ESMTP id 17E1A1B3609; Tue, 28 Feb 2006 09:18:32 +0100 (CET) Received: from ESCORPEXH03.pandasoftware.local ([172.16.0.70]) by escorpexh05.pandasoftware.local with Microsoft SMTPSVC(6.0.3790.211); Tue, 28 Feb 2006 09:18:52 +0100 Received: escorpexh03.pandasoftware.local 172.16.0.73 from 172.16.3.16 172.16.3.16 via HTTP with MS-WebStorage 6.5.6944 Received: from pndsoft by escorpexh03.pandasoftware.local; 28 Feb 2006 09:19:36 +0100 Subject: Re: fsync and battery-backed caches From: Javier Somoza To: Bruce Momjian Cc: "Jim C. Nasby" , Tino Wildenhain , pgsql-performance@postgresql.org In-Reply-To: <200602280106.k1S16DK16068@candle.pha.pa.us> References: <200602280106.k1S16DK16068@candle.pha.pa.us> Content-Type: multipart/alternative; boundary="=-P6PHUsQ2bd+SYl9D3G8K" Message-Id: <1141114775.1555.7.camel@pndsoft> Mime-Version: 1.0 X-Mailer: Ximian Evolution 1.4.6 Date: Tue, 28 Feb 2006 09:19:36 +0100 X-OriginalArrivalTime: 28 Feb 2006 08:18:52.0431 (UTC) FILETIME=[9BFD41F0:01C63C3F] X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=2.605 required=5 tests=[AWL=0.103, HTML_MESSAGE=0.001, RAZOR2_CF_RANGE_51_100=0.5, RAZOR2_CF_RANGE_E8_51_100=1.5, RAZOR2_CHECK=0.5, UNPARSEABLE_RELAY=0.001] X-Spam-Score: 2.605 X-Spam-Level: ** X-Archive-Number: 200602/427 X-Sequence-Number: 17413 --=-P6PHUsQ2bd+SYl9D3G8K Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable Yeah, i saw it. It says full-page-writes can be disabled without problems. But i wanted to confirm fsync cannot be disabled although i have battery. Thanks!! :-) > We do mention battery-backed cache in our docs: >=20 > http://www.postgresql.org/docs/8.1/static/wal.html >=20 > If it is unclear, please let us know. Javier Somoza Oficina de Direcci=F3n Estrat=E9gica mailto:jsomoza@pandasoftware.es Panda Software Buenos Aires, 12 48001 BILBAO - ESPA=D1A Tel=E9fono: 902 24 365 4 Fax: 94 424 46 97 http://www.pandasoftware.es Panda Software, una de las principales compa=F1=EDas desarrolladoras de soluciones de protecci=F3n contra virus e intrusos, presenta su nueva familia de soluciones. Todos los usuarios de ordenadores, desde las redes m=E1s grandes a los dom=E9sticos, disponen ahora de nuevos productos con excelentes tecnolog=EDas de seguridad. M=E1s informaci=F3n en: http://www.pandasoftware.es/productos =20 =A1Prot=E9jase ahora contra virus e intrusos! Pruebe gratis nuestros productos en http://www.pandasoftware.es/descargas/ =20 =20 =20 =20 =20 =20 =20 =20 --=-P6PHUsQ2bd+SYl9D3G8K Content-Type: text/html; charset=utf-8
            Yeah, i saw it. It says full-page-writes can be disabled without problems.
            But i wanted to confirm fsync cannot be disabled although i have battery.

            Thanks!!   :-)
We do mention battery-backed cache in our docs:

	http://www.postgresql.org/docs/8.1/static/wal.html

If it is unclear, please let us know.
Javier Somoza
Oficina de Dirección Estratégica

mailto:jsomoza@pandasoftware.es

Panda Software
Buenos Aires, 12
48001 BILBAO - ESPAÑA
Teléfono: 902 24 365 4
Fax:  94 424 46 97

http://www.pandasoftware.es
Panda Software, una de las principales compañías desarrolladoras de soluciones de protección contra virus e intrusos, presenta su nueva familia de soluciones. Todos los usuarios de ordenadores, desde las redes más grandes a los domésticos, disponen ahora de nuevos productos con excelentes tecnologías de seguridad. Más información en: http://www.pandasoftware.es/productos

¡Protéjase ahora contra virus e intrusos! Pruebe gratis nuestros productos en http://www.pandasoftware.es/descargas/








--=-P6PHUsQ2bd+SYl9D3G8K-- From jnasby@pervasive.com Tue Feb 28 17:23:52 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id 019D59DC847 for ; Tue, 28 Feb 2006 13:23:52 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 67785-03 for ; Tue, 28 Feb 2006 13:23:51 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from noel.decibel.org (noel.decibel.org [67.100.216.10]) by postgresql.org (Postfix) with ESMTP id C0ED39DC876 for ; Tue, 28 Feb 2006 13:23:50 -0400 (AST) Received: by noel.decibel.org (Postfix, from userid 1001) id 8553656467; Tue, 28 Feb 2006 11:23:35 -0600 (CST) Received: (hashcash-sendmail, from uid 1001); Tue, 28 Feb 2006 11:23:34 -0600 Date: Tue, 28 Feb 2006 11:23:34 -0600 From: "Jim C. Nasby" To: Javier Somoza Cc: Bruce Momjian , Tino Wildenhain , pgsql-performance@postgresql.org Subject: Re: fsync and battery-backed caches Message-ID: <20060228172334.GV82012@pervasive.com> References: <200602280106.k1S16DK16068@candle.pha.pa.us> <1141114775.1555.7.camel@pndsoft> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1141114775.1555.7.camel@pndsoft> X-Operating-System: FreeBSD 6.0-RELEASE-p4 amd64 X-Distributed: Join the Effort! http://www.distributed.net User-Agent: Mutt/1.5.11 X-Hashcash: 1:20:060228:jsomoza@pandasoftware.es::rN9zQXol/y+JVsv0:0000000000000 0000000000000000000000003yOg X-Hashcash: 1:20:060228:pgman@candle.pha.pa.us::/1ARJvwQ7c9qtW8y:000000000000000 0000000000000000000000004hEP X-Hashcash: 1:20:060228:tino@wildenhain.de::dIStB0nu5qwMTS3u:0000000000000000000 00000000000000000000000032aR X-Hashcash: 1:20:060228:pgsql-performance@postgresql.org::6vE8B2EeR2ytWbtW:00000 00000000000000000000000033fd X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=1.355 required=5 tests=[AWL=-1.145, RAZOR2_CF_RANGE_51_100=0.5, RAZOR2_CF_RANGE_E8_51_100=1.5, RAZOR2_CHECK=0.5] X-Spam-Score: 1.355 X-Spam-Level: * X-Archive-Number: 200602/436 X-Sequence-Number: 17422 Actually, you can't assume that a BBU means you can safely disable full-page-writes. Depending on the controller, it's still possible to end up with partially written pages. BTW, if your mailer makes doing so convenient, it would be nice to trim down your .signature; note that it's about 3x longer than the email you actually sent. On Tue, Feb 28, 2006 at 09:19:36AM +0100, Javier Somoza wrote: > > Yeah, i saw it. It says full-page-writes can be disabled > without problems. > But i wanted to confirm fsync cannot be disabled although i > have battery. > > Thanks!! :-) > > > > > We do mention battery-backed cache in our docs: > > > > http://www.postgresql.org/docs/8.1/static/wal.html > > > > If it is unclear, please let us know. > > Javier Somoza > Oficina de Direcci?n Estrat?gica > mailto:jsomoza@pandasoftware.es > > Panda Software > Buenos Aires, 12 > 48001 BILBAO - ESPA?A > Tel?fono: 902 24 365 4 > Fax: 94 424 46 97 > http://www.pandasoftware.es > Panda Software, una de las principales compa??as desarrolladoras de > soluciones de protecci?n contra virus e intrusos, presenta su nueva > familia de soluciones. Todos los usuarios de ordenadores, desde las > redes m?s grandes a los dom?sticos, disponen ahora de nuevos productos > con excelentes tecnolog?as de seguridad. M?s informaci?n en: > http://www.pandasoftware.es/productos > > > > ?Prot?jase ahora contra virus e intrusos! Pruebe gratis nuestros > productos en http://www.pandasoftware.es/descargas/ > > > > > > > > > -- Jim C. Nasby, Sr. Engineering Consultant jnasby@pervasive.com Pervasive Software http://pervasive.com work: 512-231-6117 vcard: http://jim.nasby.net/pervasive.vcf cell: 512-569-9461 From jsomoza@pandasoftware.es Tue Feb 28 17:54:18 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id DCD539DCB9E for ; Tue, 28 Feb 2006 13:54:18 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 75669-07 for ; Tue, 28 Feb 2006 13:54:17 -0400 (AST) X-Greylist: delayed 00:27:13.243499 by SQLgrey- Received: from bilbao.pandasoftware.es (unknown [194.30.100.202]) by postgresql.org (Postfix) with ESMTP id 3A0D39DCB5D for ; Tue, 28 Feb 2006 13:54:14 -0400 (AST) Received: from escorpexh05.pandasoftware.local (escorpext02 [192.168.100.182]) by bilbao.pandasoftware.es (Postfix) with ESMTP id D8B741B3923; Tue, 28 Feb 2006 18:26:29 +0100 (CET) Received: from ESCORPEXH03.pandasoftware.local ([172.16.0.70]) by escorpexh05.pandasoftware.local with Microsoft SMTPSVC(6.0.3790.211); Tue, 28 Feb 2006 18:26:50 +0100 Received: escorpexh03.pandasoftware.local 172.16.0.73 from 172.16.3.16 172.16.3.16 via HTTP with MS-WebStorage 6.5.6944 Received: from pndsoft by escorpexh03.pandasoftware.local; 28 Feb 2006 18:27:34 +0100 Subject: Re: fsync and battery-backed caches From: Javier Somoza To: "Jim C. Nasby" Cc: Bruce Momjian , Tino Wildenhain , pgsql-performance@postgresql.org In-Reply-To: <20060228172334.GV82012@pervasive.com> References: <200602280106.k1S16DK16068@candle.pha.pa.us> <1141114775.1555.7.camel@pndsoft> <20060228172334.GV82012@pervasive.com> Content-Type: multipart/alternative; boundary="=-J3lZlvR3YpaghtVpGv1Q" Message-Id: <1141147654.1555.46.camel@pndsoft> Mime-Version: 1.0 X-Mailer: Ximian Evolution 1.4.6 Date: Tue, 28 Feb 2006 18:27:34 +0100 X-OriginalArrivalTime: 28 Feb 2006 17:26:50.0234 (UTC) FILETIME=[28AFDDA0:01C63C8C] X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.002 required=5 tests=[HTML_MESSAGE=0.001, UNPARSEABLE_RELAY=0.001] X-Spam-Score: 0.002 X-Spam-Level: X-Archive-Number: 200602/438 X-Sequence-Number: 17424 --=-J3lZlvR3YpaghtVpGv1Q Content-Type: text/plain Content-Transfer-Encoding: 7bit Ups sorry. > Actually, you can't assume that a BBU means you can safely disable > full-page-writes. Depending on the controller, it's still possible to > end up with partially written pages. > > BTW, if your mailer makes doing so convenient, it would be nice to trim > down your .signature; note that it's about 3x longer than the email you > actually sent. --=-J3lZlvR3YpaghtVpGv1Q Content-Type: text/html; charset=utf-8
            Ups sorry.

Actually, you can't assume that a BBU means you can safely disable
full-page-writes. Depending on the controller, it's still possible to
end up with partially written pages.

BTW, if your mailer makes doing so convenient, it would be nice to trim
down your .signature; note that it's about 3x longer than the email you
actually sent.

--=-J3lZlvR3YpaghtVpGv1Q-- From jnasby@pervasive.com Tue Feb 28 21:09:27 2006 X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id 4EDBA9DC876 for ; Tue, 28 Feb 2006 17:09:27 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 22079-02 for ; Tue, 28 Feb 2006 17:09:28 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from noel.decibel.org (noel.decibel.org [67.100.216.10]) by postgresql.org (Postfix) with ESMTP id 2D1859DC869 for ; Tue, 28 Feb 2006 17:09:24 -0400 (AST) Received: by noel.decibel.org (Postfix, from userid 1001) id 97FB156468; Tue, 28 Feb 2006 15:09:26 -0600 (CST) Received: (hashcash-sendmail, from uid 1001); Tue, 28 Feb 2006 15:09:25 -0600 Date: Tue, 28 Feb 2006 15:09:25 -0600 From: "Jim C. Nasby" To: Javier Somoza Cc: Bruce Momjian , Tino Wildenhain , pgsql-performance@postgresql.org Subject: Re: fsync and battery-backed caches Message-ID: <20060228210925.GX82012@pervasive.com> References: <200602280106.k1S16DK16068@candle.pha.pa.us> <1141114775.1555.7.camel@pndsoft> <20060228172334.GV82012@pervasive.com> <1141147654.1555.46.camel@pndsoft> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1141147654.1555.46.camel@pndsoft> X-Operating-System: FreeBSD 6.0-RELEASE-p4 amd64 X-Distributed: Join the Effort! http://www.distributed.net User-Agent: Mutt/1.5.11 X-Hashcash: 1:20:060228:jsomoza@pandasoftware.es::+Rthp3+Yh3ew90zE:0000000000000 00000000000000000000000086wA X-Hashcash: 1:20:060228:pgman@candle.pha.pa.us::UVjVwg7k7GbFeToP:000000000000000 0000000000000000000000000FJw X-Hashcash: 1:20:060228:tino@wildenhain.de::AXGOC7fo9JyI+dYX:0000000000000000000 0000000000000000000000003gj/ X-Hashcash: 1:20:060228:pgsql-performance@postgresql.org::nbAiatcPdGzqkHk1:00000 0000000000000000000000000XT6 X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.108 required=5 tests=[AWL=0.108] X-Spam-Score: 0.108 X-Spam-Level: X-Archive-Number: 200602/444 X-Sequence-Number: 17430 Ok, you absolutely can't guarantee you won't get partial page writes then. A UPS buys you no more data safety than being plugged directly into the wall. UPS's fail. People trip over cords. Breakers fail. Even if you have multiple power supplies on multiple circuits fed by different UPS's you can *still* have unexpected power failures. The 'master' for distributed.net had exactly that happen recently; the two breakers feeding it (from 2 seperate UPS's) failed simultaneously. In a nutshell, having a server on a UPS is notthing at all like having a BBU on the raid controller: commiting to the BBU is essentially the same as committing to the drives, unless the BBU runs out of power before the server has power restored, or fails in some similar fasion. But because there's many fewer parts involved, such a failure of the BBU is far less likely than a failure up-stream. So, if you want performance, get a controller with a BBU and allow it to cache writes. While you're at it, try and get one that will automatically disable write caching if the BBU fails for some reason. On Tue, Feb 28, 2006 at 06:27:34PM +0100, Javier Somoza wrote: > > Ups sorry. > > > > Actually, you can't assume that a BBU means you can safely disable > > full-page-writes. Depending on the controller, it's still possible to > > end up with partially written pages. > > > > BTW, if your mailer makes doing so convenient, it would be nice to trim > > down your .signature; note that it's about 3x longer than the email you > > actually sent. > > -- Jim C. Nasby, Sr. Engineering Consultant jnasby@pervasive.com Pervasive Software http://pervasive.com work: 512-231-6117 vcard: http://jim.nasby.net/pervasive.vcf cell: 512-569-9461