dodgy smartctl output for Intel DC P3605

[hogfather]

Hello

I was hoping someone with experience with these drives, or similar, can shed some light on what I believe are incorrect smartctl numbers.  I bought two such drives from ebay for like 100 EUR each and they live a pretty hard life in my home lab where they are punished with mainly write intensive workloads.  The workloads are mainly my dev Kubernets setup which runs multiple Apache Pulsar clusters. 

From the stats I noticed that the "Data Units Read" and "Data Units Written" often reset back to 0 when they go past about 2.2 - 2.5TB.  I would imagine that these should be an aggregate of all data written to the drives.  One drives shows it's only been used 2%, but it's been on for 6.5 years.  I find that hard to believe and I actually have no idea how much data has been written to this particular drive.  The "Power On Hours" and "Power Cycles" seem to update correctly.
 

I read some posts on other forums where people we saying that these stats can be off. Is that true?  At the end of the day, I don't mind because none of my drives store important data for long. If anything the data is stored for a few hours before getting wiped and rewritten.  On the topic of writing, I'm certain that I have written more than 500 TB to the drive below which should amount to 5.7% (1.6TB @ 3 DWPD = 8760TB written), yet the "Percentage Used" hasn't moved.

 

$ sudo smartctl -a /dev/nvme0
smartctl 7.2 2020-12-30 r5155 [x86_64-linux-5.15.0-88-generic] (local build)
=== START OF INFORMATION SECTION ===
Model Number:                       INTEL SSDPEDME016T4S
Firmware Version:                   8DV1RA13
PCI Vendor ID:                      0x8086
PCI Vendor Subsystem ID:            0x108e

 

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

SMART/Health Information (NVMe Log 0x02)
Critical Warning:                   0x00
Temperature:                        34 Celsius
Available Spare:                    100%
Available Spare Threshold:          10%
Percentage Used:                    2%
Data Units Read:                    4,247,474 [2.17 TB]
Data Units Written:                 3,160,725 [1.61 TB]
Host Read Commands:                 144,368,876,738
Host Write Commands:                21,241,519,364
Controller Busy Time:               1,303
Power Cycles:                       62
Power On Hours:                     57,074
Unsafe Shutdowns:                   3
Media and Data Integrity Errors:    0
Error Information Log Entries:      0

Error Information (NVMe Log 0x01, 16 of 64 entries)
No Errors Logged

 

Any ideas or thoughts?

 

Cheers!

Edited January 9 by hogfather
typo in DWPD calculation

[Jarsky]

Yeah weird; DUR/DUW should be across the lifetime of the drive and shouldn't be resetting. It's odd because your HRC/HWC look pretty consistant with the Power On Hours. 

 

We can derive the total RW from the HRC/HWC values though if we know the sector size which is probably 512

 

Usage (TB's) = (HRC/HWC * 512)/10^12 would be our formula

 

So in your case the values would be:

73.88TB(R) = (144368876738 * 512)/10^12
10.90TB(W) = (21241519364 * 512)/10^12

 

 

[Jarsky]

Might want to also check if theres a firmware update for your SSD controller as well You can use the ISDCT tool for that
https://carll.medium.com/upgrading-the-firmware-of-intel-dc-series-ssds-in-linux-debian-458a704c087a

[hogfather]

Thanks for the reply @Jarsky. Good point on the firmware.  I tried ' sudo isdct show -intelssd' and it produces :

 

"FirmwareUpdateAvailable : No known update for SSD. If an update is expected, please contact your SSD Vendor representative about firmware update for this drive."

 

Which is actually correct, because as far as I know my drives are the 3605 versions, which were for Oracle (from memory).   I might try and find some Oracle tool to check the firmware with.

 

The calculation your provided make total sense, but I really don't trust the number from smartctl.

 

Anyway, thanks a bunch for taking a look.