[Linux-cluster] Home-brew SAN/iSCSI

[Andrew A. Neuschwander]

Madison Kelly wrote:
> Andrew A. Neuschwander wrote:
>> Madison Kelly wrote:
>>> Hi all,
>>>
>>>   Until now, I've been building 2-node clusters using DRBD+LVM for 
>>> the shared storage. I've been teaching myself clustering, so I don't 
>>> have a world of capital to sink into hardware at the moment. I would 
>>> like to start getting some experience with 3+ nodes using a central 
>>> SAN disk.
>>>
>>>   So I've been pricing out the minimal hardware for a four-node 
>>> cluster and have something to start with. My current hiccup though is 
>>> the SAN side. I've searched around, but have not been able to get a 
>>> clear answer.
>>>
>>>   Is it possible to build a host machine (CentOS/Debian) to have a 
>>> simple MD device and make it available to the cluster nodes as an 
>>> iSCSI/SAN device? Being a learning exercise, I am not too worried 
>>> about speed or redundancy (beyond testing failure types and recovery).
>>>
>>> Thanks for any insight, advice, pointers!
>>>
>>> Madi
>>>
>>
>> If you want to use a Linux host as a iscsi 'server' (a target in iscsi 
>> terminiology), you can use IET, the iSCSI Enterprise Target: 
>> http://iscsitarget.sourceforge.net/. I've used it and it works well, 
>> but  it is a little CPU hungry. Obviously, you don't get the benefits 
>> of a hardware SAN, but you don't get the cost either.
>>
>> -Andrew
> 
> Thanks, Andrew! I'll go look at that now.
> 
>   I was planning on building my SAN server on an core2duo-based system 
> with 2GB of RAM. I figured that the server will do nothing but 
> host/handle the SAN/iSCSI stuff, so the CPU consumption should be fine. 
> Is there a way to quantify the "CPU/Memory hungry"-ness of running a SAN 
> box? Ie: what does a given read/write/etc call "cost"?
> 
>   As an aside, beyond hot-swap/bandwidth/quality, what generally is the 
> "advantage" of dedicated SAN/iSCSI hardware vs. white box roll-your-own?
> 
> Thanks again!
> 
> Madi
> 

I think what makes being an iSCSI target CPU hungry is that it is 
handling a block layer protocol in user space. So while what it does is 
fairly simple (i.e. no filesystem), it has to do a lot of it. Storage 
performance is usually discussed in IOPS (I/Os Per Second), but when 
rolling my own, I just throw enough spindles/raid/cpu/memory at it 
saturate a GigE link and call it a day.

I've not used a hardware iSCSI SAN, just FC. The biggest benefits, in my 
mind, of something like an EMC Clariion are the fully redundant hardware 
path and the fast fabric.

Hmm, I may be getting off-topic here. Sorry about that.

-Andrew


> -- 
> Linux-cluster mailing list
> Linux-cluster at redhat.com
> https://www.redhat.com/mailman/listinfo/linux-cluster
>