[Bioclusters] Taking a poll

[Anand S Bisen]

Glen Otero wrote:
> Greetings biocluster intelligentsia!
> 
> I have some new BioBrew (biobrew.org) feature ideas that I'd like to  
> scrutinize against the collective intelligence and experience of this  
> community. I've written a few information gathering questions that,  if 
> answered, ought to help me judge the feasibility of my ideas.  What's in 
> it for those of you who take a few minutes to respond?  Well, the first 
> 20 folks to email me (offline at  gotero at linuxprophet.com) with 
> sufficient answers to *all* 20  questions will receive a $10 ThinkGeek 
> gift certificate. The next 10  people with answers to all the questions 
> will receive a $5 ThinkGeek  gift certificate. The questions are below 
> with example answers in  parentheses (sometimes). Be as detailed as you 
> like, because more  detailed answers will win in the event of a tie 
> breaker : )
> 
> Thanks for your help!!-- Glen
> 
> 1) What is the size of your Linux cluster? (e.g. 128 nodes)
48 nodes

> 2) What is the compute node architecture? (e.g. dual 3GHz Xeon, dual  
> Opteron)
dual 3.2GHz Xeon

> 3) Do your compute nodes have local hard drives or are they diskless?
Local hard disk

> 4) What is the cluster interconnect? (e.g. GigE)
GigE

> 5) What application(s) primarily run on your cluster (e.g. BLAST, HMMER)
sequest, tandem, statistical/mathematical ad-hoc scripts

> 6) If BLAST is running on your cluster, describe the type of BLAST  jobs 
> (e.g. blastn- genome vs. genome, blastn-genome annotation with  ESTs)
NA

> 7) What type of cluster filesystem is in use on your cluster? (e.g.  
> NFS, GFS, proprietary)
NFS

> 8) If you use NFS, is your NFS server the same as the cluster head  node 
> or is it a separate server?
Seperate

> 9) If you use NFS, what type of machine is your NFS server? (e.g.  dual 
> Xeon Linux Box w/ x number of yGB hard drives)
Quad Intel Xeon 3.0 GHz with Dual Path Fiber Connect IBM TotalStorage 
FAStT600 Turbo


> 10) What is the ratio of NFS servers to compute nodes in your cluster?
8:48

> 11) How do you benchmark the throughput of your NFS server, i.e. what  
> application(s) do you use to stress the NFS server and what tool(s)  do 
> you use to measure throughput?
bonnie++

> 12) If you have a NAS/SAN, what type of machine(s) are they? (e.g.  
> NetApp w/ x number of yGB hard drives)
In all i have around 3TB of storage attached with this cluster 
consisting of 36 Fiber Channel Hard Disks

> 13) What is the ratio of NAS servers to compute nodes in your cluster?
1:48

> 14) What is the throughput of your NAS server(s)/SAN?
around 35-39 MB/s

> 15) How do you benchmark the throughput of your NAS server/SAN, i.e.  
> what application(s) do you use to stress the servers and what tool(s)  
> do you use to measure throughput?

> 16) Are you satisfied overall with your cluster filesystem solution?
Yes/No

> 17) What are the two biggest problems you have with your cluster  
> filesystem solution?
Bottleneck is NFS due to excessive amount of file I/O over NFS

> 18) With regard to cluster filesystems, what would you do differently  
> when building your next cluster? (e.g. increase NFS servers/compute  
> node ratio, different filesystem)
Try different file systems

> 19) What NFS server/compute node or NAS-SAN/compute node ratio will  you 
> aim for with the next cluster you build or upgrade?
Still evaluating

> 20) If necessary, do you mind if Glen emails you offline to seek  
> clarification on some of your answers? (Answering "Yes" is not  
> necessary to be eligible for a gift certificate).
Feel free



thanks

Anand



---
Anand Singh Bisen
http://www.abisen.com
> _______________________________________________
> Bioclusters maillist  -  Bioclusters at bioinformatics.org
> https://bioinformatics.org/mailman/listinfo/bioclusters
>