Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

That drop came with a drop in performance too...

Most of the 80-100 $/TB disks use QLC which is painfully slow (slower than a spinning hard drive) when you outrun the SLC cache... Had to experience this during a drive migration with dd.



*on sustained writes. They will absolutely trash a spinning drive on reads.


If you wanna resize a partition, or anything else that essentially rewrites the whole disk... have fun.


I mean yes, but isn't that something quite rare?

At least I never feel the need to do it, the closet I came to something like that was when I switched from a 240 GiB SSD to a 1 TiB one and just mirrored the old disk to the new one with dd, increased the partition and run a resize2fs. While that required ~30 Minutes it was a once in a decade thing for me.


A QLC with 40+ TB will still be quite snappy without cache.

While cacheless TLC gets parity with MLC at around 8 TB.

So, yes QLC flash needs really big drives to get enough of aggregate write performance.

Below that, there is not much rationale to use it evlconomically vs TLC.


QLC is also much lower endurance, so at those sizes there's also the question of how much over-provisioning needs to happen to enable acceptable endurance, while still being cheap enough to out compete the alternatives.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: