SSD Write Endurance 25nm Vs 34nm

[Ao1]

Here are a couple of charts showing relocated sector events for the intrepid X25-V. I had forgotten that relocated sectors turned up on the X25-V before the MWI had expired. It follows the bath tub curve quite well. (Infant mortalities, stability and then progressive failure).

[kaktus1907]

I'm really hoping it will appear to be 5K P/E(Toshiba Type B 24 nm T-Nands).. sadly corsair performance pro's smart values arent any different than plextors

[Christopher]

I'm not sure how upset I would be if I bought a Performance Pro and I got 24nm instead of 32nm. While it is uncouth to swap flash without saying so, the 24nn uses much, much less power. The M3P maxes out at 2.6w, and it doesn't even get above ambient during endurance testing. If it puts in a halfway decent showing, the 24nm might be what you want.

We will see how the M3P does, but previous drives using Toshiba toggle have not done well at all (Samsung's Toggle appears to be a different story).

[Christopher]

I haven't gotten to test mine yet, I've updated the firmware so they are ready.

Have you got a recent screenshot showing the M3Ps SMART status/values?

Certainly. I'll post it later, but all current/worst values are nominal. Only power on/cycles and host writes are changing.

I'll post it when I get home.

[Anvil]

Thanks Ao1,
Hopefully they'll be able to make "drives" like that again.
It has been uneventful except for enduring more than any other drive, so far.

Christopher,
Just wait until something interesting happens.

[Christopher]

M3P Smart


So power cycles, power on hours, unsafe shutdown and host writes are the only values which increment so far.

I expect if/when a block goes bad MWI and reallocations will change.

All current/worst values are still at 100.

[Anvil]

474556*64MiB that's close to 29TiB

I expect CDI and or others will pick up on the writes attribute, lets hope reallocations won't happen for a while, at the current speed it probably won't take more than a few weeks though.

[Christopher]

474556*64MiB that's close to 29TiB

I expect CDI and or others will pick up on the writes attribute, lets hope reallocations won't happen for a while, at the current speed it probably won't take more than a few weeks though.

That was a shot from last night. It's currently at 714341 (44,646 GiB). I just didn't want anyone thinking that the attribute didn't work correctly (it does -- B1 RAW * 64 = host writes MiB).

[canthearu]

That M3P is in a real hurry. I'm not sure where it is in a hurry to get to, but where-ever it is going, it won't take very long.

[Christopher]

That M3P is in a real hurry. I'm not sure where it is in a hurry to get to, but where-ever it is going, it won't take very long.

It's going to Hell, and quickly at that. I'd expect to maybe see a reallocation in around two weeks -- somewhere near 3000PE cycles or so. I hope I'm wrong though. Fortunately for me, I usually am.

Maybe Plextor's price premium is in part due to higher binned NAND, perhaps analogous to the Kingston HyperX 5K? Doubtful, but I remain hopeful. I think they just charge more because it's fast.

--------------------------------------------

Plextor M3P 128GB Day 2

49,245.08 GiB
48.09 TiB

271.21 MB/s Average

48 Hours

Rellocated Event Count 0



--------------------------------------------

Samsung 830 256GB Day 72

1,707,352.20 GiB
1,667.33 TiB

300.36 MB/s Average
1694 Hours

7260 Wear Leveling Count
MWI 1

6/0 Erase/Program Fail
Used Reserved Block Count: 12/24572 sectors


--------------------------------------------

[Anvil]

I've been looking at the SMART data on the 330 and it does not look to be 3K NAND. (it could still be though)

From what I can see, Raw NAND writes points to MWI exhaustion at about 5K which means ~590TiB of NAND writes and 835TiB of Host writes.
(based on the first 5 MWI movements, the next few days will tell whether it sticks, I'm recording every 10 minutes so the change is not immediately recorded)

[canthearu]

From what I can see, Raw NAND writes points to MWI exhaustion at about 5K which means ~590TiB of NAND writes and 835TiB of Host writes.

Heh, so basicly twice the Intel 520 60gig drive.

Looks like you might win this one :P

[Anvil]

It looks that way

It's early days yet, I'm happy with the 330 so far, throughput is about where I expected it to be.

[B.A.T]

Todays update:

m4
963.7975 TiB
4053 hours
Avg speed 74.36 MiB/s.
AD gone from 63 to 59.
P/E 16598.
MD5 OK.
Reallocated sectors : 00


Intel X25-M G1 80GB
662.57 TiB
23365 hours
Reallocated sectors : 162 to 163
Available Reserved space: 90
MWI=124
MD5 =OK
42.86 MiB/s on avg


Intel X25-E 64GB
148.12 TiB
452-30=422 hours
Reallocated sectors : 0
Available Reserved space: 100
MWI=99
MD5 =OK
101.03 MiB/s on avg

[Christopher]

I'm kinda excited about the 330... I wonder if maybe it's just cheaper to use Intel's stash of NAND? Maybe it really is just Cherryville with 300i and not 400i FW... and no other differences.

I'd be happy just to get 5K PE cycles out of the M3P, as fast as it is.

[AMD_Freak]

I'm kinda excited about the 330... I wonder if maybe it's just cheaper to use Intel's stash of NAND? Maybe it really is just Cherryville with 300i and not 400i FW... and no other differences.

I'd be happy just to get 5K PE cycles out of the M3P, as fast as it is.

I hope you get 10K ill be happy to know mine will last

[Christopher]

--------------------------------------------

Plextor M3P 128GB Day 3

72,655.01 GiB
70.95 TiB

273.05 MB/s Average

72 Hours

Rellocated Event Count 0

--------------------------------------------

Samsung 830 256GB Day 73

1,732,685.11 GiB
1,692.07 TiB

300.05 MB/s Average
1717 Hours

7525 Wear Leveling Count
MWI 1

6/0 Erase/Program Fail
Used Reserved Block Count: 12/24572 sectors


--------------------------------------------

The pace of both drives is really phenomenal. We'll see where the 830 ends up after more than 72 hours, but switching both drives into the other rig seems to have resulted in tangible and worthwhile performance increases. The top current speeds are just higher, resulting in higher averages.

The 830 was only doing 282 MB/s Avg four days ago. An extra 20MB/s is nothing to sneeze at.

EDIT
10,000 PE cycles on the Plextor would probably be somewhere around 1.09PiB

[Anvil]

The M3P is already ahead of the 330, if it can keep up the pace until the end I'd be impressed.

I wonder if there are plans on using IMFT 5K NAND, would be very interesting on a Plextor.

[[XC] Oj101]

The forum doesn't allow for searches of three characters, does anyone know/remember if the Intel 320 series (preferably 120 GB) was tested here?

[Anvil]

Intel 330 120GB

66.96TB Host writes
Reallocated sectors : 05 0
Available Reserved Space : E8 100
MWI 94
[F1] Total LBAs Written 2194022
[F2] Total LBAs Read 22623 // no movement
[F9] Total NAND Writes 48334GB
POH 191
MD5 OK

122.68MiB/s on avg (~95 hours)

--

Kingston SSDNow 40GB (X25-V)

995.75TB Host writes
Reallocated sectors : 05 46
Available Reserved Space : E8 99
POH 8916
MD5 OK

33.59MiB/s on avg (~95 hours)

[Anvil]

The forum doesn't allow for searches of three characters, does anyone know/remember if the Intel 320 series (preferably 120 GB) was tested here?

It was one of the original drives that started this test.
One_Hertz tested a 320 40GB, a great drive, my drive outlasts it but that's 34nm NAND for you.

You'll find a bit of info in the first post, it failed this January at 685TiB written, outstanding performance imho

[B.A.T]

Todays update:
I got a big update today.

First:
I got the Mtron from GullLars today. I'll be start testing it in a couple of days after I've done some maintenace on my rig. I'll post some screenshots tomorrow.

Second:
I updated some drivers on the rig today and a round of windows update. After the restart I noticed that the icon for the ASU G1 was strange. Trying to open it failed and when I looked at the ssd I got this error message.



Checking CDI I the G1 was still being detected but available reserved space had dropped from 90 til 89 and reallocated sectors gone from 163 to 169.


In disk management the ssd is shown as unformated and I had to format it to make it work again.


I copied back all the files and the correct setings for ASU. Since all data was lost I have to relay on host write in smart to keep track of writes.
Before I started up ASU I checked CDI and now a lot had happend. Available reserved space had dropped from 89 to 78 and reallocated sectors had dropped from 169 to 73.
I refreshed CDI and while I looking at it the value increases. I adjusted smartlog to update every minute and here are the change and the time. I removed all timeslots that didn't change.

09:57:31.203 163
10:28:08.472 166
10:31:03.354 169
11:21:12.077 73
11:22:12.824 81
11:23:13.617 86
11:24:16.719 86
11:25:19.119 90
11:26:18.134 94
11:28:20.517 95
11:29:21.247 97
11:32:25.219 98
11:44:36.236 100
11:47:38.179 103

Looks like I took a out a big chunck of blocks but why this strange behavior on the reallocated sectors I have no explanation for. I think the next days will be exciting if the G1 continues or looses more sectors.

m4
968.9236 TiB
4082 hours
Avg speed 74.50 MiB/s.
AD gone from 59 to 55
P/E 16710.
MD5 OK.
Reallocated sectors : 00


Intel X25-M G1 80GB
666.52 TiB
23392 hours
Reallocated sectors : 163 to 163 to 73 to 103
Available Reserved space: 90 to 89 to 78
MWI=124 to 116
MD5 =OK
43.81 MiB/s on avg


Intel X25-E 64GB TiB skrevet med en snittfart på MiB/s. SSDen er testet i (
157.16 TiB
480-30=450 hours
Reallocated sectors : 0
Available Reserved space: 100
MWI=99 to 98
MD5 =OK
99.71 MiB/s on avg


Finally the E changes mwi from 99 to 98. It happened at 152,3694 TiB according to smartlog. It means that mwi=1 will happen at almost 15 PiB.....

[canthearu]

What happened with the G1 (I think) is that the counter wrapped around from 255 back to 0,

So reallocated sectors is now 103+256 = 359. But the G1 is looking a bit hurt ... showing same sort of symptoms as my Torqx 2 did.

[B.A.T]

I wonder why I lost all data on the G1. That was the strangest thing...

[Christopher]

That is exciting, B.A.T. I wonder if maybe the drive dropped too many blocks at one time and the drive couldn't recover them, corrupting the partition (??)

The Intels don't keep track or read/erase/program failures unfortunately.


What kind of MTRON are you doing?