LAM/MPI CLuster System With FreeBSD 5.3 HOWTO

 [媒介]mpi（message passing interface）动静传递接口它不是一个和议，但它的位置仍旧本质上是一个和议了。它重要用来在散布式保存体例中的并路途序通讯。mpi是一个因变量库，它不妨经过fortran和c步调举行挪用，mpi的长处是它速率比拟快，并且移植性比拟好。cluster暂时罕见的cluster(集群)框架结构有两种，一种是web/internet cluster system，这种框架结构主假如将材料安置在各别的长机上头，亦即由多部长机同声控制一项效劳；而其余一种则是所谓的平行演算了(parallel algorithms cluster system)！平行演算本来即是将同一个演算的处事，交给所有cluster内里的一切cpu来举行同步演算的一个功效。因为运用到多个cpu的演算本领，以是不妨加速演算的速率。此文书档案所安置架设的lam/mpi cluster system属于后者,因为试验情况前提以及自己本领的控制,大概文书档案有局部证明不精细,如有疑义请来函与我接洽,我将全力完备此文书档案,感谢![软硬件及平台]server \\ freebsd 5.3 stableip:172.18.5.247 hostname: center.the9.comclient \\ freebsd 5.3 releaseip:172.18.5.80 hostname: node1.the9.comapache_1.3.29 \\ all ports installphp4-4.3.10php4-gd-4.3.10php4-extensions-1.0lam-6.5.9ganglia-monitor-core-2.5.6ganglia-webfrontend-2.5.5[手段]架设一套鉴于freebsd 5.3的lam/mpi cluster system.[安置及摆设]一,各节点体例 /etc/hosts 的基础摆设 \\ 即使内网有dns,则摆设好体例中的 /etc/resolv.conf 即可!center.the9.com#more /etc/hosts172.18.5.247 center.the9.com172.18.5.80 node1.the9.comnode1.the9.com#more /etc/hosts172.18.5.247 center.the9.com172.18.5.80 node1.the9.com二,apache+php server 的架设center.the9.com#cd /usr/ports/www/apache13-modssl#make install clean \\ 安置 apache#cd /usr/ports/lang/php4-extensions#make install clean \\ 安置 php. 牢记这边确定要采用安置gd库#vi /usr/local/etc/apache/http.conf \\ 介入以次关系参数addtype application/x-httpd-php .phpaddtype application/x-httpd-php-source .phps三,nfs server-client 的架设nfs server(center.the9.com)#vi /etc/rc.conf \\ 介入以次关系参数nfs_server_enable="yes"nfs_server_flags="-u -t -n 4 -h 172.18.5.247"mountd_enable="yes"mountd_flags="-r -l"rpcbind_enable="yes"rpcbind_flags="-l -h 172.18.5.247"#vi /etc/exports \\ 摆设nfs共享目次/cluster -maproot=0:0 -network 172.18.5.0 -mask 255.255.255.0#/etc/rc.d/rpcbind start#/etc/rc.d/mountd start#/etc/rc.d/nfsd start \\ 启用nfs servernfs client(node1.the9.com)#vi /etc/rc.conf \\ 介入以次关系参数nfs_client_enable="yes"#vi /etc/fstab \\ 介入以次关系参数172.18.5.247:/cluster /cluster nfs rw 0 0#mount /cluster \\ mount /cluster 目次四,lam/mpi cluster system的架设step 1: 基础安置center.the9.com#cd /usr/ports/net/lam#make install clean \\ 安置 lam#cd /usr/ports/sysutils/ganglia-monitor-core #make install clean \\ 安置cluster system 所需的monitor core#cd /usr/ports/sysutils/ganglia-webfrontend#make install clean \\ 安置上头monitor core 所需的web guinode1.the9.com#cd /usr/ports/net/lam#make install clean \\ 安置 lam#cd /usr/ports/sysutils/ganglia-monitor-core #make install clean \\ 安置cluster system 所需的monitor corestep 2: 摆设center.the9.com#cd /usr/local/etc/#cp gmond.conf.sample gmond.conf#cp gmetad.conf.sample gmetad.conf#vi gmond.conf \\ 窜改name和mcast_if 的参数# the name of the cluster this node is a part of# default: "unspecified"name "bsdcluster"# the multicast interface for gmond to send/receive data on# default: the kernel decides based on routing configurationmcast_if lnc0#vi gmetad.conf \\ 窜改data_source 的参数# data_source "my cluster" 10 localhost my.machine.edu:8649 1.2.3.5:8655# data_source "my grid" 50 1.3.4.7:8655 grid.org:8651 grid-backup.org:8651# data_source "another source" 1.3.4.7:8655 1.3.4.8data_source "bsdcluster" 10 center.the9.com:8649 node1.the9.com:8649 #vi /usr/local/etc/lam-bhost.def \\ 介入各node 的hostnamecenter.the9.comnode1.the9.comnode1.the9.com \\ 基础上,每个新增节点的摆设都要和之上center.the9.com 的摆设普遍.node2.the9.comnodex.the9.com ........五,monitor web gui 的摆设center.the9.com#vi /usr/local/etc/apache/http.conf \\ 介入以次关系参数,摆设cluster monitor web的路途alias /ganglia/ "/usr/local/www/ganglia/"<directory "/usr/local/www/ganglia">options indexes followsymlinks multiviewsallowoverride noneorder allow,denyallow from all</directory>#vi /etc/rc.conf \\ 介入以次参数apache_enable="yes"apache_flags="-dssl"apache_pidfile="/var/run/httpd.pid"#/usr/local/etc/rc.d/apache.sh start \\ 启用apache六,启用并调节和测试cluster system以及查看尝试center.the9.com node1.the9.com nodex.the9.com etc....#/usr/local/etc/rc.d/gmetad.sh start#/usr/local/etc/rc.d/gmond.sh start \\ 启用cluster 各node的monitor corecenter.the9.com$lamboot -dv \\ 启用各节点的lam daemonlam 6.5.9/mpi 2 c++/romio - indiana universitylamboot: boot schema file: /usr/local/etc/lam-bhost.deflamboot: opening hostfile /usr/local/etc/lam-bhost.deflamboot: found the following hosts:lamboot: n0 center.the9.comlamboot: n1 node1.the9.comlamboot: resolved hosts:lamboot: n0 center.the9.com --> 172.18.5.247lamboot: n1 node1.the9.com --> 172.18.5.80lamboot: found 2 host node(s)lamboot: origin node is 0 (center.the9.com)executing hboot on n0 (center.the9.com - 1 cpu)...lamboot: attempting to execute "hboot -t -c lam-conf.lam -d -v -i " -h 172.18.5.247 -p 53433 -n 0 -o 0 ""hboot: process schema = "/usr/local/etc/lam-conf.lam"hboot: found /usr/local/bin/lamdhboot: performing tkillhboot: tkill hboot: booting...hboot: fork /usr/local/bin/lamd[1] 28338 lamd -h 172.18.5.247 -p 53433 -n 0 -o 0 -dhboot: attempting to execute executing hboot on n1 (node1.the9.com - 1 cpu)...lamboot: attempting to execute "/usr/bin/ssh node1.the9.com -n echo $shell"lamboot: got remote shell /bin/shlamboot: attempting to execute "/usr/bin/ssh node1.the9.com -n (. ./.profile; hboot -t -c lam-conf.lam -d -v -s -i "-h 172.18.5.247 -p 53433 -n 1 -o 0 " )"hboot: process schema = "/usr/local/etc/lam-conf.lam"hboot: found /usr/local/bin/lamdhboot: performing tkillhboot: tkill hboot: booting...hboot: fork /usr/local/bin/lamd[1] 43110 lamd -h 172.18.5.247 -p 53433 -n 1 -o 0 -dtopology done lamboot completed successfully$lamhalt -dv \\ 遏止各节点的lam daemon$ lamhalt -dvlam 6.5.9/mpi 2 c++/romio - indiana universityshutting down lamlamhalt: sending halt to n1 (node1.the9.com)lamhalt: waiting for halt acks from remote lam daemonslamhalt: received halt ack from n1 (node1.the9.com)lamhalt: sending final halt to n0 (center.the9.com)lamhalt: local lam daemon haltedlam halted$lamnodes \\ 察看node info$lamexec n echo "hello" \\ 察看node run statuscenter.the9.com#ps ax28338 ?? i 0:00.04 /usr/local/bin/lamd -h 172.18.5.247 -p 53433 -n 0 -o 0 -dnode1.the9.com#ps ax43110 ?? s 0:00.05 /usr/local/bin/lamd -h 172.18.5.247 -p 53433 -n 1 -o 0 -dcluster monitor web guihttp://center.the9.com/ganglia/ \\ 用这个察看体例数据,仍旧很直觉的,是以rrdtool 天生的 images. :)cpus total: 2 hosts up: 2 hosts down: 0 avg load (15, 5, 1m):1%, 4%, 0% localtime:2004-12-31 10:50 total cpus: 2total memory: 0.2 gbtotal disk: 8.0 gbmost full disk: 61.2% used \\ 试验情况的呆板比拟烂,包容包容. :)[参考]http://lam-mpi.org/ lam-mpihttp://www.beowulf.org/ beowulf faqhttp://www.lasg.ac.cn/cgi-bin/forum/topic.cgi?forum=4&topic=2247 mpi cluster with rh9http://lists.freebsd.org/mailman/listinfo/freebsd-cluster freebsd cluster maillist