Got 6 Samsung 870 EVO - 100% failure rate

HI Guys, had 6 of these (4TB version) and 100% are dead. For one i RMAd it, got a new one and the new one died again as well!

Used with MOBO sata and broadcom controller.

Scanning 3 which are still alive and they have THOUSANDS of bad blocks. Didn't realized how bad it is because i was using these for RAID10 array and the data was rarely read. OS stopped booting, i was able to get most important data back. Don't buy these. Even cheapest SSDs are better. Slow but not silently failing.

 

Could it be that a firmware update came out to fix the bugs and you ended up forgetting to update and that's why it was defective? if you had updated will be that the ssd would be good?
or is there no firmware update for it?

 

I guess the update to fix the read-only bug is for NVMe SSDs, which are incorrectly going into readonly mode. Sure that can be fixed as totally good drive is getting write-locked.

For my SSDs it's flash chips failure, something different. There's no update for that...

Badblock test is still running. Probably these drives would fail after couple months, but i had rare reads and 4 of them were working in Raid10

 

Look at this... that's unbelivable. 6 of 6 are dead.

root@debian:~# smartctl --all /dev/sdc
smartctl 7.2 2020-12-30 r5155 [x86_64-linux-5.10.0-23-amd64] (local build)
Copyright (C) 2002-20, Bruce Allen, Christian Franke, www.smartmontools.org

=== START OF INFORMATION SECTION ===
Device Model: Samsung SSD 870 EVO 4TB
Serial Number: S6BCNJ0R909371E
LU WWN Device Id: 5 002538 f3191dd03
Firmware Version: SVT01B6Q
User Capacity: 4,000,787,030,016 bytes [4.00 TB]
Sector Size: 512 bytes logical/physical
Rotation Rate: Solid State Device
Form Factor: 2.5 inches
TRIM Command: Available, deterministic, zeroed
Device is: Not in smartctl database [for details use: -P showall]
ATA Version is: ACS-4 T13/BSR INCITS 529 revision 5
SATA Version is: SATA 3.3, 6.0 Gb/s (current: 6.0 Gb/s)
Local Time is: Fri May 26 09:24:22 2023 EDT
SMART support is: Available - device has SMART capability.
SMART support is: Enabled

=== START OF READ SMART DATA SECTION ===
SMART overall-health self-assessment test result: PASSED

General SMART Values:
Offline data collection status: (0x00) Offline data collection activity
was never started.
Auto Offline Data Collection: Disabled.
Self-test execution status: ( 0) The previous self-test routine completed
without error or no self-test has ever
been run.
Total time to complete Offline
data collection: ( 0) seconds.
Offline data collection
capabilities: (0x53) SMART execute Offline immediate.
Auto Offline data collection on/off support.
Suspend Offline collection upon new
command.
No Offline surface scan supported.
Self-test supported.
No Conveyance Self-test supported.
Selective Self-test supported.
SMART capabilities: (0x0003) Saves SMART data before entering
power-saving mode.
Supports SMART auto save timer.
Error logging capability: (0x01) Error logging supported.
General Purpose Logging supported.
Short self-test routine
recommended polling time: ( 2) minutes.
Extended self-test routine
recommended polling time: ( 320) minutes.
SCT capabilities: (0x003d) SCT Status supported.
SCT Error Recovery Control supported.
SCT Feature Control supported.
SCT Data Table supported.

SMART Attributes Data Structure revision number: 1
Vendor Specific SMART Attributes with Thresholds:
ID# ATTRIBUTE_NAME FLAG VALUE WORST THRESH TYPE UPDATED WHEN_FAILED RAW_VALUE
5 Reallocated_Sector_Ct 0x0033 094 094 010 Pre-fail Always - 256
9 Power_On_Hours 0x0032 097 097 000 Old_age Always - 12905
12 Power_Cycle_Count 0x0032 099 099 000 Old_age Always - 23
177 Wear_Leveling_Count 0x0013 098 098 000 Pre-fail Always - 38
179 Used_Rsvd_Blk_Cnt_Tot 0x0013 094 094 010 Pre-fail Always - 256
181 Program_Fail_Cnt_Total 0x0032 100 100 010 Old_age Always - 0
182 Erase_Fail_Count_Total 0x0032 100 100 010 Old_age Always - 0
183 Runtime_Bad_Block 0x0013 094 094 010 Pre-fail Always - 256
187 Reported_Uncorrect 0x0032 099 099 000 Old_age Always - 9912
190 Airflow_Temperature_Cel 0x0032 060 050 000 Old_age Always - 40
195 Hardware_ECC_Recovered 0x001a 199 199 000 Old_age Always - 9912
199 UDMA_CRC_Error_Count 0x003e 100 100 000 Old_age Always - 0
235 Unknown_Attribute 0x0012 099 099 000 Old_age Always - 9
241 Total_LBAs_Written 0x0032 099 099 000 Old_age Always - 127954384698

SMART Error Log Version: 1
ATA Error Count: 9916 (device log contains only the most recent five errors)
CR = Command Register [HEX]
FR = Features Register [HEX]
SC = Sector Count Register [HEX]
SN = Sector Number Register [HEX]
CL = Cylinder Low Register [HEX]
CH = Cylinder High Register [HEX]
DH = Device/Head Register [HEX]
DC = Device Command Register [HEX]
ER = Error register [HEX]
ST = Status register [HEX]
Powered_Up_Time is measured from power on, and printed as
DDd+hh:mm:SS.sss where DD=days, hh=hours, mm=minutes,
SS=sec, and sss=millisec. It "wraps" after 49.710 days.

Error 9916 occurred at disk power-on lifetime: 12905 hours (537 days + 17 hours)
When the command that caused the error occurred, the device was active or idle.

After command completion occurred, registers were:
ER ST SC SN CL CH DH
-- -- -- -- -- -- --
40 51 90 d8 41 39 40 Error: UNC at LBA = 0x003941d8 = 3752408

Commands leading to the command that caused the error were:
CR FR SC SN CL CH DH DC Powered_Up_Time Command/Feature_Name
-- -- -- -- -- -- -- -- ---------------- --------------------
60 08 90 d8 41 39 40 12 18:52:32.848 READ FPDMA QUEUED
b0 d5 01 00 4f c2 40 00 18:52:32.848 SMART READ LOG
47 00 01 30 06 00 40 00 18:52:32.848 READ LOG DMA EXT
47 00 01 30 00 00 40 00 18:52:32.848 READ LOG DMA EXT
47 00 01 00 00 00 40 00 18:52:32.848 READ LOG DMA EXT

Error 9915 occurred at disk power-on lifetime: 12905 hours (537 days + 17 hours)
When the command that caused the error occurred, the device was active or idle.

After command completion occurred, registers were:
ER ST SC SN CL CH DH
-- -- -- -- -- -- --
40 51 00 d8 41 39 40 Error: UNC at LBA = 0x003941d8 = 3752408

Commands leading to the command that caused the error were:
CR FR SC SN CL CH DH DC Powered_Up_Time Command/Feature_Name
-- -- -- -- -- -- -- -- ---------------- --------------------
60 08 00 d8 41 39 40 00 18:52:32.661 READ FPDMA QUEUED
b0 da 00 00 4f c2 40 0e 18:52:32.661 SMART RETURN STATUS
47 00 01 30 06 00 40 0e 18:52:32.661 READ LOG DMA EXT
47 00 01 30 00 00 40 0e 18:52:32.661 READ LOG DMA EXT
47 00 01 00 00 00 40 0e 18:52:32.661 READ LOG DMA EXT

Error 9914 occurred at disk power-on lifetime: 12905 hours (537 days + 17 hours)
When the command that caused the error occurred, the device was active or idle.

After command completion occurred, registers were:
ER ST SC SN CL CH DH
-- -- -- -- -- -- --
40 51 70 d8 41 39 40 Error: UNC at LBA = 0x003941d8 = 3752408

Commands leading to the command that caused the error were:
CR FR SC SN CL CH DH DC Powered_Up_Time Command/Feature_Name
-- -- -- -- -- -- -- -- ---------------- --------------------
60 08 70 d8 41 39 40 0e 18:52:32.473 READ FPDMA QUEUED
b0 d1 01 01 4f c2 40 09 18:52:32.473 SMART READ ATTRIBUTE THRESHOLDS [OBS-4]
47 00 01 30 06 00 40 09 18:52:32.473 READ LOG DMA EXT
47 00 01 30 00 00 40 09 18:52:32.473 READ LOG DMA EXT
47 00 01 00 00 00 40 09 18:52:32.473 READ LOG DMA EXT

Error 9913 occurred at disk power-on lifetime: 12905 hours (537 days + 17 hours)
When the command that caused the error occurred, the device was active or idle.

After command completion occurred, registers were:
ER ST SC SN CL CH DH
-- -- -- -- -- -- --
40 51 48 d8 41 39 40 Error: UNC at LBA = 0x003941d8 = 3752408

Commands leading to the command that caused the error were:
CR FR SC SN CL CH DH DC Powered_Up_Time Command/Feature_Name
-- -- -- -- -- -- -- -- ---------------- --------------------
60 08 48 d8 41 39 40 09 18:52:32.285 READ FPDMA QUEUED
b0 d0 01 00 4f c2 40 07 18:52:32.285 SMART READ DATA
47 00 01 30 06 00 40 07 18:52:32.285 READ LOG DMA EXT
47 00 01 30 00 00 40 07 18:52:32.285 READ LOG DMA EXT
47 00 01 00 00 00 40 07 18:52:32.285 READ LOG DMA EXT

Error 9912 occurred at disk power-on lifetime: 12905 hours (537 days + 17 hours)
When the command that caused the error occurred, the device was active or idle.

After command completion occurred, registers were:
ER ST SC SN CL CH DH
-- -- -- -- -- -- --
40 51 38 d8 41 39 40 Error: UNC at LBA = 0x003941d8 = 3752408

Commands leading to the command that caused the error were:
CR FR SC SN CL CH DH DC Powered_Up_Time Command/Feature_Name
-- -- -- -- -- -- -- -- ---------------- --------------------
60 08 38 d8 41 39 40 07 18:52:32.102 READ FPDMA QUEUED
ec 00 01 00 00 00 40 05 18:52:32.102 IDENTIFY DEVICE
60 08 28 d0 41 39 40 05 18:52:32.102 READ FPDMA QUEUED
ec 00 01 00 00 00 40 0f 18:52:32.102 IDENTIFY DEVICE
47 00 01 30 06 00 40 0f 18:52:32.102 READ LOG DMA EXT

SMART Self-test log structure revision number 1
Num Test_Description Status Remaining LifeTime(hours) LBA_of_first_error
# 1 Extended offline Completed: read failure 90% 12886 37555416
# 2 Extended offline Completed: read failure 90% 12885 37555416

SMART Selective self-test log data structure revision number 1
SPAN MIN_LBA MAX_LBA CURRENT_TEST_STATUS
1 0 0 Not_testing
2 0 0 Not_testing
3 0 0 Not_testing
4 0 0 Not_testing
5 0 0 Not_testing
256 0 65535 Read_scanning was never started
Selective self-test flags (0x0):
After scanning selected spans, do NOT read-scan remainder of disk.
If Selective self-test is pending on power-up, resume after 0 minute delay.

 

"disk power-on lifetime: 12905 hours (537 days + 17 hours)", maybe you wrote a ton of data, also maybe RAID usage killed them.

 

Old ass news.
https://www.techpowerup.com/forums/...ware-certain-batches-prone-to-failure.291504/

 

it's gone a bit downhill for samsung since the excellent 850 series (got three of those working like a charm for like 7 or 8 years, two Pro's and one Evo).

 

(127954384698*512)/1024/1024/1024/1024 =~ 59.6TBW. Rated for 2400 TBW, that's not even 10%

Also the other 2 were not working in raid (that's why probably they failed much sooner).

 

Yeah i mean man, one from 6 is bad luck. Even 2 can be bad luck but 100% failure rate that's f* up considering how much RMA will cost them...

Im running these tests and they just started, already got over 15k bad block on one.

 

they're qlc, right ?

 

tlc, the supposedly "better" and "premium" ones QLC is like 1.5x cheaper, wondering how shitty that is

 

Damn. Now I'm afraid to get another 970 Evo (2TB this time, already have the 1TB model) as Samsung has dropped the prices significantly. Costs 100 bucks now. But I hear more and more disaster stories about Samsung. Go Intel, I guess?

 

Ouch. That just killed Samsung storage for me.

 

Guys the best part is that only around 10% of the drives got checked ... so OMFG, if i have 10k errors now probably it'll be like 50k bad blocks when i finish

 

Contacted samsung rep today, to see what's the deal about V6 manufacturing process because also wanted to buy some to get these ones to RMA and move data, but these dumbasses "won't give any information", it's a clown show... they won't even lie they fixed anything. They also won't tell how much returns they have so i'm not even able to pick ANYTHING from samsung which could work lol

I'm thinking about RMA'ing it and selling for half price or 1/3 on local ebay tbh, because my linux totally crashed on raid10 if i had it in "normal" setup probably half files would be gone. You're right that the price is great but seriously this piece of crap isn't able to retain any data for any sane amount of time. For the first drive I RMA'd it because i lost all my VM's which were stored on the drive. Had many large files, wasn't able to fully read anything from it in full because there was always a badblock somewhere. Seems to be happening to data which isn't touched for a while.

For me goodram was ok, but slow. Got an intel, but that was enterprise drive. As for something comparable to samsung seems crucial 500MX is ok, but using it for short time so can't tell for sure if that is ok...

 

I run some MX500: 500GB, 1TB, 2x 2TB (in various machines).
They have DRAM and SLC cache and perform well as single drive or raid drives (raid1). And they are very cheap right now.

 

Man, what are the odds of buying 6 drives and all of them failing!?...

 

High during the occurrence of a bad batch when all drives have close manufacturing dates.

 

Tonight I ran an extended SMART self-test on my 870 EVO. For the life of me I cannot figure out how to view the results.

 

Just install Smasung Magician app and it will tell you the status in human language.