OpenIndiana Distribution

On a DELL R710 with one H700 and two H800 RAID controllers we see
zpool errors when reading several TB during a zfs send/recv backup
procedure.

c4t4d0 ONLINE 0 0 0
c4t5d0 ONLINE 0 0 0
c4t6d0 FAULTED 0 0 0 too many errors
c4t7d0 FAULTED 0 0 0 too many errors
c4t8d0 REMOVED 0 0 0

fmdump reports

50%  defect.sunos.eft.unexpected_telemetry

Problem in: dev:////pci@0,0
           Affects: -
               FRU: -
          Location: -

50%  fault.sunos.eft.unexpected_telemetry

Problem in: dev:////pci@0,0
           Affects: -
               FRU: -
          Location: -

and a list of:

100%  fault.fs.zfs.io_failure_wait

Problem in: zfs://pool=spool
           Affects: zfs://pool=spool
               FRU: -
          Location: -
...

The corresponding devices are gone:

scsi: [ID 107833 kern.warning] WARNING: /pci@0,0/pci8086,3410@9/pci1028,1f15@0/sd@0,0 (sd0):
drive offline
...

There is a quad-GbE card and a usually also a dual port 10GBE-card
in the machine. Removing the 10GbE-card does not help. The system
is still operational with the remaining components. After reboot the
zpool is available again. In case of a permanent error on a disk replacing /
resilvering does not work, it just runs into the same error again.

Any ideas?