sbcli-pre 1.1.6__zip → 1.1.8__zip

{sbcli_pre-1.1.6 → sbcli_pre-1.1.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sbcli-pre
-Version: 1.1.6
+Version: 1.1.8
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli_pre-1.1.6 → sbcli_pre-1.1.8}/env_var

@@ -1,5 +1,5 @@
 SIMPLY_BLOCK_COMMAND_NAME=sbcli-pre
-SIMPLY_BLOCK_VERSION=1.1.6
+SIMPLY_BLOCK_VERSION=1.1.8
 
 SIMPLY_BLOCK_DOCKER_IMAGE=simplyblock/simplyblock:pre-release
 

{sbcli_pre-1.1.6 → sbcli_pre-1.1.8}/sbcli_pre.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sbcli-pre
-Version: 1.1.6
+Version: 1.1.8
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli_pre-1.1.6 → sbcli_pre-1.1.8}/simplyblock_cli/cli.py

@@ -10,7 +10,8 @@ from simplyblock_core import compute_node_ops as compute_ops
 from simplyblock_core import storage_node_ops as storage_ops
 from simplyblock_core import mgmt_node_ops as mgmt_ops
 from simplyblock_core import constants
-from simplyblock_core.controllers import pool_controller, lvol_controller, snapshot_controller, device_controller
+from simplyblock_core.controllers import pool_controller, lvol_controller, snapshot_controller, device_controller, \
+    tasks_controller
 from simplyblock_core.controllers import caching_node_controller, health_controller
 from simplyblock_core.models.pool import Pool
 
@@ -324,6 +325,10 @@ class CLIWrapper:
         sub_command = self.add_sub_command(subparser, "list-tasks", 'List tasks by cluster ID')
         sub_command.add_argument("cluster_id", help='UUID of the cluster')
 
+        # cancel task
+        sub_command = self.add_sub_command(subparser, "cancel-task", 'Cancel task by ID')
+        sub_command.add_argument("id", help='UUID of the Task')
+
         # delete cluster
         sub_command = self.add_sub_command(
             subparser, 'delete', 'Delete Cluster',
@@ -846,7 +851,10 @@ class CLIWrapper:
                 ret = cluster_ops.update_cluster(args.id)
 
             elif sub_command == "list-tasks":
-                ret = cluster_ops.list_tasks(args.cluster_id)
+                ret = tasks_controller.list_tasks(args.cluster_id)
+
+            elif sub_command == "cancel-task":
+                ret = tasks_controller.cancel_task(args.id)
 
             elif sub_command == "graceful-shutdown":
                 ret = cluster_ops.cluster_grace_shutdown(args.id)

{sbcli_pre-1.1.6 → sbcli_pre-1.1.8}/simplyblock_core/cluster_ops.py

@@ -588,28 +588,6 @@ def update_cluster(cl_id):
     logger.info("Done")
     return True
 
-
-def list_tasks(cluster_id):
-    db_controller = DBController()
-    cluster = db_controller.get_cluster_by_id(cluster_id)
-    if not cluster:
-        logger.error("Cluster not found: %s", cluster_id)
-        return False
-
-    data = []
-    tasks = db_controller.get_job_tasks(cluster_id)
-    for task in tasks:
-        data.append({
-            "Task ID": task.uuid,
-            "Target ID": task.device_id or task.node_id,
-            "Function": task.function_name,
-            "Retry": f"{task.retry}/{constants.TASK_EXEC_RETRY_COUNT}",
-            "Status": task.status,
-            "Result": task.function_result,
-            "Date": time.strftime("%Y-%m-%d %H:%M:%S", time.gmtime(task.date)),
-        })
-    return utils.print_table(data)
-
  
 def cluster_grace_startup(cl_id):
     db_controller = DBController()

{sbcli_pre-1.1.6 → sbcli_pre-1.1.8}/simplyblock_core/controllers/device_controller.py

@@ -92,7 +92,7 @@ def get_alceml_name(alceml_id):
     return f"alceml_{alceml_id}"
 
 
-def _def_create_device_stack(device_obj, snode):
+def _def_create_device_stack(device_obj, snode, force=False):
 
     rpc_client = RPCClient(
         snode.mgmt_ip, snode.rpc_port,
@@ -105,7 +105,8 @@ def _def_create_device_stack(device_obj, snode):
     ret = rpc_client.bdev_passtest_create(test_name, device_obj.nvme_bdev)
     if not ret:
         logger.error(f"Failed to create bdev: {test_name}")
-        return False
+        if not force:
+            return False
 
     alceml_id = device_obj.get_id()
     alceml_name = get_alceml_name(alceml_id)
@@ -114,14 +115,16 @@ def _def_create_device_stack(device_obj, snode):
                                         dev_cpu_mask=snode.dev_cpu_mask)
     if not ret:
         logger.error(f"Failed to create alceml bdev: {alceml_name}")
-        return False
+        if not force:
+            return False
 
     # add pass through
     pt_name = f"{alceml_name}_PT"
     ret = rpc_client.bdev_PT_NoExcl_create(pt_name, alceml_name)
     if not ret:
         logger.error(f"Failed to create pt noexcl bdev: {pt_name}")
-        return False
+        if not force:
+            return False
 
     subsystem_nqn = snode.subsystem + ":dev:" + alceml_id
     logger.info("Creating subsystem %s", subsystem_nqn)
@@ -150,7 +153,8 @@ def _def_create_device_stack(device_obj, snode):
                                         dev_cpu_mask=snode.dev_cpu_mask)
         if not ret:
             logger.error(f"Failed to create jm bdev: {device_obj.jm_bdev}")
-            return False
+            if not force:
+                return False
 
     device_obj.testing_bdev = test_name
     device_obj.alceml_bdev = alceml_name
@@ -186,11 +190,12 @@ def restart_device(device_id, force=False):
     logger.info(f"Restarting device {device_id}")
     device_set_unavailable(device_id)
 
-    ret = _def_create_device_stack(device_obj, snode)
+    ret = _def_create_device_stack(device_obj, snode, force=force)
 
     if not ret:
         logger.error("Failed to create device stack")
-        return False
+        if not force:
+            return False
 
     logger.info("Make other nodes connect to the device")
     snodes = db_controller.get_storage_nodes()

{sbcli_pre-1.1.6 → sbcli_pre-1.1.8}/simplyblock_core/controllers/tasks_controller.py

@@ -3,7 +3,7 @@ import logging
 import time
 import uuid
 
-from simplyblock_core import kv_store
+from simplyblock_core import kv_store, constants, utils
 from simplyblock_core.controllers import tasks_events
 from simplyblock_core.models.job_schedule import JobSchedule
 
@@ -68,3 +68,36 @@ def add_device_to_auto_restart(device):
 
 def add_node_to_auto_restart(node):
     return _add_task(JobSchedule.FN_NODE_RESTART, node.cluster_id, node.get_id(), "")
+
+
+def list_tasks(cluster_id):
+    cluster = db_controller.get_cluster_by_id(cluster_id)
+    if not cluster:
+        logger.error("Cluster not found: %s", cluster_id)
+        return False
+
+    data = []
+    tasks = db_controller.get_job_tasks(cluster_id)
+    for task in tasks:
+        data.append({
+            "Task ID": task.uuid,
+            "Target ID": task.device_id or task.node_id,
+            "Function": task.function_name,
+            "Retry": f"{task.retry}/{constants.TASK_EXEC_RETRY_COUNT}",
+            "Status": task.status,
+            "Result": task.function_result,
+            "Date": time.strftime("%Y-%m-%d %H:%M:%S", time.gmtime(task.date)),
+        })
+    return utils.print_table(data)
+
+
+def cancel_task(task_id):
+    task = db_controller.get_task_by_id(task_id)
+    if not task:
+        logger.error("Task not found: %s", task_id)
+        return False
+
+    task.canceled = True
+    task.write_to_db(db_controller.kv_store)
+    tasks_events.task_canceled(task)
+    return True

{sbcli_pre-1.1.6 → sbcli_pre-1.1.8}/simplyblock_core/controllers/tasks_events.py

@@ -30,3 +30,8 @@ def task_updated(task, caused_by=ec.CAUSED_BY_CLI):
 
 def task_status_change(task, new_state, old_status, caused_by=ec.CAUSED_BY_CLI):
     _task_event(task, f"task status changed from: {old_status} to: {new_state}", caused_by, ec.EVENT_STATUS_CHANGE)
+
+
+def task_canceled(task, caused_by=ec.CAUSED_BY_CLI):
+    _task_event(task, f"Task canceled: {task.uuid}", caused_by, ec.EVENT_STATUS_CHANGE)
+

{sbcli_pre-1.1.6 → sbcli_pre-1.1.8}/simplyblock_core/kv_store.py

@@ -274,3 +274,8 @@ class DBController:
 
     def get_job_tasks(self, cluster_id, reverse=True):
         return JobSchedule().read_from_db(self.kv_store, id=cluster_id, reverse=reverse)
+
+    def get_task_by_id(self, task_id):
+        for task in self.get_job_tasks(""):
+            if task.uuid == task_id:
+                return task

{sbcli_pre-1.1.6 → sbcli_pre-1.1.8}/simplyblock_core/models/job_schedule.py

@@ -19,6 +19,8 @@ class JobSchedule(BaseModel):
         "device_id": {"type": str, 'default': ""},
         "date": {"type": int, 'default': 0},
 
+        "canceled": {"type": bool, 'default': False},
+
         "function_name": {"type": str, 'default': ""},
         "function_params": {"type": dict, 'default': {}},
         "function_result": {"type": str, 'default': ""},

{sbcli_pre-1.1.6 → sbcli_pre-1.1.8}/simplyblock_core/services/tasks_runner_restart.py

@@ -79,6 +79,12 @@ def task_runner_device(task):
         device_controller.device_set_unavailable(device.get_id())
         return True
 
+    if task.canceled:
+        task.function_result = "canceled"
+        task.status = JobSchedule.STATUS_DONE
+        task.write_to_db(db_controller.kv_store)
+        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()}, retry")
@@ -106,20 +112,15 @@ def task_runner_device(task):
         task.write_to_db(db_controller.kv_store)
         tasks_events.task_updated(task)
 
-    # # resetting device
-    # logger.info(f"Resetting device {device.get_id()}")
-    # device_controller.reset_storage_device(device.get_id())
-    # time.sleep(5)
-    # device = _get_device(task)
-    # if device.status == NVMeDevice.STATUS_ONLINE and device.io_error is False:
-    #     logger.info(f"Device is online: {device.get_id()}")
-    #     task.function_result = "done"
-    #     task.status = JobSchedule.STATUS_DONE
-    #     task.write_to_db(db_controller.kv_store)
-    #     return True
-
-    logger.info(f"Restarting device {device.get_id()}")
-    device_controller.restart_device(device.get_id(), force=True)
+    # set device online for the first 3 retries
+    if task.retry < 3:
+        logger.info(f"Set device online {device.get_id()}")
+        device_controller.device_set_online(device.get_id())
+    else:
+        logger.info(f"Restarting device {device.get_id()}")
+        device_controller.restart_device(device.get_id(), force=True)
+
+    # check device status
     time.sleep(5)
     device = _get_device(task)
     if device.status == NVMeDevice.STATUS_ONLINE and device.io_error is False:
@@ -157,6 +158,12 @@ def task_runner_node(task):
         task.write_to_db(db_controller.kv_store)
         return True
 
+    if task.canceled:
+        task.function_result = "canceled"
+        task.status = JobSchedule.STATUS_DONE
+        task.write_to_db(db_controller.kv_store)
+        return True
+
     if task.status != JobSchedule.STATUS_RUNNING:
         task.status = JobSchedule.STATUS_RUNNING
         task.write_to_db(db_controller.kv_store)