> For what purposes are you clustering? There are 2 basic types of > clusters - high availability clusters, and compute clusters. Assuming > you want HA clusters, visit http://www.linux-ha.org
Also, within the compute clusters, you have essentially 3 different types - massively parallel clusters, shared-memory clusters, and pipeline clusters, each of which are better for different workloads. Massively parallel clusters - The computation is easily dividable among any number of nodes, and very little data is needed to be shared among nodes. Pipeline clusters - There are X independent jobs, so you can split up the process by at most X nodes. Shared memory clusters - same as either above, but a lot of memory sharing needs to take place. This usually requires specialized equipment. Jon > > -- > Ed Wilts, Mounds View, MN, USA > mailto:[EMAIL PROTECTED] > Member #1, Red Hat Community Ambassador Program > > > -- > redhat-list mailing list > unsubscribe mailto:[EMAIL PROTECTED] > https://www.redhat.com/mailman/listinfo/redhat-list > -- redhat-list mailing list unsubscribe mailto:[EMAIL PROTECTED] https://www.redhat.com/mailman/listinfo/redhat-list