用VMWare 实现4节点的Lustre 并行文件系统集群

作者:   发表于：2006-11-08 13:18:34
简介: 本文介绍了通过2台物理服务器和vmware系统，虚拟出4个独立的linux服务器实现

环境配置: 2台物理服务器, 4个虚拟节点.

Server1: AMD64 ,   host OS SLES9SP3+errata x86-64 version, vmware server beta(latest build)

              vmware guestOS 1 :   RHEL4U3 x86-64 version      => mds
              vmware guestOS 2 :   RHEL4U3 x86-64 version      => client

              lustre的那些rpm包我装的是X86-64的版本(版本1.4.6)

Server2: Intel dual core EM64T, host OS SLES9SP3+errara x86-64 version,vmware server beta(latest build)

             vmware guestOS 1: RHEL4U3 x86 version     => ost1
             vmware guestOS 1: RHEL4U3 x86 version     => ost1

             lustre的那些rpm包我装的是X86的版本(版本1.4.6)
[/color]
============================================================================
config.sh 文件内容

#!/bin/sh

# config.sh

# Create nodes
rm -f config.xml
lmc -m config.xml --add net --node node-mds --nid n1 --nettype tcp
lmc -m config.xml --add net --node node-ost1 --nid n3 --nettype tcp
lmc -m config.xml --add net --node node-ost2 --nid n4 --nettype tcp
lmc -m config.xml --add net --node client --nid n2 --nettype tcp

# Cofigure MDS
lmc -m config.xml --add mds --node node-mds --mds mds-test --fstype ldiskfs --dev /tmp/mds-test --size 50000

# Configures OSTs
lmc -m config.xml --add lov --lov lov-test --mds mds-test --stripe_sz 1048576 --stripe_cnt 0 --stripe_pattern 0
lmc -m config.xml --add ost --node node-ost1 --lov lov-test --ost ost1-test --fstype ldiskfs --dev /tmp/ost1-test --size 100000
lmc -m config.xml --add ost --node node-ost2 --lov lov-test --ost ost2-test --fstype ldiskfs --dev /tmp/ost2-test --size 100000

# Configure client (this is a 'generic' client used for all client mounts)
lmc -m config.xml --add mtpt --node client --path /mnt/lustre --mds mds-test --lov lov-test

===============================================================================

所有4个node 的 /etc/hosts 文件内容

[root@n1 ~]# cat /etc/hosts
# Do not remove the following line, or various programs
# that require network functionality will fail.
127.0.0.1                localhost
192.168.0.31             n1
192.168.0.32             n2
192.168.0.33             n3
192.168.0.34             n4
===============================================================================
产生xml文件之后，分别scp到每个node的/root目录
===============================================================================
启动OST
root 登陆到ost1,运行 lconf --reformat --node node-ost1 config.xml
root 登陆到ost1,运行 lconf --reformat --node node-ost2 config.xml
root 登陆到mds,运行 lconf --reformat --node node-mds config.xml
root 登陆到client,运行 lconf --node client config.xml

这个时候，在client node 上,用root运行 df -hT 命令， 已经看到 client node的 /mnt/lustre 被mount上了,   
===============================================================================
屏幕信息

启动OST1的时候的屏幕信息
[root@n3 ~]# lconf --reformat --node node-ost1 config.xml
loading module: libcfs srcdir None devdir libcfs
loading module: lnet srcdir None devdir lnet
loading module: ksocklnd srcdir None devdir klnds/socklnd
loading module: lvfs srcdir None devdir lvfs
loading module: obdclass srcdir None devdir obdclass
loading module: ptlrpc srcdir None devdir ptlrpc
loading module: ost srcdir None devdir ost
loading module: ldiskfs srcdir None devdir ldiskfs
loading module: fsfilt_ldiskfs srcdir None devdir lvfs
loading module: obdfilter srcdir None devdir obdfilter
NETWORK: NET_node-ost1_tcp NET_node-ost1_tcp_UUID tcp n3
OSD: ost1-test ost1-test_UUID obdfilter /tmp/ost1-test 100000 ldiskfs no 0 0
OST mount options: errors=remount-ro
[root@n3 ~]#

启动OST2的屏幕信息
[root@n4 ~]# lconf --reformat --node node-ost2 config.xml
loading module: libcfs srcdir None devdir libcfs
loading module: lnet srcdir None devdir lnet
loading module: ksocklnd srcdir None devdir klnds/socklnd
loading module: lvfs srcdir None devdir lvfs
loading module: obdclass srcdir None devdir obdclass
loading module: ptlrpc srcdir None devdir ptlrpc
loading module: ost srcdir None devdir ost
loading module: ldiskfs srcdir None devdir ldiskfs
loading module: fsfilt_ldiskfs srcdir None devdir lvfs
loading module: obdfilter srcdir None devdir obdfilter
NETWORK: NET_node-ost2_tcp NET_node-ost2_tcp_UUID tcp n4
OSD: ost2-test ost2-test_UUID obdfilter /tmp/ost2-test 100000 ldiskfs no 0 0
OST mount options: errors=remount-ro
[root@n4 ~]#


启动MDS的屏幕信息

[root@n1 ~]# lconf --reformat --node node-mds config.xml
loading module: libcfs srcdir None devdir libcfs
loading module: lnet srcdir None devdir lnet
loading module: ksocklnd srcdir None devdir klnds/socklnd
loading module: lvfs srcdir None devdir lvfs
loading module: obdclass srcdir None devdir obdclass
loading module: ptlrpc srcdir None devdir ptlrpc
loading module: mdc srcdir None devdir mdc
loading module: osc srcdir None devdir osc
loading module: lov srcdir None devdir lov
loading module: mds srcdir None devdir mds
loading module: ldiskfs srcdir None devdir ldiskfs
loading module: fsfilt_ldiskfs srcdir None devdir lvfs
NETWORK: NET_node-mds_tcp NET_node-mds_tcp_UUID tcp n1
MDSDEV: mds-test mds-test_UUID /tmp/mds-test ldiskfs no
recording clients for filesystem: FS_fsname_UUID
Recording log mds-test on mds-test
LOV: lov_mds-test 4f3bf_lov_mds-test_f34d7ba738 mds-test_UUID 0 1048576 0 0 [u'ost1-test_UUID', u'ost2-test_UUID'] mds-test
OSC: OSC_n1_ost1-test_mds-test 4f3bf_lov_mds-test_f34d7ba738 ost1-test_UUID
OSC: OSC_n1_ost2-test_mds-test 4f3bf_lov_mds-test_f34d7ba738 ost2-test_UUID
End recording log mds-test on mds-test
MDSDEV: mds-test mds-test_UUID /tmp/mds-test ldiskfs 50000 no
MDS mount options: errors=remount-ro
[root@n1 ~]#


启动client 的屏幕信息

[root@n2 ~]# lconf --node client config.xml
loading module: libcfs srcdir None devdir libcfs
loading module: lnet srcdir None devdir lnet
loading module: ksocklnd srcdir None devdir klnds/socklnd
loading module: lvfs srcdir None devdir lvfs
loading module: obdclass srcdir None devdir obdclass
loading module: ptlrpc srcdir None devdir ptlrpc
loading module: osc srcdir None devdir osc
loading module: lov srcdir None devdir lov
loading module: mdc srcdir None devdir mdc
loading module: llite srcdir None devdir llite
NETWORK: NET_client_tcp NET_client_tcp_UUID tcp n2
LOV: lov-test e0002_lov-test_a77190f32b mds-test_UUID 0 1048576 0 0 [u'ost1-test_UUID', u'ost2-test_UUID'] mds-test
OSC: OSC_n2_ost1-test_MNT_client e0002_lov-test_a77190f32b ost1-test_UUID
OSC: OSC_n2_ost2-test_MNT_client e0002_lov-test_a77190f32b ost2-test_UUID
MDC: MDC_n2_mds-test_MNT_client 96c98_MNT_client_1567f4dc95 mds-test_UUID
MTPT: MNT_client MNT_client_UUID /mnt/lustre mds-test_UUID lov-test_UUID


检查 client node   文件系统加载情况

[root@n2 ~]# df -hT
Filesystem     Type     Size   Used Avail Use% Mounted on
/dev/mapper/VolGroup00-LogVol00
               ext3     4.1G   3.0G   920M   77% /
/dev/sda1      ext3      99M    14M    80M   15% /boot
none          tmpfs     187M      0   187M    0% /dev/shm
config lustre_lite     190M   8.5M   171M    5% /mnt/lustre
[root@n2 ~]#