![[PukiWiki]](image/pukiwiki.png "[PukiWiki]")
|
LSF 1-node 構成で LSF クラスタを構築 |
| Community Edition | Suite for Workgroups | Suite for HPC | |
| Node limit | 10 | 128 | n/a |
| Job limit | 1000 | 25,000 | 100,000 |
# useradd -u 600 -g users lsfadmin # id -a lsfadmin uid=600(lsfadmin) gid=100(users) groups=100(users)
あとで、クラスタの各ノードに lsfadmin を作って、/usr/share/lsf を NFS で共有する。明示的に UID を指定して同じにする必要がある
# mkdir /usr/share/lsf # chown lsfadmin:user /usr/share/lsf
# yum install nfs-utils
/usr/share/lsf 192.168.38.0/24(rw,async,no_root_squash)
# systemctl enable nfs-server # systemctl start nfs-server
# yum install avahi-tools # systemctl enable avahi-tools # systemctl status avahi-daemon
# firewall-cmd --add-service=mdns --zone=public --permanent # firewall-cmd --reloadavahi は mDNSサービス。同一セグメント内であれば自動的に名前解決してくれる。Apple の Bonjour 互換
# yum install java-1.8.0-openjdk ed openssh-server openssh-clients
#SELINUX=enforcing
SELINUX=disabled
SELINUXTYPE=targeted
# reboot
# getenforce Disabled
# ssh-keygen Generating public/private rsa key pair. Enter file in which to save the key (/root/.ssh/id_rsa): Created directory '/root/.ssh'. Enter passphrase (empty for no passphrase): Enter same passphrase again:公開鍵に passphrase をつけないのがミソ
# touch ~/.ssh/authorized_keys # chmod 600 ~/.ssh/authorized_keys # cat id_rsa.pub >> authorized_keys # ssh-keyscan localhost lsf1 >> ~/.ssh/known_hosts
# ssh lsf1
# tar xvf lsfce10.1-x86_64.tar.gz lsfce10.1-x86_64/ lsfce10.1-x86_64/pmpi/ lsfce10.1-x86_64/pmpi/platform_mpi-09.01.02.00u.x64.bin lsfce10.1-x86_64/lsf/ lsfce10.1-x86_64/lsf/lsf10.1_lsfinstall_linux_x86_64.tar.Z lsfce10.1-x86_64/lsf/lsf10.1_linux2.6-glibc2.3-x86_64.tar.Z lsfce10.1-x86_64/pac/ lsfce10.1-x86_64/pac/pac10.1_basic_linux-x64.tar.Z # mkdir /usr/share/lsf_distrib # cd /usr/share/lsf_distrib # tar xvf /tmp/lsfce10.1-x86_64/lsf/lsf10.1_lsfinstall_linux_x86_64.tar.Z # cp /tmp/lsfce10.1-x86_64/lsf/lsf10.1_linux2.6-glibc2.3-x86_64.tar.Z /usr/share/lsf_distrib # ls -l /usr/share/lsf_distrib total 978336 -rw-r--r-- 1 root root 1001815749 Dec 1 12:23 lsf10.1_linux2.6-glibc2.3-x86_64.tar.Z drwxrwxr-x 8 33209 10007 265 Jul 11 2016 lsf10.1_lsfinstall
lsfinstall は展開して、アプリ本体は tar.Z のままにするのがミソ
基本 /usr/share/lsf_distrib/lsf10.1_lsfinstall/install.config のデフォルト設定をコメントアウトするだけ
# diff -u install.config.org install.config
--- install.config.org 2017-12-01 12:33:06.269907001 -0500
+++ install.config 2017-12-01 12:34:11.501804388 -0500
@@ -40,7 +40,7 @@
# (During an upgrade, specify the existing value.)
#**********************************************************
# -----------------
-# LSF_TOP="/usr/share/lsf"
+LSF_TOP="/usr/share/lsf"
# -----------------
# Full path to the top-level installation directory {REQUIRED}
#
@@ -50,7 +50,7 @@
# all host types (approximately 300 MB per host type).
#
# -----------------
-# LSF_ADMINS="lsfadmin user1 user2"
+LSF_ADMINS="lsfadmin"
# -----------------
# List of LSF administrators {REQUIRED}
#
@@ -67,7 +67,7 @@
# Secondary LSF administrators are optional.
#
# -----------------
-# LSF_CLUSTER_NAME="cluster1"
+LSF_CLUSTER_NAME="cluster1"
# -----------------
# Name of the LSF cluster {REQUIRED}
#
@@ -82,7 +82,7 @@
#**********************************************************
#
# -----------------
-# LSF_MASTER_LIST="hostm hosta hostc"
+LSF_MASTER_LIST="lsf1"
# -----------------
# List of LSF server hosts to be master or master candidate in the
# cluster {REQUIRED when you install for the first time or during
@@ -92,7 +92,7 @@
# cluster. The first host listed is the LSF master host.
#
# -----------------
-# LSF_TARDIR="/usr/share/lsf_distrib/"
+LSF_TARDIR="/usr/share/lsf_distrib/"
# -----------------
# Full path to the directory containing the LSF distribution tar files.
#
# cd /usr/share/lsf_distrib/lsfcd_install # ./lsfinstall -f install.config
Press Enter to continue viewing the license agreement, or enter "1" to accept the agreement, "2" to decline it, "3" to print it, "4" to read non-IBM terms, or "99" to go back to the previous screen. 1
Searching LSF 10.1 distribution tar files in /usr/share/lsf_distrib Please wait ... 1) linux2.6-glibc2.3-x86_64 Press 1 or Enter to install this host type: 1
/usr/share/lsf/conf/lsf.conf に LSF_RSH=ssh を追加
$ diff -u lsf.conf.org lsf.conf
--- lsf.conf.org 2017-12-01 12:44:24.513623864 -0500
+++ lsf.conf 2017-12-01 12:44:44.460237613 -0500
@@ -81,3 +81,6 @@
LSB_BJOBS_PENDREASON_LEVEL=1
LSF_MASTER_LIST="lsf1"
LSF_EGO_DAEMON_CONTROL=N
+
+LSF_RSH=ssh
+
LSF_RSH="ssh -o 'PasswordAuthentication no' -o 'StrictHostKeyChecking no'"
# . /usr/share/lsf/conf/profile.lsf # lsfstartup Starting up all LIMs ... Do you really want to start up LIM on all hosts ? [y/n]y Start up LIM on <lsf1> ...... done Waiting for Master LIM to start up ... Master LIM is ok Starting up all RESes ... Do you really want to start up RES on all hosts ? [y/n]y Start up RES on <lsf1> ...... done Starting all slave daemons on LSBATCH hosts ... Do you really want to start up slave batch daemon on all hosts ? [y/n] y Start up slave batch daemon on <lsf1> ...... done Done starting up LSF daemons on the local LSF cluster ...
# lsid IBM Spectrum LSF Community Edition 10.1.0.0, Jun 15 2016 Copyright IBM Corp. 1992, 2016. All rights reserved. US Government Users Restricted Rights - Use, duplication or disclosure restricted by GSA ADP Schedule Contract with IBM Corp. My cluster name is cluster1 My master name is lsf1 # lshosts HOST_NAME type model cpuf ncpus maxmem maxswp server RESOURCES lsf1 X86_64 PC6000 116.1 2 1023M 1.9G Yes (mg) # bhosts HOST_NAME STATUS JL/U MAX NJOBS RUN SSUSP USUSP RSV lsf1 ok - 2 0 0 0 0 0
停止は
# lsfshutdown
