- 12 Sep, 2016 20 commits
-
-
Tim Wickberg authored
Will handle NO_VAL/INFINITE <-> NO_VAL64/INFINITE64 conversion, as well as MEM_PER_CPU flag.
-
Tim Wickberg authored
-
Dominik Bartkiewicz authored
-
Dominik Bartkiewicz authored
MaxMemPerNode, MaxMemPerCPU, DefMemPerNode, DefMemPerCPU
-
Dominik Bartkiewicz authored
-
Dominik Bartkiewicz authored
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Tim Wickberg authored
Used to pack/unpack new uint64_t arrays into older uint32_t array format for RPCs.
-
Tim Wickberg authored
Change RPCs and add encode/decode logic for past version. Change variables and structures to uint64_t: def_mem_per_cpu, max_mem_per_cpu, free_mem, real_memory, actual_real_mem, job_mem_lim, step_mem_limit, pn_min_memory, job_mem. Change MEM_PER_CPU flag to 64th bit instead of 32nd bit. Note that additional work is required to address local variables. Also need to add table conversion logic to MySQL, as mem_req column needs to change type to 'bigint unsigned' from 'int unsigned'.
-
Tim Wickberg authored
-
Tim Wickberg authored
Copy previous format, but do not change yet. Update RPCs involving: def_mem_per_cpu max_mem_per_cpu free_mem real_memory actual_real_mem job_mem_lim
-
Morris Jette authored
-
-
Morris Jette authored
-
Morris Jette authored
bug 3065
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Tim Wickberg authored
Add Slurm overview by Alex on first day, move KNL to second morning, shift roadmap to right after lunch.
-
Morris Jette authored
bug 3065
-
- 09 Sep, 2016 10 commits
-
-
Morris Jette authored
-
Morris Jette authored
Previous cap was 2 sec (default TCP timeout) times the node count and divided by 1000. A 9000 node job would have the messages spread out over 18 seconds. This change caps the spread at 5 seconds and assumes the normal TCP logic can handle the rest bug 3044
-
Morris Jette authored
-
Morris Jette authored
If the overhead of determining the hostlist for a given task list is too high, then report a hostlist of "Unknown" instead. If the overhead is too high, then srun will become unresponsive and communications will timeout/fail. bug 3044
-
Morris Jette authored
-
Morris Jette authored
Modify srun task completion handling to only build the task/node string for logging purposes if it is needed. Modified for performance purposes. bug 3044
-
Morris Jette authored
Add get_log_level() function to return the highest LOG_LEVEL_* used for any logging mechanism.
-
Tim Wickberg authored
This reverts commit 1ec2a4ae.
-
Morris Jette authored
Conflicts: src/api/step_launch.c
-
Alejandro Sanchez authored
Bug 3063.
-
- 08 Sep, 2016 10 commits
-
-
Brian Christiansen authored
In scontrol show nodes.
-
Morris Jette authored
Restructure srun command locking for task_exit processing logic for improved parallelism. This change decreases the amount of time consumed by serial logic by 2 orders of magnitude. bug 3044
-
Brian Christiansen authored
-
Brian Christiansen authored
Grab federations from db at startup instead of waiting for db_update and load from state if the db is down.
-
Brian Christiansen authored
-
Brian Christiansen authored
Instead of making a separate copy. All of the cluster_recs are now in the federation_rec with a pointer to the local cluster rec.
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
Select federations base off which clusters belong to them.
-
Morris Jette authored
-