On Mon, 2009-09-14 at 21:51 +0200, Peter Jakobi wrote: > Granted that the more expensive sata-ssd shoudl implement at least one > of these (proprietary mumble <unnamed> mumble) counter-measures. > > But hotspots or swap hitting the same logical sector all the time? > Changing 512B all the time, requiring write/erase cycles all the time > on the same cell. (what are the numbers here: 100K cycles, 1M at best > for the most expensive?)
The minimums I have seen are 10,00 and 100,000. Although actual rewrites numbers may be a lot higher in actual usage. I haven't see the numbers for the latest general of flash chips. They may actually be the 1M number you mentioned. > > Consider USB sticks and directly soldered-in flash in small and still > expensive gizmos. Gizmos naturally without any mention of anything at > all in available docs wrt flash and wear-leveling? All of the manufacturer literature I've seen over the years has mentioned wear leveling. I definite know that Kingston and Corsair use wear leveling in all of the USB flash drives. With naked flash chips the software drive, it's all up to the software drivers/file systems. > Consider FAT and it's tendency of hot spots and it's unhappy marriage > to stupid bad old flash - I'd still suspect that as the reason for the > death my old creative muvo... Entirely possible is they didn't put some wear leveling in the file system layer above the flash driver. The wear leveling on those device must come from the software they are using. In the case of the Linux on the IPAQ and Nokia Internet Tablets (NIT) and N900, the wear leveler is the JFFS2 file system. The NITS supplemented their built in flash with SSD devices (*SD memory cards). The swap partition were by default stored on one of the SD cards. > > Is it indeed safe nowadays to assume that some basic wear leveling is > implemented at HW-LEVEL in say HTC androids or Nokia's N900-to-be - so > I can really place ordinary swap and logs on flash without having to > consider/add work-arounds against hotspots? Android uses YAFF2 AFAIK. Wear leveling is definitely a part of that driver. As to the N900, I'm totally sure how the 32 GB of flash is being uses. From the developer lists I read, it's going to be divided up a differently than the previous N70/N8x0 devices. Part is the root fs, part will be ext3 as /opt for installed apps, and the rest will be FAT which will be used for user data and presented to a PC as USB storage when connected to a PC. > > Merely finding hints online that wearleveling on flash has been known > in the mid-nineties doesn't convince me this issue is indeed ancient > history. As I didn't mention on my previous post, the wear leveling on the IPAQ running Linux was due to JFFS2. I just used the figure of 100,000 rewrites that I saw mentioned for flash chips. > Doubly so for mass-market consumer/prosumer-grade stuff, > where builtin obsolescence is a marketing device. > > still sceptical, As for as flash drives, I believe that wear leveling is a part of all of them. So it's a non issue for me. Device that have naked flash chips is where I could be concerned. Devices that use the flash as basically ROM should have nothing to worry about. Devices that use the flash for R/W storage, there you have to be concerned. IF there is no wear leveling or babd chip detection in storage driver, the device could very well drive itself into non-operation. -- Stephen Johnson <sjohn...@monsters.org> _______________________________________________ Discuss mailing list Discuss@lopsa.org http://lopsa.org/cgi-bin/mailman/listinfo/discuss This list provided by the League of Professional System Administrators http://lopsa.org/
