Date: Tue, 15 Feb 2011 10:20:32 +0000 From: krad <kraduk@gmail.com> To: FreeBSD <freebsd-questions@freebsd.org> Subject: Re: FreeBSD and SSD drives Message-ID: <AANLkTimXr6X3tpUegogP-2vTVTYw9g6T5hLvvNJL8Zg1@mail.gmail.com> In-Reply-To: <20110214235507.GA66554@guilt.hydra> References: <AANLkTim-u5Nd8NQ_t555o5qYwRd5Ltf6Ud5rYD_G2x7N@mail.gmail.com> <20110213092353.GA58281@guilt.hydra> <20110213073801.65518b9c@scorpio> <20110213131051.00001ebf@unknown> <20110213085805.72f0132d@scorpio> <20110213164748.GB60459@guilt.hydra> <AANLkTi=NOUgFC3iOesKkb9%2BgLEpAAKdvcMh8Am99im%2Bi@mail.gmail.com> <20110213181223.GD55168@orange.esperance-linux.co.uk> <AANLkTinGpj1Eb2FAybP%2BDOWUs48LeHC0d6=bMRZbby%2Bx@mail.gmail.com> <7583C9E5-EA30-4C75-BDF7-C1BA123B8334@mac.com> <20110214235507.GA66554@guilt.hydra>
next in thread | previous in thread | raw e-mail | index | archive | help
On 14 February 2011 23:55, Chad Perrin <perrin@apotheon.com> wrote: > On Mon, Feb 14, 2011 at 03:32:30PM -0800, Chuck Swiger wrote: >> >> >From what I understand (a quick review of wikipedia helps :), modern >> >flash cards are now typically rated for 100K writes, include ECC bits >> >to actually correct or at least detect errors and try to remap bad >> >blocks to unused blocks, and implement wear-leveling techniques of >> >varying degrees of effectiveness. >> >> Regards, >> -- >> -Chuck >> >> PS: Reposted from a NetBSD thread, was >> <D5AF2A8E-FEF0-467E-BE4A-B01243E21F1A@mac.com>.... > > Just make sure you double-check the rating for the specific SSD storage > hardware you're actually using. =A0The fact the state of the art is bette= r > now than it was does not mean you are using state of the art hardware. > > -- > Chad Perrin [ original content licensed OWL: http://owl.apotheon.org ] > We have the main DB server on our portal running directly on some of these http://www.oracle.com/us/043970.pdf. Its a high volume site so we really needed the speed. They are supposed to last 6 years but we shall see. We have the 1 TB version, all mirrored giving us 500 GB. We run solaris 10 on top with zfs, so we should see any data corruption very quickly if it starts to happen. The cluster has been running for about a year now
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?AANLkTimXr6X3tpUegogP-2vTVTYw9g6T5hLvvNJL8Zg1>