Jul  1 06:51:45 UNRAID1 kernel: sas: I_T 0700000000000000 recovered

Jul  1 06:51:45 UNRAID1 kernel: sas: sas_ata_task_done: SAS error 8d

Jul  1 06:51:45 UNRAID1 kernel: ata23: sas eh calling libata port error handler

Jul  1 06:51:45 UNRAID1 kernel: ata24: sas eh calling libata port error handler

Jul  1 06:51:45 UNRAID1 kernel: ata25: sas eh calling libata port error handler

Jul  1 06:51:45 UNRAID1 kernel: ata26: sas eh calling libata port error handler

Jul  1 06:51:45 UNRAID1 kernel: ata27: sas eh calling libata port error handler

Jul  1 06:51:45 UNRAID1 kernel: ata28: sas eh calling libata port error handler

Jul  1 06:51:45 UNRAID1 kernel: ata28: failed to read log page 10h (errno=-2)

Jul  1 06:51:45 UNRAID1 kernel: ata28.00: exception Emask 0x1 SAct 0x1 SErr 0x0 action 0x6 t0

Jul  1 06:51:45 UNRAID1 kernel: ata28.00: failed command: READ FPDMA QUEUED

Jul  1 06:51:45 UNRAID1 kernel: ata28.00: cmd 60/10:00:27:a4:2f/00:00:86:00:00/40 tag 0 ncq 8192 in

Jul  1 06:51:45 UNRAID1 kernel:          res 01/04:04:1f:a4:2f/00:00:86:00:00/40 Emask 0x3 (HSM violation)

Jul  1 06:51:45 UNRAID1 kernel: ata28.00: status: { ERR }

Jul  1 06:51:45 UNRAID1 kernel: ata28.00: error: { ABRT }

Jul  1 06:51:45 UNRAID1 kernel: ata28: hard resetting link

Jul  1 06:51:45 UNRAID1 kernel: sas: sas_form_port: phy3 belongs to port5 already(1)!

Jul  1 06:51:47 UNRAID1 kernel: drivers/scsi/mvsas/mv_sas.c 1701:mvs_I_T_nexus_reset for device[3]:rc= 0

Jul  1 06:51:47 UNRAID1 kernel: sas: sas_ata_hard_reset: Found ATA device.

Jul  1 06:51:47 UNRAID1 kernel: ata28.00: configured for UDMA/133

Jul  1 06:51:47 UNRAID1 kernel: ata28: EH complete

Jul  1 06:51:47 UNRAID1 kernel: sas: --- Exit sas_scsi_recover_host

Jul  1 10:00:02 UNRAID1 kernel: sas: command 0xea0876c0, task 0xf749a3c0, timed out: BLK_EH_NOT_HANDLED

 

Brand new system, about a month old. First parity sync went fine and no problems.. now during my monthly parity sync I got this. I can't access the WebGUI but I can access everything else. Using 3x SAS2LP-MV8s in a Norco 4224. I don't understand the dupe file errors after this happened. I verified there is not dupe files, and Stationary is a "cache only" share.

 

EDIT: Restarted the system, no drives have any SMART errors. This seems like either one of the SAS2LP-MV8 controllers is faulty or driver issues?

syslog.txt

Please see 5.0RC3 - BLK_EH_NOT_HANDLED causes freeze.

 

(this topic should probably be merged into that one)

Thanks, feel free to merge if needed. So it is definitely a driver issue? Tom said on that thread he planned on releasing a modified version with a different driver but it never seemed to happen.

 

EDIT: Went back to B14 as some suggested on the thread. My parity speed on RC5 peaked at ~75MB/s and averaged about ~60MB/s. I'm seeing sustained 100-107MB/s on B14 (currently at 3%). I would say there definitely are some issues. Guess I will wait for RC6 and hope it is fixed...