sbcli-dev 10.3.3__tar.gz → 10.3.5__tar.gz

{sbcli_dev-10.3.3 → sbcli_dev-10.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: sbcli-dev
-Version: 10.3.3
+Version: 10.3.5
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli_dev-10.3.3 → sbcli_dev-10.3.5}/sbcli_dev.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: sbcli-dev
-Version: 10.3.3
+Version: 10.3.5
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli_dev-10.3.3 → sbcli_dev-10.3.5}/simplyblock_core/distr_controller.py

@@ -140,6 +140,12 @@ def get_distr_cluster_map(snodes, target_node, distr_name=""):
         "map_prob": [d for k, d in map_prob.items()]
     }
     if cluster.enable_node_affinity:
+        if target_node.is_secondary_node and distr_name:
+            for index, snode in enumerate(snodes):
+                for bdev in snode.lvstore_stack:
+                    if bdev['type'] == "bdev_distr" and bdev['name'] == distr_name:
+                        local_node_index = index
+                        break
         cl_map['ppln1'] = local_node_index
     return cl_map
 
@@ -208,14 +214,25 @@ def send_cluster_map_to_node(node):
     db_controller = DBController()
     snodes = db_controller.get_storage_nodes_by_cluster_id(node.cluster_id)
     rpc_client = RPCClient(node.mgmt_ip, node.rpc_port, node.rpc_username, node.rpc_password, timeout=10)
-    cluster_map_data = get_distr_cluster_map(snodes, node)
-    cluster_map_data['UUID_node_target'] = node.get_id()
-    ret = rpc_client.distr_send_cluster_map(cluster_map_data)
-    if not ret:
-        logger.error("Failed to send cluster map")
-        logger.info(cluster_map_data)
-        return False
-    return True
+
+    if node.is_secondary_node:
+        for snode in db_controller.get_primary_storage_nodes_by_secondary_node_id(node.get_id()):
+            for bdev in snode.lvstore_stack:
+                if bdev['type'] == "bdev_distr":
+                    cluster_map_data = get_distr_cluster_map(snodes, node, bdev["name"])
+                    ret = rpc_client.distr_send_cluster_map(cluster_map_data)
+                    if not ret:
+                        logger.error("Failed to send cluster map")
+                        return False
+        return True
+    else:
+        cluster_map_data = get_distr_cluster_map(snodes, node)
+        ret = rpc_client.distr_send_cluster_map(cluster_map_data)
+        if not ret:
+            logger.error("Failed to send cluster map")
+            logger.info(cluster_map_data)
+            return False
+        return True
 
 
 def send_cluster_map_to_distr(node, distr_name):

{sbcli_dev-10.3.3 → sbcli_dev-10.3.5}/simplyblock_core/env_var

@@ -1,5 +1,5 @@
 SIMPLY_BLOCK_COMMAND_NAME=sbcli-dev
-SIMPLY_BLOCK_VERSION=10.3.3
+SIMPLY_BLOCK_VERSION=10.3.5
 
 SIMPLY_BLOCK_DOCKER_IMAGE=simplyblock/simplyblock:main
 DOCKER_USER=hamdysimplyblock

{sbcli_dev-10.3.3 → sbcli_dev-10.3.5}/simplyblock_core/services/storage_node_monitor.py

@@ -138,7 +138,7 @@ def update_cluster_status(cluster_id):
                 break
 
             if node.online_since:
-                diff = datetime.now() - datetime.fromisoformat(snode.online_since)
+                diff = datetime.now() - datetime.fromisoformat(node.online_since)
                 if diff.total_seconds() < 60:
                     can_activate = False
                     break

{sbcli_dev-10.3.3 → sbcli_dev-10.3.5}/simplyblock_core/services/tasks_runner_failed_migration.py

@@ -2,7 +2,7 @@
 import logging
 import time
 import sys
-
+from datetime import datetime
 
 from simplyblock_core import constants, db_controller, utils
 from simplyblock_core.controllers import tasks_events, tasks_controller, device_controller
@@ -33,6 +33,20 @@ def task_runner(task):
         return True
 
     if task.status in [JobSchedule.STATUS_NEW ,JobSchedule.STATUS_SUSPENDED]:
+        if task.status == JobSchedule.STATUS_NEW:
+            for node in db_controller.get_storage_nodes_by_cluster_id(task.cluster_id):
+                if node.online_since:
+                    try:
+                        diff = datetime.now() - datetime.fromisoformat(node.online_since)
+                        if diff.total_seconds() < 60:
+                            task.function_result = "node is online < 1 min, retrying"
+                            task.status = JobSchedule.STATUS_SUSPENDED
+                            task.retry += 1
+                            task.write_to_db(db_controller.kv_store)
+                            return False
+                    except Exception as e:
+                        logger.error(f"Failed to get online since: {e}")
+
         task.status = JobSchedule.STATUS_RUNNING
         task.write_to_db(db_controller.kv_store)
         tasks_events.task_updated(task)

{sbcli_dev-10.3.3 → sbcli_dev-10.3.5}/simplyblock_core/services/tasks_runner_migration.py

@@ -30,6 +30,20 @@ def task_runner(task):
         return True
 
     if task.status in [JobSchedule.STATUS_NEW, JobSchedule.STATUS_SUSPENDED]:
+        if task.status == JobSchedule.STATUS_NEW:
+            for node in db_controller.get_storage_nodes_by_cluster_id(task.cluster_id):
+                if node.online_since:
+                    try:
+                        diff = datetime.now() - datetime.fromisoformat(node.online_since)
+                        if diff.total_seconds() < 60:
+                            task.function_result = "node is online < 1 min, retrying"
+                            task.status = JobSchedule.STATUS_SUSPENDED
+                            task.retry += 1
+                            task.write_to_db(db_controller.kv_store)
+                            return False
+                    except Exception as e:
+                        logger.error(f"Failed to get online since: {e}")
+
         task.status = JobSchedule.STATUS_RUNNING
         task.write_to_db(db_controller.kv_store)
         tasks_events.task_updated(task)
@@ -41,15 +55,6 @@ def task_runner(task):
         task.write_to_db(db_controller.kv_store)
         return False
 
-    if snode.online_since:
-        diff = datetime.now() - datetime.fromisoformat(snode.online_since)
-        if diff.total_seconds() < 60:
-            task.function_result = "node is online < 1 min, retrying"
-            task.status = JobSchedule.STATUS_SUSPENDED
-            task.retry += 1
-            task.write_to_db(db_controller.kv_store)
-            return False
-
     rpc_client = RPCClient(snode.mgmt_ip, snode.rpc_port, snode.rpc_username, snode.rpc_password,
                            timeout=5, retry=2)
     if "migration" not in task.function_params:

{sbcli_dev-10.3.3 → sbcli_dev-10.3.5}/simplyblock_core/services/tasks_runner_new_dev_migration.py

@@ -33,6 +33,20 @@ def task_runner(task):
         return True
 
     if task.status in [JobSchedule.STATUS_NEW ,JobSchedule.STATUS_SUSPENDED]:
+        if task.status == JobSchedule.STATUS_NEW:
+            for node in db_controller.get_storage_nodes_by_cluster_id(task.cluster_id):
+                if node.online_since:
+                    try:
+                        diff = datetime.now() - datetime.fromisoformat(node.online_since)
+                        if diff.total_seconds() < 60:
+                            task.function_result = "node is online < 1 min, retrying"
+                            task.status = JobSchedule.STATUS_SUSPENDED
+                            task.retry += 1
+                            task.write_to_db(db_controller.kv_store)
+                            return False
+                    except Exception as e:
+                        logger.error(f"Failed to get online since: {e}")
+
         task.status = JobSchedule.STATUS_RUNNING
         task.write_to_db(db_controller.kv_store)
         tasks_events.task_updated(task)
@@ -44,15 +58,6 @@ def task_runner(task):
         task.write_to_db(db_controller.kv_store)
         return False
 
-    if snode.online_since:
-        diff = datetime.now() - datetime.fromisoformat(snode.online_since)
-        if diff.total_seconds() < 60:
-            task.function_result = "node is online < 1 min, retrying"
-            task.status = JobSchedule.STATUS_SUSPENDED
-            task.retry += 1
-            task.write_to_db(db_controller.kv_store)
-            return False
-
     rpc_client = RPCClient(snode.mgmt_ip, snode.rpc_port, snode.rpc_username, snode.rpc_password, timeout=5, retry=2)
     if "migration" not in task.function_params:
         all_devs_online = True

{sbcli_dev-10.3.3 → sbcli_dev-10.3.5}/simplyblock_core/storage_node_ops.py

@@ -866,7 +866,7 @@ def _connect_to_remote_jm_devs(this_node, jm_ids=[]):
                     continue
                 if node.jm_device and node.jm_device.status == JMDevice.STATUS_ONLINE:
                     remote_devices.append(node.jm_device)
-                    if len(remote_devices) >= 2 :
+                    if len(remote_devices) >= 3 :
                         break
 
     new_devs = []
@@ -2793,7 +2793,7 @@ def get_next_ha_jms(current_node):
                 except :
                     pass
     jm_count = dict(sorted(jm_count.items(), key=lambda x: x[1]))
-    return list(jm_count.keys())[:2]
+    return list(jm_count.keys())[:3]
 
 
 def get_node_jm_names(current_node):
@@ -2805,7 +2805,7 @@ def get_node_jm_names(current_node):
         jm_list.append("JM_LOCAL")
 
     if current_node.enable_ha_jm:
-        for jm_dev in current_node.remote_jm_devices[:2]:
+        for jm_dev in current_node.remote_jm_devices[:3]:
             jm_list.append(jm_dev.remote_bdev)
     return jm_list
 
@@ -2939,7 +2939,7 @@ def create_lvstore(snode, ndcs, npcs, distr_bs, distr_chunk_bs, page_size_in_blo
     return True
 
 
-def _create_bdev_stack(snode, lvstore_stack=None, primary_node=False):
+def _create_bdev_stack(snode, lvstore_stack=None, primary_node=None):
     rpc_client = RPCClient(snode.mgmt_ip, snode.rpc_port, snode.rpc_username, snode.rpc_password)
 
     created_bdevs = []
@@ -2971,7 +2971,7 @@ def _create_bdev_stack(snode, lvstore_stack=None, primary_node=False):
                     jm_list.append(bdev_name)
                 else:
                     jm_list.append("JM_LOCAL")
-                for jm_dev in primary_node.remote_jm_devices[:2]:
+                for jm_dev in primary_node.remote_jm_devices[:3]:
                     jm_list.append(jm_dev.remote_bdev)
                 params['jm_names'] = jm_list
             else:

{sbcli_dev-10.3.3 → sbcli_dev-10.3.5}/simplyblock_core/utils.py

@@ -664,6 +664,9 @@ def strfdelta(tdelta):
 
 def handle_task_result(task: JobSchedule, res: dict, allowed_error_codes = None):
     if res:
+        if not allowed_error_codes:
+            allowed_error_codes = [0]
+
         res_data = res[0]
         migration_status = res_data.get("status")
         error_code = res_data.get("error", -1)