From mboxrd@z Thu Jan 1 00:00:00 1970 From: Mirko Benz Subject: Re: parity check for read? Date: Wed, 04 Apr 2007 13:29:10 +0200 Message-ID: <46138C06.5020903@web.de> References: <461254DF.3050503@web.de> <17938.49705.840745.66635@notabene.brown> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: In-Reply-To: <17938.49705.840745.66635@notabene.brown> Sender: linux-raid-owner@vger.kernel.org To: Neil Brown Cc: Linux RAID List-Id: linux-raid.ids Neil, Exactly what I had in mind. Some vendors claim they do parity checking for reads. Technically it=20 should be possible for Linux RAID as well but is not implemented =96 co= rrect? Reliability data for unrecoverable read errors: - enterprise SAS drive (ST3300655SS): 1 in 10^16 bits transfered, ~ 1=20 error in 1,1 PB - enterprise SATA drive (ST3500630NS): 1 in 10^14 bits transfered, ~ 1=20 error in 11 TB =46or a single SATA drive @ 50 MB/s it take on average 2,7 days to=20 encounter an error. =46or a large RAID with several drives this becomes much lower or am I=20 viewing this wrong? Regards, Mirko Neil Brown schrieb: > On Tuesday April 3, mirko.benz@web.de wrote: > =20 >> Hi, >> >> Is parity calculation and validation for read operations supported? >> =20 > > I guess what you are asking is: > > With raid5, I would like the drive to handle a read request by > reading all the blocks in the stripe and checking the parity. If > the parity is correct, return the data blocks. If it is not, then > fail the read request. Is that possible? > > No, it is not. > > If you are really asking something else, please be more specific. > > NeilBrown > > =20 - To unsubscribe from this list: send the line "unsubscribe linux-raid" i= n the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html