Regarding the useful life of NAND Flash

[MaxMouseDLL]

Over the course of the years I've been around at MC, the question of NAND shelf life has been raised a couple of times, and no one has a definitive answer, until now. Hack a day set about systematically destroying a flash memory device via read/write cycles alone, now I know this flash memory probably isn't the same as the NAND contained within the PSP, but it's a pretty accurate analogue, here's what hack a day have to say on the subject:

The Flash_Destroyer finally succeeded in rewriting that EEPROM until its demise. When we originally looked at the device it had already recorded 2.5 million successful rewrites. The first appearance of corrupt data occurred at 11,494,069 but that doesn’t tell the whole story. The chip kept working for another 200,000 rewrites before finally showing repeated data corruption.
We do find the writeup pretty interesting. There’s one thing that we can’t stop coming back to though. In the discussion of our original article [Tiago] pointed out that long-term data retention isn’t being tested here. If the abuse of that EEPROM had ended after say five million rewrites, would it have been able to hold the data long-term without corruption?

It would seem that you're safe for at least 10,000,000 read/write cycles of your flash storage device, before corruption occurs, and as we know, the PSP contains extra blocks which it can use in the event of a permanent corruption (At least for most blocks, some are critical), so the useful shelf life of a PSP's NAND as a whole, is probably in the region of 10,000,000 ~ 20,000,000 read/write cycles.

[ThreeDog]

Question: If they got that much out of one chip why are all these SSDs slowing down or crapping out?

I see this is an EEPROM, does this even compare to consumer grade nand?

Not that i have extreme knowledge in the area but this seems to be a case of comparing apples to dildos,

Sure a PSP NAND will last 100 flashes with bad black management but consumer grade nand generally can't even manage sustained operations within a computer without deteriorating quickly.. and that's with wear leveling. You can destroy SSD grade NAND performance with defrag, they advice you remove anything that will produce many reads/writes even relocating your "my documents" folders etc from them to prevent things degrading and failing.

* SLC NAND Flash is typically rated at about 100K cycles (Samsung OneNAND KFW4G16Q2M)
* MLC NAND Flash is typically rated at about 5K-10K cycles (Samsung K9G8G08U0M)
* SLC Floating Gate NOR Flash has typical Endurance rating of 100K to 1,000K cycles (Numonyx M58BW 100K; Spansion S29CD016J 1000K)
* MLC Floating Gate NOR Flash has typical Endurance rating of 100K cycles (Numonyx J3 Flash)

Is this even a fair compare?

So as a noob tell me what im missing here mate as i said im no expert

[MaxMouseDLL]

Is this even a fair compare?

Maybe not, I was going for ball park figures in the wild, of your average vanilla EEPROM IC, as it's a well known fact that rated this and rated that doesn't mean jack and leans heavily on estimates of the parent company thus also depends on how conservative they are with their math (Some take averages, some take averages and add a bit on some take away, some take the lowest performance from the range.. etc etc)

Also (and here's the important part) EEPROM = Electronically Erasable Programmable Read Only Memory IE: NAND = EEPROM, or under it's umbrella term Flash Memory.

Flash memory is a non-volatile computer storage technology that can be electrically erased and reprogrammed. It is primarily used in memory cards, USB flash drives, and solid-state drives for general storage and transfer of data between computers and other digital products. It is a specific type of EEPROM (electrically-erasable programmable read-only memory) that is erased and programmed in large blocks

Anyway, even if someone can chime in and tell me that this doesn't relate to the PSP's NAND flash it is still a nice demonstration of testing a standard EEPROM to (logical) destruction.

Edit: K9F1208U0A 32M NAND Flash: extended reliability of 100K program/erase cycles by providing ECC(Error Correcting Code) with real time mapping-out algorithm.

This is probably unrelated then, delete the thread as it's probably way off base.

Edit 2: Maybe not...

Memory wear

Another limitation is that flash memory has a finite number of program-erase cycles (typically written as P/E cycles). Most commercially available flash products are guaranteed to withstand around 100,000 P/E cycles, before the wear begins to deteriorate the integrity of the storage.[7] Micron Technology and Sun Microsystems announced an SLC flash memory chip rated for 1,000,000 P/E cycles on December 17, 2008.[8]

The guaranteed cycle count may apply only to block zero (as is the case with TSOP NAND parts), or to all blocks (as in NOR). This effect is partially offset in some chip firmware or file system drivers by counting the writes and dynamically remapping blocks in order to spread write operations between sectors; this technique is called wear leveling. Another approach is to perform write verification and remapping to spare sectors in case of write failure, a technique called Bad Block Management (BBM). For portable consumer devices, these wearout management techniques typically extend the life of the flash memory beyond the life of the device itself, and some data loss may be acceptable in these applications. For high reliability data storage, however, it is not advisable to use flash memory that would have to go through a large number of programming cycles. This limitation is meaningless for 'read-only' applications such as thin clients and routers, which are only programmed once or at most a few times during their lifetimes.

NAND is rated for Block zero (I remember speaking to a dev about this at one point, but I forget who, possibly SilverSpring), this test is for general data corruption, but meh... still delete it, it's not the actual PSP IC being tested so, you're right that a comparison is probably unfair.

Edit 3: anyone got a spare PSP that I can destroy?

[ThreeDog]

lol we'll keep it open im interested i have i learned a bit and hopefully will learn more

[The_ByteMaster]

My first PSP is from June 2005, bought on the same day Swaploit was released , and is still working fine. It has had about 8-10 reflashes, and I don't bother with custom themes etc. nor do I change settings very often (also writes to flash).

I wonder if there's a way to see the number of bad block remaps on the NAND chip, similar to a HDD. It wasn't included on any of the many System Info programs when homebrew was still booming, so probably not.

This also puts a big question mark with Sony's decision to collect all kinds of usage stats and write those to flash, as this "useless" information will degrade the flash faster. (Note: I tried to find the relevant thread for this; it was an analysis of one of the 6.xx OFWs and it turned out there's stats like number of game starts, etc.)