Is the 830 going to hit 6PB at this block failure rate?
Incidentally, looks like a typo on the WLC number...
Printable View
Is the 830 going to hit 6PB at this block failure rate?
Incidentally, looks like a typo on the WLC number...
When write amplification is taken into account, 24K Write Cycles sounds right. At 5.5PiB write, that is 22528 WLC. But that assumes a perfect 1.0 write amp. rate, which only a few SSDs can accomplish using compression (SandForce chips, I think). If we assume that 24781 WLC is the entire drive, then the drive has has 6.05 PiB written. 6.05 / 5.5 is a write amplification rate of ~ 1.1 Not too bad!
I believe so, but maybe not by much. There was a typo in the last update's WLC, this one is right. Incidentally, because the read and write failures are so steady and predictable, I think it bodes well for 6PB.
The WLC is probably accurate for the whole drive, but most WLCs are usually for just a single device/channel/etc. I figured WA at 1.1 -- if you take the LBA written and divide it by WLC you get about 231GB written per PE cycle. lBA writes are ahead of ASU by about 15GB (I "lost" some writes for about 14 hours one day).
And Since it came up, it looks like SF drives using non-2281 controllers (ones with better SMART data) have another attribute that shows GB erased in addition to host and raw writes. I'll have to perform some more in depth analysis, but it looks like the actual WA for a mostly incompressible workload is significantly higher than the host/raw number would indicate.
Here are todays update:
m4
1909.4236 TiB
7789 hours
Avg speed 73.58 MiB/s.
AD 35 to 29
P/E 32873
C3 136440144 to 172698757
01 41196 to 54019 (1)
CE 90
MD5 OK.
Reallocated sectors : 00
http://www.diskusjon.no/index.php?ap...tach_id=508041
Intel X25-E 64GB
1.27 PiB
4299-30=4269 hours
Reallocated sectors : 85 to 130
Available Reserved space: 66 to 65
MWI= 91
MD5 =OK
78.89 MiB/s on avg
http://www.diskusjon.no/index.php?ap...tach_id=508042
Mtron Pro 7025 32GB
Paused until new firmware is updated.
OCZ Vertex 1 120GB
Will start after an update to the latest firmware.
Here are todays update:
m4
1921.2473 TiB
7884 hours
Avg speed 73.46 MiB/s.
AD 29 to 23
P/E 33079
C3 172698757 to 221068763
01 54019 72375 (1)
CE 90
MD5 OK.
Reallocated sectors : 00
http://www.diskusjon.no/index.php?ap...tach_id=508144
Intel X25-E 64GB
1.29 PiB
4348-30=4318 hours
Reallocated sectors : 130 to 183
Available Reserved space: 65 to 63
MWI= 91
MD5 =OK
78.72 MiB/s on avg
http://www.diskusjon.no/index.php?ap...tach_id=508145
Mtron Pro 7025 32GB
Paused until new firmware is updated.
OCZ Vertex 1 120GB
Will start after an update to the latest firmware.
Kingston SSDNow 40GB (X25-V)
1348.84TB Host writes 44198881*32)
Reallocated sectors : 05 768 -
Available Reserved Space : E8 86 (86)
POH 12257
MD5 OK
32.02MiB/s on avg (~194 hours)
--
Here are todays update:
m4
1927.2346 TiB
7908 hours
Avg speed 73.42 MiB/s.
AD 23 to 18.
P/E 33183
C3 221068763 to 247252828
01 72375 to 82343 (1)
CE 90
MD5 OK.
Reallocated sectors : 00
http://www.diskusjon.no/index.php?ap...tach_id=508217
Intel X25-E 64GB
1.29 PiB
4372-30=4342 hours
Reallocated sectors : 183 to 205
Available Reserved space: 63 to 62
MWI= 91
MD5 =OK
78.72 MiB/s on avg
http://www.diskusjon.no/index.php?ap...tach_id=508218
Mtron Pro 7025 32GB
Paused until new firmware is updated.
OCZ Vertex 1 120GB
Will start after an update to the latest firmware.
Samsung 830 256GB Day 237
(GiB) 5,887,996
(TiB) 5,749
(PiB) 5.65
(Avg) 298.72 MB/s over the past 2000+ hours
(B1) Wear Leveling Count: 25,454
(B5) Program Fail Count: 0
(B6) Erase Fail Count: 17
(B7) Runtime Bad Block Count: 134
(05) Reallocated Sectors: 548864
Read Failures: 117
(POH) 5752
-------------------
It's chugging along still.
Shipment confirmed on a few 840 Pro's. (not meant for endurance testing though)
I'll be ordering a few non Pro's for testing, that is, if no one else had planned on testing the TLC's?
(anyways, testing more than one of these drives wouldn't hurt)
So, they are rapidly getting available in these parts of the world.
@Anvil
The TLC 840 sounds exciting :) There'll be no more drives for me before I get enough sparetime to fix the two that's been waiting the last couple of months. Looks like that won't happen before december.
Here are todays update:
m4
1945.4780 TiB
7983 hours
Avg speed 73.28 MiB/s.
AD 18 to 8.
P/E 33500
C3 247252828 to 337721144
01 82343 to 118725 (1)
CE 90
MD5 OK.
Reallocated sectors : 00
http://www.diskusjon.no/index.php?ap...tach_id=508476
Intel X25-E 64GB
1.31 PiB
4447-30=4417 hours
Reallocated sectors : 205 to 255 to 5
Available Reserved space: 62 to 61
MWI= 91
MD5 =OK
78.41 MiB/s on avg
http://www.diskusjon.no/index.php?ap...tach_id=508477
Mtron Pro 7025 32GB
Paused until new firmware is updated.
OCZ Vertex 1 120GB
Will start after an update to the latest firmware.
Anvil, waiting for the 120gig 840's to become avaliable. Other options include the intel 335, corsair neutron and plextor m5 pro.
I've ordered a samsung 840 TLC 120gig and a Plextor M5 pro 120gig
Will decide on the Plextor's fate after I play with it a bit .... but the 840 will burn :)
OK ;)
I might join in on testing the 840 at some later point, depending on your results.
The Pro's should be here by tomorrow, I'll play some on a PCIE 3.0 controller (9207) thats been sitting in it's box for a few months.
(A real shame that there has been no time to play)
I've got a few of the new Sammies in 120s, but not sure what I'm going to do with them yet.
Christopher: Someone has to help me work out if these samsung 840's are any good! :)
I'm impressed with the read speed. To be certain, the write speed is not in the 830 's class, but considering TLC has seven guard bands and 8 voltage levels, I think it's a miracle it works at all! It's still supposed to be 3K PE cycles (I think) but the MWI is based on 1K PEs.
Sequential and random reads are significanty better than the 256GB 830, while write speed is worse than the 64GB 830. All writes are limited to about 130MB/s. All in all, I'm incredibly impressed -- it's faster than many of the SLC drives I have, and I don't just mean the MTRONS.
------
THe 830 is up to 12.5 trillion LBAs written. It's not significant in any way, except it sounds like a whole lot.
I've just received my samsung 840 120gig .... Will have a play with it later.
I don't think i'll be able to part with the M5 Pro yet ....
Christopher ... I'm impressed with the read performance of the samsung 840 as well. It is certainly the match of any normal MLC drive.
Anyway, time to get down to business ... to start off with, some benchmarks for the samsung 840:
http://www.canthearu.com/samsung840/asssd.png http://www.canthearu.com/samsung840/crystaldiskmark.png
http://www.canthearu.com/samsung840/ASU-performance.png
Read performance is fantastic .... easily as good as any SATA 6 drive I've seen.
Write performance, while not as good, is still as good as your average 120gig sandforce drive .... which really is plenty for the tasks it needs to do.
Initial smart values
http://www.canthearu.com/samsung840/initalsmart.png
Still plenty of juicy data there!
I benched the Pro's last night (128GB and 256GB), will be posting tonight in the Storage forum.
The Pro's are rather nice :)
Drive Details:
Make: Samsung
Model: 840
Capacity GB: 128 GB
Interface: SATA 6Gb/s
Controller: Samsung MDX
NAND maker: Samsung
NAND process: 21nm TLC
NAND part#: unknown
NAND P/E spec: 1000 cycles
NAND type: Toggle Mode
Testing Environment:
OS: Windows 7 x64
Hardware Platform: Intel 1155 Z77
Test Details:
Static Data: 39.2 GB
Over-Provisioning: 0 GB
% Compression: 46%
ASU Endurance test Started:
http://www.canthearu.com/samsung840/ASUStarted.png
There is a problem with some 840s and LBA writes ; right now, F1 won't increment past 2.04TB and may reset with power cycles. It's hardly a big deal, so if you see it, don't think you're going crazy.