Overview
Comment: | Refocus slice/sliver/nodes explanation to researcher's PoV. |
---|---|
Downloads: | Tarball | ZIP archive | SQL archive |
Timelines: | family | ancestors | descendants | both | trunk |
Files: | files | file ages | folders |
SHA1: |
d6a9583f4f19b9579bf27d7f8cd64401 |
User & Date: | ivan on 2012-10-07 22:03:36 |
Other Links: | manifest | tags |
Context
2012-10-07
| ||
22:31 | Keep base CN coop diagram at sight, be more explicit about additional antenna usage. check-in: 2d9ee92f63 user: ivan tags: trunk | |
22:03 | Refocus slice/sliver/nodes explanation to researcher's PoV. check-in: d6a9583f4f user: ivan tags: trunk | |
18:24 | Don't zoom all over the testbed architecture, introduce CN, nodes and admins. check-in: 695af32b2b user: ivan tags: trunk | |
Changes
Modified script.txt from [1a6ed75dc5] to [d52f0b2d78].
98 98 - Avoids problems with firewalls and private networks in nodes. 99 99 - Uses IPv6 to avoid address scarcity and incompatibility between CNs. 100 100 - Mgmt connections are short-lived to tolerate link instability. 101 101 - Gateways are entry points to the mgmt network. 102 102 - They help extend it over multiple CNs by external means (e.g. FEDERICA, the 103 103 Internet). 104 104 - They can also route the management network to the Internet. 105 -- Researchers run experiments in slices spread over several nodes (as 106 - slivers). *##* 105 +- Experiments are configured by researchers in the server and run in nodes. *##* 107 106 108 107 ** Slices, slivers and nodes 109 -# Axel: Reverse, from PoV of researcher: select nodes, run as slivers, gruop in slices. 110 -- These concepts are inspired in PlanetLab. 111 -- A slice is a management concept that groups a set of related slivers. 112 -- A sliver holds the resources (CPU, memory, disk, bandwidth, interfaces…) 113 - allocated for a slice in a given node. 114 -- A node hosts several slivers at the same time. *##* 108 +- Particularly, researchers select nodes for running experiments. 109 +- Each node is able to run several experiments simultaneously. 110 +- An experiment runs in a given node as a sliver which holds a share of its 111 + resources (CPU, memory, disk, bandwidth, interfaces…). 112 +- Finally, related slivers are grouped in a slice for management purposes. 113 +- All these concepts are inspired in PlanetLab. *##* 115 114 116 115 ** Node architecture 117 116 # Axel: More stress on node itself. 118 117 # Ivan: Don't zoom!! 119 118 allows the realization of these concepts. *##* A node consists of a CD, a RD 120 119 and a rD connected to the same wired local network. *##* 121 120