TuranTimur TuranTimur

OCP 4.2/4.3 All-In-One (UPI mode)

This document assume reader is familiar with the OCP4x installation process.

Setup the install-config.yaml to deploy a single master and no workers
```
apiVersion: v1
baseDomain: example.com
```

	/**********************************************
	*
	* MSSQL
	*
	***********************************************/

	# Installation
	https://nagarkotideepak9.medium.com/installing-microsoft-sql-mssql-in-red-hat-8-37adc1c5b42e
	* mssql 설치
	* odbc 설치 -> 이 부분 참고

	# roles/myrole/action_plugins/myshell.py

	class ActionModule(ActionBase):

	def run(self, tmp=None, task_vars=None):

	super(ActionModule, self).run(tmp, task_vars)
	module_args = self._task.args.copy()
	module_args['_raw_params'] = module_args.get('cmd')
	module_args['_uses_shell'] = True

	root@98c54cfbe5b9:/examples# mpirun -np 1 -H localhost:1 -bind-to none -map-by slot -x NCCL_DEBUG=INFO -x LD_LIBRARY_PATH -mca pml ob1 -mca btl ^openib python benchmarks-horovod_v2/scripts/tf_cnn_benchmarks/tf_cnn_benchmarks.py --model resnet101 --batch_size 16 --variable_update horovod
	/usr/local/lib/python3.5/dist-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
	from ._conv import register_converters as _register_converters
	TensorFlow: 1.5
	Model: resnet101
	Dataset: imagenet (synthetic)
	Mode: training
	SingleSess: False
	Batch size: 16 global
	16.0 per device

	with tf.device("/job:ps/task:0"):
	weights_1 = tf.Variable(...)
	biases_1 = tf.Variable(...)
	...

	worker_devices = ["/job:worker/task:0/gpu:0", ..., "/job:worker/task:7/gpu:0"]
	for worker_device in worker_devices:
	with tf.device(worker_device):
	with tf.device("/job:worker/task:7"):
	input, labels = ...

	#!/opt/openstack/venv/bin/python
	import MySQLdb
	import sys
	import json

	connection = MySQLdb.connect(
	host=sys.argv[1], user="nova",
	passwd=sys.argv[2], db="nova")
	cursor = connection.cursor()
	cursor.execute("select network_info, instance_uuid from instance_info_caches where deleted=0")

	import signal, os, time

	def handler(signum, frame):
	print 'Signal handler called with signal', signum
	raise IOError("Couldn't open device!")

	# Set the signal handler and a 5-second alarm
	signal.signal(signal.SIGALRM, handler)
	signal.alarm(5)

	- name: create repo file of myrepository
	ini_file: dest=/etc/yum.repos.d/myrepository.repo
	section="{{ item.section }}"
	option="{{ item.option }}"
	value="{{ item.value }}"
	with_items:
	- { section: 'myrepository', option: 'name', value: 'myrepository_repo'}
	- { section: 'myrepository', option: 'baseurl', value: 'http://xxx.xxx.xxx.xxx/'}
	- { section: 'myrepository', option: 'enabled', value: '1'}
	- { section: 'myrepository', option: 'gpgcheck', value: '0'}