Difference between revisions of "Lustre: Parallel FileSystem"

From Define Wiki
Jump to navigation Jump to search
Line 19: Line 19:
 
* [[Lustre: Using lustre-iokit]]
 
* [[Lustre: Using lustre-iokit]]
 
* [[Lustre: Using IOR to Benchmark]]
 
* [[Lustre: Using IOR to Benchmark]]
 +
 +
== Lustre Configuration for MRC Notes ==
 +
1. On all the server create this configuration file:
 +
for mds:
 +
<syntaxhighlight>
 +
#cat /etc/modprobe.d/lustre.conf
 +
options lnet networks=tcp0(eth2)
 +
</syntaxhighlight>
 +
for oss
 +
<syntaxhighlight>
 +
#cat /etc/modprobe.d/lustre.conf
 +
options lnet networks=tcp0(bond0)
 +
</syntaxhighlight>
 +
load the lustre module
 +
<syntaxhighlight>
 +
modprobe -v lustre
 +
</syntaxhighlight>
 +
 +
2. create lustre filesystem
 +
on MDS1
 +
<syntaxhighlight>
 +
mkfs.lustre --mgs --reformat --servicenode=10.10.17.193@tcp0  --servicenode=10.10.17.194@tcp0 /dev/sda
 +
 +
mkfs.lustre --mdt --fsname=lfs1  --reformat --index=0 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.193@tcp0  --servicenode=10.10.17.194@tcp0 --mkfsoptions="-J size=2048" /dev/sdb
 +
  </syntaxhighlight>
 +
on MDS2
 +
  <syntaxhighlight>
 +
mkfs.lustre --mdt --fsname=lfs2  --reformat --index=0 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.194@tcp0  --servicenode=10.10.17.193@tcp0 --mkfsoptions="-J size=2048" /dev/sdc
 +
  </syntaxhighlight>
 +
on lustre01-oss1.boston.co.uk
 +
  <syntaxhighlight>
 +
mkfs.lustre --ost --fsname=lfs1  --reformat --index=0 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.200@tcp0 --mkfsoptions="-J size=2048" /dev/sdb
 +
  </syntaxhighlight>
 +
 +
on lustre01-oss2.boston.co.uk
 +
  <syntaxhighlight>
 +
mkfs.lustre --ost --fsname=lfs1  --reformat --index=1 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.201@tcp0 --mkfsoptions="-J size=2048" /dev/sdb
 +
  </syntaxhighlight>
 +
 +
on lustre01-oss3.boston.co.uk
 +
  <syntaxhighlight>
 +
mkfs.lustre --ost --fsname=lfs1  --reformat --index=2 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.202@tcp0 --mkfsoptions="-J size=2048" /dev/sdb
 +
  </syntaxhighlight>
 +
 +
on lustre01-oss4.boston.co.uk
 +
  <syntaxhighlight>
 +
mkfs.lustre --ost --fsname=lfs1  --reformat --index=3 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.203@tcp0 --mkfsoptions="-J size=2048" /dev/sdb
 +
  </syntaxhighlight>
 +
 +
on lustre02-oss1.boston.co.uk
 +
  <syntaxhighlight>
 +
mkfs.lustre --ost --fsname=lfs2  --reformat --index=0 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.210@tcp0 --mkfsoptions="-J size=2048" /dev/sdb
 +
  </syntaxhighlight>
 +
 +
on lustre02-oss2.boston.co.uk
 +
  <syntaxhighlight>
 +
mkfs.lustre --ost --fsname=lfs2  --reformat --index=1 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.211@tcp0 --mkfsoptions="-J size=2048" /dev/sdb
 +
  </syntaxhighlight>
 +
 +
on lustre02-oss3.boston.co.uk
 +
  <syntaxhighlight>
 +
mkfs.lustre --ost --fsname=lfs2  --reformat --index=2 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.212@tcp0 --mkfsoptions="-J size=2048" /dev/sdb
 +
  </syntaxhighlight>
 +
 +
on lustre02-oss4.boston.co.uk
 +
  <syntaxhighlight>
 +
mkfs.lustre --ost --fsname=lfs2  --reformat --index=3 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.213@tcp0 --mkfsoptions="-J size=2048" /dev/sdb
 +
  </syntaxhighlight>
 +
 +
on all the nodes:
 +
 +
  <syntaxhighlight>
 +
mkdir -p /lustre/mgt
 +
mkdir -p /lustre/lfs1-mdt
 +
mkdir -p /lustre/lfs2-mdt
 +
mkdir -p /lustre/lfs1-ost00
 +
mkdir -p /lustre/lfs1-ost01
 +
mkdir -p /lustre/lfs1-ost02
 +
mkdir -p /lustre/lfs1-ost03
 +
mkdir -p /lustre/lfs2-ost00
 +
mkdir -p /lustre/lfs2-ost01
 +
mkdir -p /lustre/lfs2-ost02
 +
mkdir -p /lustre/lfs2-ost03
 +
mkdir -p /lustre/lfs2-ost04
 +
  </syntaxhighlight>
 +
 +
disable iptables and selinux
 +
 +
mounting the targets
 +
 +
on MDS1
 +
<syntaxhighlight>
 +
mount -t lustre /dev/sda /lustre/mgt
 +
 +
mount -t lustre /dev/sdb /lustre/lfs1-mdt
 +
</syntaxhighlight>
 +
on lustre01-oss1.boston.co.uk
 +
  <syntaxhighlight>
 +
mount -t lustre /dev/sdb /lustre/lfs1-ost00
 +
  </syntaxhighlight>
 +
on lustre01-oss2.boston.co.uk
 +
  <syntaxhighlight>
 +
mount -t lustre /dev/sdb /lustre/lfs1-ost01
 +
  </syntaxhighlight>
 +
on lustre01-oss3.boston.co.uk
 +
  <syntaxhighlight>
 +
mount -t lustre /dev/sdb /lustre/lfs1-ost02
 +
  </syntaxhighlight>
 +
on lustre01-oss4.boston.co.uk
 +
  <syntaxhighlight>
 +
mount -t lustre /dev/sdb /lustre/lfs1-ost03
 +
  </syntaxhighlight>
 +
 +
on MDS2
 +
  <syntaxhighlight>
 +
mount -t lustre /dev/sdc /lustre/lfs2-mdt
 +
  </syntaxhighlight>
 +
on lustre02-oss1.boston.co.uk
 +
  <syntaxhighlight>
 +
mount -t lustre /dev/sdb /lustre/lfs2-ost00
 +
  </syntaxhighlight>
 +
on lustre02-oss2.boston.co.uk
 +
  <syntaxhighlight>
 +
mount -t lustre /dev/sdb /lustre/lfs2-ost01
 +
  </syntaxhighlight>
 +
on lustre02-oss3.boston.co.uk
 +
  <syntaxhighlight>
 +
mount -t lustre /dev/sdb /lustre/lfs2-ost02
 +
  </syntaxhighlight>
 +
on lustre02-oss4.boston.co.uk
 +
  <syntaxhighlight>
 +
mount -t lustre /dev/sdb /lustre/lfs2-ost03
 +
</syntaxhighlight>
 +
 +
mount client:
 +
<syntaxhighlight>
 +
mount -t lustre 10.10.17.193@tcp0:10.10.17.194@tcp0:/lfs1 /mnt/lfs1
 +
</syntaxhighlight>
 +
 +
Configuartion file to create on MDS1/2 for HA
 +
 +
install peacemaker, corosync and pcs
 +
 +
 +
cat /etc/corosync/corosync.conf for MDS pair
 +
  <syntaxhighlight>
 +
# Please read the corosync.conf.5 manual page
 +
compatibility: whitetank
 +
 +
totem {
 +
                version: 2
 +
                secauth: off
 +
                interface {
 +
                                member {
 +
                                                memberaddr: 172.28.50.193
 +
                                }
 +
                                member {
 +
                                                memberaddr: 172.28.50.194
 +
                                }
 +
                                ringnumber: 0
 +
                                bindnetaddr: 172.28.50.0
 +
                                mcastport: 5405
 +
                                ttl: 1
 +
                }
 +
                interface {
 +
                member {
 +
                        memberaddr: 10.0.0.1
 +
                }
 +
                member {
 +
                        memberaddr: 10.0.0.2
 +
                }
 +
                ringnumber: 1
 +
                bindnetaddr: 10.0.0.0
 +
                mcastport: 5405
 +
                ttl: 1
 +
        }
 +
 +
                transport: udpu
 +
                token: 17000
 +
                rrp_mode: passive
 +
}
 +
 +
logging {
 +
                fileline: off
 +
                to_logfile: yes
 +
                to_syslog: yes
 +
                debug: on
 +
                logfile: /var/log/cluster/corosync.log
 +
                debug: off
 +
                timestamp: on
 +
                logger_subsys {
 +
                                subsys: AMF
 +
                                debug: off
 +
                }
 +
}
 +
  </syntaxhighlight>
 +
 +
 +
cat /etc/corosync/service.d/pacemaker
 +
  <syntaxhighlight>
 +
service {
 +
        # Load the Pacemaker Cluster Resource Manager
 +
        name: pacemaker
 +
        ver:  1
 +
}
 +
  </syntaxhighlight>
 +
 +
 +
 +
cat /usr/lib/ocf/resource.d/heartbeat/Lustre-LDISKFS
 +
chmod 755 /usr/lib/ocf/resource.d/heartbeat/Lustre-LDISKFS
 +
  <syntaxhighlight>
 +
#!/bin/sh
 +
#
 +
# Lustre-LDISKFS
 +
#      Description: Manages a Lustre target on a shared storage medium.
 +
#
 +
# usage: ./Lustre-LDISKFS {start|stop|status|monitor|validate-all|meta-data}
 +
#
 +
#      OCF parameters are as below:
 +
#      OCF_RESKEY_label
 +
# OCF_RESKEY_mountpoint
 +
#
 +
# OCF_RESKEY_label : label of the target the script should operate on
 +
# OCF_RESKEY_mountpoint : name of the target the script should operate on
 +
 +
: ${OCF_FUNCTIONS_DIR=${OCF_ROOT}/resource.d/heartbeat}
 +
. ${OCF_FUNCTIONS_DIR}/.ocf-shellfuncs
 +
 +
usage() {
 +
    echo "usage: $0 {start|stop|status|monitor|meta-data}"
 +
}
 +
 +
meta_data() {
 +
    cat <<END
 +
<?xml version="1.0"?>
 +
<!DOCTYPE resource-agent SYSTEM "ra-api-1.dtd">
 +
<resource-agent name="Lustre-LDISKFS">
 +
<version>1.0</version>
 +
 +
<longdesc lang="en">
 +
Resource script for a Lustre LDISKFS Target.
 +
</longdesc>
 +
 +
<shortdesc lang="en">Manages Lustre LDISKFS Targets</shortdesc>
 +
 +
<parameters>
 +
<parameter name="label" required="1">
 +
<longdesc lang="en">
 +
The label of the target. blkid to display.
 +
</longdesc>
 +
<shortdesc lang="en">label</shortdesc>
 +
<content type="string" default="" />
 +
</parameter>
 +
 +
<parameter name="mountpoint" required="1">
 +
<longdesc lang="en">
 +
The mount point for the target
 +
</longdesc>
 +
<shortdesc lang="en">mountpoint</shortdesc>
 +
<content type="string" default="" />
 +
</parameter>
 +
 +
 +
 +
</parameters>
 +
 +
<actions>
 +
<action name="start" timeout="60" />
 +
<action name="stop" timeout="60" />
 +
<action name="notify" timeout="60" />
 +
<action name="monitor" depth="0" timeout="40" interval="20" />
 +
<action name="validate-all" timeout="5" />
 +
<action name="meta-data" timeout="5" />
 +
</actions>
 +
</resource-agent>
 +
END
 +
}
 +
 +
Target_start() {
 +
    # See if the device is already mounted.
 +
    if Target_status >/dev/null 2>&1; then
 +
        ocf_log info "Target $TARGET is already started."
 +
        return $OCF_SUCCESS
 +
    fi
 +
 +
# this is not necessary, mount should start modules
 +
#    if ! grep -e 'lustre$' /proc/filesystems >/dev/null; then
 +
#        ocf_log err "Couldn't find the lustre module in /proc/filesystems"
 +
#        return $OCF_ERR_ARGS
 +
#    fi
 +
 +
# start the target
 +
#    if ! chroma-agent mount_target --uuid $TARGET; then
 +
    if ! mount -t lustre LABEL=$TARGET $MOUNT_POINT; then
 +
        ocf_log err "Couldn't start target $TARGET"
 +
        return $OCF_ERR_GENERIC
 +
    fi
 +
    return $OCF_SUCCESS
 +
}
 +
 +
Target_notify() {
 +
    return $OCF_SUCCESS
 +
}
 +
 +
Target_stop() {
 +
    # started already?
 +
    Target_status >/dev/null 2>&1
 +
    if [ $? -eq $OCF_NOT_RUNNING ]; then
 +
        # woo!  nothing to do.
 +
        rc=$OCF_SUCCESS
 +
    else
 +
#        chroma-agent unmount_target --uuid $TARGET
 +
        umount $MOUNT_POINT
 +
    fi
 +
 +
    return $rc
 +
}
 +
 +
Target_status() {
 +
    # call the agent to see if it's running
 +
 +
 +
#    if chroma-agent target_running --uuid $TARGET >/dev/null 2>&1; then
 +
    if cat /proc/mounts |grep $MOUNT_POINT >/dev/null 2>&1; then
 +
        rc=$OCF_SUCCESS
 +
        msg="$TARGET is started (running)"
 +
    else
 +
        rc=$OCF_NOT_RUNNING
 +
        msg="$TARGET is stopped"
 +
    fi
 +
 +
    if [ "$OP" = "status" ]; then
 +
        ocf_log info "$msg"
 +
    fi
 +
 +
    return $rc
 +
}
 +
 +
Target_validate_all() {
 +
return $OCF_SUCCESS
 +
}
 +
 +
if [ $# -ne 1 ]; then
 +
    usage
 +
    exit $OCF_ERR_ARGS
 +
fi
 +
 +
TARGET=$OCF_RESKEY_label
 +
MOUNT_POINT=$OCF_RESKEY_mountpoint
 +
OP=$1
 +
 +
# These operations do not require instance parameters
 +
case $OP in
 +
meta-data)    meta_data
 +
              exit $OCF_SUCCESS
 +
              ;;
 +
usage)        usage
 +
              exit $OCF_SUCCESS
 +
              ;;
 +
status)      Target_status
 +
              exit $?
 +
              ;;
 +
monitor)      Target_status
 +
              exit $?
 +
              ;;
 +
validate-all) Target_validate_all
 +
              exit $?
 +
              ;;
 +
stop)        Target_stop
 +
              exit $?
 +
              ;;
 +
start)        Target_start
 +
              ;;
 +
*)            usage
 +
              exit $OCF_ERR_UNIMPLEMENTED
 +
              ;;
 +
esac
 +
exit $?
 +
</syntaxhighlight>
 +
 +
On MDS1
 +
<syntaxhighlight>
 +
pcs resource create MGT ocf:heartbeat:Lustre-LDISKFS label=“MGS“ mountpoint=“/lustre/mgt“
 +
pcs resource create lfs1_mgt ocf:heartbeat:Lustre-LDISKFS label=“lfs1-MDT0000“ mountpoint=“/lustre/lfs1-mdt“
 +
</syntaxhighlight>
 +
On MDS2
 +
<syntaxhighlight>
 +
pcs resource create lfs2_mgt ocf:heartbeat:Lustre-LDISKFS label=“lfs2-MDT0000“ mountpoint=“/lustre/lfs2-mdt“
 +
</syntaxhighlight>
 +
 +
More notes:
 +
notes:
 +
# no need to add mount point on /etc/fstab
 +
# no need for pcsd and etc on oss nodes
 +
# before, failover
 +
##make sure data movement through
 +
### pcs resource move mgt to lustre02
 +
### pcs resource move lfs1 mgt ...
 +
### pcs resource ...
 +
### pcs property set no-quorum-policy=ignore
 +
### need to enlarge the time interval to 300 second through pcs resource show --full
 +
#### <syntaxhighlight> pcs resource update Lustre_mdt op stop interval=0 timeout=300 </syntaxhighlight>
 +
#### <syntaxhighlight> pcs resource update Lustre_mdt op monitor interval=5 timeout=60 </syntaxhighlight>
 +
### when using infiniband, we need to make sure lustre module start before infiniband module
 +
### set rules for priority to let resource on two nodes(not recommended). Normally, a resource should just on one node.
 +
### need to keep an eye on /var/log message  make sure no more error messages coming out.

Revision as of 14:55, 24 March 2015

Whamcloud.jpg


Lustre

Installation

Configuration / Operation

Benchmarking

Lustre Configuration for MRC Notes

1. On all the server create this configuration file: for mds: 

#cat /etc/modprobe.d/lustre.conf
options lnet networks=tcp0(eth2)

for oss 

#cat /etc/modprobe.d/lustre.conf
options lnet networks=tcp0(bond0)

load the lustre module 

modprobe -v lustre

2. create lustre filesystem on MDS1 

mkfs.lustre --mgs --reformat --servicenode=10.10.17.193@tcp0  --servicenode=10.10.17.194@tcp0 /dev/sda
 
mkfs.lustre --mdt --fsname=lfs1  --reformat --index=0 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.193@tcp0  --servicenode=10.10.17.194@tcp0 --mkfsoptions="-J size=2048" /dev/sdb

on MDS2 

mkfs.lustre --mdt --fsname=lfs2  --reformat --index=0 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.194@tcp0  --servicenode=10.10.17.193@tcp0 --mkfsoptions="-J size=2048" /dev/sdc

on lustre01-oss1.boston.co.uk 

mkfs.lustre --ost --fsname=lfs1  --reformat --index=0 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.200@tcp0 --mkfsoptions="-J size=2048" /dev/sdb

on lustre01-oss2.boston.co.uk 

mkfs.lustre --ost --fsname=lfs1  --reformat --index=1 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.201@tcp0 --mkfsoptions="-J size=2048" /dev/sdb

on lustre01-oss3.boston.co.uk 

mkfs.lustre --ost --fsname=lfs1  --reformat --index=2 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.202@tcp0 --mkfsoptions="-J size=2048" /dev/sdb

on lustre01-oss4.boston.co.uk 

mkfs.lustre --ost --fsname=lfs1  --reformat --index=3 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.203@tcp0 --mkfsoptions="-J size=2048" /dev/sdb

on lustre02-oss1.boston.co.uk 

mkfs.lustre --ost --fsname=lfs2  --reformat --index=0 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.210@tcp0 --mkfsoptions="-J size=2048" /dev/sdb

on lustre02-oss2.boston.co.uk 

mkfs.lustre --ost --fsname=lfs2  --reformat --index=1 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.211@tcp0 --mkfsoptions="-J size=2048" /dev/sdb

on lustre02-oss3.boston.co.uk 

mkfs.lustre --ost --fsname=lfs2  --reformat --index=2 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.212@tcp0 --mkfsoptions="-J size=2048" /dev/sdb

on lustre02-oss4.boston.co.uk 

mkfs.lustre --ost --fsname=lfs2  --reformat --index=3 --mgsnid=10.10.17.193@tcp0 --mgsnid=10.10.17.194@tcp0 --servicenode=10.10.17.213@tcp0 --mkfsoptions="-J size=2048" /dev/sdb

on all the nodes: 

mkdir -p /lustre/mgt
mkdir -p /lustre/lfs1-mdt
mkdir -p /lustre/lfs2-mdt
mkdir -p /lustre/lfs1-ost00
mkdir -p /lustre/lfs1-ost01
mkdir -p /lustre/lfs1-ost02
mkdir -p /lustre/lfs1-ost03
mkdir -p /lustre/lfs2-ost00
mkdir -p /lustre/lfs2-ost01
mkdir -p /lustre/lfs2-ost02
mkdir -p /lustre/lfs2-ost03
mkdir -p /lustre/lfs2-ost04

disable iptables and selinux

mounting the targets

on MDS1 

mount -t lustre /dev/sda /lustre/mgt

mount -t lustre /dev/sdb /lustre/lfs1-mdt

on lustre01-oss1.boston.co.uk 

mount -t lustre /dev/sdb /lustre/lfs1-ost00

on lustre01-oss2.boston.co.uk 

mount -t lustre /dev/sdb /lustre/lfs1-ost01

on lustre01-oss3.boston.co.uk 

mount -t lustre /dev/sdb /lustre/lfs1-ost02

on lustre01-oss4.boston.co.uk 

mount -t lustre /dev/sdb /lustre/lfs1-ost03

on MDS2 

mount -t lustre /dev/sdc /lustre/lfs2-mdt

on lustre02-oss1.boston.co.uk 

mount -t lustre /dev/sdb /lustre/lfs2-ost00

on lustre02-oss2.boston.co.uk 

mount -t lustre /dev/sdb /lustre/lfs2-ost01

on lustre02-oss3.boston.co.uk 

mount -t lustre /dev/sdb /lustre/lfs2-ost02

on lustre02-oss4.boston.co.uk 

mount -t lustre /dev/sdb /lustre/lfs2-ost03

mount client: 

mount -t lustre 10.10.17.193@tcp0:10.10.17.194@tcp0:/lfs1 /mnt/lfs1

Configuartion file to create on MDS1/2 for HA

install peacemaker, corosync and pcs


cat /etc/corosync/corosync.conf for MDS pair 

# Please read the corosync.conf.5 manual page
compatibility: whitetank
 
totem {
                version: 2
                secauth: off
                interface {
                                member {
                                                memberaddr: 172.28.50.193
                                }
                                member {
                                                memberaddr: 172.28.50.194
                                }
                                ringnumber: 0
                                bindnetaddr: 172.28.50.0
                                mcastport: 5405
                                ttl: 1
                }
                interface {
                member {
                        memberaddr: 10.0.0.1
                }
                member {
                        memberaddr: 10.0.0.2
                }
                ringnumber: 1
                bindnetaddr: 10.0.0.0
                mcastport: 5405
                ttl: 1
        }
 
                transport: udpu
                token: 17000
                rrp_mode: passive
}
 
logging {
                fileline: off
                to_logfile: yes
                to_syslog: yes
                debug: on
                logfile: /var/log/cluster/corosync.log
                debug: off
                timestamp: on
                logger_subsys {
                                subsys: AMF
                                debug: off
                }
}


cat /etc/corosync/service.d/pacemaker 

service {
        # Load the Pacemaker Cluster Resource Manager
        name: pacemaker
        ver:  1
}


cat /usr/lib/ocf/resource.d/heartbeat/Lustre-LDISKFS chmod 755 /usr/lib/ocf/resource.d/heartbeat/Lustre-LDISKFS 

#!/bin/sh
#
# Lustre-LDISKFS
#      Description: Manages a Lustre target on a shared storage medium.
#
# usage: ./Lustre-LDISKFS {start|stop|status|monitor|validate-all|meta-data}
#
#      OCF parameters are as below:
#       OCF_RESKEY_label
#	OCF_RESKEY_mountpoint
#
# OCF_RESKEY_label : label of the target the script should operate on
# OCF_RESKEY_mountpoint : name of the target the script should operate on

: ${OCF_FUNCTIONS_DIR=${OCF_ROOT}/resource.d/heartbeat}
. ${OCF_FUNCTIONS_DIR}/.ocf-shellfuncs

usage() {
    echo "usage: $0 {start|stop|status|monitor|meta-data}"
}

meta_data() {
    cat <<END
<?xml version="1.0"?>
<!DOCTYPE resource-agent SYSTEM "ra-api-1.dtd">
<resource-agent name="Lustre-LDISKFS">
<version>1.0</version>

<longdesc lang="en">
Resource script for a Lustre LDISKFS Target.
</longdesc>

<shortdesc lang="en">Manages Lustre LDISKFS Targets</shortdesc>

<parameters>
<parameter name="label" required="1">
<longdesc lang="en">
The label of the target. blkid to display.
</longdesc>
<shortdesc lang="en">label</shortdesc>
<content type="string" default="" />
</parameter>

<parameter name="mountpoint" required="1">
<longdesc lang="en">
The mount point for the target
</longdesc>
<shortdesc lang="en">mountpoint</shortdesc>
<content type="string" default="" />
</parameter>



</parameters>

<actions>
<action name="start" timeout="60" />
<action name="stop" timeout="60" />
<action name="notify" timeout="60" />
<action name="monitor" depth="0" timeout="40" interval="20" />
<action name="validate-all" timeout="5" />
<action name="meta-data" timeout="5" />
</actions>
</resource-agent>
END
}

Target_start() {
    # See if the device is already mounted.
    if Target_status >/dev/null 2>&1; then
        ocf_log info "Target $TARGET is already started."
        return $OCF_SUCCESS
    fi

# this is not necessary, mount should start modules 
#    if ! grep -e 'lustre$' /proc/filesystems >/dev/null; then
#        ocf_log err "Couldn't find the lustre module in /proc/filesystems"
#        return $OCF_ERR_ARGS
#    fi

# start the target
#    if ! chroma-agent mount_target --uuid $TARGET; then
    if ! mount -t lustre LABEL=$TARGET $MOUNT_POINT; then
        ocf_log err "Couldn't start target $TARGET"
        return $OCF_ERR_GENERIC
    fi
    return $OCF_SUCCESS
}

Target_notify() {
    return $OCF_SUCCESS
}

Target_stop() {
    # started already?
    Target_status >/dev/null 2>&1
    if [ $? -eq $OCF_NOT_RUNNING ]; then
        # woo!  nothing to do.
        rc=$OCF_SUCCESS
    else
#        chroma-agent unmount_target --uuid $TARGET
        umount $MOUNT_POINT 
    fi

    return $rc
}

Target_status() {
    # call the agent to see if it's running


#    if chroma-agent target_running --uuid $TARGET >/dev/null 2>&1; then
    if cat /proc/mounts |grep $MOUNT_POINT >/dev/null 2>&1; then
        rc=$OCF_SUCCESS
        msg="$TARGET is started (running)"
    else
        rc=$OCF_NOT_RUNNING
        msg="$TARGET is stopped"
    fi

    if [ "$OP" = "status" ]; then
        ocf_log info "$msg"
    fi

    return $rc
}

Target_validate_all() {
	return $OCF_SUCCESS
}

if [ $# -ne 1 ]; then
    usage
    exit $OCF_ERR_ARGS
fi

TARGET=$OCF_RESKEY_label
MOUNT_POINT=$OCF_RESKEY_mountpoint
OP=$1

# These operations do not require instance parameters
case $OP in
meta-data)    meta_data
              exit $OCF_SUCCESS
              ;;
usage)        usage
              exit $OCF_SUCCESS
              ;;
status)       Target_status
              exit $?
              ;;
monitor)      Target_status
              exit $?
              ;;
validate-all) Target_validate_all
              exit $?
              ;;
stop)         Target_stop
              exit $?
              ;;
start)        Target_start
              ;;
*)            usage
              exit $OCF_ERR_UNIMPLEMENTED
              ;;
esac
exit $?

On MDS1 

pcs resource create MGT ocf:heartbeat:Lustre-LDISKFS label=“MGS“ mountpoint=“/lustre/mgt“
pcs resource create lfs1_mgt ocf:heartbeat:Lustre-LDISKFS label=“lfs1-MDT0000“ mountpoint=“/lustre/lfs1-mdt“

On MDS2 

pcs resource create lfs2_mgt ocf:heartbeat:Lustre-LDISKFS label=“lfs2-MDT0000“ mountpoint=“/lustre/lfs2-mdt“

More notes: notes:

  1. no need to add mount point on /etc/fstab
  2. no need for pcsd and etc on oss nodes
  3. before, failover
    1. make sure data movement through
      1. pcs resource move mgt to lustre02
      2. pcs resource move lfs1 mgt ...
      3. pcs resource ...
      4. pcs property set no-quorum-policy=ignore
      5. need to enlarge the time interval to 300 second through pcs resource show --full 
        1.  pcs resource update Lustre_mdt op stop interval=0 timeout=300
        2.  pcs resource update Lustre_mdt op monitor interval=5 timeout=60
      6. when using infiniband, we need to make sure lustre module start before infiniband module
      7. set rules for priority to let resource on two nodes(not recommended). Normally, a resource should just on one node.
      8. need to keep an eye on /var/log message make sure no more error messages coming out.
Retrieved from "http://wiki.define-technology.com/mediawiki-1.35.0/index.php?title=Lustre:_Parallel_FileSystem&oldid=6095"