>
>2) TRIM does often not work in RAID because of several reasons, the primary one
>being that most of the RAID controllers are still not completely understanding the
>difference between HDD and SSD and therefore do not pass the TRIM command to the
>devices. Depending on the configuration of the RAID (true RAID or just striping
>/ mirroring), there are additional issues that I won't go into in public.

Its this part that really shows that SSDs aren't 100% yet. You'd expect any SATA or SAS drive to be able to plug into any compliant controller, single drive or RAID, but you can't with SSD. I'm hoping that within the next generation or two that the SSD controllers are able to deal with its internal "issues" and not require special considerations. It just reminds me of switching from CHS to LBA on HDD and we still seem to be on the CHS side of SSDs.


>3) TRIM only works if there are idle cycles, if the drives are subjected to 100%
>load all the time, then there is simply no time to execute TRIM without inserting
>idle periods. This is the scenario that Linus referred to, however, outside any
>extreme case in the enterprise environment, it will happen in a blue moon.
>

Would something like the following work:

1. Auto TRIM after so many consecutive writes that cause whole block rewrites. Perhaps a mini TRIM of sorts, only do a couple pages worth to not interfere too much under a heavy load.

2. TRIM before entering a SLEEP state.

3. Support full TRIM as normal.

Maybe they already do this, I don't know.


Did anyone ever worry about which controller your HDD had on board?