multipathd & EMC Clariion CX-4

Hi all,

I'm experiencing problems trying to set up a multipathd config with a EMC Clariion CX-4 SAN.
It seems that the CX4 is actually active/passive regarding SPs. My servers (ubuntu-server 11.04) has QLogic Fiber Cards.
Here is my multipath.conf :

##
## This is a template multipath-tools configuration file
## Uncomment the lines relevent to your environment
##
defaults {
 user_friendly_names yes
}
blacklist {
 #devnode "*"
 devnode "^(ram|raw|loop|fd|md|dm-|sr|scd|st)[0-9]*"
 devnode "^hd[a-z][[0-9]*]"
 devnode "^cciss!c[0-9]d[0-9]*[p[0-9]*]"
}
devices {
 device {
  vendor "DGC "
  product "*"
  path_grouping_policy group_by_prio
  getuid_callout "/lib/udev/scsi_id -g -u -d /dev/%n"
  prio_callout "/sbin/mpath_prio_emc /dev/%n"
  hardware_handler "1 emc"
  features "1 queue_if_no_path"
# failback 15
# rr_weight priorities
  no_path_retry 300
  path_checker emc_clarion
  failback immediate
# rr_min_io 100
  product_blacklist LUN_Z
 }
}

multipaths {

 multipath {
  wwid 360060160174026008cf8cef961cde011
  alias NPCD
 }

 multipath {
                wwid 36006016017402600f2ed610b62cde011
                alias NDO
        }

 multipath {
                wwid 360060160174026000c984cc67acde011
                alias NAGIOS
        }

}

And here is the result of a multipath -ll :

sdg: checker msg is "directio checker reports path is down"
sdm: checker msg is "directio checker reports path is down"
NDO (36006016017402600f2ed610b62cde011) dm-8 DGC ,RAID 5
[size=50G][features=1 queue_if_no_path][hwhandler=1 emc]
\_ round-robin 0 [prio=2][active]
 \_ 2:0:0:1 sdd 8:48 [active][ready]
 \_ 5:0:0:1 sdj 8:144 [active][ready]
\_ round-robin 0 [prio=0][enabled]
 \_ 2:0:1:1 sdg 8:96 [active][faulty]
 \_ 5:0:1:1 sdm 8:192 [active][faulty]
sde: checker msg is "directio checker reports path is down"
sdk: checker msg is "directio checker reports path is down"
NAGIOS (360060160174026000c984cc67acde011) dm-6 DGC ,RAID 5
[size=40G][features=1 queue_if_no_path][hwhandler=1 emc]
\_ round-robin 0 [prio=2][active]
 \_ 2:0:1:2 sdh 8:112 [active][ready]
 \_ 5:0:1:2 sdn 8:208 [active][ready]
\_ round-robin 0 [prio=0][enabled]
 \_ 2:0:0:2 sde 8:64 [active][faulty]
 \_ 5:0:0:2 sdk 8:160 [active][faulty]
sdc: checker msg is "directio checker reports path is down"
sdi: checker msg is "directio checker reports path is down"
NPCD (360060160174026008cf8cef961cde011) dm-7 DGC ,RAID 5
[size=100G][features=1 queue_if_no_path][hwhandler=1 emc]
\_ round-robin 0 [prio=2][active]
 \_ 2:0:1:0 sdf 8:80 [active][ready]
 \_ 5:0:1:0 sdl 8:176 [active][ready]
\_ round-robin 0 [prio=0][enabled]
 \_ 2:0:0:0 sdc 8:32 [active][faulty]
 \_ 5:0:0:0 sdi 8:128 [active][faulty]

So when trying to write on a virtual device /dev/mapper/NAGIOS (for exemple) I see many I/O errors on 'faulty disks'. When tresspassing LUNs on the clariion, I see ready disks becoming faulty and faulty ones becoming ready ... I also have udevd (udev-work) burning my CPUs while trying to rename '/dev/disk/by-id/wwn-0xetcetc...udev-tmp'
What's wrong with my config ? Am I missing something ?
Thx by advance for your help,
Regards,