SGE 우선 순위

# vi /opt/gridengine/default/common/sge_request
-p -500

1) 미적용시 기본적으로 "0"이 적용
2) 사용자는 -1023 ~ -1까지 우선순위를 낮출 수가 있다.
3) -1023이 가장 낮은 우선순위이고, -1이 가장 높은 우선순위
4) qsub 작업 시 기본 우선순위를 -500으로 지정하였고, #$ -p -100등으로 우선순위 옵션을 변경해서 submit

ifconfig shows wrong MAC for ib0

Infiniband hardware address can be incorrect! Please read BUGS section in ifconfig(8).
infiniband A0:00:03:00:FE:80:00:00:00:00:00:00:00:00:00:00:00:00:00:00  txqueuelen 1024  (InfiniBand)

# man ifconfig

BUGS

       Ifconfig  uses  the  ioctl  access method to get the full address information, which limits hardware addresses to 8 bytes.  Because Infiniband hardware address has 20

       bytes, only the first 8 bytes are displayed correctly.  Please use ip link command from iproute2 package to display link layer  informations  including  the  hardware address

즉, Infiniband hardware address는 20 bytes로 ifconfig 명령으로 표기할 수 없습니다. ifconfig 명령어가 아닌 iproute 패키지의 ip 명령어를 사용하거나 패치를 하면 된다.

※ 1Gb Ethernet의 Mac address는 6Bytes로 구성되어 있음
※ Infiniband는 20Bytes로 구성되어 있는데 8Bytes 이하 00으로 표시 됨!!

ex) ifconfig ib1
A0:00:03:00:FE:80:00:00:00:00:00:00:00:00:00:00:00:00:00:00

ex) ip a show ib1
a0:00:03:00:fe:80:00:00:00:00:00:00:00:02:c9:03:00:a2:fb:32

INSTALLING BOOST LIBRARIES, TOPHAT, SAM TOOLS, CUFFLINKS ON CENTOS7

Boost Libraries

$ tar zxvfp boost_1_62_0.tar.gz

$ cd boost_1_62_0/

$ ./bootstrap.sh --prefix=/BiO/hadoop/program/linux_tools/boost_1_62_0 --with-libraries=all

$ ./b2

$ ./b2 install

$ export BOOST_ROOT=/BiO/hadoop/program/linux_tools/boost_1_62_0

$ export LD_LIBRARY_PATH=$BOOST_ROOT/lib:$LD_LIBRARY_PATH

TopHat

$ tar xzvf tophat-2.1.1.tar.gz

$ cd tophat-2.1.1

$ ./configure --prefix /BiO/hadoop/program/linux_tools/tophat-2.1.1 \
 --with-boost=/BiO/hadoop/program/linux_tools/boost_1_62_0

$ make

$ sudo make install

SAM tools

$ cd samtools-0.1.19/ 

$ make

$ mkdir -p /BiO/hadoop/program/linux_tools/isbyeon_test/samtools-0.1.19/bin  \
/BiO/hadoop/program/linux_tools/isbyeon_test/samtools-0.1.19/include/bam \
/BiO/hadoop/program/linux_tools/isbyeon_test/samtools-0.1.19/lib \

$ cp libbam.a /BiO/hadoop/program/linux_tools/isbyeon_test/samtools-0.1.19/lib/

$ cp *.h /BiO/hadoop/program/linux_tools/isbyeon_test/samtools-0.1.19/include/bam/

Cufflinks

$ tar jxfp 3.2.8.tar.bz2

$ cd eigen-eigen-07105f7124f9/

$ mkdir /BiO/hadoop/program/linux_tools/isbyeon_test/eigen3

$ cp -rv ./Eigen/ /BiO/hadoop/program/linux_tools/isbyeon_test/eigen3

$ export EIGEN_CPPFLAGS="-I/BiO/hadoop/program/linux_tools/isbyeon_test/eigen3"

$ tar zxvfp cufflinks-2.2.1.tar.gz

$ cd cufflinks-2.2.1/

$ ./configure --prefix=//BiO/hadoop/program/linux_tools/isbyeon_test/cufflinks-2.2.1 \
--with-boost=/BiO/hadoop/program/linux_tools/boost_1_62_0 \
--with-bam=/BiO/hadoop/program/linux_tools/isbyeon_test/samtools-0.1.19

$ make

$ make install

CONTROLLING IPOIB MODE(DATAGRAM MODE, CONNECTED MODE)

datagram mode

2KB IB MTU: 2044 bytes.(maximum)

4KB IB MTU: 4092 bytes.(maximum)

connected mode

65520 bytes.(maximum)

Controlling IPoIB mode

# cat /sys/class/net/ib0/mode

datagram

# cd /etc/sysconfig/network-scripts

# ./ifdown ib0

# echo connected > /sys/class/net/ib0/mode

# ./ifup ib0

# cat /sys/class/net/ib0/mode

connected

# vi /etc/infiniband/openib.conf

#SET_IPOIB_CM=auto

SET_IPOIB_CM=yes

IPOIB_MTU=65520

※ connected mode = no
# sed -i 's/SET_IPOIB_CM=auto/SET_IPOIB_CM=no/g' /etc/infiniband/openib.conf

Installation of Son of Grid Engine(SGE) on CentOS7

master# hostnamectl set-hostname qmaster.local

master# vi /etc/hosts
192.168.56.101  qmaster.local qmaster
192.168.56.102  compute01.local compute01

master# mkdir -p /BiO/src
master# yum -y install epel-release
master# yum -y install jemalloc-devel openssl-devel ncurses-devel pam-devel libXmu-devel hwloc-devel hwloc hwloc-libs java-devel javacc ant-junit libdb-devel motif-devel csh ksh xterm db4-utils perl-XML-Simple perl-Env xorg-x11-fonts-ISO8859-1-100dpi xorg-x11-fonts-ISO8859-1-75dpi
master# groupadd -g 490 sgeadmin
master# useradd -u 495 -g 490 -r -m  -d /home/sgeadmin -s /bin/bash -c "SGE Admin" sgeadmin
master# visudo
%sgeadmin       ALL=(ALL)       NOPASSWD: ALL
master# cd /BiO/src
master# wget http://arc.liv.ac.uk/downloads/SGE/releases/8.1.9/sge-8.1.9.tar.gz
master# tar zxvfp sge-8.1.9.tar.gz
master# cd sge-8.1.9/source/
master# sh scripts/bootstrap.sh && ./aimk && ./aimk -man
master# export SGE_ROOT=/BiO/gridengine && mkdir $SGE_ROOT
master# echo Y | ./scripts/distinst -local -allall -libs -noexit
master# chown -R sgeadmin.sgeadmin /BiO/gridengine

master# cd  $SGE_ROOT
master# ./install_qmaster
press enter at the intro screen
press "y" and then specify sgeadmin as the user id
leave the install dir as /BiO/gridengine
You will now be asked about port configuration for the master, normally you would choose the default (2) which uses the /etc/services file
accept the sge_qmaster info
You will now be asked about port configuration for the master, normally you would choose the default (2) which uses the /etc/services file
accept the sge_execd info
leave the cell name as "default"
Enter an appropriate cluster name when requested
leave the spool dir as is
press "n" for no windows hosts!
press "y" (permissions are set correctly)
press "y" for all hosts in one domain
If you have Java available on your Qmaster and wish to use SGE Inspect or SDM then enable the JMX MBean server and provide the requested information - probably answer "n" at this point!
press enter to accept the directory creation notification
enter "classic" for classic spooling (berkeleydb may be more appropriate for large clusters)
press enter to accept the next notice
enter "20000-20100" as the GID range (increase this range if you have execution nodes capable of running more than 100 concurrent jobs)
accept the default spool dir or specify a different folder (for example if you wish to use a shared or local folder outside of SGE_ROOT
enter an email address that will be sent problem reports
press "n" to refuse to change the parameters you have just configured
press enter to accept the next notice
press "y" to install the startup scripts
press enter twice to confirm the following messages
press "n" for a file with a list of hosts
enter the names of your hosts who will be able to administer and submit jobs (enter alone to finish adding hosts)
skip shadow hosts for now (press "n")
choose "1" for normal configuration and agree with "y"
press enter to accept the next message and "n" to refuse to see the previous screen again and then finally enter to exit the installer

master# cp /BiO/gridengine/default/common/settings.sh /etc/profile.d/
master# qconf -ah compute01.local
compute01.local added to administrative host list

master# yum -y install nfs-utils
master# vi /etc/exports
/BiO 192.168.56.0/24(rw,no_root_squash)

master# systemctl start rpcbind nfs-server
master# systemctl enable rpcbind nfs-server


compute01# yum -y install hwloc-devel
compute01# hostnamectl set-hostname compute01.local
compute01# vi /etc/hosts
192.168.56.101  qmaster.local qmaster
192.168.56.102  compute01.local compute01

compute01# groupadd -g 490 sgeadmin
compute01# useradd -u 495 -g 490 -r -m  -d /home/sgeadmin -s /bin/bash -c "SGE Admin" sgeadmin

compute01# yum -y install nfs-utils
compute01# systemctl start rpcbind
compute01# systemctl enable rpcbind
compute01# mkdir /BiO
compute01# mount -t nfs 192.168.56.101:/BiO /BiO
compute01# vi /etc/fstab
192.168.56.101:/BiO  /BiO                   nfs     defaults        0 0

compute01# export SGE_ROOT=/BiO/gridengine
compute01# export SGE_CELL=default
compute01# cd $SGE_ROOT
compute01# ./install_execd
compute01# cp /BiO/gridengine/default/common/settings.sh /etc/profile.d/