From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailout.micron.com ([137.201.242.129]) by bombadil.infradead.org with esmtps (Exim 4.80.1 #2 (Red Hat Linux)) id 1YYHVM-0004Ro-Il for linux-mtd@lists.infradead.org; Wed, 18 Mar 2015 17:11:41 +0000 From: "Jeff Lauruhn (jlauruhn)" To: Richard Weinberger , Boris Brezillon , Andrea Marson Subject: RE: RFC: detect and manage power cut on MLC NAND (linux-mtd Digest, Vol 144, Issue 70) Message-ID: <0D23F1ECC880A74392D56535BCADD7354973EA09@NTXBOIMBX03.micron.com> References: <0D23F1ECC880A74392D56535BCADD7354973E51A@NTXBOIMBX03.micron.com> <55093B1E.2050805@dave.eu> <20150318100645.1babecfd@bbrezillon> <55096A75.8080207@nod.at> In-Reply-To: <55096A75.8080207@nod.at> Content-Language: en-US Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Cc: Andrea Scian , "linux-mtd@lists.infradead.org" , "dedekind1@gmail.com" List-Id: Linux MTD discussion mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Date: Wed, 18 Mar 2015 17:11:46 -0000 Disturb is a block level affect, but in operation data is often layout in c= ontinuous blocks, so if one block is seeing a lot of reads or P/E cycles, t= here's a high probability the blocks around it are also seeing very similar= read and P/E patterns.=20 Jeff Lauruhn NAND Application Engineer Embedded Business Unit -----Original Message----- From: Richard Weinberger [mailto:richard@nod.at]=20 Sent: Wednesday, March 18, 2015 5:07 AM To: Boris Brezillon; Andrea Marson Cc: Jeff Lauruhn (jlauruhn); linux-mtd@lists.infradead.org; Andrea Scian; d= edekind1@gmail.com Subject: Re: RFC: detect and manage power cut on MLC NAND (linux-mtd Digest= , Vol 144, Issue 70) Am 18.03.2015 um 10:06 schrieb Boris Brezillon: >> 1) IIUC read/program disturb effects exhibit at block level. >> In a typical embedded linux systems there are software parts -=20 >> bootloader, kernel image etc. - that virtually are never changed=20 >> (almost >> ...) but are read many times. Other parts - application libraries,=20 >> log files etc. - are read and wrote many times instead. >> If these two kinds of software are stored in different MTD partitions=20 >> - ket's say partition A for bootloader, kernel etc. and partition B=20 >> for application libraries, log files etc. - can we say that=20 >> read/write operations performed on partition B have no disturb effects o= n partition A? >=20 > AFAIK, read/write disturb effects only occur on pages of the same=20 > block, so we shouldn't see bitflips on partition A caused by=20 > read/write on partition B. I already saw corruptions on nearby blocks but I'm not sure if really plain= read disturb was the root cause as this NAND chips showed in general funny= symptoms. Jeff, can you tell us more? Thanks, //richard