This is an old revision of the document!
Table of Contents
Virtual HPCC services
Thoughts on how to create virtual compute nodes in the HPCC stack. Specifically, trying to solve the need for tiny, but many, compute nodes for the nano physic applications. Like virtual compute nodes with a single core CPU with 100 MB or less of memory running a lean Scientific Linux operating system. Here is a good introduction: http://www.slideshare.net/gpaterno1/comparing-iaas-vmware-vs-openstack-vs-googles-ganeti-28016375
Building Ganeti
I'll select Ganeti to start with as it appears the simplest to setup. I've no need for services like fail-over or migration. Just the ability to rapidly many tiny nodes from a template. It also appears that Ganeti clusters can be embedded with Openstack later.
On hold, these Xen tools are very nice, no need for Ganeti up front (virt-manager, virt-clone, virsh).
Building Xen
To come.
Testing Xen
| 3d Lennard-Jones melt: for 10,000 steps with 32,000 atoms | ||
|---|---|---|
| Queue, node, HT | Jobs/Node, Loop Time | Comment |
| hp12, n15, no-HT | 01 jobs, 481 | |
| hp12, n15, no-HT | 07 jobs, 482 | |
| hp12, n2, yes-HT | 01 jobs, 470 | |
| hp12, n2, yes-HT | 15 jobs, 804 | known penalty |
| bss24, no-HT | 01 jobs, 844 | |
| bss24, no HT | 02 jobs, 770 | |
| bss24vm, bvm1, no-HT | 01 jobs, 776 | 1 vcpu, 100 ram |
| bss24vm, bvm1, no-HT | 02 jobs, 850 | 2 vcpu, 100 ram |
| bss24vm, bvm1, no-HT | 03 jobs, 1273 | 3 vcpu, 256 ram |
| bss24vm, bvm1, no-HT | 04 jobs, 1735 | 4 vcpu, 512 ram |
| bss24vm, bvm2, no-HT | 08 jobs, 3582 | 8 vcpus, 1024 ram |
