sbcli-pre 1.0.8__zip → 1.1.0__zip

{sbcli_pre-1.0.8 → sbcli_pre-1.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sbcli-pre
-Version: 1.0.8
+Version: 1.1.0
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli_pre-1.0.8 → sbcli_pre-1.1.0}/env_var

@@ -1,5 +1,5 @@
 SIMPLY_BLOCK_COMMAND_NAME=sbcli-pre
-SIMPLY_BLOCK_VERSION=1.0.8
+SIMPLY_BLOCK_VERSION=1.1.0
 
 SIMPLY_BLOCK_DOCKER_IMAGE=simplyblock/simplyblock:pre-release
 

{sbcli_pre-1.0.8 → sbcli_pre-1.1.0}/sbcli_pre.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sbcli-pre
-Version: 1.0.8
+Version: 1.1.0
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli_pre-1.0.8 → sbcli_pre-1.1.0}/simplyblock_core/constants.py

@@ -58,6 +58,6 @@ TASK_EXEC_INTERVAL_SEC = 30
 TASK_EXEC_RETRY_COUNT = 8
 
 SIMPLY_BLOCK_SPDK_CORE_IMAGE = "simplyblock/spdk-core:latest"
-SIMPLY_BLOCK_SPDK_ULTRA_IMAGE = "simplyblock/spdk:faster-bdev-startup-latest"
+SIMPLY_BLOCK_SPDK_ULTRA_IMAGE = "simplyblock/spdk:prerelease-latest"
 
 GELF_PORT = 12201

sbcli_pre-1.1.0/simplyblock_core/controllers/tasks_controller.py

@@ -0,0 +1,70 @@
+# coding=utf-8
+import logging
+import time
+import uuid
+
+from simplyblock_core import kv_store
+from simplyblock_core.controllers import tasks_events
+from simplyblock_core.models.job_schedule import JobSchedule
+
+logger = logging.getLogger()
+db_controller = kv_store.DBController()
+
+
+def _validate_new_task_node_restart(cluster_id, node_id):
+    tasks = db_controller.get_job_tasks(cluster_id)
+    for task in tasks:
+        if task.function_name == JobSchedule.FN_NODE_RESTART and task.node_id == node_id:
+            if task.status != JobSchedule.STATUS_DONE:
+                logger.info(f"Task found, skip adding new task: {task.get_id()}")
+                return False
+    return True
+
+
+def _validate_new_task_dev_restart(cluster_id, node_id, device_id):
+    tasks = db_controller.get_job_tasks(cluster_id)
+    for task in tasks:
+        if task.function_name == JobSchedule.FN_DEV_RESTART and task.device_id == device_id:
+            if task.status != JobSchedule.STATUS_DONE:
+                logger.info(f"Task found, skip adding new task: {task.get_id()}")
+                return False
+        elif task.function_name == JobSchedule.FN_NODE_RESTART and task.node_id == node_id:
+            if task.status != JobSchedule.STATUS_DONE:
+                logger.info(f"Task found, skip adding new task: {task.get_id()}")
+                return False
+    return True
+
+
+def _add_task(function_name, cluster_id, node_id, device_id):
+
+    if function_name in [JobSchedule.FN_DEV_RESTART, JobSchedule.FN_DEV_MIG]:
+        if not _validate_new_task_dev_restart(cluster_id, node_id, device_id):
+            return False
+    elif function_name == JobSchedule.FN_NODE_RESTART:
+        if not _validate_new_task_node_restart(cluster_id, node_id):
+            return False
+
+    task_obj = JobSchedule()
+    task_obj.uuid = str(uuid.uuid4())
+    task_obj.cluster_id = cluster_id
+    task_obj.node_id = node_id
+    task_obj.device_id = device_id
+    task_obj.date = int(time.time())
+    task_obj.function_name = function_name
+    task_obj.status = JobSchedule.STATUS_NEW
+    task_obj.write_to_db(db_controller.kv_store)
+    tasks_events.task_create(task_obj)
+    return task_obj.uuid
+
+
+def add_device_mig_task(device_id):
+    device = db_controller.get_storage_devices(device_id)
+    return _add_task(JobSchedule.FN_DEV_MIG, device.cluster_id, device.node_id, device.get_id())
+
+
+def add_device_to_auto_restart(device):
+    return _add_task(JobSchedule.FN_DEV_RESTART, device.cluster_id, device.node_id, device.get_id())
+
+
+def add_node_to_auto_restart(node):
+    return _add_task(JobSchedule.FN_NODE_RESTART, node.cluster_id, node.get_id(), "")

{sbcli_pre-1.0.8 → sbcli_pre-1.1.0}/simplyblock_core/services/distr_event_collector.py

@@ -144,8 +144,8 @@ while True:
     )
     num_of_events = constants.DISTR_EVENT_COLLECTOR_NUM_OF_EVENTS
     try:
-        events = client.distr_status_events_get()
-        # events = client.distr_status_events_discard_then_get(0, num_of_events)
+        # events = client.distr_status_events_get()
+        events = client.distr_status_events_discard_then_get(0, num_of_events)
         if not events:
             logger.error("Distr events empty")
             continue
@@ -161,8 +161,8 @@ while True:
             logger.info(f"Processing event: {eid}")
             process_event(eid)
 
-        # logger.info(f"Discarding events: {num_of_events}")
-        # events = client.distr_status_events_discard_then_get(num_of_events, 0)
+        logger.info(f"Discarding events: {num_of_events}")
+        events = client.distr_status_events_discard_then_get(num_of_events, 0)
 
     except Exception as e:
         logger.error("Failed to process distr events")

{sbcli_pre-1.0.8 → sbcli_pre-1.1.0}/simplyblock_core/services/tasks_runner_migration.py

@@ -48,7 +48,7 @@ while True:
         logger.error("No clusters found!")
     else:
         for cl in clusters:
-            tasks = db_controller.get_job_tasks(cl.get_id())
+            tasks = db_controller.get_job_tasks(cl.get_id(), reverse=False)
             for task in tasks:
                 delay_seconds = constants.TASK_EXEC_INTERVAL_SEC
                 if task.function_name == JobSchedule.FN_DEV_MIG:

{sbcli_pre-1.0.8 → sbcli_pre-1.1.0}/simplyblock_core/services/tasks_runner_restart.py

@@ -15,6 +15,19 @@ from graypy import GELFUDPHandler
 from simplyblock_core.models.storage_node import StorageNode
 
 
+# configure logging
+logger_handler = logging.StreamHandler(stream=sys.stdout)
+logger_handler.setFormatter(logging.Formatter('%(asctime)s: %(levelname)s: %(message)s'))
+gelf_handler = GELFUDPHandler('0.0.0.0', constants.GELF_PORT)
+logger = logging.getLogger()
+logger.addHandler(gelf_handler)
+logger.addHandler(logger_handler)
+logger.setLevel(logging.DEBUG)
+
+# get DB controller
+db_controller = kv_store.DBController()
+
+
 def _get_node_unavailable_devices_count(node_id):
     node = db_controller.get_storage_node_by_id(node_id)
     devices = []
@@ -31,6 +44,16 @@ def _get_device(task):
             return dev
 
 
+def _validate_no_task_node_restart(cluster_id, node_id):
+    tasks = db_controller.get_job_tasks(cluster_id)
+    for task in tasks:
+        if task.function_name == JobSchedule.FN_NODE_RESTART and task.node_id == node_id:
+            if task.status != JobSchedule.STATUS_DONE:
+                logger.info(f"Task found, skip adding new task: {task.get_id()}")
+                return False
+    return True
+
+
 def task_runner(task):
     if task.function_name == JobSchedule.FN_DEV_RESTART:
         return task_runner_device(task)
@@ -49,6 +72,13 @@ def task_runner_device(task):
         device_controller.device_set_retries_exhausted(device.get_id(), True)
         return True
 
+    if not _validate_no_task_node_restart(task.cluster_id, task.node_id):
+        task.function_result = "canceled: node restart found"
+        task.status = JobSchedule.STATUS_DONE
+        task.write_to_db(db_controller.kv_store)
+        device_controller.device_set_unavailable(device.get_id())
+        return True
+
     node = db_controller.get_storage_node_by_id(task.node_id)
     if node.status != StorageNode.STATUS_ONLINE:
         logger.error(f"Node is not online: {node.get_id()} , skipping task: {task.get_id()}")
@@ -113,7 +143,8 @@ def task_runner_node(task):
         storage_node_ops.set_node_status(task.node_id, StorageNode.STATUS_UNREACHABLE)
         return True
 
-    if _get_node_unavailable_devices_count(node.get_id()) == 0:
+    # if _get_node_unavailable_devices_count(node.get_id()) == 0:
+    if node.status == StorageNode.STATUS_ONLINE:
         logger.info(f"Node is online: {node.get_id()}, no restart needed")
         task.function_result = "skipped because node is online"
         task.status = JobSchedule.STATUS_DONE
@@ -138,7 +169,8 @@ def task_runner_node(task):
     if ret:
         logger.info(f"Node restart succeeded")
 
-    if _get_node_unavailable_devices_count(node.get_id()) == 0:
+    # if _get_node_unavailable_devices_count(node.get_id()) == 0:
+    if node.status == StorageNode.STATUS_ONLINE:
         logger.info(f"Node is online: {node.get_id()}, no restart needed")
         task.function_result = "done"
         task.status = JobSchedule.STATUS_DONE
@@ -150,18 +182,6 @@ def task_runner_node(task):
     return False
 
 
-# configure logging
-logger_handler = logging.StreamHandler(stream=sys.stdout)
-logger_handler.setFormatter(logging.Formatter('%(asctime)s: %(levelname)s: %(message)s'))
-gelf_handler = GELFUDPHandler('0.0.0.0', constants.GELF_PORT)
-logger = logging.getLogger()
-logger.addHandler(gelf_handler)
-logger.addHandler(logger_handler)
-logger.setLevel(logging.DEBUG)
-
-# get DB controller
-db_controller = kv_store.DBController()
-
 logger.info("Starting Tasks runner...")
 while True:
     time.sleep(3)

{sbcli_pre-1.0.8 → sbcli_pre-1.1.0}/simplyblock_core/utils.py

@@ -257,7 +257,7 @@ def process_records(records, records_count):
 
 def ping_host(ip):
     logger.debug(f"Pinging ip ... {ip}")
-    response = os.system(f"ping -c 1 {ip} > /dev/null")
+    response = os.system(f"ping -c 1 -W 3 {ip} > /dev/null")
     if response == 0:
         logger.debug(f"{ip} is UP")
         return True

sbcli_pre-1.0.8/simplyblock_core/controllers/tasks_controller.py

@@ -1,54 +0,0 @@
-# coding=utf-8
-import logging
-import time
-import uuid
-
-from simplyblock_core import kv_store
-from simplyblock_core.controllers import tasks_events
-from simplyblock_core.models.job_schedule import JobSchedule
-
-logger = logging.getLogger()
-db_controller = kv_store.DBController()
-
-
-def _add_task(function_name, cluster_id, node_id, device_id):
-    tasks = db_controller.get_job_tasks(cluster_id)
-    for task in tasks:
-        if task.function_name != function_name:
-            continue
-
-        if function_name in [JobSchedule.FN_DEV_RESTART, JobSchedule.FN_DEV_MIG]:
-            if task.device_id == device_id:
-                if task.status != JobSchedule.STATUS_DONE:
-                    logger.info(f"Task found, skip adding new task: {task.get_id()}")
-                    return
-        elif function_name == JobSchedule.FN_NODE_RESTART:
-            if task.node_id == node_id:
-                if task.status != JobSchedule.STATUS_DONE:
-                    logger.info(f"Task found, skip adding new task: {task.get_id()}")
-                    return
-
-    task_obj = JobSchedule()
-    task_obj.uuid = str(uuid.uuid4())
-    task_obj.cluster_id = cluster_id
-    task_obj.node_id = node_id
-    task_obj.device_id = device_id
-    task_obj.date = int(time.time())
-    task_obj.function_name = function_name
-    task_obj.status = JobSchedule.STATUS_NEW
-    task_obj.write_to_db(db_controller.kv_store)
-    tasks_events.task_create(task_obj)
-    return task_obj.uuid
-
-
-def add_device_mig_task(device_id):
-    device = db_controller.get_storage_devices(device_id)
-    return _add_task(JobSchedule.FN_DEV_MIG, device.cluster_id, device.node_id, device.get_id())
-
-
-def add_device_to_auto_restart(device):
-    return _add_task(JobSchedule.FN_DEV_RESTART, device.cluster_id, device.node_id, device.get_id())
-
-
-def add_node_to_auto_restart(node):
-    return _add_task(JobSchedule.FN_NODE_RESTART, node.cluster_id, node.get_id, "")