Keep in mind that the 180MB/s is based on a rather large block size, the endurance test is writing a mix of block sizes and >50% is less than 128KB in size.
It looks like the controller struggles with this mix.
Printable View
Keep in mind that the 180MB/s is based on a rather large block size, the endurance test is writing a mix of block sizes and >50% is less than 128KB in size.
It looks like the controller struggles with this mix.
Kingston V+100's apparent WA gets weirder...after being exactly the same twice in a row (4.166666x), it's down to 2.61x overall. At this point I'd guess the SMART attribute that's declining isn't MWI as we know it (i.e., not a linear scaling--relative to P/E cycle--counter) and therefore my WA calculations are basically useless :p:
It was at 92 (equiv) after 6TiB and is at 89.5 (equiv) after 12.59TiB...so yeah, definitely not linear and seemingly not related to P/E cycles (unless recent WA has gone from ~4.17x to ~1.19x, which I suppose is possible).
There are a few more attributes that could start changing, nothing like a P/E counter though. (unless there is some trick to interpreting AD)
C300 Update
254.5TiB host writes, 14 MWI, 4300 raw wear indicator, 2048/1 reallocations, 63.0MiB/sec (going back up again...), MD5 OK
SF-1200 nLTT Update (from much earlier today--I seem to be out of sync with the MWI movement)
123.188TiB host writes, 84.47TiB NAND writes, 60 MWI, wear range delta 3, 1351.5 raw wear (equiv), 56.15MiB/sec, MD5 OK
The M4 is going quite far already but I bet the C300 will go even further because of 34nm NAND and same controller type.
260.63TB Host writes
Reallocated sectors : 6
MD5 OK
33.36MiB/s on avg (~43 hours)
m4 update:
375.405 TiB
1234 hours
Avg speed 90.34 MiB/s.
AD gone from 140 to 137.
P/E 6581.
MD5 OK.
Still no reallocated sectors
Attachment 119358
Kingston V+100:
17.3295 TiB
66 hours
Avg speed 76.59 MiB/s.
AD gone from 179 to 177.
P/E ?
MD5 OK.
Attachment 119359
SMART attribute AD is definitely not MWI-as-we-know it. If it were, WA would have been .65x over the past ~4.8TiB. This Kingston V+100 is a weird one :p:
0-Fill
110.64 hours
103.1149 TiB written
139.78 MB/s
MD5 ok
05: 0
B1: 29
E9: 41984
EA/F1: 106048
F2: 128
MWI: 76%
I misunderstood Ao1's post, I thought he wanted to see the results if I changed to 0-fill.
I changed back to 46% compression and the speeds are still 57.06 MB/sec. Basically the same as what it was before at higher MWI levels. From my understanding LTT has not kicked in yet.
If LTT has not kicked in now I somehow doubt it's going to. Could you please confirm write speed if you switch to 100% (Incompressible)? This is a retail drive, yes?
100% incompressible is about 41.13 MB/sec
As far as i know, it is a standard retail drive.
I think from here on out, sticking with 100% incompressible (to mitigate the skew from 53TiB of 0-fill) might not be a bad idea....or at least until MWI zeros out. (then return to 46% or move to 67%)
^^ This only applies to the SF-based drives ??
Wheew!! (wiping browe)...thought I screwed up there for a second! :)
I have considered alternating the fill-value for each session, not that it makes much of a difference.
So, 110 hours to get to ~75% = 440 hours to 0% or 18 days. LLT cannot have been set on this particular drive, so is it a peculiarity on this particular drive or do Corsair have a different policy on LTT?
110 hours is just how long it's been since he changed to 0-fill setting. MWI only moved from 81 to 76 in that time...but NAND write speed was also very low (~18.9MiB/sec).
With the 46% setting (had nearly the same NAND write speed as 100%), his drive was on pace to hit MWI=1 after a total of 41.5 days.
C300 Update
247.522TiB host writes, 13 MWI, 4351 raw wear, 2048/1 reallocations, 62.95MiB/sec, MD5 OK
SF-1200 nLTT Update
128TiB host writes, 88.28TiB NAND writes, 58 MWI, 1412.5 raw wear (equiv), wear range delta 3, 56.05MiB/sec, MD5 OK
m4 update:
380.0042 TiB
1248 hours
Avg speed 90.19 MiB/s.
AD gone from 137 to 134.
P/E 6661.
MD5 OK.
Still no reallocated sectors
Attachment 119374
Kingston V+100:
21.1626 TiB
81 hours
Avg speed 76.51 MiB/s.
AD no change - 177.
P/E ?
MD5 OK.
Attachment 119375
The Kingston is a strange one.... No change on AD.....
I'll be gone for the weekend and the next update will be monday.
Not really because the Indilinx controller has a really high WA. Ideally, you would need NAND that is rated for many erase cycles like 50nm SLC in the Intel X25-E drive with a controller that is modern ( supports TRIM ) and has a really low WA like the Sandforce which uses compression and gets quite a low WA of around 0.6 or a controller like the Intel / Crucial ones with a WA of 1.1. Based on this theory, I would expect the C300 to outlast the M4 because the controller is almost the same between the M4 and the C300 while the C300 has better lasting 34nm NAND ( compared to the M4 with lesser 25nm NAND ).
M225->Vertex Turbo 64GB Update:
145.27 TiB
540.5 hours
MWI 27 (drops by 1 for every 50 raw wear)
3678 Raw Wear
111.22 MB/s avg for the last 16.3 hours (on W7 x64)
MD5 OK
C4-Erase Failure Block Count(Realloc Sectors) at 2 (Bank 6/Block 2406; Bank 3/Block 3925)
Attachment 119381