You can get the same Kingston as I have for £199 each at amazon Run for it!!
Printable View
You can get the same Kingston as I have for £199 each at amazon Run for it!!
Vertex 4 reallocated sectors at 15.
I'm seriously doubting this drive is going to last more then another 100-200TiB.
Intel 520 60GB - Day 88
Drive hours: 2,058
ASU GiB written: 653,647.21 GiB (638.33 TiB)
Avg MB/s: 95.42 MB/s
MD5: OK
Host GB written (F1): 658,293.19 GiB (642.86 TiB, 21065382 raw)
NAND writes (F9): 466,026 GiB (455.10 TiB)
Reallocated sectors (05): 0
Failure count (AB, AC): 0 program, 0 erase
Raw Error Rate (8B): 112 normalised
Avaliable Reserved Space (AA): 100 normalised
Media Wearout Indicator (E9): 1
Vertex 4 128GB - Day 35
Drive hours: 844 (556 + 288)
ASU GiB written: 366,203.35 GiB (357.62 TiB)
Avg MB/s: 124.59 MB/s
MD5: OK
Sector GB written (E8): 369,363.89 GiB (360.71 TiB, 486156078177 + 288456133860 raw)
Reallocated sectors (05): 16
Raw Read Error Rate (01): 6
Remaining Life (E9): 39 (69 current - 30)
12 new bad blocks for the vertex 4. Upgrading ASU and restarting testing.
What sort of over-provisioning is there by default on the Vertex 4?
@Anvil
The normal 7% from the conversion of binary gigabytes (GiB) into decimal gigabytes. (GB)
OK, so the norm then.
I normally over-provision ~10% on most drives, especially if they are in a raid.
(during my V4 128GB testing it has been set to 100GB, 19.5GB over-provisioning)
I've been a fan of OCZ for a few years now for putting to market many new interesting products.Quote:
Originally Posted by canthearu
The Octane and V4 are not. I'm still a fan of SandForce and this testing just put more weight to my opinion.
Todays update:
m4
913.7974 TiB
3857 hours
Avg speed 74.35 MiB/s.
AD gone from 91 to 88.
P/E 15749.
MD5 OK.
Reallocated sectors : 00
http://www.diskusjon.no/index.php?ap...tach_id=491588
Intel X25-M G1 80GB
633.51 TiB
23169hours
Reallocated sectors : 158 to 159
Available Reserved space: 90
MWI=124
MD5 =OK
42.44 MiB/s on avg
http://www.diskusjon.no/index.php?ap...tach_id=491592
Intel X25-E 64GB
79.86 TiB
257-30=227 hours
Reallocated sectors : 0
Available Reserved space: 100
MWI=99
MD5 =OK
101.23 MiB/s on avg
http://www.diskusjon.no/index.php?ap...tach_id=491590
Just out of curiosity are you guys doing this with MHDD or similar (cutting the drive/changing the MaxLBA) or is this something else with a custom firmware? The handful of SSD's here I've just cut the drives but haven't really done a lot of stress testing to see the efficacy of that.Quote:
Originally Posted by Anvil
None of the drives in the endurance test have been given additional overprovisioning.
Vertex 4 at 21 reallocations now (359.91 TiB in ASU)
Kingston SSDNow 40GB (X25-V)
971.74TB Host writes
Reallocated sectors : 05 43
Available Reserved Space : E8 99
POH 8708
MD5 OK
33.90MiB/s on avg (~55 hours)
All off them within a few days?Quote:
Originally Posted by canthearu
Yep, all but 2 or 3 in the last 48h.
The Kingston can go for months and then pop a few sectors.
Re-allocations have been showing movements for a long time though, they just don't accelerate like some other drives tend to do.
The cheese is sliding off the this one's cracker! ... 33 reallocations now (365.67 TiB in ASU)Quote:
Originally Posted by canthearu
On the positive side, it does inform about whats to happen, much too early though.
Lets see how much it can take...
Todays update:
m4
919.4075 TiB
3879 hours
Avg speed 74.34MiB/s.
AD gone from 88 to 84.
P/E 15844.
MD5 OK.
Reallocated sectors : 00
http://www.diskusjon.no/index.php?ap...tach_id=491695
Intel X25-M G1 80GB
636.77 TiB
23191 hours
Reallocated sectors : 159
Available Reserved space: 90
MWI=124
MD5 =OK
42.52 MiB/s on avg
http://www.diskusjon.no/index.php?ap...tach_id=491699
Intel X25-E 64GB
87.55 TiB
279-30=249 hours
Reallocated sectors : 0
Available Reserved space: 100
MWI=99
MD5 =OK
101.21 MiB/s on avg
http://www.diskusjon.no/index.php?ap...tach_id=491697
Samsung 830 256GB Day 63
1,549,609.88GiB
1,513.29 TiB
290.85 MB/s Average
1535 Hours
6732 Wear Leveling Count
MWI 1
6/0 Erase/Program Fail
Used Reserved Block Count: 12/24576 sectors
------------
Another realloc happened last night.
What about the Intel 520, it's been a few days without updates.Quote:
Originally Posted by canthearu
I just noticed it was yesterday :), the extra reports on the Vertex made me think several days had gone by.
Attachment 127006
I'll update if canthearu posts on the 520.
The plan is to start testing a new drive tomorrow, that is if it gets here.
--
Kingston SSDNow 40GB (X25-V)
974.80TB Host writes
Reallocated sectors : 05 43
Available Reserved Space : E8 99
POH 8735
MD5 OK
33.66MiB/s on avg (~82 hours)
Looks like we are hitting 1 PiB with just a couple of days between us :)
I'm waiting a little with the C300. GullLars might sell me one of his C300 64GB when he updates his raid0 setup.
It could be a close race to 1PB, 1 PiB you should win :)
I noticed the post about the C300, would be great!
I hoped the Samsung 830 64GB could join me all the way but sadly no.....
I wonder how far they can go?!? Looks like only the sky is the limit :)
I really think that 830 64GB could have made it to the moon by now, it's too bad it went through weeks of super high WA. Had it not, it would have had 900TB when I stopped testing.
Vertex 4 up to 52 reallocations (at 372.45 TiB in ASU)
The intel 520 is still running fine .... nothing really to report these except slightly higher write numbers :)
I'll do a full update tonight.
have you done any recent data retention tests on the x-25v rebadge? or are you waiting to hit 1 PB? I'm still trying to figure out what i should do with my little tanks when i have money to upgrade (going from a pair of x-25V to I'm leaning towards an M4 128GB- only on a P45 chipset atm with them though)
I think Anvil is going to wait just like me until 1 PiB is broken.
I'm waiting for 1PiB before doing more retention testing.
It had a very short retention-test about a week ago, just a few hours disconnected while reinstalling the rig.
I believe the last retention test was at 7 or 800 TiB, it lasted a full weekend w/o power.
Intel 520 60GB - Day 90
Drive hours: 2,105
ASU GiB written: 669,275.64 GiB (653.59 TiB)
Avg MB/s: 95.36 MB/s
MD5: OK
Host GB written (F1): 674,065.59 GiB (658.27 TiB, 21570099 raw)
NAND writes (F9): 477,189 GiB (466.00 TiB)
Reallocated sectors (05): 0
Failure count (AB, AC): 0 program, 0 erase
Raw Error Rate (8B): 114 normalised
Avaliable Reserved Space (AA): 100 normalised
Media Wearout Indicator (E9): 1
Vertex 4 128GB - Day 37
Drive hours: 889 (556 + 333)
ASU GiB written: 386,979.39 GiB (377.91 TiB)
Avg MB/s: 126.04 MB/s
MD5: OK
Sector GB written (E8): 390,244.80 GiB (381.10 TiB, 486156078177 + 332246594530raw)
Reallocated sectors (05): 93
Raw Read Error Rate (01): 6
Remaining Life (E9): 34 (64 current - 30)
The vertex 4 is killing blocks at an increasing rate. Things are progressing quickly ... there may not be a tomorrow for this drive. It seems to roughly doubling the block reallocation count every 24 hours.
The Intel 520 is just doing its thing, quietly and without fuss. Which means one day it will simply die without warning, shattering the dreams of it's owner, along with all their data .... where that point is, who knows.
Todays update:
m4
926.2206TiB
3906 hours
Avg speed 74.34MiB/s.
AD gone from 84 to 80.
P/E 15960.
MD5 OK.
Reallocated sectors : 00
http://www.diskusjon.no/index.php?ap...tach_id=491812
Intel X25-M G1 80GB
640.74 TiB
23218 hours
Reallocated sectors : 159
Available Reserved space: 90
MWI=124
MD5 =OK
42.61 MiB/s on avg
http://www.diskusjon.no/index.php?ap...tach_id=491815
Intel X25-E 64GB
96.87TiB
305-30=275 hours
Reallocated sectors : 0
Available Reserved space: 100
MWI=99
MD5 =OK
101.18 MiB/s on avg
http://www.diskusjon.no/index.php?ap...tach_id=491816
Looks like my endurance rig has some kind of error, which means I get the occasional BSOD.
Sometime soon I'll need to run memtest86 on it to find out what is wrong and attempt to correct it. This will mean the drives will get at least a small retention test.
Can you rule out that it's caused by one of the drives?
Are you able to catch what BSOD it is and is it the same one?
BTW, got a new drive for Endurance testing today, breaking it in as we speak :)
(just running some reference benchmarks and recording SMART, ...)
Kingston SSDNow 40GB (X25-V)
977.38TB Host writes
Reallocated sectors : 05 43
Available Reserved Space : E8 99
POH 8757
MD5 OK
33.56MiB/s on avg (~104 hours)
--
Here's the new one, an Intel 330 120GB
47.7GB Free space, filled with W7, a Virtual Machine, mp3 files, total used space 64GB
Attachment 127030
Exciting!! :up: A 3K unit . How does it perform?
Hard to tell!
It's on it's 4th loop.
Currently it's about 25MB/s faster than the Corsair Force 3 (Async) but it needs 20 hours to get to the first reference point I've got on the F3.
Not sure what settings I ended up using on the F3, will check.
Need maybe a couple of days to stabilize?
Did you do the standard benchmark?
It will need some time.
I'll post the benchmarks later, ran a few different compression settings for later comparisons.
Not sure it they do some sort of testing as it had > 30 power on hours, next to no writes though. (kept the screenshots)
Here's a link to the F3, ~24 hours into the test.
(doesn't look like the links are working properly, it's on this page though, post #1693)
edit:
21+3 hours for the F3 so I'll compare them when the 330 has been running for 24 hours.
The Force 3 did 8K GB each day so if this goes past that it's a pretty good contestant.
Average speed is in the low 120s, loop counter is at 33.
The pauses at the end of the loop (deleting and TRIM) is what is killing the average speed, the drive is doing about 140MB/s throughout the loop.
It's already well past 1TiB
The BSOD is 0x1A error code. (memory manager)
I am able to get linx to fail as well, so it isn't to do with the drives!
Samsung 830 256GB Day 66
1,576,835.44GiB
1,639.88 TiB
287.82 MB/s Average
1568 Hours
6850 Wear Leveling Count
MWI 1
6/0 Erase/Program Fail
Used Reserved Block Count: 12/24572 sectors
Yep, I saw the same on my vertex 4 ... at least on the older 1.3FW .... 180gig or so average speed, bought down by the delete cycle to 145meg or so.Quote:
Originally Posted by Anvil
Anyway, woot for the 3k unit .... lets see who wins, the bigger 330, or the smaller but higher endurance 520.
I'm sitting at 1.51PiB LBA writes at the moment. Not too shabby, but I was really hoping to hit 2PiB before 84 days. Probably will be closer to 90.
Now that Anvil's dropped the new drive, I feel like I should toss another one in there, too. Suggestions?
It's already past 2TiB, avg speed is 123.nMB/s and that includes 3 rounds of MD5 testing.
As the 330 is twice the capacity of the 520 I'm optimistic on behalf of the 330 :)
Christopher,
I'll just throw in a few suggestions in no particular order
- Kingston 3K
- SanDisk Extreme
- Crucial v4 (a new series of "low cost" drives, SATA 3Gb/s with OK write speed for a 3Gb/s drive, low iops so not sure how it would perform)
- Corsair Performance Pro
- Plextor (if you can find a "cheap" one)
- Something upcoming using the 88SS9187 controller
It should be something that is not dated :) other than that it's up to you.
I'm thinking about getting a 256GB M3P and runnin' the 128GB M3P! The speed is downright magical, and I think it would be worthwhile. I have a 3K and the Mushkin Enhance Chronos Deluxe 120GB still, might be good to get back to my roots, but I don't know if another SandForce is where I need to be going. The Extreme is still interesting though, but I want a 128GB that's as fast as the 830.
I agree about not going SF, something new would be good. (other than SF)
Phison's new 6gbps controller is out... but I don't know if I'll be rushing out to buy one.
I reckon that the M3P 128GB could burn though 21TiB a day, using about 186 PE cycles in the process, or around 1300 a week (~147TiB). That's not terrible!
What drives are using the Phison controller?
The new MyDigitalSSD BP3 up (up to 512GB) using the S8 Phison. It's... how do I say this... about what you'd expect. I still want to play with one, though.
Well, maybe in a few years one could get a 512GB drive at a reasonable price for using in this thread :)
Are there any reviews on the Phison that you have noted?
(a few benchmarks could tell if it's worth spending time and money on something using that controller)
I checked in on the 330, not much have changed except for TiB written, it's down to 122.x MB/s over a 12-14 hour period.
Todays update:
m4
932.0644 TiB
3929 hours
Avg speed 74.35 MiB/s.
AD gone from 80 to 77.
P/E 16059.
MD5 OK.
Reallocated sectors : 00
http://www.diskusjon.no/index.php?ap...tach_id=491903
Intel X25-M G1 80GB
644.13 TiB
23241 hours
Reallocated sectors : 159 to 161
Available Reserved space: 90
MWI=124
MD5 =OK
42.66 MiB/s on avg
http://www.diskusjon.no/index.php?ap...tach_id=491907
Intel X25-E 64GB
104.83 TiB
328-30=298 hours
Reallocated sectors : 0
Available Reserved space: 100
MWI=99
MD5 =OK
101.16 MiB/s on avg
http://www.diskusjon.no/index.php?ap...tach_id=491905
No movement on mwi for the E even after 100TiB of writing, wonder when the first drop will come. Besides that all 3 have been very stabile the last 12 days. Writespeeds are barely moving so it looking good. :)
BIOS update may have resolved my stability problems (I was running a VERY early bios version, the very initial version), running linx in background to check.
Edit: Vertex 4 at 214 reallocations. Still working though
That's good news, using the initial bios version often is risky business.
214 reallocations, that should translate to 214 bad blocks, not sure how many MBs per block on your drive. (there should be plenty left)
The Crucial m4s are showing factory bad block count which in some cases (on some of my drives) exceeds your current bad block count. (if we assume 1 reallocation consumes 1 block)
Yeah, I jumped on the Z77 chipset very early because I wanted Intel's USB3 rather then a 3rd party chipset. But things are starting to be ironed out now:Quote:
Originally Posted by Anvil
a) Updated BIOS seems to have fixed stability.
b) Updated Intel graphics drivers have helped.
c) Updated RST drivers (11.1 rather then 11.0) means smartlog is working right now.
d) Updated crystaldiskinfo now shows thresholds like it should.
But one good thing is that boot times are excellent!
holy crap is that SLC flash?Quote:
Originally Posted by Christopher
Kingston SSDNow 40GB (X25-V)
980.23TB Host writes
Reallocated sectors : 05 43
Available Reserved Space : E8 99
POH 8782
MD5 OK
34.47MiB/s on avg (~24 hours)
--
Intel 330 120GB
10.27TB Host writes
Reallocated sectors : 05 0
Available Reserved Space : E8 100
[F1] Total LBAs Written 336465
[F2] Total LBAs Read 14536
[F9] Total NAND Writes 7396GB
POH 58
MD5 OK
122.72MiB/s on avg (~24 hours)
Here's the initial benchmarks, FOB performance.
Attachment 127063
Attachment 127064
Attachment 127065
No, that's Samsung Toggle mode NAND.Quote:
Originally Posted by Cyber-Mav
The capacity of the drive leads to those figures.
No, it's just 256GB of thunder and lightning. It's comparable to a 64GB drive with 409TiB (~419,580 GiB). Not terrible, but not earth shattering either. At least, not yet.Quote:
Originally Posted by Cyber-Mav
I got tired of the drives I was running not putting in the kind of performance I was hoping for, so I had to reach for a bigger hammer in the 830 256GB.
does toggle mode nand as in the plextor m3 have more durability than regular nand such as that in the crucial m4?
Not necessarily; they're still governed by the same principles which limit endurance. With that said, the companies which make NAND and SSDs tend to find the best flash out of their fab facilites to put in their own drives. Intel/Micron(Crucial) and Samsung make flash, and this flash can go either in their own products, or get sold to other companies. Usually, they keep the best stuff for themselves. (Note that Toshiba does make flash, and does make drives, but they primarily are OEM units and some enterprise oriented offerings, but the same still probably applies to them)Quote:
Originally Posted by Cyber-Mav
The Plextor M3P is a fine product, but it might actually have less endurance than the M4. Perhaps we'll find out soon, I think I'm going to test one.
Samsung 830 256GB Day 67
1,603,779.67GiB
1,566.19 TiB
288.07 MB/s Average
1590 Hours
6967 Wear Leveling Count
MWI 1
6/0 Erase/Program Fail
Used Reserved Block Count: 12/24572 sectors
I stopped the 830 and migrated to RC, all is well.
Vertex 4 looks dead:
Attachment 127104
Smart values at end of life:
Attachment 127105
Drive has now disappeared from windows. I'll attempt to resurrect.
[device is not ready] never was a good sign!
It's worth a bit of effort of course, it was showing the signs of a dying drive...
At 61% remaining life it is quite the disappointment. (if this is it)
Well, I got it running again. It is now Zombie Vertex 4.
A couple of restarts got it re-detected.
Remaining life is probably closer to 31% given the drive life reset when I upgraded firmware. In any case, not good at all.
Zombie Vertex 4 stopped again ... same position and error.
Wondering if I should try secure erase.
This sounds very familiar... See the two VTs and the Octane...Quote:
Originally Posted by canthearu
~30% is better, nevertheless, Remaining Life is there for a reason.
What about giving it a some extra over-provisioning?
Todays update:
m4
938.1534 TiB
3953 hours
Avg speed 74.35 MiB/s.
AD gone from 77 to 74.
P/E 16162.
MD5 OK.
Reallocated sectors : 00
http://www.diskusjon.no/index.php?ap...tach_id=491993
Intel X25-M G1 80GB
647.67 TiB
23265 hours
Reallocated sectors : 161
Available Reserved space: 90
MWI=124
MD5 =OK
42.71 MiB/s on avg
http://www.diskusjon.no/index.php?ap...tach_id=491997
Intel X25-E 64GB
113.14 TiB
352-30= 322 hours
Reallocated sectors : 0
Available Reserved space: 100
MWI=99
MD5 =OK
101.12 MiB/s on avg
http://www.diskusjon.no/index.php?ap...tach_id=491995
Attachment 127106
So much for the marketing gimmick otherwise known as the Ndurance 2.0. Is Ndurance just a throttling process? Surely someone has a grasp by now on what is going on with the V4 sustained write speeds?
That is what I've been thinking for the last week.Quote:
Originally Posted by Ao1
Ndurance 2.0 = almost lasts as long as the NAND is designed for.
What is even more confounding is how they are making the marvell controllers perform so poorly for endurance when the they have typically experienced perfectly fine endurance control.
It's all about the flash. Period.
For sure it would appear from testing in this thread that the grade of NAND used in Intel/ Micron/ Samsung SSD’s is superior to what others like $OCZ can buy on the open market, but that does not explain everything. So far the 520 has behaved much better than any other SF based drive. The premature block failures of the Octane/ Petrol drives are occurring before the P/E cycles have hardly been touched. It’s almost like something is accelerating/ inducing damage to the NAND. (Maybe it’s the overclock).
So what gives with the V4? Is it a form of throttling that causes write speed to drop by half? Someone must know, but no one is saying anything. If it was an Intel/ Micron/ Samsung/ Toshiba product the world and his dog would be screaming about it from the rooftops.
They are still sceaming trying to get their Vertex 2's to work. :shocked: :ROTF:Quote:
Originally Posted by Ao1
Kingston SSDNow 40GB (X25-V)
982.99TB Host writes
Reallocated sectors : 05 45 up 2
Available Reserved Space : E8 99
POH 8806
MD5 OK
33.84MiB/s on avg (~48 hours)
--
Intel 330 120GB
20.37TB Host writes
Reallocated sectors : 05 0
Available Reserved Space : E8 100
[F1] Total LBAs Written 667628
[F2] Total LBAs Read 14536
[F9] Total NAND Writes 14696GB
POH 81
MD5 OK
122.49MiB/s on avg (~48 hours)
6 more days until the PB! :cool:Quote:
Originally Posted by Anvil
The 40GB drive has amazed me!
(got 3 more of them and I'll be keeping them, all of them are in use as boot drives with ~1TB of data written)
The 330 is rather nice as well, when prices settle it should be a great low cost alternative.
I need more time with the V4s, what I can say is that the 256GB drive does not behave like the 128GB.
One more reallocated sector on the X25-V, it is now 46.
MWI on the 330 changed to 99, should be able to find out exactly when using the log-file.
(current values are 21.81TB Host writes, NAND writes are at 15729GB)
Samsung 830 256GB Day 68
1,628,111.97GiB
1,589.95 TiB
279.63 MB/s Average
1615 Hours
7072 Wear Leveling Count
MWI 1
6/0 Erase/Program Fail
Used Reserved Block Count: 12/24572 sectors
It's getting... a little slow.
Just tried a secure erase on the vertex 4, but no dice ... the drive continues to die after a loop or two, disconnecting with the same error experienced before.
At least it seems that the drive lets you get your data off it though ... I guess it is a small blessing.
Vertex 4 being removed from testing with disgust! The end.
Gonna have to start thinking of a new drive to test.
This thread and Anvils app thread got "Sticky" designation. :clap:
About time. :up:
Woot and I see that Anvil even got the MOD tag ...gratz one of the few threads I make a point at looking at daily.
Congratz Anvil :)
My update comes later tonight. This nice weather must be enjoyed first. :cool:
Todays update:
m4
945.7750 TiB
3983 hours
Avg speed 74.36 MiB/s.
AD gone from 74 to 69.
P/E 16292.
MD5 OK.
Reallocated sectors : 00
http://www.diskusjon.no/index.php?ap...tach_id=492104
Intel X25-M G1 80GB
652.10 TiB
23295hours
Reallocated sectors : 161 to 162
Available Reserved space: 90
MWI=124
MD5 =OK
42.77 MiB/s on avg
http://www.diskusjon.no/index.php?ap...tach_id=492108
Intel X25-E 64GB
123.52 TiB
382-30=352 hours
Reallocated sectors : 0
Available Reserved space: 100
MWI=99
MD5 =OK
101.08 MiB/s on avg
http://www.diskusjon.no/index.php?ap...tach_id=492106
Samsung 830 256GB Day 68
1,645,138.28GiB
1,606.58 TiB
284.20 MB/s Average
1632 Hours
7146 Wear Leveling Count
MWI 1
6/0 Erase/Program Fail
Used Reserved Block Count: 12/24572 sectors
Attachment 127120
@canthearu
391.26TiB is the latest recording I've got for the V4, how much did the last effort add to this?
A pity about the V4, much too early.
--
The 330s MWI changed to 98 this afternoon, looks like it'll take a few readings before it stabilizes.
MWI 99
Host Writes F1 (241) 691942*32=21263GiB = 21.11TiB
NAND Writes F9 (249) 15230GB = 14.87TiB
MWI 98
Host Writes F1 (241) 957613*32=30643616 = 29.22TiB
NAND Writes F9 (249) 21086GB = 20.59TiB
Intel 330 120GB
30.64TB Host writes
Reallocated sectors : 05 0
Available Reserved Space : E8 100
MWI 98
[F1] Total LBAs Written 1003997
[F2] Total LBAs Read 22623
[F9] Total NAND Writes 22110GB
POH 106
MD5 OK
122.55MiB/s on avg (~9 hours)
--
Kingston SSDNow 40GB (X25-V)
985.91TB Host writes
Reallocated sectors : 05 46 up 1
Available Reserved Space : E8 99
POH 8831
MD5 OK
36.92MiB/s on avg (~9 hours)
--
Both drives had a short break 9 hours ago, I had to check that MD5 testing was correctly configured for the 330. (Host reads were stuck, all was OK)
... and Thanks!
RIP V4.
I guess there is not much more to do with current SATA technology, the SSD market is going to stabilize until SATA 12 Gbps comes. The question is, which company selling SSD will survive until then? All of them?
@Anvil
The v4 did virtually nothing while in zombie mode, so I'm going to take it from the time of the first error - (maybe 100GB overall added after first error, which is virtually nothing)
Vertex 4 Death Certificate:
Date of Death: 25/5/2012 - 8:15am (UTC +8 Timezone)
Days of Operation: Approx day 39
Cause of Death: Excessive bad blocks cause drive to enter panic lock state during erase phase.
Total ASU Writes are 400,650.26 GiB (391.25 TiB)
Total Host writes as per SMART 403,316.99 GiB (393.86 TiB)
Remaining life: 31 (61 new - 30 used on old firmware)
Disappointing result for a 128gb drive!
Opps, the poor old Intel 520 got left behind in all this commotion:
Intel 520 60GB - Day 93.5
Drive hours: 2,188
ASU GiB written: 693,156.65 GiB (676.91 TiB)
Avg MB/s: 93.47 MB/s
MD5: OK
Host GB written (F1): 698,113.12 GiB (681.75 TiB, 22339620 raw)
NAND writes (F9): 494,215 GiB (482.63 TiB)
Reallocated sectors (05): 0
Failure count (AB, AC): 0 program, 0 erase
Raw Error Rate (8B): 120 normalised
Avaliable Reserved Space (AA): 100 normalised
Media Wearout Indicator (E9): 1
The V4 did slightly better than the Octane... Not that either one performed
any kind of acceptable.
Christopher ... I'm less inclined to now believe that you simply got a drive with dodgy NAND. Something else is killing the NAND prematurely.
What could kill just one part of one NAND device? Who knows?Quote:
Originally Posted by canthearu
I've prepped up a new drive, the M3P 128GB. I should start it up soon, but preliminary testing shows that it should be able to just about match the 830 256GB's speed at half the capacity, and that pleases me.
UPDATE
The M3P is baking in the oven now... it doesn't look like the MWI works (I'm terribly angered by this), unless MWI is based on >5KPE cycles or something. Either that, or it's based solely on reallocations (very possible). It's averaging around 270MB/s for the first couple of hours.
@Christopher/ canthearu
The V4 and Octane both used IMFT 25nm? The first post does not indicate the NAND part number. Do you know what it is?
Edit:
According to the info in the first page of the thread there is a consistent premature failure of all drives that have used Indilinx controllers, regardless of model or NAND type used. Only two of the Indilinx drives managed to get past the MWI, but considering the NAND that was used in those drives they should have lasted longer. The other three failed well before the MWI expired.
There is nothing wrong with the Marvell controller. It has been used problem free by Intel & Micron for years. I’d say that this is clear evidence that Indilinx firmware is the problem and not the NAND.
• Crucial M225 64 GB – Samsung 51nm (SLC?) = 880 TB (Exceeded)
• OCZ Vertex Turbo 64 GB – Samsung 51nm (SLC?) = 116 TB (MWI – 58)
• OCZ Vertex Turbo 64 GB – Samsung 51nm (SLC)? = 499 TB (Exceeded)
• Octane 128 GB – Intel 25nm = 303.82 TB (MWI – 85)
• Vertex 4 128GB – Intel 25nm = 393 TB (MWI – 31)
I split the failed drives chart so that the drives that did not meet it's MWI specification are separated in a new chart.
(the original was getting crowded)
Attachment 127128
Attachment 127129
@Christopher
My 330 does not update Host Reads (it needs assistance), not sure how to handle it but it appears to be stuck until it's given a small break. (weird)
Could be the same thing with the M3P, give it some time, it might start moving.
270 MB/s is awesome for a 128GB drive, what are your "settings"?
Anvil, if I’m reading the table in the first post correctly it looks like the Kingston V100+ reached MWI 0 @ 196 TB. It then notched up a total of 368 TB before it died. It used 32nm Toshiba NAND, so I guess the P/E spec was 5K (?). (Actual = 6K+)
I noticed and did find it a bit strange
Host Writes/Capacity is not the same as MWI though so it could be that MWI still had some left.
(will have to go back and find some screenshots or look at the SMART attributes and values)
I can’t remember if P/E specs are based on the minimum or average count. It’s in the thread somewhere and I believe Intel stated it was the minimum, but I can’t be 100% sure.
If it is the minimum then relocations should (in theory) not occur until after the MWI has expired. If it is average it would be reasonable for relocations to occur.
It would be interesting to do a chart to see when relocations first appeared for each drive tested and map them to the P/E cycle count. I started to do it, but its way too much work to go through all the posts to find out. (Not too bad to do if the log files are still available).
Anyway let’s assume that the P/E count is based on the minimum count. A relocation event before the P/E count has expired should not occur. If it does occur it should be a limited and isolated occurrence. Relocations past the MWI should be expected, but as the X25-V and other drives have shown writes can go significantly past the MWI without resulting in major relocations. Compare that to the Octane and V4, which both used IMFT NAND (AFAIK).
$OCZ Octane (Relocations started at MWI 97 and then rapidly accelerated to 226 before total failure of the drive)
$OCZ Vertex 4 128 GB (Relocations started at MWI 52 and then rapidly accelerated to 243 before total failure drive.)
Samsung 830 256 GB – First relocation occurred past the MWI (1,160.90 TB) and has slowly increased to 12 having written a further 446 TB of data.
Edit:
As the MWI is based on the theoretical P/E count it should be possible to determine the combined sum of WA & WL for each drive that has been tested at the point that the MWI expired (assuming the drive reported decent SMART info).
Capacity *P/E spec / ((WA) * (WL)) = Total theoretical write capability
Ao1,
V4 128GB Intel 29F64G08ACME3
Octane 128GB Intel 29F64G08ACME2
The 830 really has 6, and not 12, reallocation events. Somehow, the 830's used reserved block count attribute is double runtime bad block count. Reallocated sector count is 2048 x Used Reserve.
Not sure why this is, exactly as I don't think it's using 2MB blocks, but I don't think it's had 12 reallocations regardless.
Anvil,
I just think Plextor couldn't add a traditional MWI. Like the Octane, the M3P is just using reallocations to determine MWI (the pre 1.03FW already possessed a reallocated sector count). This would have been much easier to add then a "real" MWI counter. All in all, I was very excited to see all the new attributes in 1.03, but it looks as though they're mostly useless (aside from the write counter).
Plextor M3P 128GB Day 0
12,267.39 GiB
11.98 TiB
268.31 MB/s Average
10 Hours
Rellocated Event Count 0
Attachment 127138
Attachment 127139
Samsung 830 256GB Day 69
1,665,964.47 GiB
1,626.91 TiB
299.17 MB/s Average
1653 Hours
7260 Wear Leveling Count
MWI 1
6/0 Erase/Program Fail
Used Reserved Block Count: 12/24572 sectors
The M3P is using the 9174-BLD2, Toshiba TH58TEG702HBA4C 24nm Toggle in 8 packages x4 die x32gbit.
I'm using 39.5 GB (42,479,930,379 bytes) static data.
Test officially started 27-May-2012 02:22:32 hours.