The doc are inconsistent with the term sector. At one point the refer to sectors as groups of blocks, suggesting that blocks are sectors.
Then in 1.5.1: The 512-byte sector size of the SD Card is the same as that in an IDE magnetic disk drive.... And in 1.5.2. Defect and Error Management : SD Cards contain a sophisticated defect and error management system. This system is analogous to the systems found in magnetic disk drives and in many cases offers enhancements. For instance, disk drives do not typically perform a read after write to confirm the data is written correctly because of the performance penalty that would be incurred. SD Cards do a read after write under margin conditions to verify that the data is written correctly. In the rare case that a bit is found to be defective, SD Cards replace this bad bit with a spare bit within the sector header. If necessary, SD Cards will even replace the entire sector with a spare sector. This is completely transparent to the host and does not consume any user data space. 2009/3/27 Bobby Clark <bcl...@airmail.net> > Hi Michael, > > > > Did a little bit more checking. The smallest block size appears to be 512 > bytes. The more common block size is 1024 bytes to 2048 bytes for the > larger cards. At the time of the document in 2003 they were saying that for > a 4 mega byte area they allotted a 3 percent amount of cells or 234 512 byte > blocks as a buffer or wear leveling area. First they wear level over the > 4 MB zone. Then as sections hit the wear out limit they take them out of > service and mark them as used up. Once the 234 blocks are gone the part > will fail critically. At that point the part will not be able to hide the > faults from you. If you look at the fist page of SanDisk patent 6,594,183 > it shows a nice diagram of the address translation table to block scheme. > The diagram is also on page 4 figure 2. There are some other SanDisk > patents that clearly show the SD card arrangement in more detail, but the > one noted has some good diagrams. In some of the original SD cards they > actually had a controller/interface chip coupled to an off the shelf flash > chip. Think of the controller as an address translation engine more than > anything else. > > > Bobby > > ----- Original Message ----- > *From:* Michael Schnell <mschn...@lumino.de> > *To:* uClinux development list <uclinux-dev@uclinux.org> > *Sent:* Friday, March 27, 2009 6:42 AM > *Subject:* Re: [uClinux-dev] SD card corruption upon reboot and de-power > > > Not exactly. The 4MB zone is just the area that they give 3 percent > additional memory cells. Each 4MB zone would have the extra 3 percent. > > I can't imagine how this is supposed to work, as I don't believe that such > a 4MB area can be partly erased, (as small erase blocks result in a high > hardware price. > > But maybe there is some kind of trick that I don't understand yet. > > -Michael > > ------------------------------ > > _______________________________________________ > uClinux-dev mailing list > uClinux-dev@uclinux.org > http://mailman.uclinux.org/mailman/listinfo/uclinux-dev > This message was resent by uclinux-dev@uclinux.org > To unsubscribe see: > http://mailman.uclinux.org/mailman/options/uclinux-dev > > > _______________________________________________ > uClinux-dev mailing list > uClinux-dev@uclinux.org > http://mailman.uclinux.org/mailman/listinfo/uclinux-dev > This message was resent by uclinux-dev@uclinux.org > To unsubscribe see: > http://mailman.uclinux.org/mailman/options/uclinux-dev >
_______________________________________________ uClinux-dev mailing list uClinux-dev@uclinux.org http://mailman.uclinux.org/mailman/listinfo/uclinux-dev This message was resent by uclinux-dev@uclinux.org To unsubscribe see: http://mailman.uclinux.org/mailman/options/uclinux-dev
