Hi, Over the past two weeks, from a standing start, I¹ve worked on a Hadoop based parallel genetic sequence alignment algorithm as part of my university masters project.
Thankfully that¹s now up and running, along the way I got some great help from members of this group and I deeply appreciate that strangers would take time out of their busy lives to shed a bit of light on what seemed at times an insurmountable task. On Monday I get to play with a 32 node system and the only advice I have so far is to benchmark my algorithm with 5gb per node. I wonder if, if you were starting out again on your first big Hadoop map reduce job what would would you differently ? What advice would you give me starting out ? Thanks again, I really appreciate your support. Best Chris Regards, Chris MacKenzie <http://www.chrismackenziephotography.co.uk/> <http://www.chrismackenziephotography.co.uk/>Expert> <http://plus.google.com/+ChrismackenziephotographyCoUk/posts> <http://www.linkedin.com/in/chrismackenziephotography/>