<div dir="ltr">Hi Krishna <br><br> I'm running glusterfs servers and clients on all the nodes that are connected to the private network and I want to run glusterfs clients (only) on researcher computers that have only access to the head node from an external network. <br>
I've attached an image of the final setup I want to reach ... <br> What I'm missing now: Head node doesn't iSCSI mount the toaster and doesn't isn't a glusterfs server. The researcher's computer doesn't act as a glusterfs client ... <br>
<br><br><br><br>--<br>TIA <br>Paolo <br><br><br><br><br><br><br><br><div class="gmail_quote">On Sat, Sep 20, 2008 at 10:32 PM, Krishna Srinivas <span dir="ltr"><<a href="mailto:krishna@zresearch.com">krishna@zresearch.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"><div class="Ih2E3d">On Sun, Sep 21, 2008 at 1:46 AM, Paolo Supino <<a href="mailto:paolo.supino@gmail.com">paolo.supino@gmail.com</a>> wrote:<br>
> Hi Krishna<br>
><br>
> I have all intentions of mounting the toaster's filesystems on the<br>
> head node using iSCSI (see my original post), but I have a problem: I<br>
> have 35 servers in the gluster filesystem that the researchers don't see<br>
> directly: the head node hides the private network with<br>
> PAT/PNAT/Masquerading (pick your favorite acronym) so the clients only<br>
> see the head node but not all the gluster filesystem servers behind it.<br>
> The glusterfs clients get a wrong image of the gluster filesystem ... I<br>
> could simply remove the PAT/PNAT/Masquerading (pick your favorite<br>
> acronym), but I'd rather not do that because that adds an overhead in<br>
> systems administration and breaks the rule of KISS.<br>
><br>
<br>
</div>Ah OK, you have 35 storage servers apart from toaster.<br>
If I understand you correctly, you are planing to run glusterfs<br>
client on head node and re-export this mount point to the<br>
researchers' nodes?<br>
If yes, you could setup port forwarding on head node and avoid<br>
re-exporting completely so that researchers' nodes access the<br>
storage nodes directly.<br>
<br>
Regards<br>
<font color="#888888">Krishna<br>
</font><div><div></div><div class="Wj3C7c"><br>
><br>
><br>
> --<br>
> TIA<br>
> Paolo<br>
><br>
><br>
><br>
> Krishna Srinivas wrote:<br>
>> Paolo,<br>
>><br>
>> You could mount toaster's partition on head node using iscsi.<br>
>> Run glusterfs server on head node exporting the two partitions.<br>
>> Run glusterfs client on the researcher's nodes.<br>
>><br>
>> Krishna<br>
>><br>
>> 2008/9/18 Paolo Supino <<a href="mailto:paolo.supino@gmail.com">paolo.supino@gmail.com</a>>:<br>
>>> Hi<br>
>>><br>
>>> now that I have a new shiney parallel filesystem :-) I want to take<br>
>>> it a step forward (the fun never ends ;-) ) ...<br>
>>> A few words on my HPC cluster:<br>
>>> 1. The private network between the compute nodes, head and toaster<br>
>>> (Netapp FAS 2020) is Gigabit Ethernet.<br>
>>> 2. The toaster exports 2.1 and 5.1 TB volumes served over NFSv3 (ouch..)<br>
>>> 3. Only the head node is multi homed and connected to the faculty<br>
>>> network, where the researchers are ...<br>
>>><br>
>>> What I thought of doing:<br>
>>> 1. Re export the toaster using iSCSI.<br>
>>> 2. Mount the iSCSI exports on the head and add them to the gluster<br>
>>> volume. This is pretty straight forward :-) and voilą I have a uniform<br>
>>> 9.3TB volume ...<br>
>>> 3. The last part is the tricky part that I still have to figure out:<br>
>>> have the researchers be able to be gluster clients of this volume<br>
>>> without exposing the private network to the faculty network (I don't<br>
>>> want to NFS export it)<br>
>>><br>
>>><br>
>>><br>
>>><br>
>>> --<br>
>>> Paolo<br>
>>> _______________________________________________<br>
>>> Gluster-users mailing list<br>
>>> <a href="mailto:Gluster-users@gluster.org">Gluster-users@gluster.org</a><br>
>>> <a href="http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users" target="_blank">http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users</a><br>
>>><br>
><br>
><br>
</div></div></blockquote></div><br></div>