X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (neptune.hub.org [200.46.204.2]) by svr1.postgresql.org (Postfix) with ESMTP id CBDB9D1B46F for ; Tue, 25 Nov 2003 19:05:05 +0000 (GMT) Received: from svr1.postgresql.org ([200.46.204.71]) by localhost (neptune.hub.org [200.46.204.2]) (amavisd-new, port 10024) with ESMTP id 16929-08 for ; Tue, 25 Nov 2003 15:04:33 -0400 (AST) Received: from node-4024d1a2.mdw.onnet.us.uu.net (node-40241d3a.mdw.onnet.us.uu.net [64.36.29.58]) by svr1.postgresql.org (Postfix) with ESMTP id B3A1FD1B45F for ; Tue, 25 Nov 2003 15:04:33 -0400 (AST) Received: from localhost (localhost [127.0.0.1]) by node-4024d1a2.mdw.onnet.us.uu.net (Postfix) with ESMTP id 2BA7637D0B for ; Tue, 25 Nov 2003 12:59:54 -0600 (CST) Subject: Re: Maximum Possible Insert Performance? From: Suchandra Thapa To: pgsql-performance@postgresql.org In-Reply-To: <87brr11c44.fsf@stark.dyndns.tv> References: <200311240925.58070.josh@agliodbs.com> <200311241004.37969.josh@agliodbs.com> <87brr11c44.fsf@stark.dyndns.tv> Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-by9rSZ6nTuoexoHmUfLz" Organization: Message-Id: <1069786793.19104.33.camel@hepcat> Mime-Version: 1.0 X-Mailer: Ximian Evolution 1.2.2 (1.2.2-5) Date: 25 Nov 2003 12:59:54 -0600 X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200311/298 X-Sequence-Number: 4858 --=-by9rSZ6nTuoexoHmUfLz Content-Type: text/plain Content-Transfer-Encoding: quoted-printable On Mon, 2003-11-24 at 19:16, Greg Stark wrote: > William Yu writes: >=20 > > > You're right, though, mirroring a solid state drive is pretty pointle= ss; if > > > power fails, both mirrors are dead. > >=20 > > Actually no. Solid state memory is non-volatile. They retain data even = without > > power. >=20 > Note that flash ram only has a finite number of write cycles before it fa= ils. >=20 > On the other hand that might not be so bad for WAL which writes sequentia= lly, > you can easily calculate how close you are to the maximum. For things like > heap storage or swap it's awful as you can get hot spots that get written= to > thousands of times before the rest of the space is used. I could be wrong, but I was under the impression that most of the newer flash disks tended to spread writes out over the drive so that hotspots are minimized.=20=20 --=20 Suchandra Thapa --=-by9rSZ6nTuoexoHmUfLz Content-Type: application/pgp-signature; name=signature.asc Content-Description: This is a digitally signed message part -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.1 (GNU/Linux) iD8DBQA/w6ap6nShCjt5AZIRAii6AKCfCeSjosYKgxEJi628ftZwpqO7JACeMGUl fr3exMlo0k2CFdP57BGevPs= =S6Ro -----END PGP SIGNATURE----- --=-by9rSZ6nTuoexoHmUfLz--