I have the same issue with three 6TB WD Red Plus. There is no problem until zfs scrub runs. Maybe it is not a sata bus problem, but a disk problem. All reports here seems to use WD Red disks and you can find similar reports for this disks and zfs with other hardware.
I will test my three disks in an other hardware this weekend to check if it is a helios problem or a disk problem.
Model Family: Western Digital Red
Device Model: WDC WD60EFRX-68L0BN1
Firmware Version: 82.00A82
[363042.880705] ata2.00: exception Emask 0x2 SAct 0x100060 SErr 0x400 action 0x6
[363042.880715] ata2.00: irq_stat 0x08000000
[363042.880722] ata2: SError: { Proto }
[363042.880730] ata2.00: failed command: READ FPDMA QUEUED
[363042.880741] ata2.00: cmd 60/80:28:20:14:60/00:00:0b:00:00/40 tag 5 ncq dma 65536 in
res 40/00:28:20:14:60/00:00:0b:00:00/40 Emask 0x2 (HSM violation)
[363042.880746] ata2.00: status: { DRDY }
[363042.880751] ata2.00: failed command: READ FPDMA QUEUED
[363042.880761] ata2.00: cmd 60/00:30:a0:14:60/01:00:0b:00:00/40 tag 6 ncq dma 131072 in
res 40/00:28:20:14:60/00:00:0b:00:00/40 Emask 0x2 (HSM violation)
[363042.880765] ata2.00: status: { DRDY }
[363042.880770] ata2.00: failed command: READ FPDMA QUEUED
[363042.880779] ata2.00: cmd 60/80:a0:a0:15:60/00:00:0b:00:00/40 tag 20 ncq dma 65536 in
res 40/00:28:20:14:60/00:00:0b:00:00/40 Emask 0x2 (HSM violation)
[363042.880783] ata2.00: status: { DRDY }
[363042.880793] ata2: hard resetting link
[363043.356670] ata2: SATA link up 6.0 Gbps (SStatus 133 SControl 300)
[363043.357984] ata2.00: configured for UDMA/133
[363043.358054] sd 1:0:0:0: [sdb] tag#5 UNKNOWN(0x2003) Result: hostbyte=0x00 driverbyte=0x08 cmd_age=0s
[363043.358062] sd 1:0:0:0: [sdb] tag#5 Sense Key : 0x5 [current]
[363043.358068] sd 1:0:0:0: [sdb] tag#5 ASC=0x21 ASCQ=0x4
[363043.358076] sd 1:0:0:0: [sdb] tag#5 CDB: opcode=0x88 88 00 00 00 00 00 0b 60 14 20 00 00 00 80 00 00
[363043.358084] blk_update_request: I/O error, dev sdb, sector 190845984 op 0x0:(READ) flags 0x700 phys_seg 1 prio class 0
[363043.358098] zio pool=datastore vdev=/dev/disk/by-id/ata-WDC_WD60EFRX-68L0BN1_WD-WX72D507JSP5-part1 error=5 type=1 offset=97712095232 size=65536 flags=1808b0
[363043.358145] sd 1:0:0:0: [sdb] tag#6 UNKNOWN(0x2003) Result: hostbyte=0x00 driverbyte=0x08 cmd_age=0s
[363043.358152] sd 1:0:0:0: [sdb] tag#6 Sense Key : 0x5 [current]
[363043.358157] sd 1:0:0:0: [sdb] tag#6 ASC=0x21 ASCQ=0x4
[363043.358163] sd 1:0:0:0: [sdb] tag#6 CDB: opcode=0x88 88 00 00 00 00 00 0b 60 14 a0 00 00 01 00 00 00
[363043.358170] blk_update_request: I/O error, dev sdb, sector 190846112 op 0x0:(READ) flags 0x700 phys_seg 2 prio class 0
[363043.358178] zio pool=datastore vdev=/dev/disk/by-id/ata-WDC_WD60EFRX-68L0BN1_WD-WX72D507JSP5-part1 error=5 type=1 offset=97712160768 size=131072 flags=40080cb0
[363043.358214] sd 1:0:0:0: [sdb] tag#20 UNKNOWN(0x2003) Result: hostbyte=0x00 driverbyte=0x08 cmd_age=0s
[363043.358220] sd 1:0:0:0: [sdb] tag#20 Sense Key : 0x5 [current]
[363043.358226] sd 1:0:0:0: [sdb] tag#20 ASC=0x21 ASCQ=0x4
[363043.358232] sd 1:0:0:0: [sdb] tag#20 CDB: opcode=0x88 88 00 00 00 00 00 0b 60 15 a0 00 00 00 80 00 00
[363043.358239] blk_update_request: I/O error, dev sdb, sector 190846368 op 0x0:(READ) flags 0x700 phys_seg 16 prio class 0
[363043.358248] zio pool=datastore vdev=/dev/disk/by-id/ata-WDC_WD60EFRX-68L0BN1_WD-WX72D507JSP5-part1 error=5 type=1 offset=97712291840 size=65536 flags=1808b0
[363043.358275] ata2: EH complete