I'm running debian stable with a 2 x nvme Raid 1.
Here is the hardware/hoster it's running on
https://www.hetzner.com/dedicated-rootserver/ex62-nvme?country=us
Almost every second day mdadm monitoring reports a fail event and leaves the array degraded.
It only disables 1 partition as you can see here:
This is an automatically generated mail message from mdadm
running on xxx
A Fail event had been detected on md device /dev/md/2.
It could be related to component device /dev/nvme1n1p3.
Faithfully yours, etc.
P.S. The /proc/mdstat file currently contains the following:
Personalities : [raid1] [linear] [multipath] [raid0] [raid6] [raid5] [raid4] [raid10]
md2 : active raid1 nvme1n1p3[1](F) nvme0n1p3[0]
465895744 blocks super 1.2 [2/1] [U_]
bitmap: 4/4 pages [16KB], 65536KB chunk
md0 : active (auto-read-only) raid1 nvme1n1p1[1] nvme0n1p1[0]
33521664 blocks super 1.2 [2/2] [UU]
md1 : active raid1 nvme0n1p2[0] nvme1n1p2[1]
523712 blocks super 1.2 [2/2] [UU]
unused devices: <none>
This happens on both disks. One time it's nvme0n1p3 and next time it's nvme1n1p3.
I then just re-add the failed partition with
mdadm --re-add /dev/md2 /dev/nvme0n1p3
or
mdadm --re-add /dev/md2 /dev/nvme1n1p3
and after the resync it works for a day or two.
In dmesg I found this:
[94879.144892] nvme nvme1: I/O 311 QID 1 timeout, reset controller
[94879.252851] nvme nvme1: completing aborted command with status: 0007
[94879.252970] blk_update_request: I/O error, dev nvme1n1, sector 452352001
[94879.253091] nvme nvme1: completing aborted command with status: fffffffc
[94879.253223] blk_update_request: I/O error, dev nvme1n1, sector 68159504
[94879.253418] md: super_written gets error=-5
I tried to check the health of the devices with these commands, but they don't give me stats like "Reallocated_Sector_Ct" or "Reported_Uncorrect".
smartctl -x /dev/nvme1
smartctl 6.6 2016-05-31 r4324 [x86_64-linux-4.9.0-8-amd64] (local build)
Copyright (C) 2002-16, Bruce Allen, Christian Franke, www.smartmontools.org
=== START OF INFORMATION SECTION ===
Model Number: KXG50ZNV512G TOSHIBA
Serial Number: 28SS10F6TYST
Firmware Version: AAGA4102
PCI Vendor/Subsystem ID: 0x1179
IEEE OUI Identifier: 0x00080d
Total NVM Capacity: 512,110,190,592 [512 GB]
Unallocated NVM Capacity: 0
Controller ID: 0
Number of Namespaces: 1
Namespace 1 Size/Capacity: 512,110,190,592 [512 GB]
Namespace 1 Formatted LBA Size: 512
Local Time is: Mon May 13 10:34:11 2019 CEST
Firmware Updates (0x14): 2 Slots, no Reset required
Optional Admin Commands (0x0017): Security Format Frmw_DL *Other*
Optional NVM Commands (0x005f): Comp Wr_Unc DS_Mngmt Wr_Zero Sav/Sel_Feat *Other*
Maximum Data Transfer Size: 512 Pages
Warning Comp. Temp. Threshold: 78 Celsius
Critical Comp. Temp. Threshold: 82 Celsius
Namespace 1 Features (0x02): NA_Fields
Supported Power States
St Op Max Active Idle RL RT WL WT Ent_Lat Ex_Lat
0 + 6.00W - - 0 0 0 0 0 0
1 + 2.40W - - 1 1 1 1 0 0
2 + 1.90W - - 2 2 2 2 0 0
3 - 0.0500W - - 3 3 3 3 1500 1500
4 - 0.0050W - - 4 4 4 4 6000 14000
5 - 0.0030W - - 5 5 5 5 50000 80000
Supported LBA Sizes (NSID 0x1)
Id Fmt Data Metadt Rel_Perf
0 + 512 0 2
1 - 4096 0 1
=== START OF SMART DATA SECTION ===
SMART overall-health self-assessment test result: PASSED
SMART/Health Information (NVMe Log 0x02, NSID 0xffffffff)
Critical Warning: 0x00
Temperature: 47 Celsius
Available Spare: 100%
Available Spare Threshold: 10%
Percentage Used: 57%
Data Units Read: 31,858,921 [16.3 TB]
Data Units Written: 293,589,002 [150 TB]
Host Read Commands: 4,130,502,428
Host Write Commands: 889,121,505
Controller Busy Time: 13,552
Power Cycles: 7
Power On Hours: 6,720
Unsafe Shutdowns: 0
Media and Data Integrity Errors: 0
Error Information Log Entries: 0
Warning Comp. Temperature Time: 0
Critical Comp. Temperature Time: 0
Temperature Sensor 1: 47 Celsius
Error Information (NVMe Log 0x01, max 128 entries)
No Errors Logged
nvme smart-log /dev/nvme1
Smart Log for NVME device:nvme1 namespace-id:ffffffff
critical_warning : 0
temperature : 47 C
available_spare : 100%
available_spare_threshold : 10%
percentage_used : 57%
data_units_read : 31,858,921
data_units_written : 293,589,023
host_read_commands : 4,130,502,429
host_write_commands : 889,122,059
controller_busy_time : 13,552
power_cycles : 7
power_on_hours : 6,720
unsafe_shutdowns : 0
media_errors : 0
num_err_log_entries : 0
Warning Temperature Time : 0
Critical Composite Temperature Time : 0
Temperature Sensor 1 : 47 C
Temperature Sensor 2 : 0 C
Temperature Sensor 3 : 0 C
Temperature Sensor 4 : 0 C
Temperature Sensor 5 : 0 C
Temperature Sensor 6 : 0 C
Temperature Sensor 7 : 0 C
Temperature Sensor 8 : 0 C
nvme smart-log-add /dev/nvme1
NVMe Status:INVALID_LOG_PAGE(4109)
smartctl -A /dev/nvme1
smartctl 6.6 2016-05-31 r4324 [x86_64-linux-4.9.0-8-amd64] (local build)
Copyright (C) 2002-16, Bruce Allen, Christian Franke, www.smartmontools.org
=== START OF SMART DATA SECTION ===
SMART/Health Information (NVMe Log 0x02, NSID 0xffffffff)
Critical Warning: 0x00
Temperature: 46 Celsius
Available Spare: 100%
Available Spare Threshold: 10%
Percentage Used: 57%
Data Units Read: 31,858,924 [16.3 TB]
Data Units Written: 293,591,327 [150 TB]
Host Read Commands: 4,130,502,490
Host Write Commands: 889,172,096
Controller Busy Time: 13,552
Power Cycles: 7
Power On Hours: 6,721
Unsafe Shutdowns: 0
Media and Data Integrity Errors: 0
Error Information Log Entries: 0
Warning Comp. Temperature Time: 0
Critical Comp. Temperature Time: 0
Temperature Sensor 1: 46 Celsius
I only noticed the issue after apache failed to start and I repaired the filesystem with fsck.ext4 -f. Before I didn't have setup root mail correctly.
So looks to me like a hardware error and I should get rid of both nvmes.
Is there anything I can try to fix these issues and save the nvmes? Or at least to get all the smart values like "Reported_Uncorrect" or "Offline_Uncorrectable".
