From dbf77cdf0ac9be48cb1348c8e4beedfc7e250e87 Mon Sep 17 00:00:00 2001
From: David Hendriks <davidhendriks93@gmail.com>
Date: Wed, 16 Sep 2020 16:25:14 +0100
Subject: [PATCH] busy with hpc slurm and condor stuff
---
binarycpython/utils/grid_options_defaults.py | 22 ++++++---
binarycpython/utils/hpc.py | 52 ++++++++++++++++++++
2 files changed, 68 insertions(+), 6 deletions(-)
create mode 100644 binarycpython/utils/hpc.py
diff --git a/binarycpython/utils/grid_options_defaults.py b/binarycpython/utils/grid_options_defaults.py
index bbcda861e..19ecc0220 100644
--- a/binarycpython/utils/grid_options_defaults.py
+++ b/binarycpython/utils/grid_options_defaults.py
@@ -118,27 +118,37 @@ grid_options_defaults_dict = {
########################################
# Slurm stuff
########################################
- "slurm": 0, # dont use the slurm by default
+ slurm_ntasks=>1, # 1 CPU required per job
+ slurm_partition=>'all', # MUST be defined
+ slurm_jobname=>'binary_grid', # not required but useful
+ slurm_use_all_node_CPUs=>0, # if given nodes, set to 1
+ # if given CPUs, set to 0
+
+ "slurm": 0, # dont use the slurm by default. 1 = use slurm
"slurm_command": "", # Command that slurm runs (e.g. run_flexigrid or join_datafiles)
"slurm_dir": "", # working directory containin scripts output logs etc.
- # slurm_njobs=>'', # number of scripts
- # slurm_jobid=>'', # slurm job id (%A)
+ "slurm_njobs": 0, # number of scripts; set to 0 as default
+ "slurm_jobid": '', # slurm job id (%A)
+ "slurm_memory": 512, # in MB, the memory use of the job
+ "slurm_warn_max_memory": 1024, # in MB : warn if mem req. > this
+ "slurm_use_all_node_CPUs": 0, # 1 = use all of a node's CPUs. 0 = use a given amount of CPUs
+ "slurm_postpone_join": 0, # if 1 do not join on slurm, join elsewhere
+
# slurm_jobarrayindex=>'', # slurm job array index (%a)
# slurm_jobname=>'binary_grid', # set to binary_grid
# slurm_postpone_join=>0, # if 1, data is not joined, e.g. if you
# # want to do it off the slurm grid (e.g. with more RAM)
# slurm_postpone_sbatch=>0, # if 1, don't submit, just make the script
# # (defaults to $ENV{PWD} if undef)
- # slurm_memory=>512, # in MB, the memory use of the job
- # slurm_warn_max_memory=>1024, # in MB : warn if mem req. > this
# slurm_partition=>undef,
# slurm_ntasks=>1, # 1 CPU required per array job: usually only need this
# slurm_time=>0, # 0 = infinite time
- # slurm_use_all_node_CPUs=>0, # 1 = use all of a node's CPUs (0)
# # you will want to use this if your Slurm SelectType is e.g. linear
# # which means it allocates all the CPUs in a node to the job
# slurm_control_CPUs=>0, # if so, leave this many for Perl control (0)
# slurm_array=>undef,# override for --array, useful for rerunning jobs
+
+
########################################
# Condor stuff
########################################
diff --git a/binarycpython/utils/hpc.py b/binarycpython/utils/hpc.py
new file mode 100644
index 000000000..e33bf362c
--- /dev/null
+++ b/binarycpython/utils/hpc.py
@@ -0,0 +1,52 @@
+"""
+File containing functions for HPC computing, distributed tasks on clusters etc.
+
+Mainly divided in 2 sections: Slurm and Condor
+"""
+
+import os
+import time
+
+class slurm_grid():
+
+
+
+
+def create_directories_hpc(working_dir):
+ """
+ Function to create a set of directories, given a root directory
+
+ These directories will contain stuff for the HPC runs
+ """
+
+ #
+ if not os.path.exist(working_dir):
+ print("Error. Working directory {} does not exist! Aborting")
+ raise ValueError
+
+ directories_list = ['scripts','stdout','stderr','results','logs','status','joining']
+
+ #
+ for subdir in directories_list:
+ full_path = os.path.join(working_dir, subdir)
+ os.makedirs(full_path, exist_ok=False)
+
+ # Since the directories are probably made on some mount which has to go over NFS
+ # we should explicitly check if they are created
+
+ print("Waiting for directories")
+ directories_exist = False
+ while directories_exist:
+ directories_exist = True
+
+ for subdir in directories_list:
+ full_path = os.path.join(working_dir, subdir)
+
+ if not os.path.exist(full_path):
+ time.sleep(1)
+ directories_exist = False
+
+ print("Directories exist")
+
+
+
--
GitLab