[Bioclusters] parallel blast???

Romualdo Zayas Lagunas bioclusters@bioinformatics.org
Tue, 17 Sep 2002 09:41:06 -0500 (CDT)

On Mon, 16 Sep 2002, Chris Dagdigian wrote:

> Be careful with your benchmarks as they can be meaningless or 
> misleading. You will find that the speed of blast distributed within a 
> cluster or compute farm is directly related to 2 things: (a) the amount 
> of physical memory in the compute  nodes and (b) the speed of your 
> storage or disk I/O system.

I'll be.
> You can have the fastest server on earth but if you searching with 
> blast against an NFS mounted database and your network or fileserver is 
> slow then your blast searching speeds will be horrible. Give me a small 
> number of speedy linux boxes and I can bring a $300,000 NFS/NAS system 
> to its knees. Storage does matter.
> Blast performance also depends on you tune your DRM (gridengine or LSF 
> etc. etc.) and how  you adjust your workflow with respect to splitting 
> large databases, locally caching data on compute nodes etc. etc.

I'm sorry, I didn't understand DRM, what does that mean???  

> What are you trying to benchmark for? Picking the right CPU?
Yes we want to buy a cluster and we want the "right" CPU.

> Some people on this list may have already done this. My personal
> is Intel Pentium III's right now because:
> o P IV's are way too expensive
> o P III's are dirt cheap
> o There are a ton of dual-CPU motherboard options for the PIII allowing 
> me flexible choices of system packaging and vendor
> o Athalon / AMDs are super fast but your motherboard choices are 
> limited and you need to be really  careful about cooling and ventilation

But, PTM III is an "old" processor, it isn't????
PTM IV, I agree with you...
Athlon....I don't know enough about that...