Jim Garlick
Jim Garlick
Has there been any discussion about ATX style power control? E.g. press the power button once and the OS shuts down, and then powers off. Hold down the button to...
Problem: flux job list is too easy to confuse with flux-jobs(1), but the former is a test tool that emits JSON. Omit the list, list-inactive, and list-ids subcommands from help...
Problem: if a job is stuck completing for whatever reason (such as the painfully slow epilog on LC systems, but another one would be a hung node), `flux jobs` shows...
Problem: it's easy to confuse `flux job` with `flux jobs`. Perhaps `flux job list`, which outputs JSON, should just be a test program that is not installed (or a hidden...
This issue tracks reliability/administration issues that would prevent Flux from being deployed as the native resource manager on production systems. - [x] #4311 - [x] #4446 - [x] #4301 -...
Problem: the job-ingest `feasibility` plugin sends jobspec to the scheduler for an early determination of request feasibility, but the `jobspec-defaults` jobtap plugin has not yet assigned default values for jobspec...
This issue tracks the implementation of queues for partitioned resources, needed for rollout of Flux as the native resource manager on production systems. - [x] #4386 (default queue, and queue-specific...
On fluke, where only Flux is installed, trying to build a simple mpi hello world program fails with: ``` [garlick@fluke108:mpi-test]$ module list Currently Loaded Modules: 1) intel-classic-tce/2021.6.0 2) mvapich2-tce/2.3.6 3)...
This tracks problems with Flux that prevent it from working with the TOSS4 /usr/tce environment (MPI, compilers, tools, libraries) - [ ] flux-framework/flux-security#148 - [x] flux-framework/flux-pmix#40 - [x] #4371 -...
Problem: A simple hello world program cannot be linked on fluke using the openmpi-tce/4.1.2 package because slurm's libpmi2.so library is not installed. ``` [garlick@fluke108:~]$ module load openmpi-tce Lmod is automatically...