To wrap up the QLC saga: Crucial P1 SSDs (QLC) peaking at >50% IO usage, >1s long tail latencies, cluster fell over under load, HDDs faster (!) Samsung 970 Evo Plus SSDs (TLC) peaking at ~3% IO usage, <10ms long tail latencies, cluster *very* happy. Stay away from QLC.
-
Hm, that's interesting, and it indicates that QLC controllers might not be mature enough (can you list the designers of the controllers, not just the SSD as whole?). Generally, it's mostly a matter of cost: With QLC (misleading name, btw) you get 33% more bit per area than TLC…
-
-
Google-fu tells me that's used as TLC controller – I don't know whether that was ever meant to deal with memory with four bit per cell, which would be very desirable from a correction point of view.
-
Manufacturer website and feature sheets praise newer chips for the introduction of QLC support – so I'd argue your problem is with SSDs built from QLC NAND flash and controllers that weren't meant to deal with these, not with QLC itself.
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.