I've recently acquired 14 of used Toshiba PX04SVB320 SSDs off eBay.
For some strange reason, every time I access their SMART values using smartctl, their "Non-medium error count" values increment by 1. This is for all of them without an exception.
First I've installed them in a Dell R620 server with H710P RAID controller (Similar to LSI 9271-8i). Then I've installed them on a Supermicro server with LSI 9266-8i. The outcome was the same.
I'll test them on a HBA tomorrow to see if the cause is somehow the RAID card.
I've done a fio write test on one of them to see if that one's value go higher than others on the next check. But no, it made no difference. They were all just incremented by 1 again. So this has nothing to do with IO operations.
I'm actively using Toshiba PX02SMB160 series SSDs but I don't see this happening with them. They are SAS SSDs from the same maker, older generation, though.
I was wondering if anyone had something similar with any SAS SSDs.
From what I read "Non-medium error count" errors are just SCSI command errors which might be related to bad cable, backplane or card. But this doesn't seem to be the case here. So it might be some other SCSI command getting error'ed. Any idea what it might be?
Here is how I read those values. Note that there is only a second between these 2 commands and all the drives are idle.
And here's the complete SMART output of one:
For some strange reason, every time I access their SMART values using smartctl, their "Non-medium error count" values increment by 1. This is for all of them without an exception.
First I've installed them in a Dell R620 server with H710P RAID controller (Similar to LSI 9271-8i). Then I've installed them on a Supermicro server with LSI 9266-8i. The outcome was the same.
I'll test them on a HBA tomorrow to see if the cause is somehow the RAID card.
I've done a fio write test on one of them to see if that one's value go higher than others on the next check. But no, it made no difference. They were all just incremented by 1 again. So this has nothing to do with IO operations.
I'm actively using Toshiba PX02SMB160 series SSDs but I don't see this happening with them. They are SAS SSDs from the same maker, older generation, though.
I was wondering if anyone had something similar with any SAS SSDs.
From what I read "Non-medium error count" errors are just SCSI command errors which might be related to bad cable, backplane or card. But this doesn't seem to be the case here. So it might be some other SCSI command getting error'ed. Any idea what it might be?
Here is how I read those values. Note that there is only a second between these 2 commands and all the drives are idle.
Code:
root@debian:~# for i in {0..11}; do echo -e "\nDisk $i"; smartctl -a -d megaraid,$i /dev/sdb | grep 'Serial number\|Non-medium error count'; done
Disk 0
Serial number: 56G0A00KT40E
Non-medium error count: 143
Disk 1
Serial number: 56G0A00LT40E
Non-medium error count: 132
Disk 2
Serial number: 56G0A01DT40E
Non-medium error count: 140
Disk 3
Serial number: 56G0A00TT40E
Non-medium error count: 126
Disk 4
Serial number: 56G0A01GT40E
Non-medium error count: 136
Disk 5
Serial number: 56G0A00XT40E
Non-medium error count: 132
Disk 6
Serial number: 56G0A00AT40E
Non-medium error count: 139
Disk 7
Serial number: 56G0A00QT40E
Non-medium error count: 142
Disk 8
Serial number: 56G0A00NT40E
Non-medium error count: 143
Disk 9
Serial number: 56G0A00MT40E
Non-medium error count: 135
Disk 10
Serial number: 56G0A006T40E
Non-medium error count: 136
Disk 11
Serial number: 56E0A00LT40E
Non-medium error count: 276
root@debian:~# for i in {0..11}; do echo -e "\nDisk $i"; smartctl -a -d megaraid,$i /dev/sdb | grep 'Serial number\|Non-medium error count'; done
Disk 0
Serial number: 56G0A00KT40E
Non-medium error count: 144
Disk 1
Serial number: 56G0A00LT40E
Non-medium error count: 133
Disk 2
Serial number: 56G0A01DT40E
Non-medium error count: 141
Disk 3
Serial number: 56G0A00TT40E
Non-medium error count: 127
Disk 4
Serial number: 56G0A01GT40E
Non-medium error count: 137
Disk 5
Serial number: 56G0A00XT40E
Non-medium error count: 133
Disk 6
Serial number: 56G0A00AT40E
Non-medium error count: 140
Disk 7
Serial number: 56G0A00QT40E
Non-medium error count: 143
Disk 8
Serial number: 56G0A00NT40E
Non-medium error count: 144
Disk 9
Serial number: 56G0A00MT40E
Non-medium error count: 136
Disk 10
Serial number: 56G0A006T40E
Non-medium error count: 137
Disk 11
Serial number: 56E0A00LT40E
Non-medium error count: 277And here's the complete SMART output of one:
Code:
root@debian:~# smartctl -a -d megaraid,0 /dev/sdb
smartctl 6.4 2014-10-07 r4002 [x86_64-linux-3.16.0-4-amd64] (local build)
Copyright (C) 2002-14, Bruce Allen, Christian Franke, www.smartmontools.org
=== START OF INFORMATION SECTION ===
Vendor: TOSHIBA
Product: PX04SVB320
Revision: 0106
Compliance: SPC-4
User Capacity: 3,200,631,791,616 bytes [3.20 TB]
Logical block size: 512 bytes
Physical block size: 4096 bytes
LU is resource provisioned, LBPRZ=1
Rotation Rate: Solid State Device
Form Factor: 2.5 inches
Logical Unit id: 0x500003970c88f3b9
Serial number: 56G0A00KT40E
Device type: disk
Transport protocol: SAS (SPL-3)
Local Time is: Tue May 5 04:37:02 2020 UTC
SMART support is: Available - device has SMART capability.
SMART support is: Enabled
Temperature Warning: Enabled
=== START OF READ SMART DATA SECTION ===
SMART Health Status: OK
Percentage used endurance indicator: 0%
Current Drive Temperature: 23 C
Drive Trip Temperature: 64 C
Manufactured in week 20 of year 2016
defect list format 6 unknown
Elements in grown defect list: 0
Error counter log:
Errors Corrected by Total Correction Gigabytes Total
ECC rereads/ errors algorithm processed uncorrected
fast | delayed rewrites corrected invocations [10^9 bytes] errors
read: 0 0 0 0 0 7842.635 0
write: 0 0 0 0 0 3781.659 0
verify: 0 0 0 0 0 0.108 0
Non-medium error count: 145
SMART Self-test log
Num Test Status segment LifeTime LBA_first_err [SK ASC ASQ]
Description number (hours)
# 1 Background short Completed - 171 - [- - -]
# 2 Background short Completed - 171 - [- - -]
Long (extended) Self Test duration: 1800 seconds [30.0 minutes]
