Do not auto-prune instance types if there are too many (#235)

I was previously only allowing 1 memory size/core count combination to keep
the number of compute resources down and also was combining multiple instance
types in one compute resource if possible.
This was to try to maximize the number of instance types that were configured.

This led to people not being able to configure the exact instance types they
wanted.
The preference is to notify the user and let them choose which instances types
to exclude or to reduce the number of included types.

So, I've reverted to my original strategy of 1 instance type per compute resource and 1 CR per queue.
The compute resources can be combined into any queues that the user wants using
custom slurm settings.

I had to exclude instance types in the default configuration in order to keep from exceeding the PC limits.

Resolves #220

Update ParallelCluster version in config files and docs.

Clean up security scan.

Author: cartalla

.gitignore

@@ -1,7 +1,10 @@
 
+
 .mkdocs_venv/
 _site
 site/
 .vscode/
 source/resources/parallel-cluster/config/build-files/*/*/parallelcluster-*.yml
+security_scan/bandit-env
+security_scan/bandit.log
 security_scan/cfn_nag.log

Makefile

@@ -1,8 +1,8 @@
 
-.PHONY: help local-docs test clean
+.PHONY: help local-docs security_scan test clean
 
 help:
-	@echo "Usage: make [ help | local-docs | github-docs | clean ]"
+	@echo "Usage: make [ help | local-docs | github-docs | security_scan | test | clean ]"
 
 .mkdocs_venv/bin/activate:
 	rm -rf .mkdocs_venv

docs/deploy-parallel-cluster.md

@@ -4,7 +4,7 @@ A ParallelCluster configuration will be generated and used to create a ParallelC
 The first supported ParallelCluster version is 3.6.0.
 Version 3.7.0 is the recommended minimum version because it supports compute node weighting that is proportional to instance type
 cost so that the least expensive instance types that meet job requirements are used.
-The current latest version is 3.8.0.
+The current latest version is 3.9.1.
 
 ## Prerequisites
 

docs/res_integration.md

@@ -30,7 +30,7 @@ The following example shows the configuration parameters for a RES with the Envi
 # Command line values override values in the config file.
 #====================================================================
 
-StackName: res-eda-pc-3-8-0-rhel8-x86-config
+StackName: res-eda-pc-3-9-1-rhel8-x86-config
 
 Region: <region>
 SshKeyPair: <key-name>
@@ -42,10 +42,10 @@ ErrorSnsTopicArn: <topic-arn>
 TimeZone: 'US/Central'
 
 slurm:
-  ClusterName: res-eda-pc-3-8-0-rhel8-x86
+  ClusterName: res-eda-pc-3-9-1-rhel8-x86
 
   ParallelClusterConfig:
-    Version: '3.8.0'
+    Version: '3.9.1'
     Image:
       Os: 'rhel8'
     Architecture: 'x86_64'

security_scan/security_scan.sh

@@ -5,9 +5,9 @@
 scriptdir=$(dirname $(readlink -f $0))
 
 cd $scriptdir/..
-./install.sh --config-file ~/slurm/res-eda/res-eda-pc-3-7-2-centos7-x86-config.yml --cdk-cmd synth
+./install.sh --config-file ~/slurm/res-eda/res-eda-pc-3-9-1-rhel8-x86-config.yml --cdk-cmd synth
 
-cfn_nag_scan --input-path $scriptdir/../source/cdk.out/res-eda-pc-3-7-2-centos7-x86-config.template.json --deny-list-path $scriptdir/cfn_nag-deny-list.yml --fail-on-warnings &> $scriptdir/cfn_nag.log
+cfn_nag_scan --input-path $scriptdir/../source/cdk.out/res-eda-pc-3-9-1-rhel8-x86-config.template.json --deny-list-path $scriptdir/cfn_nag-deny-list.yml --fail-on-warnings &> $scriptdir/cfn_nag.log
 
 cd $scriptdir
 if [ ! -e $scriptdir/bandit-env ]; then

source/cdk/cdk_slurm_stack.py

@@ -181,6 +181,15 @@ def get_slurm_rest_api_version(config):
 
 # Feature support
 
+def MAX_NUMBER_OF_QUEUES(parallel_cluster_version):
+    return 50
+
+def MAX_NUMBER_OF_COMPUTE_RESOURCES(parallel_cluster_version):
+    return 50
+
+def MAX_NUMBER_OF_COMPUTE_RESOURCES_PER_QUEUE(parallel_cluster_version):
+    return 50
+
 # Version 3.7.0:
 PARALLEL_CLUSTER_SUPPORTS_LOGIN_NODES_VERSION = parse_version('3.7.0')
 def PARALLEL_CLUSTER_SUPPORTS_LOGIN_NODES(parallel_cluster_version):
@@ -194,6 +203,10 @@ def PARALLEL_CLUSTER_SUPPORTS_MULTIPLE_COMPUTE_RESOURCES_PER_QUEUE(parallel_clus
 def PARALLEL_CLUSTER_SUPPORTS_MULTIPLE_INSTANCE_TYPES_PER_COMPUTE_RESOURCE(parallel_cluster_version):
     return parallel_cluster_version >= PARALLEL_CLUSTER_SUPPORTS_MULTIPLE_INSTANCE_TYPES_PER_COMPUTE_RESOURCE_VERSION
 
+PARALLEL_CLUSTER_SUPPORTS_NODE_WEIGHTS_VERSION = parse_version('3.7.0')
+def PARALLEL_CLUSTER_SUPPORTS_NODE_WEIGHTS(parallel_cluster_version):
+    return parallel_cluster_version >= PARALLEL_CLUSTER_SUPPORTS_NODE_WEIGHTS_VERSION
+
 # Version 3.8.0
 
 PARALLEL_CLUSTER_SUPPORTS_CUSTOM_ROCKY_8_VERSION = parse_version('3.8.0')
@@ -297,6 +310,7 @@ def DEFAULT_OS(config):
 
     'x2iezn',            # Intel Xeon Platinum 8252 4.5 GHz 1.5 TB
 
+    'u',
     #'u-6tb1',            # Intel Xeon Scalable (Skylake) 6 TB
     #'u-9tb1',            # Intel Xeon Scalable (Skylake) 9 TB
     #'u-12tb1',           # Intel Xeon Scalable (Skylake) 12 TB
@@ -371,7 +385,80 @@ def DEFAULT_OS(config):
 
 default_excluded_instance_types = [
     '.+\.(micro|nano)', # Not enough memory
-    '.*\.metal.*'
+    '.*\.metal.*',
+
+    # Reduce the number of selected instance types to 25.
+    # Exclude larger core counts for each memory size
+    # 2 GB:
+    'c7a.medium',
+    'c7g.medium',
+    # 4 GB: m7a.medium, m7g.medium
+    'c7a.large',
+    'c7g.large',
+    # 8 GB: r7a.medium, r7g.medium
+    'm5zn.large',
+    'm7a.large',
+    'm7g.large',
+    'c7a.xlarge',
+    'c7g.xlarge',
+    # 16 GB: r7a.large, x2gd.medium, r7g.large
+    'r7iz.large',
+    'm5zn.xlarge',
+    'm7a.xlarge',
+    'm7g.xlarge',
+    'c7a.2xlarge',
+    'c7g.2xlarge',
+    # 32 GB: r7a.xlarge, x2gd.large, r7g.xlarge
+    'r7iz.xlarge',
+    'm5zn.2xlarge',
+    'm7a.2xlarge',
+    'm7g.2xlarge',
+    'c7a.4xlarge',
+    'c7g.4xlarge',
+    # 64 GB: r7a.2xlarge, x2gd.xlarge, r7g.2xlarge
+    'r7iz.2xlarge',
+    'm7a.4xlarge',
+    'm7g.4xlarge',
+    'c7a.8xlarge',
+    'c7g.8xlarge',
+    # 96 GB:
+    'm5zn.6xlarge',
+    'c7a.12xlarge',
+    'c7g.12xlarge',
+    # 128 GB: x2iedn.xlarge, r7iz.4xlarge, x2gd.2xlarge, r7g.4xlarge
+    'r7a.4xlarge',
+    'm7a.8xlarge',
+    'm7g.8xlarge',
+    'c7a.16xlarge',
+    'c7g.8xlarge',
+    # 192 GB: m5zn.12xlarge, m7a.12xlarge, m7g.12xlarge
+    'c7a.24xlarge',
+    # 256 GB: x2iedn.2xlarge, x2iezn.2xlarge, x2gd.4xlarge, r7g.8xlarge
+    'r7iz.8xlarge',
+    'r7a.8xlarge',
+    'm7a.16xlarge',
+    'm7g.16xlarge',
+    'c7a.32xlarge',
+    # 384 GB: 'r7iz.12xlarge', r7g.12xlarge
+    'r7a.12xlarge',
+    'm7a.24xlarge',
+    'c7a.48xlarge',
+    # 512 GB: x2iedn.4xlarge, x2iezn.4xlarge, x2gd.8xlarge, r7g.16xlarge
+    'r7iz.16xlarge',
+    'r7a.16xlarge',
+    'm7a.32xlarge',
+    # 768 GB: r7a.24xlarge, x2gd.12xlarge
+    'x2iezn.6xlarge',
+    'm7a.48xlarge',
+    # 1024 GB: x2iedn.8xlarge, x2iezn.8xlarge, x2gd.16xlarge
+    'r7iz.32xlarge',
+    'r7a.32xlarge',
+    # 1536 GB: x2iezn.12xlarge, x2idn.24xlarge
+    'r7a.48xlarge',
+    # 2048 GB: x2iedn.16xlarge
+    'x2idn.32xlarge',
+    # 3072 GB: 'x2iedn.24xlarge',
+    # 4096 GB: x2iedn.32xlarge
 ]
 
 architectures = [

source/cdk/config_schema.py

@@ -43,7 +43,7 @@ StackName: slurmminimal-config
 
 slurm:
   ParallelClusterConfig:
-    Version: 3.8.0
+    Version: 3.9.1
     # @TODO: Choose the CPU architecture: x86_64, arm64. Default: x86_64
     # Architecture: x86_64
     # @TODO: Update DatabaseStackName with stack name you deployed ParallelCluster database into. See: https://docs.aws.amazon.com/parallelcluster/latest/ug/tutorials_07_slurm-accounting-v3.html#slurm-accounting-db-stack-v3

source/resources/config/default_config.yml

@@ -37,7 +37,7 @@ StackName: slurm-all-arm-config
 
 slurm:
   ParallelClusterConfig:
-    Version: 3.8.0
+    Version: 3.9.1
     Architecture: arm64
     # @TODO: Update DatabaseStackName with stack name you deployed ParallelCluster database into. See: https://docs.aws.amazon.com/parallelcluster/latest/ug/tutorials_07_slurm-accounting-v3.html#slurm-accounting-db-stack-v3
     # Database:

source/resources/config/slurm_all_arm_instance_types.yml

@@ -37,7 +37,7 @@ StackName: slurm-all-x86-config
 
 slurm:
   ParallelClusterConfig:
-    Version: 3.8.0
+    Version: 3.9.1
     Architecture: x86_64
     # @TODO: Update DatabaseStackName with stack name you deployed ParallelCluster database into. See: https://docs.aws.amazon.com/parallelcluster/latest/ug/tutorials_07_slurm-accounting-v3.html#slurm-accounting-db-stack-v3
     # Database: