Cluster Computing Tutorial (Request)
8 minutes ago, Electronics Wizardy said:Ha Ha me again
The thing with clusters is that the software the master runs is normally very depend't on exactly what you want to do on the nodes and why your making a cluster. Normally your running a cluster for 1 of 2 main reasons, or a combo of both.
1. HA(high availability. This is when you have 2 or more servers running the same thing at once, and only one is used at a time, with the other nodes seeing if the main one is running, and if it fails, they will take the same ip and config, and can switch in about 100msec, so you won't notice any downtime. This is mainly used for things where uptime is very imporant, like the stock exchange. The easy way to do this is heartbeart on linux or drbd.
2. High performance. This is when you split a task into smaller ones to have work on little chunks. This is used for things like rendering, scientific computations, VM's. THe controller depends on the exact task, but something like a beowolf cluster can be used to shove work out to a ton of slaves with a variable value, and have them work on that chuck.
If you want to do any of this you first need a task to cluster.
Thanks for the response, but I've already set it up.

Create an account or sign in to comment
You need to be a member in order to leave a comment
Create an account
Sign up for a new account in our community. It's easy!
Register a new accountSign in
Already have an account? Sign in here.
Sign In Now