SSD Write Endurance 25nm Vs 34nm

[Ao1]

Benchmarks generate temp files that auto delete. When that happens a TRIM command is issued.

I'm assuming you can write at the device level based on the fact that you can read from it directly. I'm not 100% sure, which is why I asked the question. I'm even more unsure about what level the TRIM command comes from.

It might help explain why a TRIM "hang" does not occur whilst the V2 is being benchmarked.


EDIT - I'm going to terminate the V2 endurance test. Seems pointless if DuraClass is going to throttle the drive to make sure it lasts 5 years.

[bulanula]

EDIT - I'm going to terminate the V2 endurance test. Seems pointless if DuraClass is going to throttle the drive to make sure it lasts 5 years.

Too bad. Well, at least we can see what the Intel controller will do after things really get going at about 50TB of writes etc. !

[lowfat]

EDIT - I'm going to terminate the V2 endurance test. Seems pointless if DuraClass is going to throttle the drive to make sure it lasts 5 years.

That is ridiculous. What a useless 'feature'.

[Ao1]

Well it was expected, but I didn't think performance would drop so low.

I was getting huge response times for uncompressible data. 87ms for a 4MB sequential xfer/ 11.37 IOPS. For writes 570ms/ 1.75 IOPS

I don't really get why Duraclass is needed when the drive benefits from compression.