Appreciate the recommendations.
Update:
badblocks has finished with 0/0/0 errors. I also ran a smart long on the rest of the drives and everything looks good. So maybe a cosmic ray hit my box at the time I created the Z2 pool but the plan now is to completely reload TrueNAS, create a new RAIDZ2 pool with all 8 drives, and the new pool for 24-48 hours. Still seems a bit odd to me but sometimes thats how things go. I figure after a create the new pool if I write 50TB of bunk data and then run a scrub that should hopefully put enough stress on the system the bring out any errors if they are going to happen again.
SMART info the the suspect drive after running badblocks:
truenas_admin@nas[~]$ sudo smartctl -a /dev/sdg
smartctl 7.4 2023-08-01 r5530 [x86_64-linux-6.6.44-production+truenas] (local build)
Copyright (C) 2002-23, Bruce Allen, Christian Franke, www.smartmontools.org
=== START OF INFORMATION SECTION ===
Model Family: Western Digital Ultrastar DC HC530
Device Model: WDC WUH721414ALE6L4
Serial Number: 9MGBVN0T
LU WWN Device Id: 5 000cca 290c5641b
Firmware Version: LDGNW400
User Capacity: 14,000,519,643,136 bytes [14.0 TB]
Sector Sizes: 512 bytes logical, 4096 bytes physical
Rotation Rate: 7200 rpm
Form Factor: 3.5 inches
Device is: In smartctl database 7.3/5528
ATA Version is: ACS-2, ATA8-ACS T13/1699-D revision 4
SATA Version is: SATA 3.2, 6.0 Gb/s (current: 6.0 Gb/s)
Local Time is: Sat Nov 16 14:37:10 2024 CST
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: (0x82) Offline data collection activity
was completed without error.
Auto Offline Data Collection: Enabled.
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: ( 101) seconds.
Offline data collection
capabilities: (0x5b) SMART execute Offline immediate.
Auto Offline data collection on/off support.
Suspend Offline collection upon new
command.
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: (1400) 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: 16
Vendor Specific SMART Attributes with Thresholds:
ID# ATTRIBUTE_NAME FLAG VALUE WORST THRESH TYPE UPDATED WHEN_FAILED RAW_VALUE
1 Raw_Read_Error_Rate 0x000b 100 100 001 Pre-fail Always - 0
2 Throughput_Performance 0x0005 137 137 054 Pre-fail Offline - 92
3 Spin_Up_Time 0x0007 096 096 001 Pre-fail Always - 159
4 Start_Stop_Count 0x0012 100 100 000 Old_age Always - 9
5 Reallocated_Sector_Ct 0x0033 100 100 001 Pre-fail Always - 0
7 Seek_Error_Rate 0x000b 100 100 001 Pre-fail Always - 0
8 Seek_Time_Performance 0x0005 128 128 020 Pre-fail Offline - 18
9 Power_On_Hours 0x0012 100 100 000 Old_age Always - 63
10 Spin_Retry_Count 0x0013 100 100 001 Pre-fail Always - 0
12 Power_Cycle_Count 0x0032 100 100 000 Old_age Always - 9
22 Helium_Level 0x0023 100 100 025 Pre-fail Always - 100
192 Power-Off_Retract_Count 0x0032 100 100 000 Old_age Always - 49
193 Load_Cycle_Count 0x0012 100 100 000 Old_age Always - 49
194 Temperature_Celsius 0x0002 063 063 000 Old_age Always - 32 (Min/Max 20/58)
196 Reallocated_Event_Count 0x0032 100 100 000 Old_age Always - 0
197 Current_Pending_Sector 0x0022 100 100 000 Old_age Always - 0
198 Offline_Uncorrectable 0x0008 100 100 000 Old_age Offline - 0
199 UDMA_CRC_Error_Count 0x000a 100 100 000 Old_age Always - 0
SMART Error Log Version: 1
No Errors Logged
SMART Self-test log structure revision number 1
Num Test_Description Status Remaining LifeTime(hours) LBA_of_first_error
# 1 Short offline Completed without error 00% 9 -
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
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.
The above only provides legacy SMART information - try 'smartctl -x' for more
Update 3:
And the mystery continues. After running badblocks on one of the suspicious drives and coming up with zero errors I reloaded TrueNAS and wrote about 20TB of bogus data. This morning I kicked off a scrub which faulted two of my drives, one of which being the 9MGBVN0T drive, I checked SMART and it reports nothing bad. Does anyone have any thoughts on this? I am going to try and RMA the drives but I have a feeling they are going to tell me to pound sand because all the other tests Iāve run clearly show there arenāt any problems.
Since itās been discussed before I am going to install a larger PSU tomorrow in case that is contributing but I would think the power/stress required to write 20TB would be about the same for a scrub. I also hooked up a kill-a-watt which shows itās currently consuming ~150 watts so I really donāt think itās the issue but at this point I am grasping at straws here and willing to try anything.
Output of zpool status
NAME STATE READ WRITE CKSUM
spinners ONLINE 0 0 0
raidz2-0 ONLINE 0 0 0
90559c5a-b761-4204-816b-0e8cc7cd9506 FAULTED 791 890 0 too many errors
41ff962a-64e4-452a-92b0-d0285ea73282 ONLINE 0 0 0
3fd69d0f-4e75-47c6-a5c1-b419418d2431 ONLINE 0 0 0
6fcd9e15-28e2-4d9d-92b7-2959e87c3c16 ONLINE 0 0 0
311f270b-7938-4796-b271-d294f6de14a2 ONLINE 0 0 0
fc6432da-a266-4c15-b0e6-6b4b30dd7172 ONLINE 0 0 0
892ad932-9cba-47d4-a19d-a883f8a31a19 FAULTED 1.55K 1.67K 0 too many errors
e284540f-4563-44b2-baa6-fcdf66ecea9d ONLINE 0 0 0
The faulted drive above with 1.55k read errors maps to the 9MGBVN0T drive. Hereās the SMART data for the 9MGBVN0T drive after starting the scrub and faulting the pool.
=== START OF INFORMATION SECTION ===
Model Family: Western Digital Ultrastar DC HC530
Device Model: WDC WUH721414ALE6L4
Serial Number: 9MGBVN0T
LU WWN Device Id: 5 000cca 290c5641b
Firmware Version: LDGNW400
User Capacity: 14,000,519,643,136 bytes [14.0 TB]
Sector Sizes: 512 bytes logical, 4096 bytes physical
Rotation Rate: 7200 rpm
Form Factor: 3.5 inches
Device is: In smartctl database 7.3/5528
ATA Version is: ACS-2, ATA8-ACS T13/1699-D revision 4
SATA Version is: SATA 3.2, 6.0 Gb/s (current: 6.0 Gb/s)
Local Time is: Sun Nov 17 06:02:22 2024 PST
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: (0x80) Offline data collection activity
was never started.
Auto Offline Data Collection: Enabled.
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: ( 101) seconds.
Offline data collection
capabilities: (0x5b) SMART execute Offline immediate.
Auto Offline data collection on/off support.
Suspend Offline collection upon new
command.
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: (1400) 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: 16
Vendor Specific SMART Attributes with Thresholds:
ID# ATTRIBUTE_NAME FLAG VALUE WORST THRESH TYPE UPDATED WHEN_FAILED RAW_VALUE
1 Raw_Read_Error_Rate 0x000b 100 100 001 Pre-fail Always - 0
2 Throughput_Performance 0x0005 137 137 054 Pre-fail Offline - 92
3 Spin_Up_Time 0x0007 092 092 001 Pre-fail Always - 318
4 Start_Stop_Count 0x0012 100 100 000 Old_age Always - 14
5 Reallocated_Sector_Ct 0x0033 100 100 001 Pre-fail Always - 0
7 Seek_Error_Rate 0x000b 100 100 001 Pre-fail Always - 0
8 Seek_Time_Performance 0x0005 128 128 020 Pre-fail Offline - 18
9 Power_On_Hours 0x0012 100 100 000 Old_age Always - 79
10 Spin_Retry_Count 0x0013 100 100 001 Pre-fail Always - 0
12 Power_Cycle_Count 0x0032 100 100 000 Old_age Always - 14
22 Helium_Level 0x0023 100 100 025 Pre-fail Always - 100
192 Power-Off_Retract_Count 0x0032 100 100 000 Old_age Always - 60
193 Load_Cycle_Count 0x0012 100 100 000 Old_age Always - 60
194 Temperature_Celsius 0x0002 063 063 000 Old_age Always - 32 (Min/Max 20/58)
196 Reallocated_Event_Count 0x0032 100 100 000 Old_age Always - 0
197 Current_Pending_Sector 0x0022 100 100 000 Old_age Always - 0
198 Offline_Uncorrectable 0x0008 100 100 000 Old_age Offline - 0
199 UDMA_CRC_Error_Count 0x000a 100 100 000 Old_age Always - 0
SMART Error Log Version: 1
No Errors Logged
SMART Self-test log structure revision number 1
Num Test_Description Status Remaining LifeTime(hours) LBA_of_first_error
# 1 Short offline Completed without error 00% 9 -
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
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.
The above only provides legacy SMART information - try 'smartctl -x' for more
tl;dr drives run just fine until I do a scrub. Right after scrub starts drives go to faulted. Please help.
I only see a single short smart test in the log you posted, run a long one.
Nevermind, I see you have tried but it doesnāt get logged.
Surely you should be able to RMA the drive based on that alone.
Any chance it is the wires? Moving them around make any changes on which disks are considered degraded?
1 Like
Good call! Iāll give that a try today.
Checksum errors on a drive withour SMART finding anything wrong could be issues with the controler and/or cables.
Someone recently reported he had eventually pinpoined drive errors toā¦ a fan being powered from the same rail as the drives: Moving the fan to a different power cable put an end to drive errors. Do not neglect anythingā¦
1 Like
Thanks for the pointers.
Other than the drive backplane the only other thing plugged directly into the PSU is the motherboard. Previously I had the fans at the rear of the backplane plugged into the mobo but Iāve since moved them back to being powered from the backplane as when the were on the mobo one of them was only spinning at 400 rpm.
Iāve got new SAS cables and power supply (Corsair RM750e, the same that is used in the 45 Drives HL15) ordered as of today.
I am currently running SMART long on the 9MGBVN0T drive as the rest of them have completed and did actually log to SMART, though I donāt expect there to be an issue here as all of the SMART data looks fine to me.
While I wait for cables and PSU I am going to do as Fleshmauler recommended and swap the drives around after the SMART test concludes, then I will clear the ZFS errors, initiate another scrub (that seems to be what triggers the failures), and see if the errors follow the drive or the slot. I may also take the drives out of the backplane and directly connect them to SATA cables after this test as well just to rule out the backplane itself.
Based off all the smart data and running of badblocks on one the 9MGBVN0T drive I feel like the problem has to be an underlying hardware issue and nothing to do with the driveā¦but at I guess weāll see where the troubleshooting goes. It really is slow going once you graduate to larger drives.
2 Likes
I had a high-quality PSU with 500 W for a while with 8 drives and it caused many problems. Since switching to 750 W everything is fine. Also PSUs age, so having some buffer is advisable.
For comparison: I have an old Dell PowerEdge R440 which has a dual 1200 W PSU. Yes it has 2 CPUs, but the 8 drive bays are 2.5".
2 Likes
Update 4:
Moved the drives around and run a scrub and the failures didnāt follow the backplane slots AND it is two totally different drives marked as faulted this time.
Luckily Iāve got a new PSU and SAS cables being delivered today. Going to swap those out and try one more time. If i still get failures I plan on trying the drives outside of the backplane.
Talk about a small project gone south; I am riding the struggle bus with this one.
Final update:
It appears to be stable now. I replaced both the PSU and the SFF-8482 to SATA cables at the same time so Iāll never really know which was the root cause but at this point I am over it.
I just wanted to thank everyone who commented again for their assistance.
4 Likes