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.
-
Cool story. I'll tell that to my qlc drive that's been doing just fine since I got it. Not all people have the same use cases.
If you have a read-mostly workload then it's probably fine. If you ever wind up having to do sustained writes and relying on performance not being terribad, you'll regret using QLC. At least the crucial ones fall over *badly*, not just "really slow" but pathologically slow.
-
-
How often do you do sustained writes on anything that's not your work computer?
-
Any time I'm copying data, recording audio/video, etc. The Crucial P1s fall over after *mere seconds* of sustained random writes.
- 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.