help me about creating cluster by pelican hpc iam beginer

[hogat]

hi i have 4 computer pentum 4 and one hub i put 4 cd pelican hpc 1.8 in to my computer and boot them lively but i see one node on each theme i read pdf on cd but dont get any thing what i do for create cluster on these 4 computer ? what i should to do? please say exactly i am beginer ? have i should define ip node ? and ... best regard Hogat

[Michael Creel]

The tutorial on the homepage (which is the same as the pdf included with the releases) explains exactly what you need to do. There is also a screencast video on the homepage which shows the steps to follow. Please check those out carefully and then I'll be happy to answer specific questions.
Cheers, M.

[hogat]

hi dear and thank u if u means pdf at desktop i and my freind Saman read it but dont get any thing
can u say briefly what i should to do? i have 4 cd pelican hpc an network with one hub
how i create cluster how create dhcp for outomatic ip for computer and ...?
we want test pelican after build cluster what i should to do?
pelican can work use other linux or windows as node?
your project is buty and interesting but your doc and toturial is week
best regard
Hogat and Saman

[Michael Creel]

I have a feeling I'm being trolled...

[hogat]

hi we worked this : connect 3 computer to switch of network an disconnect network from other network
insert live pelican 1.8 in one computer then up with it then at terminal we write "pelican_setup"  then
"pelican_restart_hpc" and then insert other two cd live pelican 1.8 at other our tow computer an boot
theme my bios was boot from cdrom because when we select boot from lan an restart computer WindowsXp
Uping on . so we select boot from cd atlast i press "No" at "pelican_restart_hpc" untile it show 3 node is verified . at /home/user/tmp/bhosts  we see
10.11.12.4
10.11.12.1
10.11.12.3
but
when i run
$lamboot
and
when i run
$lamnodes -i
i see
no  171.0.0.1:1 origin,this_node
what is problem ? our cluster dont verifiy nodes ? what we should to do?
our node in bios can not up with lan booting
what we must to do ?
what is problem?
best regard
Hogat And Saman

[Michael Creel]

Okay, I see that you are serious about this. First, I'm not sure what happens if you try to boot the compute nodes from CD, rather than netboot. I'm pretty sure that it will not work properly, because the compute nodes will not NFS mount the exported /home directory. That will no doubt make the cluster virtually useless. Sorry, but netboot is required for the compute nodes. You might try to use rom-o-matic (google it) to work around problems with your nodes. Some versions of ParallelKnoppix allowed you to boot the nodes from CD.

The specific problem you see with lamboot is because you are not calling lamboot correctly  - you need to specify the bhost file. There is really no need to do this, because PelicanHPC already does it for you.  Do "man lamboot" and "man bhost" to learn more about this, and also examine the script /usr/bin/pelican_restarthpc on a running PelicanHPC frontend node. The LAM/MPI documentation explains this in detail.

I will possibly try to make PelicanHPC support booting the nodes from CD in the future.

Cheers, Michael

[hogat]

well i want go to university tomorrow  and test this  ,  see i say true ?
problem is two matter my NIC not support netboot then i should get gpxe-0.9.7+-gpxe.dsk and put it on floppy disk and set boot in bios boot from floppy until my pc load with netboot and then put my pelican cd in computer .
and other that  
when my frontend node verified comput node i should write command
$lamboot -d  /home/user/tmp/bhost
up text is correct?
thanks very much
best regard to u
Hogat

[Michael Creel]

You only need to get the compute node to netboot using rom-o-matic or something similar. There is no need for a CD for the compute node, it will get everything it needs from the frontend node. Also, there is no need for you to lamboot, that is also done automatically. You can call "pelican_restarthpc" from the terminal any time you add or remove compute nodes, to automatically lamboot whatever nodes are available. You might like to examine that script (it's in /usr/bin) to see how nodes are found and lambooted.

Good luck with netboot - that is the only barrier to getting this to work.

Michael

[hogat]

hi
this odd to me . you said that no need cd for comput node .
this means that pelican hpc use cpu and ram of comput node with out os on those system ?
i say true? where i can get how pelican work ? it use what algorithm ?what is it mecanism?
u can guide me how work gpxe or rom-o-mati ? how create floppy disk for netbooting from it.
very thanks for your help and your patient
best regard
Hogat

[Michael Creel]

The CD is used to boot the frontend node, but then the frontend node works as a netboot server (tftp, dhcp, nfs) to let the other nodes (the compute nodes) boot by netboot. If your compute nodes are not capable of netboot, then it is possible to use rom-o-matic or perhaps other means to work around it. The rom-o-matic page has documentation, but it is a little confusing the first time you try it. In my opinion, a better solution is to purchase a network card that has PXE capabilities. They can be bought cheaply second hand.

[hogat]

Hi
at last i success to load by netboot
this all :
i  insert pelican hpc into one pc and load it then
#pelican_setup
and i select  select  "eth0    network_device_eth0  " because pc have two Nic then
#pelican_restart_hpc
and press "NO"
and then insert cd gpxe into other pc and reboot it and in frontend node at  #pelican_restart_hpc
i press no
but when pc's  that gpxe cd in it , load
i see follow, what is problem?

net0:00:15:f2:08:a2:c0 no PCI 02:05.0 (open)[Link:up TX0 TXE:0 RX:0 RXE:0 ] waiting for Linkup on eth0 ... ok
net0:10.11.12.3/255.255.255.0 gw 0.0.0.0
Booting from filename "pxelinux.0"
tftp://10.11.12.1/pxelinux.0 ... connection  time out (0x4c126035)  
could not load tftp:10.11.12.1/pxelinux.0 :connection time out (0x4c126035)
no more Network Device

at the frontend node i have :
#cat  ~/tmp/bohsts
10.11.12.1
#
what is my mistake ? what i should to do?
oh
Michael my english is very bad?  
very thanks
best regard
Hogat

[Michael Creel]

Hi Hogat,

I'm sorry, but I don't know what is the cause of this problem. I don't have experience with gpxe, so I really don't know how it will work. The fact that the compute node receives an IP means that the machines are connected properly. I don't know why tftp is timing out. Sorry, but I don't have any ideas.

One thing you might do is set up a virtual cluster using QEMU, Virtualbox or VMware server. This is a convenient way to learn, and it will solve your problems of netboot. The screencast video on the PelicanHPC homepage shows how that can be done.

Another solution is to buy an ethernet card that is equipped to do PXE. They are pretty cheap secondhand. Are you sure your cards won't do PXE? It is an option than is often turned off by default. You might need to activate it in your BIOS setup.

Michael

[hogat]

hi  Michael  
On Wed, Sep 16, 2009 at 10:00 PM, hogat allah shahamiri
<[e-mail]> wrote:
> hi
> i think i forget  to write  two slash after  tftp:
> please think that is right
> and the line is :  tftp://10.11.12.1/pxelinux.0  is TRUE  then what is problem?
> if no this wrong and problem is in tftp:10.11.12.1/pxelinux.0
> what i should to do exactly?
> i want cluster computers in university by pelican hpc 1.8
> but i have above problem
> i am in wait
> best regard
> Hogat
>
> On 9/16/09, Miller, Shao <[e-mail]> wrote:
>> Hello again Hogat,
>>
>> Your DHCP filename should be simply:
>>
>> pxelinux.0
>>
>> or
>>
>> tftp://10.11.12.1/pxelinux.0
>>
>> But not:
>>
>> tftp:10.11.12.1/pxelinux.0
>>
>> If this change does not fix your problem, please describe what your DHCP
>> server's filename option is set to.
>>
>> - Shao Miller
>>

Hi
The error code 0x4c126035 is a TFTP timeout.
Maybe your TFTP server IP is wrong(the 'next-server' option handed out
by gPXE) or the filename is not correct, or the TFTP server simply
isn't running at the server.

Thomas

if thomas say correct how solve it in pelican?
thanks

[Michael Creel]

Sorry, but I don't know. I attempt to support hardware that does PXE boot, but I don't have the resources to try to support work arounds like gpxe. I would be happy to receive a HOWTO document that describes how to do it, but I can't try to figure it out myself - too many other things to do.

[hogat]

#Hi
this is very very odd to me
i understood that tftp  is  not run .
i test this :
# /etc/init.d/atftpd start then i do #ps -aux  but i don't  saw tftp or ftp or atftp
then i act this
#sudo  ps -aux but again i dont see tftp proccess
then i  change the 'USE_INETD=true' to 'USE_INETD=false' in  '/etc/init.d/atftpd'
and then /etc/init.d/atftpd start then i get #ps but again not exist.
at last i test this  /usr/sbin/atftpd --daemon /var/lib/tftpboot
and again i get #ps -aux but tftp process not exist .

this odd why tftp process not run?
well when i run commands for example  :
#/usr/sbin/atftpd --daemon /var/lib/tftpboot
i see command prompt means ' # '  and this is no error.
what happened ? what i should to do ?
i use live cd linux
best regard
Hogat

[hogat]

but if tftp not running how i could to get pxelinux.0 in
/var/lib/tftpboot with tftp client on WindowsXp .

[Michael Creel]

Sorry, offhand I don't know what the process name is when the atftpd daemon is started. Whatever it is, it is running after you do pelican_setup. I went back and looked at your original message, and I see you're using a hub. Why don't you try to connect the frontend and a single compute node using a crossover cable? If the hub is managed, it can mess things up by handing out IP addresses. An unmanaged switch is what I use.

[Shporang]

Often times to set up PXE boot you need to enable it in a few places in the bios.  On the computer I've used Pelican on I needed to enable PXE boot on the ethernet card, enable the bios to boot from PXE and then set PXE to the first boot device...or some similar procedure...I haven't messed with it in a while, but if you hunt around in your bios long enough you should be able to figure it out.  Hope this helps.

[Davids]

Hi Michael

i happen to have followed all the steps for setting up a pelicanhpc cluster. however i have a problem. am using the pelican Version 2.6, i was able to set up on the frontend node, but when i go to turn on the compute nodes, my compute nodes get client IP well.
then unfortunately they show the following words:
PXE -E32 : TFTP open timeout,

and when i compare the issue by installing using the older version pelican V1.9 cd, the nodes will net boot successfully, but i prefer to using the newer version. what could be the problem with the V2.6 SEPT 2011.

[Michael Creel]

If I recall correctly, v1.9 was based on Debian Lenny, and v2.0 was the first release based on Squeeze. The problem is likely due to the different kernels, and the support included with the kernel for networking hardware. It is possible that your compute nodes need some NIC module that is not included with the kernel used on Squeeze. That seems like the most likely explanation to me. Unfortunately, if this is the problem, there's no easy fix.