clustershell
clustershell copied to clipboard
cea-hpc
Scalable cluster administration Python framework — Manage node sets, node groups and execute commands on cluster nodes in parallel.
Add advanced interactive features in clush.py, like: - add automatic unreachable nodes exclusion - result tagging for fast nodeset switching - ...
We need to regroup Worker non-regression tests in order to be able to tests all differents Worker with the same tests.
We need to regroup Engine non-regression tests in order to be able to tests all differents Engine (soon 3 of them) with the same tests.
EnginePoll and EngineEPoll shared a lot of similar code. The incoming EngineSelect will also shared a lot of code with the 2 other ones. It is simple to factorize this...
Instead of having a static topology configuration file on the management node, add a way to use DNS-SD/DNSExt to know about gateway state changes (and maybe load).
By default, clustershell folds node sets in all dimensions. This can actually be quite annoying sometimes as other tools don't support that. For example, Slurm doesn't and requires that the...
Several functional aspect are either not present in all Worker subclasses, or named differently. For example, consider `SimpleWorker.retcode()` and `DistantWorker.iter_retcode()`. Neither method are present in the Worker interface.
After `--rcopy` (#55) added in 1.4, add a new `clush` feature : a reverse-reverse copy in order to copy hostname-tagged local files (retrieved with `--rcopy`) to remote nodes.
Low priority, but good to know and if ever someone is interested to fix it, here is the only issue: ``` ====================================================================== ERROR: Failure: ImportError (No module named 'cPickle') ----------------------------------------------------------------------...
Hello, My hostnames are of types: -abcdefghhh0001 -ijklmnophhh0001 Common name is hhh0001. Is it possible to regroup: [abcdefg,ijklmno]hhh0001 ? Best regards,
