sbcli-pre 1.3.4__zip → 1.3.6__zip

{sbcli_pre-1.3.4 → sbcli_pre-1.3.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sbcli-pre
-Version: 1.3.4
+Version: 1.3.6
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli_pre-1.3.4 → sbcli_pre-1.3.6}/env_var

@@ -1,5 +1,5 @@
 SIMPLY_BLOCK_COMMAND_NAME=sbcli-pre
-SIMPLY_BLOCK_VERSION=1.3.4
+SIMPLY_BLOCK_VERSION=1.3.6
 
 SIMPLY_BLOCK_DOCKER_IMAGE=simplyblock/simplyblock:pre-release
 

{sbcli_pre-1.3.4 → sbcli_pre-1.3.6}/sbcli_pre.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sbcli-pre
-Version: 1.3.4
+Version: 1.3.6
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli_pre-1.3.4 → sbcli_pre-1.3.6}/simplyblock_core/services/distr_event_collector.py

@@ -160,8 +160,8 @@ while True:
             logger.info(f"Processing event: {eid}")
             process_event(eid)
 
-            logger.info(f"Discarding events: {len(events)}")
-            client.distr_status_events_discard_then_get(len(events), 0)
+        logger.info(f"Discarding events: {len(events)}")
+        client.distr_status_events_discard_then_get(len(events), 0)
 
     except Exception as e:
         logger.error("Failed to process distr events")

{sbcli_pre-1.3.4 → sbcli_pre-1.3.6}/simplyblock_core/services/tasks_runner_restart.py

@@ -5,7 +5,7 @@ import sys
 
 
 from simplyblock_core import constants, kv_store, storage_node_ops
-from simplyblock_core.controllers import device_controller, tasks_events
+from simplyblock_core.controllers import device_controller, tasks_events, health_controller
 from simplyblock_core.models.job_schedule import JobSchedule
 from simplyblock_core.models.nvme_device import NVMeDevice
 
@@ -169,6 +169,19 @@ def task_runner_node(task):
         task.write_to_db(db_controller.kv_store)
         tasks_events.task_updated(task)
 
+    # is node reachable?
+    ping_check = health_controller._check_node_ping(node.mgmt_ip)
+    logger.info(f"Check: ping mgmt ip {node.mgmt_ip} ... {ping_check}")
+    node_api_check = health_controller._check_node_api(node.mgmt_ip)
+    logger.info(f"Check: node API {node.mgmt_ip}:5000 ... {node_api_check}")
+    if not ping_check or not node_api_check:
+        # node is unreachable, retry
+        logger.info(f"Node is not reachable: {task.node_id}, retry")
+        task.function_result = f"Node is unreachable, retry"
+        task.retry += 1
+        task.write_to_db(db_controller.kv_store)
+        return False
+
     # shutting down node
     logger.info(f"Shutdown node {node.get_id()}")
     ret = storage_node_ops.shutdown_storage_node(node.get_id(), force=True)

{sbcli_pre-1.3.4 → sbcli_pre-1.3.6}/simplyblock_core/utils.py

@@ -295,6 +295,9 @@ def calculate_core_allocation(cpu_count):
     https://simplyblock.atlassian.net/browse/SFAM-885
     '''
 
+    if cpu_count > 64:
+        cpu_count = 64
+
     all_cores = list(range(0, cpu_count))
     app_thread_core = all_cores[1:2]
     jm_cpu_core = all_cores[2:3]

{sbcli_pre-1.3.4 → sbcli_pre-1.3.6}/simplyblock_web/blueprints/web_api_deployer.py

@@ -25,16 +25,16 @@ db_controller = kv_store.DBController()
 document_name = 'AWS-RunShellScript'
 output_key_prefix = 'ssm-output'
 
-# intialise clients
-ssm = boto3.client('ssm', region_name='us-east-1')
-s3 = boto3.client('s3', region_name='us-east-1')
+region = utils.get_aws_region()
+ssm = boto3.client('ssm', region_name=region)
+s3 = boto3.client('s3', region_name=region)
 
 
-def get_instance_tf_engine_instance_id():
-    tag_value = 'tfengine'
+def get_instance_tf_engine_instance_id(workspace: str):
+    tag_value = f'{workspace}-tfengine'
     tag_key = 'Name'
 
-    ec2 = boto3.client('ec2', region_name='us-east-1')
+    ec2 = boto3.client('ec2', region_name=region)
     response = ec2.describe_instances(
         Filters=[
             {
@@ -145,7 +145,7 @@ def update_cluster(d, kv_store, storage_nodes, availability_zone):
     d.status = "in_progress"
     d.write_to_db(kv_store)
 
-    instance_ids = get_instance_tf_engine_instance_id()
+    instance_ids = get_instance_tf_engine_instance_id(d.tf_workspace)
     if len(instance_ids) == 0:
         # wait for a min and try again before returning error on the API
         print('no instance IDs')
@@ -180,15 +180,21 @@ def update_cluster(d, kv_store, storage_nodes, availability_zone):
     ]
 
     # Send command with S3 output parameters
-    response = ssm.send_command(
-        InstanceIds=instance_ids,
-        DocumentName=document_name,
-        Parameters={
-            'commands': commands
-        },
-        OutputS3BucketName=tf_logs_bucket_name,
-        OutputS3KeyPrefix=output_key_prefix
-    )
+    try:
+        response = ssm.send_command(
+            InstanceIds=instance_ids,
+            DocumentName=document_name,
+            Parameters={
+                'commands': commands
+            },
+            OutputS3BucketName=tf_logs_bucket_name,
+            OutputS3KeyPrefix=output_key_prefix
+        )
+    except Exception as e:
+        print(f"Exception: {e}")
+        d.status = "failed"
+        d.write_to_db(kv_store)
+        return False, "", "Exception"
 
     command_id = response['Command']['CommandId']
     print(f'Command ID: {command_id}')

{sbcli_pre-1.3.4 → sbcli_pre-1.3.6}/simplyblock_web/utils.py

@@ -2,6 +2,7 @@ import math
 import random
 import re
 import string
+import requests
 
 from flask import jsonify
 
@@ -93,3 +94,11 @@ def get_cluster_id(request):
         cluster_id = au.split()[0]
         cluster_secret = au.split()[1]
         return cluster_id
+
+
+def get_aws_region():
+    response = requests.get('http://169.254.169.254/latest/meta-data/placement/availability-zone')
+    availability_zone = response.text
+
+    region = availability_zone[:-1]
+    return region