JorgeB

There are some known issues with some Samsung SSDs and AM3 chipsets, you could use a different controller, e.g. a 2 port Asmedia.

You don't need to wait for Limetech, key replacement is automatic.

There's appears to be an issue with IOMMU that's causing issues with one of the NVMe devices: Sep 21 19:38:00 Tower kernel: AMD-Vi: Completion-Wait loop timed out Sep 21 19:38:00 Tower kernel: AMD-Vi: Completion-Wait loop timed out Sep 21 19:38:00 Tower kernel: AMD-Vi: Completion-Wait loop timed out Sep 21 19:38:00 Tower kernel: AMD-Vi: Completion-Wait loop timed out Sep 21 19:38:00 Tower kernel: AMD-Vi: Completion-Wait loop timed out Sep 21 19:38:00 Tower kernel: nvme 0000:01:00.0: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x000000000eecd000 flags=0x0070] Sep 21 19:38:00 Tower kernel: nvme 0000:01:00.0: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x000000000eecd200 flags=0x0070] Sep 21 19:38:00 Tower kernel: nvme 0000:01:00.0: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x000000000eecd400 flags=0x0070] Sep 21 19:38:00 Tower kernel: nvme 0000:01:00.0: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x000000000eecd600 flags=0x0070] Sep 21 19:38:00 Tower kernel: nvme 0000:01:00.0: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x000000000eecd700 flags=0x0070] Sep 21 19:38:00 Tower kernel: nvme 0000:01:00.0: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x000000000eecd900 flags=0x0070] Sep 21 19:38:00 Tower kernel: nvme 0000:01:00.0: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x000000000eecdb00 flags=0x0070] Sep 21 19:38:00 Tower kernel: nvme 0000:01:00.0: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x000000000eecdd00 flags=0x0070] Sep 21 19:38:00 Tower kernel: nvme 0000:01:00.0: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x000000000eecde00 flags=0x0070] Sep 21 19:38:00 Tower kernel: nvme 0000:01:00.0: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x000000000eecdf00 flags=0x0070] Sep 21 19:38:00 Tower kernel: AMD-Vi: Event logged [IO_PAGE_FAULT device=01:00.0 domain=0x0000 address=0x000000000eece000 flags=0x0070] Sep 21 19:38:00 Tower kernel: AMD-Vi: Event logged [IO_PAGE_FAULT device=01:00.0 domain=0x0000 address=0x000000000eece200 flags=0x0070] Sep 21 19:38:00 Tower kernel: AMD-Vi: Event logged [IO_PAGE_FAULT device=01:00.0 domain=0x0000 address=0x000000000eece400 flags=0x0070] Sep 21 19:38:00 Tower kernel: AMD-Vi: Event logged [IO_PAGE_FAULT device=01:00.0 domain=0x0000 address=0x000000000eece600 flags=0x0070] Sep 21 19:38:00 Tower kernel: AMD-Vi: Event logged [IO_PAGE_FAULT device=01:00.0 domain=0x0000 address=0x000000000eece800 flags=0x0070] Sep 21 19:38:00 Tower kernel: AMD-Vi: Event logged [IO_PAGE_FAULT device=01:00.0 domain=0x0000 address=0x000000000eecea00 flags=0x0070] Sep 21 19:38:00 Tower kernel: AMD-Vi: Event logged [IO_PAGE_FAULT device=01:00.0 domain=0x0000 address=0x000000000eecec00 flags=0x0070] Sep 21 19:38:00 Tower kernel: AMD-Vi: Event logged [IO_PAGE_FAULT device=01:00.0 domain=0x0000 address=0x000000000eecee00 flags=0x0070] Sep 21 19:38:00 Tower kernel: AMD-Vi: Event logged [IO_PAGE_FAULT device=01:00.0 domain=0x0000 address=0x000000000eecf000 flags=0x0070] Sep 21 19:38:00 Tower kernel: AMD-Vi: Event logged [IO_PAGE_FAULT device=01:00.0 domain=0x0000 address=0x000000000eecf200 flags=0x0070] Sep 21 19:38:00 Tower kernel: BTRFS warning (device nvme0n1p1): csum failed root 5 ino 340162 off 15610699776 csum 0x496c4ed7 expected csum 0x276067eb mirror 2 Sep 21 19:38:00 Tower kernel: BTRFS warning (device nvme0n1p1): csum failed root 5 ino 340162 off 15610740736 csum 0x6a049d0f expected csum 0xf3ce5b4e mirror 2 Sep 21 19:38:00 Tower kernel: BTRFS warning (device nvme0n1p1): csum failed root 5 ino 340162 off 15610744832 csum 0x553ea8da expected csum 0xf96f8211 mirror 2 Sep 21 19:38:00 Tower kernel: BTRFS warning (device nvme0n1p1): csum failed root 5 ino 340162 off 15610703872 csum 0x5eb2f80a expected csum 0xd999aa21 mirror 2 Sep 21 19:38:00 Tower kernel: BTRFS warning (device nvme0n1p1): csum failed root 5 ino 340162 off 15610748928 csum 0x37e64c12 expected csum 0x91eb05dc mirror 2 Sep 21 19:38:00 Tower kernel: BTRFS warning (device nvme0n1p1): csum failed root 5 ino 340162 off 15610707968 csum 0x3d09f103 expected csum 0x1b86b19c mirror 2 Sep 21 19:38:00 Tower kernel: BTRFS warning (device nvme0n1p1): csum failed root 5 ino 340162 off 15610753024 csum 0xde65ec48 expected csum 0xf82ad979 mirror 2 Sep 21 19:38:00 Tower kernel: BTRFS warning (device nvme0n1p1): csum failed root 5 ino 340162 off 15610712064 csum 0xbd0c7e5e expected csum 0x8947912c mirror 2 I've see similar issues before with Ryzen boards but it usually affects the onboard SATA controller, in those cases updating to the latest Unraid beta usually helps, due to newer kernel, also look for a BIOS update.

Sep 21 13:22:22 BeastMode kernel: BTRFS error (device sdd1): err add delayed dir index item(index: 34) into the deletion tree of the delayed node(root id: 5, inode id: 32853371, errno: -17) Filesystem corruption on cache, best bet is to backup and re-format the pool.

SMART tests usually count down from 100% to 0.

This is the result of the improved tree checker on newer kernels, more info here, if if still mounts correctly with the older kernel easiest way is to backup and re-format the pool.

There are a lot of reported uncorrectable, run an extended SMART test, though they are not always reliable on flash devices.

If you have CA installed you can restore them all at once: previous apps.

Yes, if it's a redundant pool. Iit can also be the SSD failing, but there's no SMART report to check in the diags.

Thanks, confirmed it's a bug:

Problems with one of the cache devices: Sep 20 21:56:52 NAS kernel: sd 0:0:0:0: timing out command, waited 360s Sep 20 21:56:52 NAS kernel: sd 0:0:0:0: [sda] tag#0 UNKNOWN(0x2003) Result: hostbyte=0x00 driverbyte=0x08 Sep 20 21:56:52 NAS kernel: sd 0:0:0:0: [sda] tag#0 Sense Key : 0x4 [current] Sep 20 21:56:52 NAS kernel: sd 0:0:0:0: [sda] tag#0 ASC=0x44 ASCQ=0x0 Sep 20 21:56:52 NAS kernel: sd 0:0:0:0: [sda] tag#0 CDB: opcode=0x35 35 00 00 00 00 00 00 00 00 00 Sep 20 21:56:52 NAS kernel: print_req_error: I/O error, dev sda, sector 0 Sep 20 21:56:52 NAS kernel: BTRFS error (device sda1): bdev /dev/sda1 errs: wr 16, rd 0, flush 17, corrupt 0, gen 0 USB it not recommended for cache or array devices.

That suggests a bug, did you start with a clean beta25 install?

Then try without current ones, one at a time.

Still likely to use the mrsas drivers, instead of the HBA's mpt2sas driver, but like I said it might still work, and if you have one it's worth trying, just be aware of the limitations of using a RAID controller with Unraid.

That's a RAID controller, better option would be the 9400-16i, doesn't mean it won't work, just that's it's not recommended.

It should be about 300 to 600GB per hour, depending on the disks speed.

Currently there should be no need to run regular balances.

Simultaneous errors on multiple devices are more likely to corrupt a filesystem since errors will happen on more devices that Unraid can protect with parity.

luks means it's encrypted. Syslog doesn't show the beginning of the problem, but I still see a lot of these: Sep 19 09:24:43 pumbaa kernel: sd 1:0:11:0: Power-on or device reset occurred ... Sep 19 11:49:47 pumbaa kernel: sd 1:0:19:0: Power-on or device reset occurred Sep 19 11:49:47 pumbaa kernel: sd 1:0:18:0: Power-on or device reset occurred ... Sep 19 16:22:42 pumbaa kernel: sd 1:0:24:0: Power-on or device reset occurred These are happening frequently to multiple devices, this suggest there's still a power or connection problem.

That's not good, it has a SATA port multiplier, Asmedia if fine but only with two ports.

Don't know it but looks like a RAID controller.

No good x1 4 ports options, you have the 2 port x1 Asmedia and JMB582 controllers or the 5 port x2 JMB585 controller.

Any new PCIe devices?

Max officially supported RAM speed for your config is 2666Mhz, you're running it at 3000Mhz.