Well, almost at it.
On Fri, 22.07.2005-11:58:28 +0200, Christophe Varoqui wrote:
> hardware_handler and features params must be in the devices {} section, not in multipaths {}.
I changed the settings in /etc/multipath.conf again, as you advised.
Here is it:
# Begin of /etc/multipath.conf
defaults {
multipath_tool "/sbin/multipath -v 0 -S"
udev_dir /dev
polling_interval 10
default_selector "round-robin 0"
default_path_grouping_policy failover
default_getuid_callout "/sbin/scsi_id -g -u -s /block/%n"
default_prio_callout "/bin/false"
default_features "0"
}
multipaths {
multipath {
wwid 360060160200161a037f90d75dfca84f7
alias 416L3
path_grouping_policy failover
path_selector "round-robin 0"
}
}
devices {
device {
vendor "DGC "
product "RAID 5 "
path_grouping_policy group_by_serial
getuid_callout "/sbin/scsi_id -g -u -s /block/%n"
path_checker emc_clariion
path_selector "round-robin 0"
features "0"
hardware_handler "1 emc"
}
}
# End of /etc/multipath.conf
I figured out that the vendor value must be exactly 8 characters long.
> Also, pgpolicy is best set to group_by_serial with Clariion hw.
> You'll see it produce same grouping than failover in your case.
Hm, doesn't look the same here. It again leaves me with only one
priority group. So I stick to failover for now.
What different features are available? I just managed to freeze my
network conn (at least, haven't checked the host yet) by adding "1
queue_if_no_path" as used with the compaq entry in the examples.
I didn't manage to get failover to work, yet. Am I correct in assuming
that the multipathd daemon is only needed for path recovery? Because I
have problems getting that one to react to signals properly.
Right, gonna check what happend to the machine.
CU,
Philipp
--
Philipp Niemann DIMDI
Abteilung D / AG D4
Peripherie / UNIX-Systembetreuer Waisenhausgasse 36-38a
Tel. : 0221/4724-281 50676 Koeln
