sbcli-pre 25.5.0__tar.gz → 25.5.2__tar.gz

{sbcli-pre-25.5.0 → sbcli-pre-25.5.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sbcli-pre
-Version: 25.5.0
+Version: 25.5.2
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli-pre-25.5.0 → sbcli-pre-25.5.2}/sbcli_pre.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sbcli-pre
-Version: 25.5.0
+Version: 25.5.2
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli-pre-25.5.0 → sbcli-pre-25.5.2}/simplyblock_cli/cli.py

@@ -310,6 +310,8 @@ class CLIWrapper(CLIWrapperBase):
         self.init_cluster__complete_expand(subparser)
         self.init_cluster__show(subparser)
         self.init_cluster__get(subparser)
+        if self.developer_mode:
+            self.init_cluster__suspend(subparser)
         self.init_cluster__get_capacity(subparser)
         self.init_cluster__get_io_stats(subparser)
         self.init_cluster__get_logs(subparser)
@@ -490,6 +492,10 @@ class CLIWrapper(CLIWrapperBase):
         subcommand = self.add_sub_command(subparser, 'get', 'Gets a cluster\'s information')
         subcommand.add_argument('cluster_id', help='Cluster id', type=str).completer = self._completer_get_cluster_list
 
+    def init_cluster__suspend(self, subparser):
+        subcommand = self.add_sub_command(subparser, 'suspend', 'Put the cluster status to be suspended')
+        subcommand.add_argument('cluster_id', help='Cluster id', type=str).completer = self._completer_get_cluster_list
+
     def init_cluster__get_capacity(self, subparser):
         subcommand = self.add_sub_command(subparser, 'get-capacity', 'Gets a cluster\'s capacity')
         subcommand.add_argument('cluster_id', help='Cluster id', type=str).completer = self._completer_get_cluster_list
@@ -1067,6 +1073,12 @@ class CLIWrapper(CLIWrapperBase):
                 ret = self.cluster__show(sub_command, args)
             elif sub_command in ['get']:
                 ret = self.cluster__get(sub_command, args)
+            elif sub_command in ['suspend']:
+                if not self.developer_mode:
+                    print("This command is private.")
+                    ret = False
+                else:
+                    ret = self.cluster__suspend(sub_command, args)
             elif sub_command in ['get-capacity']:
                 ret = self.cluster__get_capacity(sub_command, args)
             elif sub_command in ['get-io-stats']:

{sbcli-pre-25.5.0 → sbcli-pre-25.5.2}/simplyblock_cli/clibase.py

@@ -389,7 +389,7 @@ class CLIWrapperBase:
     def cluster__delete(self, sub_command, args):
         return cluster_ops.delete_cluster(args.cluster_id)
 
-    def cluster_suspend(self, sub_command, args):
+    def cluster__suspend(self, sub_command, args):
         cluster_id = args.cluster_id
         return cluster_ops.suspend_cluster(cluster_id)
 

{sbcli-pre-25.5.0 → sbcli-pre-25.5.2}/simplyblock_core/cluster_ops.py

@@ -2,6 +2,7 @@
 import datetime
 import json
 import os
+import socket
 import re
 import tempfile
 import shutil
@@ -176,6 +177,21 @@ def create_cluster(blk_size, page_size_in_blocks, cli_pass,
             time.sleep(3)
 
         c.swarm.init(DEV_IP)
+        
+        hostname = socket.gethostname()
+        current_node = next((node for node in c.nodes.list() if node.attrs["Description"]["Hostname"] == hostname), None)
+        if current_node:
+            current_spec = current_node.attrs["Spec"]
+            current_labels = current_spec.get("Labels", {})
+            current_labels["app"] = "graylog"
+            current_spec["Labels"] = current_labels
+
+            current_node.update(current_spec)
+            
+            logger.info(f"Labeled node '{hostname}' with app=graylog")
+        else:
+            logger.warning("Could not find current node for labeling")
+
         logger.info("Configuring docker swarm > Done")
     except Exception as e:
         print(e)
@@ -1339,7 +1355,8 @@ def update_cluster(cluster_id, mgmt_only=False, restart=False, spdk_image=None,
         if mgmt_image:
             service_image = mgmt_image
         for service in cluster_docker.services.list():
-            if image_parts in service.attrs['Spec']['Labels']['com.docker.stack.image']:
+            if image_parts in service.attrs['Spec']['Labels']['com.docker.stack.image'] or \
+            "simplyblock" in service.attrs['Spec']['Labels']['com.docker.stack.image']:
                 logger.info(f"Updating service {service.name}")
                 service.update(image=service_image, force_update=True)
         logger.info("Done updating mgmt cluster")

{sbcli-pre-25.5.0 → sbcli-pre-25.5.2}/simplyblock_core/env_var

@@ -1,5 +1,5 @@
 SIMPLY_BLOCK_COMMAND_NAME=sbcli-pre
-SIMPLY_BLOCK_VERSION=25.5.0
+SIMPLY_BLOCK_VERSION=25.5.2
 
 
 SIMPLY_BLOCK_DOCKER_IMAGE=simplyblock/simplyblock:R25.5-Hotfix

{sbcli-pre-25.5.0 → sbcli-pre-25.5.2}/simplyblock_core/scripts/docker-compose-swarm-monitoring.yml

@@ -3,12 +3,14 @@ version: '3.8'
 services:
   ### monitoring ###
   mongodb:
-    image: "mongo:6.0"
+    image: "mongo:5.0"
     volumes:
       - "mongodb_data:/data/db"
     deploy:
       placement:
-        constraints: [node.role == manager]
+        constraints:
+          - node.role == manager
+          - node.labels.app == graylog
     networks:
       - monitoring-net
 
@@ -25,13 +27,15 @@ services:
       - "os_data:/usr/share/opensearch/data"
     deploy:
       placement:
-        constraints: [node.role == manager]
+        constraints:
+          - node.role == manager
+          - node.labels.app == graylog
     networks:
       - monitoring-net
 
   graylog:
     hostname: "server"
-    image: "graylog/graylog:6.2.2"
+    image: "graylog/graylog:5.0"
     entrypoint: "/usr/bin/tini -- wait-for-it opensearch:9200 --  /docker-entrypoint.sh"
     environment:
       GRAYLOG_NODE_ID_FILE: "/usr/share/graylog/data/config/node-id"
@@ -64,7 +68,9 @@ services:
       - "graylog_journal:/usr/share/graylog/data/journal"
     deploy:
       placement:
-        constraints: [node.role == manager]
+        constraints:
+          - node.role == manager
+          - node.labels.app == graylog
     networks:
       - monitoring-net
 

{sbcli-pre-25.5.0 → sbcli-pre-25.5.2}/simplyblock_core/services/health_check_service.py

@@ -227,7 +227,7 @@ while True:
                     if snode.secondary_node_id:
 
                         lvstore_check &= health_controller._check_node_hublvol(
-                            snode, node_bdev_names=node_bdev_names, node_lvols_nqns=subsystem_list)
+                            snode, node_bdev_names=node_bdev_names, node_lvols_nqns=subsystems)
 
                         second_node_1 = db.get_storage_node_by_id(snode.secondary_node_id)
                         if second_node_1 and second_node_1.status == StorageNode.STATUS_ONLINE:

{sbcli-pre-25.5.0 → sbcli-pre-25.5.2}/simplyblock_core/services/mgmt_node_monitor.py

@@ -6,7 +6,7 @@ from datetime import datetime
 
 
 from simplyblock_core import constants, db_controller, utils
-from simplyblock_core.controllers import mgmt_events
+from simplyblock_core.controllers import mgmt_events, health_controller
 from simplyblock_core.models.mgmt_node import MgmtNode
 
 
@@ -37,17 +37,6 @@ def set_node_offline(node):
         mgmt_events.status_change(snode, snode.status, old_status, caused_by="monitor")
 
 
-def ping_host(ip):
-    logger.info(f"Pinging ip {ip}")
-    response = os.system(f"ping -c 1 {ip}")
-    if response == 0:
-        logger.info(f"{ip} is UP")
-        return True
-    else:
-        logger.info(f"{ip} is DOWN")
-        return False
-
-
 logger.info("Starting Mgmt node monitor")
 
 
@@ -59,8 +48,15 @@ while True:
             logger.info(f"Node status is: {node.status}, skipping")
             continue
 
-        logger.info(f"Checking node {node.hostname}")
-        if not ping_host(node.mgmt_ip):
+        # 1- check node ping
+        ping_check = health_controller._check_node_ping(node.mgmt_ip)
+        logger.info(f"Check: ping mgmt ip {node.mgmt_ip} ... {ping_check}")
+        if not ping_check:
+            time.sleep(1)
+            ping_check = health_controller._check_node_ping(node.mgmt_ip)
+            logger.info(f"Check 2: ping mgmt ip {node.mgmt_ip} ... {ping_check}")
+
+        if not ping_check:
             logger.info(f"Node {node.hostname} is offline")
             set_node_offline(node)
             continue

{sbcli-pre-25.5.0 → sbcli-pre-25.5.2}/simplyblock_core/services/storage_node_monitor.py

@@ -254,8 +254,8 @@ while True:
             ping_check = health_controller._check_node_ping(snode.mgmt_ip)
             logger.info(f"Check: ping mgmt ip {snode.mgmt_ip} ... {ping_check}")
             if not ping_check:
-                # time.sleep(1)
-                # ping_check = health_controller._check_node_ping(snode.mgmt_ip)
+                time.sleep(1)
+                ping_check = health_controller._check_node_ping(snode.mgmt_ip)
                 logger.info(f"Check 2: ping mgmt ip {snode.mgmt_ip} ... {ping_check}")
 
             # 2- check node API
@@ -278,7 +278,6 @@ while True:
 
             node_port_check = True
 
-            down_ports = []
             if spdk_process and node_rpc_check and snode.lvstore_status == "ready":
                 ports = [snode.nvmf_port]
                 if snode.lvstore_stack_secondary_1:
@@ -292,8 +291,6 @@ while True:
                     ret = health_controller._check_port_on_node(snode, port)
                     logger.info(f"Check: node port {snode.mgmt_ip}, {port} ... {ret}")
                     node_port_check &= ret
-                    if not ret and port == snode.nvmf_port:
-                        down_ports |= True
 
                 for data_nic in snode.data_nics:
                     if data_nic.ip4_address:
@@ -301,8 +298,6 @@ while True:
                         logger.info(f"Check: ping data nic {data_nic.ip4_address} ... {data_ping_check}")
                         if not data_ping_check:
                             node_port_check = False
-                            down_ports |= True
-
 
             cluster = db.get_cluster_by_id(cluster.get_id())
 

{sbcli-pre-25.5.0 → sbcli-pre-25.5.2}/simplyblock_core/services/tasks_runner_failed_migration.py

@@ -102,20 +102,24 @@ def task_runner(task):
         task.write_to_db(db.kv_store)
         time.sleep(3)
 
-    if "migration" in task.function_params:
-
-        mig_info = task.function_params["migration"]
-        res = rpc_client.distr_migration_status(**mig_info)
-        out = utils.handle_task_result(task, res)
-        dev_failed_task = tasks_controller.get_failed_device_mig_task(task.cluster_id, task.device_id)
-        if not dev_failed_task:
-            device_controller.device_set_failed_and_migrated(task.device_id)
-
-        return out
-    else:
-        task.retry += 1
-        task.write_to_db(db.kv_store)
-        return False
+    try:
+        if "migration" in task.function_params:
+            mig_info = task.function_params["migration"]
+            res = rpc_client.distr_migration_status(**mig_info)
+            out = utils.handle_task_result(task, res)
+            dev_failed_task = tasks_controller.get_failed_device_mig_task(task.cluster_id, task.device_id)
+            if not dev_failed_task:
+                device_controller.device_set_failed_and_migrated(task.device_id)
+
+            return out
+    except Exception as e:
+        logger.error(f"Failed to get migration task status")
+        logger.exception(e)
+        task.function_result = "Failed to get migration status"
+
+    task.retry += 1
+    task.write_to_db(db.kv_store)
+    return False
 
 
 logger = utils.get_logger(__name__)

{sbcli-pre-25.5.0 → sbcli-pre-25.5.2}/simplyblock_core/services/tasks_runner_migration.py

@@ -104,14 +104,19 @@ def task_runner(task):
         task.write_to_db(db.kv_store)
         # time.sleep(1)
 
-    if "migration" in task.function_params:
-        mig_info = task.function_params["migration"]
-        res = rpc_client.distr_migration_status(**mig_info)
-        return utils.handle_task_result(task, res)
-    else:
-        task.retry += 1
-        task.write_to_db(db.kv_store)
-        return False
+    try:
+        if "migration" in task.function_params:
+            mig_info = task.function_params["migration"]
+            res = rpc_client.distr_migration_status(**mig_info)
+            return utils.handle_task_result(task, res)
+    except Exception as e:
+        logger.error(f"Failed to get migration task status")
+        logger.exception(e)
+        task.function_result = "Failed to get migration status"
+
+    task.retry += 1
+    task.write_to_db(db.kv_store)
+    return False
 
 
 # get DB controller

{sbcli-pre-25.5.0 → sbcli-pre-25.5.2}/simplyblock_core/services/tasks_runner_new_dev_migration.py

@@ -117,17 +117,20 @@ def task_runner(task):
         task.write_to_db(db.kv_store)
         time.sleep(3)
 
-    if "migration" in task.function_params:
-        allowed_error_codes = list(range(1, 8)) if not all_devs_online else [0]
-        mig_info = task.function_params["migration"]
-        res = rpc_client.distr_migration_status(**mig_info)
-        return utils.handle_task_result(task, res, allowed_error_codes=allowed_error_codes)
-    else:
-        task.status = JobSchedule.STATUS_SUSPENDED
-        task.retry += 1
-        task.write_to_db(db.kv_store)
-        return False
-
+    try:
+        if "migration" in task.function_params:
+            allowed_error_codes = list(range(1, 8)) if not all_devs_online else [0]
+            mig_info = task.function_params["migration"]
+            res = rpc_client.distr_migration_status(**mig_info)
+            return utils.handle_task_result(task, res, allowed_error_codes=allowed_error_codes)
+    except Exception as e:
+        logger.error(f"Failed to get migration task status")
+        logger.exception(e)
+        task.function_result = "Failed to get migration status"
+
+    task.retry += 1
+    task.write_to_db(db.kv_store)
+    return False
 
 logger = utils.get_logger(__name__)
 

{sbcli-pre-25.5.0 → sbcli-pre-25.5.2}/simplyblock_core/storage_node_ops.py

@@ -1488,6 +1488,14 @@ def restart_storage_node(
     if max_snap:
         snode.max_snap = max_snap
 
+    if not snode.l_cores:
+        if node_info.get("nodes_config") and node_info["nodes_config"].get("nodes"):
+            nodes = node_info["nodes_config"]["nodes"]
+            for node in nodes:
+                if node['cpu_mask'] == snode.spdk_cpu_mask:
+                    snode.l_cores = node['l-cores']
+                    break
+
     if max_prov:
         if not isinstance(max_prov, int):
             try:
@@ -3190,7 +3198,7 @@ def create_lvstore(snode, ndcs, npcs, distr_bs, distr_chunk_bs, page_size_in_blo
         write_protection = True
     for _ in range(snode.number_of_distribs):
         distrib_vuid = utils.get_random_vuid()
-        while distrib_vuid in distrib_list:
+        while distrib_vuid in distrib_vuids:
             distrib_vuid = utils.get_random_vuid()
 
         distrib_name = f"distrib_{distrib_vuid}"

{sbcli-pre-25.5.0 → sbcli-pre-25.5.2}/simplyblock_core/utils.py

@@ -309,7 +309,7 @@ def process_records(records, records_count, keys=None):
 
 def ping_host(ip):
     logger.debug(f"Pinging ip ... {ip}")
-    response = os.system(f"ping -c 1 -W 3 {ip} > /dev/null")
+    response = os.system(f"ping -c 3 -W 3 {ip} > /dev/null")
     if response == 0:
         logger.debug(f"{ip} is UP")
         return True