From 3fabbb5033d3923e80324817708899412b7069e3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Fri, 19 Apr 2024 17:50:19 +0800
Subject: [PATCH 01/30] add more rca scene.py

---
 common/scene.py                               |  12 +-
 handler/checker/check_handler.py              |  40 ++-
 handler/checker/check_task.py                 |   5 +-
 handler/checker/step/data_size.py             |  14 +-
 handler/checker/step/get_system_parameter.py  |  10 +-
 handler/checker/step/sql.py                   |  23 +-
 handler/checker/step/ssh.py                   |  11 +-
 handler/checker/step/stepbase.py              |   7 +-
 .../information_schema_tables_two_data.yaml   |  12 +
 handler/gather/gather_log.py                  |   3 +
 handler/rca/rca_handler.py                    |   2 +
 handler/rca/scene/ddl_disk_full_scene.py      |   8 +-
 handler/rca/scene/disconnection_scene.py      |   2 +-
 handler/rca/scene/log_error_scene.py          | 338 ++++++++++++++++++
 handler/rca/scene/major_hold_scene.py         |   2 +-
 15 files changed, 439 insertions(+), 50 deletions(-)
 create mode 100644 handler/checker/tasks/observer/table/information_schema_tables_two_data.yaml
 create mode 100644 handler/rca/scene/log_error_scene.py

diff --git a/common/scene.py b/common/scene.py
index 044445a0..735d38b0 100644
--- a/common/scene.py
+++ b/common/scene.py
@@ -17,7 +17,8 @@
 """
 from common.ssh import SshHelper
 from common.tool import StringUtils
-from common.command import get_observer_version, get_obproxy_version
+from common.command import get_observer_version, get_obproxy_version, get_observer_version_by_sql
+
 
 def filter_by_version(scene, cluster, stdio=None):
     try:
@@ -59,14 +60,19 @@ def filter_by_version(scene, cluster, stdio=None):
         stdio.exception("filter_by_version Exception : {0}".format(e))
         raise Exception("filter_by_version Exception : {0}".format(e))
 
-def get_version(nodes, type, stdio=None):
+def get_version(nodes, type,cluster, stdio=None):
     try:
         if len(nodes) < 1:
             raise Exception("input nodes is empty, please check your config")
         node = nodes[0]
         ssh = SshHelper(True, node.get("ip"), node.get("ssh_username"), node.get("ssh_password"), node.get("ssh_port"), node.get("ssh_key_file"), node)
+        version = ""
         if type == "observer":
-            version = get_observer_version(True, ssh, nodes[0]["home_path"], stdio)
+            try:
+                version = get_observer_version_by_sql(cluster,stdio)
+            except Exception as e:
+                stdio.warn("get observer version by sql fail, use node ssher to get. Exception:{0}".format(e))
+                version = get_observer_version(True, ssh, nodes[0]["home_path"], stdio)
         elif type == "obproxy":
             version = get_obproxy_version(True, ssh, nodes[0]["home_path"], stdio)
         return version
diff --git a/handler/checker/check_handler.py b/handler/checker/check_handler.py
index 5d4152b8..c7477a52 100644
--- a/handler/checker/check_handler.py
+++ b/handler/checker/check_handler.py
@@ -18,6 +18,9 @@
 
 import os
 import yaml
+
+from common.ob_connector import OBConnector
+from common.ssh import SshHelper
 from handler.checker.check_exception import CheckException
 from handler.checker.check_report import TaskReport, CheckReport, CheckrReportException
 from handler.checker.check_task import TaskBase
@@ -87,6 +90,41 @@ def __init__(self, context,  check_target_type="observer"):
         # input_param
         self.options=self.context.options
 
+        # add ssher
+        new_node=[]
+        for node in self.nodes:
+            # add ssher
+            ssher = None
+            try:
+                ssher = SshHelper(True, node.get("ip"),
+                                  node.get("ssh_username"),
+                                  node.get("ssh_password"),
+                                  node.get("ssh_port"),
+                                  node.get("ssh_key_file"),
+                                  node)
+            except Exception as e:
+                self.stdio.warn("StepBase get SshHelper fail on{0} ,Exception: {1}".format(node.get("ip"), e))
+            node["ssher"] = ssher
+            new_node.append(node)
+        self.nodes=new_node
+        self.version=get_version(self.nodes, self.check_target_type,self.cluster, self.stdio)
+
+        # add OBConnector
+        obConnector = None
+        try:
+            if self.cluster is not None:
+                obConnector=OBConnector(ip=self.cluster.get("db_host"),
+                                                   port=self.cluster.get("db_port"),
+                                                   username=self.cluster.get("tenant_sys").get("user"),
+                                                   password=self.cluster.get("tenant_sys").get("password"),
+                                                   stdio=self.stdio,
+                                                   timeout=10000)
+        except Exception as e:
+            self.stdio.warn("obConnector init error. Error info is {0}".format(e))
+        finally:
+            self.context.set_variable('check_obConnector', obConnector)
+
+
     def handle(self):
         try:
             package_name = None
@@ -173,7 +211,7 @@ def execute_one(self, task_name):
             # Verify if the version is within a reasonable range
             report = TaskReport(self.context,task_name)
             if not self.ignore_version:
-                version = get_version(self.nodes, self.check_target_type, self.stdio)
+                version = self.version
                 if version:
                     self.cluster["version"] = version
                     self.stdio.verbose("cluster.version is {0}".format(self.cluster["version"]))
diff --git a/handler/checker/check_task.py b/handler/checker/check_task.py
index bcd357b4..9605bfcf 100644
--- a/handler/checker/check_task.py
+++ b/handler/checker/check_task.py
@@ -15,7 +15,6 @@
 @file: check_task.py
 @desc:
 """
-
 from handler.checker.check_exception import StepResultFailException, \
     StepExecuteFailException, StepResultFalseException, TaskException
 from handler.checker.step.stepbase import StepBase
@@ -40,13 +39,15 @@ def execute(self):
         self.stdio.verbose("task_base execute")
         steps_nu = filter_by_version(self.task, self.cluster, self.stdio)
         if steps_nu < 0:
-            self.stdio.warn("Unadapted by version. SKIP")
+            self.stdio.warn("{0} Unadapted by version. SKIP".format(self.task['name']))
             self.report.add("Unadapted by version. SKIP", "warning")
             return "Unadapted by version.SKIP"
         self.stdio.verbose("filter_by_version is return {0}".format(steps_nu))
         if len(self.nodes) == 0:
             raise Exception("node is not exist")
+
         for node in self.nodes:
+
             self.stdio.verbose("run task in node: {0}".format(StringUtils.node_cut_passwd_for_log(node)))
             steps = self.task[steps_nu]
             nu = 1
diff --git a/handler/checker/step/data_size.py b/handler/checker/step/data_size.py
index c93a3e9d..b8d0ff0c 100644
--- a/handler/checker/step/data_size.py
+++ b/handler/checker/step/data_size.py
@@ -34,18 +34,14 @@ def __init__(self,context, step, node, task_variable_dict):
         self.task_variable_dict = task_variable_dict
 
         try:
-            is_ssh = True
-            self.ssh_helper = SshHelper(is_ssh, node.get("ip"),
-                                        node.get("ssh_username"),
-                                        node.get("ssh_password"),
-                                        node.get("ssh_port"),
-                                        node.get("ssh_key_file"),
-                                        node)
+            self.ssh_helper=self.node["ssher"]
+            if self.ssh_helper is None:
+                raise Exception("self.ssh_helper is None.")
         except Exception as e:
             self.stdio.error(
-                "GetSystemParameterHandler ssh init fail  . Please check the NODES conf Exception : {0} .".format(e))
+                "DataSizeHandler ssh init fail  . Please check the NODES conf Exception : {0} .".format(e))
             raise Exception(
-                "GetSystemParameterHandler ssh init fail . Please check the NODES conf  Exception : {0} .".format(e))
+                "DataSizeHandler ssh init fail . Please check the NODES conf  Exception : {0} .".format(e))
 
         # step report
         self.parameter = []
diff --git a/handler/checker/step/get_system_parameter.py b/handler/checker/step/get_system_parameter.py
index 8ecbc6d4..af3341c1 100644
--- a/handler/checker/step/get_system_parameter.py
+++ b/handler/checker/step/get_system_parameter.py
@@ -34,13 +34,9 @@ def __init__(self,context, step, node, task_variable_dict):
         self.task_variable_dict = task_variable_dict
 
         try:
-            is_ssh = True
-            self.ssh_helper = SshHelper(is_ssh, node.get("ip"),
-                                        node.get("ssh_username"),
-                                        node.get("ssh_password"),
-                                        node.get("ssh_port"),
-                                        node.get("ssh_key_file"),
-                                        node)
+            self.ssh_helper=self.node["ssher"]
+            if self.ssh_helper is None:
+                raise Exception("self.ssh_helper is None.")
         except Exception as e:
             self.stdio.error(
                 "GetSystemParameterHandler ssh init fail  . Please check the NODES conf Exception : {0} .".format(e))
diff --git a/handler/checker/step/sql.py b/handler/checker/step/sql.py
index 7b44d86d..c55c50a7 100644
--- a/handler/checker/step/sql.py
+++ b/handler/checker/step/sql.py
@@ -23,24 +23,21 @@
 
 
 class StepSQLHandler:
-    def __init__(self,context, step, ob_cluster, task_variable_dict):
+    def __init__(self,context, step, task_variable_dict):
         try:
             self.context = context
             self.stdio = context.stdio
-            self.ob_cluster = ob_cluster
-            self.ob_cluster_name = ob_cluster.get("cluster_name")
+            self.ob_cluster = self.context.cluster_config
+            self.ob_cluster_name = self.ob_cluster.get("cluster_name")
             self.tenant_mode = None
             self.sys_database = None
             self.database = None
-            self.ob_connector = OBConnector(ip=ob_cluster.get("db_host"),
-                                        port=ob_cluster.get("db_port"),
-                                        username=ob_cluster.get("tenant_sys").get("user"),
-                                        password=ob_cluster.get("tenant_sys").get("password"),
-                                        stdio=self.stdio,
-                                        timeout=10000)
+            self.ob_connector=self.context.get_variable('check_obConnector')
+            if self.ob_connector is None:
+                raise Exception("self.ob_connector is None.")
         except Exception as e:
-            self.stdio.error("StepSQLHandler init fail. Please check the OBCLUSTER conf. OBCLUSTER: {0} Exception : {1} .".format(ob_cluster,e))
-            raise Exception("StepSQLHandler init fail. Please check the OBCLUSTER conf. OBCLUSTER: {0} Exception : {1} .".format(ob_cluster,e))
+            self.stdio.error("StepSQLHandler init fail. Please check the OBCLUSTER conf. Exception : {0} .".format(e))
+            raise Exception("StepSQLHandler init fail. Please check the OBCLUSTER conf. Exception : {0} .".format(e))
         self.task_variable_dict = task_variable_dict
         self.enable_dump_db = False
         self.trace_id = None
@@ -73,8 +70,8 @@ def execute(self):
                 self.stdio.verbose("sql execute update task_variable_dict: {0} = {1}".format(self.step["result"]["set_value"], Util.convert_to_number(data)))
                 self.task_variable_dict[self.step["result"]["set_value"]] = Util.convert_to_number(data)
         except Exception as e:
-            self.stdio.error("StepSQLHandler execute Exception: {0}".format(e).strip())
-            raise StepExecuteFailException("StepSQLHandler execute Exception: {0}".format(e).strip())
+            self.stdio.error("StepSQLHandler execute Exception: {0}".format(e))
+            raise StepExecuteFailException("StepSQLHandler execute Exception: {0}".format(e))
 
     def update_step_variable_dict(self):
         return self.task_variable_dict
diff --git a/handler/checker/step/ssh.py b/handler/checker/step/ssh.py
index 963cd19f..282477e2 100644
--- a/handler/checker/step/ssh.py
+++ b/handler/checker/step/ssh.py
@@ -18,7 +18,6 @@
 
 from handler.checker.check_exception import StepExecuteFailException
 from handler.checker.check_report import TaskReport
-from common.ssh import SshHelper
 from common.tool import StringUtils
 from common.tool import Util
 
@@ -32,13 +31,9 @@ def __init__(self,context, step, node, task_variable_dict):
         self.step = step
         self.node = node
         try:
-            is_ssh = True
-            self.ssh_helper = SshHelper(is_ssh, node.get("ip"),
-                                        node.get("ssh_username"),
-                                        node.get("ssh_password"),
-                                        node.get("ssh_port"),
-                                        node.get("ssh_key_file"),
-                                        node)
+            self.ssh_helper=self.node["ssher"]
+            if self.ssh_helper is None:
+                raise Exception("self.ssh_helper is None.")
         except Exception as e:
             self.stdio.error(
                 "SshHandler init fail. Please check the NODES conf. node: {0}. Exception : {1} .".format(node, e))
diff --git a/handler/checker/step/stepbase.py b/handler/checker/step/stepbase.py
index a3351211..3ec68d8e 100644
--- a/handler/checker/step/stepbase.py
+++ b/handler/checker/step/stepbase.py
@@ -49,9 +49,8 @@ def execute(self, report):
                 self.task_variable_dict["remote_ip"] = \
                     docker.from_env().containers.get(self.node["container_name"]).attrs['NetworkSettings']['Networks'][
                         'bridge']["IPAddress"]
-            for key in self.node:
-                self.task_variable_dict["remote_{0}".format(key)] = self.node[key]
-
+            for node in self.node:
+                self.task_variable_dict["remote_{0}".format(node)] = self.node[node]
             if "type" not in self.step:
                 raise StepExecuteFailException("Missing field :type")
             if self.step["type"] == "get_system_parameter":
@@ -59,7 +58,7 @@ def execute(self, report):
             elif self.step["type"] == "ssh":
                 handler = SshHandler(self.context, self.step, self.node, self.task_variable_dict)
             elif self.step["type"] == "sql":
-                handler = StepSQLHandler(self.context, self.step, self.cluster, self.task_variable_dict)
+                handler = StepSQLHandler(self.context, self.step, task_variable_dict=self.task_variable_dict)
             elif self.step["type"] == "data_size":
                 handler = DataSizeHandler(self.context, self.step, self.cluster, self.task_variable_dict)
             else:
diff --git a/handler/checker/tasks/observer/table/information_schema_tables_two_data.yaml b/handler/checker/tasks/observer/table/information_schema_tables_two_data.yaml
new file mode 100644
index 00000000..f6bce02c
--- /dev/null
+++ b/handler/checker/tasks/observer/table/information_schema_tables_two_data.yaml
@@ -0,0 +1,12 @@
+info: 'A table found two records in information_schema.tables. KBA-50000056'
+task:
+  - version: "[4.0.0.0,*]"
+    steps:
+    - type: sql
+      sql: 'select count(0) from oceanbase.__all_virtual_table_stat where table_id = partition_id and (tenant_id,table_id) in (select tenant_id, table_id from oceanbase.__all_virtual_table where part_level != 0);'
+      result:
+        set_value: err_table_count
+        # report_type: warning
+        verify_type: equal
+        verify: 0
+        err_msg: 'Find have table found two records in information_schema.tables. the number of err_table_count is : #{err_table_count}.  Please get more info by "select * from oceanbase.__all_virtual_table_stat where table_id = partition_id and (tenant_id,table_id) in (select tenant_id, table_id from oceanbase.__all_virtual_table where part_level != 0);". And you can by "delete from __all_table_stat where table_id=partition_id and table_id=${partition table table_id};" and "delete from __all_column_stat where table_id=partition_id and table_id=${partition table table_id};" to fix it.'
diff --git a/handler/gather/gather_log.py b/handler/gather/gather_log.py
index ee640f4f..d5a1174f 100644
--- a/handler/gather/gather_log.py
+++ b/handler/gather/gather_log.py
@@ -35,6 +35,7 @@
 class GatherLogHandler(BaseShellHandler):
     def __init__(self, context, gather_pack_dir='./', is_scene=False):
         super(GatherLogHandler, self).__init__()
+        self.pack_dir_this_command = ""
         self.context = context
         self.stdio = context.stdio
         self.is_ssh = True
@@ -168,6 +169,7 @@ def handle_from_node(node):
 
         summary_tuples = self.__get_overall_summary(gather_tuples, self.zip_encrypt)
         self.stdio.print(summary_tuples)
+        self.pack_dir_this_command=pack_dir_this_command
         # Persist the summary results to a file
         FileUtil.write_append(os.path.join(pack_dir_this_command, "result_summary.txt"), summary_tuples)
         last_info = "For result details, please run cmd \033[32m' cat {0} '\033[0m\n".format(os.path.join(pack_dir_this_command, "result_summary.txt"))
@@ -333,6 +335,7 @@ def __pharse_log(self, ssh_helper, home_path, log_name, gather_path):
         """
         log_path = os.path.join(home_path, "log")
         if self.grep_options is not None:
+            grep_cmd=""
             if type(self.grep_options) == str:
                 grep_cmd = "grep -e '{grep_options}' {log_dir}/{log_name} >> {gather_path}/{log_name} ".format(
                     grep_options=self.grep_options,
diff --git a/handler/rca/rca_handler.py b/handler/rca/rca_handler.py
index 92f423b3..3a004891 100644
--- a/handler/rca/rca_handler.py
+++ b/handler/rca/rca_handler.py
@@ -293,6 +293,8 @@ def add_record(self, record):
 
     def add_suggest(self, suggest):
         self.suggest += suggest
+    def suggest_is_empty(self):
+        return self.suggest == "The suggest: "
 
     def export_suggest(self):
         return self.suggest
diff --git a/handler/rca/scene/ddl_disk_full_scene.py b/handler/rca/scene/ddl_disk_full_scene.py
index 89095f80..b45db4ac 100644
--- a/handler/rca/scene/ddl_disk_full_scene.py
+++ b/handler/rca/scene/ddl_disk_full_scene.py
@@ -12,7 +12,7 @@
 
 """
 @time: 2024/04/01
-@file: ddl_disk_full.py
+@file: ddl_disk_full_scene.py
 @desc:
 """
 import re
@@ -69,6 +69,9 @@ def init(self, context):
 
         tenant_data = self.ob_connector.execute_sql(
             "select tenant_id from oceanbase.__all_tenant where tenant_name = '{0}';".format(tenant_name))
+        if len(tenant_data) == 0:
+            raise RCAInitException(
+                "can not find tenant id by tenant name: {0}. Please check the tenant name.".format(tenant_name))
         self.tenant_id = tenant_data[0][0]
         if self.tenant_id is None:
             raise RCAInitException(
@@ -76,6 +79,9 @@ def init(self, context):
 
         table_id_data = self.ob_connector.execute_sql(
             "select table_id from oceanbase.__all_virtual_table where table_name = '{0}';".format(table_name))
+        if len(table_id_data) == 0:
+            raise RCAInitException(
+                "can not find table id by table name: {0}. Please check the table name.".format(table_name))
         self.table_id = table_id_data[0][0]
         if self.table_id is None:
             raise RCAInitException(
diff --git a/handler/rca/scene/disconnection_scene.py b/handler/rca/scene/disconnection_scene.py
index 1ac6d6a2..754224a0 100644
--- a/handler/rca/scene/disconnection_scene.py
+++ b/handler/rca/scene/disconnection_scene.py
@@ -12,7 +12,7 @@
 
 """
 @time: 2024/03/11
-@file: disconnectionScene.py
+@file: disconnection_scene.py
 @desc:
 """
 import re
diff --git a/handler/rca/scene/log_error_scene.py b/handler/rca/scene/log_error_scene.py
new file mode 100644
index 00000000..0973db65
--- /dev/null
+++ b/handler/rca/scene/log_error_scene.py
@@ -0,0 +1,338 @@
+#!/usr/bin/env python
+# -*- coding: UTF-8 -*
+# Copyright (c) 2022 OceanBase
+# OceanBase Diagnostic Tool is licensed under Mulan PSL v2.
+# You can use this software according to the terms and conditions of the Mulan PSL v2.
+# You may obtain a copy of Mulan PSL v2 at:
+#          http://license.coscl.org.cn/MulanPSL2
+# THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND,
+# EITHER EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT,
+# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.
+# See the Mulan PSL v2 for more details.
+
+"""
+@time: 2024/04/16
+@file: no_leader_scene.py
+@desc:
+"""
+import os
+import re
+
+from handler.rca.rca_exception import RCAInitException, RCAExecuteException
+from handler.rca.rca_handler import RcaScene, RCA_ResultRecord
+from common.tool import StringUtils
+
+
+class LogErrorScene(RcaScene):
+    def __init__(self):
+        super().__init__()
+        self.all_tenant_election_leader_info = None
+        self.work_path = None
+        self.all_tenant_ids = None
+
+    def init(self, context):
+        super().init(context)
+        ## observer version≥4.0.0.0
+        observer_version = self.observer_version
+        if observer_version is None or len(observer_version.strip()) == 0:
+            raise RCAInitException("observer version is None. Please check the NODES conf.")
+        if not (observer_version == "4.0.0.0" or StringUtils.compare_versions_greater(observer_version, "4.0.0.0")):
+            self.stdio.error("observer version is {0}, which is less than 4.0.0.0.".format(observer_version))
+            raise RCAInitException("observer version is {0}, which is less than 4.0.0.0.".format(observer_version))
+        # if self.ob_connector is None:
+        #     raise RCAInitException("ob_connector is None. Please check the NODES conf.")
+        self.verbose("observer version is {0}.".format(observer_version))
+        if self.ob_connector is None:
+            raise RCAInitException("ob_connector is None. Please check the NODES conf.")
+
+    def verbose(self, info):
+        self.stdio.verbose("[NoLeaderScene] {0}".format(info))
+
+    def execute(self):
+        try:
+            if self.observer_version >= '4.2.1.0':
+                self.execute_421()
+                return
+            # check Election leader
+            # get_all_tenant_id
+            self.verbose("start to get all tenant id...")
+            sql = "select tenant_id from oceanbase.__all_tenant;"
+            tenant_ids = self.ob_connector.execute_sql(sql)
+            if len(tenant_ids) <= 0:
+                raise RCAExecuteException("can not find any tenant id")
+            self.all_tenant_election_leader_info = {}
+            for tenant_id_data in tenant_ids:
+                record = RCA_ResultRecord()
+                try:
+                    tenant_id_data = tenant_id_data[0]
+
+                    record.add_record("tenant_id:{0}.".format(tenant_id_data))
+                    self.execute_by_tenant_id(tenant_id_data, record)
+                except Exception as e:
+                    self.verbose("check election leader error,tenant_id:{0},error:{1}".format(tenant_id_data, e))
+                    continue
+                finally:
+                    if len(record.suggest) == 13:
+                        record.add_suggest("no suggest")
+                    self.Result.records.append(record)
+        except Exception as e:
+            self.stdio.error("NoLeaderScene execute Exception:{0}".format(e))
+
+    def execute_by_tenant_id(self, tenant_id, record):
+        try:
+            record.add_record("start step1")
+            election_leader_info = self.check_election_leader_by_tenant_id(tenant_id)
+            self.verbose("election_leader_info:{0}".format(election_leader_info))
+            record.add_record("election_leader_info:{0}".format(election_leader_info))
+            if election_leader_info == "":
+                self.verbose("can not find any election leader,tenant_id:{0}".format(tenant_id))
+                record.add_record("election_leader_info is null")
+                record.add_suggest("can not find any election leader,tenant_id:{0}. Please check it.".format(tenant_id))
+                return
+            record.add_record("start step2")
+            step_next_tag = True
+            ls_ids = self.ob_connector.execute_sql(
+                "select distinct (ls_id) from oceanbase.__all_virtual_log_stat where tenant_id={0};".format(tenant_id))
+            if ls_ids is None or len(ls_ids) <= 0:
+                self.stdio.warn("not found log about election_leader. tenant_id: {0}".format(tenant_id))
+                record.add_suggest(
+                    "not found log on oceanbase.__all_virtual_log_stat. tenant_id: {0}".format(tenant_id))
+                return
+
+            for ls_id in ls_ids:
+                ls_id = ls_id[0]
+                leader_ls_id_bool = self.ob_connector.execute_sql(
+                    'select count(0) from oceanbase.__all_virtual_log_stat where role="LEADER" and tenant_id={0} and ls_id="{1}";'.format(
+                        tenant_id, ls_id))
+                leader_ls_id_bool = leader_ls_id_bool[0]
+                if leader_ls_id_bool <= 0:
+                    record.add_record(
+                        "tenant_id: {0}, ls_id: {1} on oceanbase.__all_virtual_log_stat no LEADER".format(tenant_id,
+                                                                                                          ls_id))
+                    record.add_suggest(
+                        "tenant_id: {0}, ls_id: {1} on oceanbase.__all_virtual_log_stat no LEADER".format(tenant_id,
+                                                                                                          ls_id))
+                    self.stdio.warn(
+                        "tenant_id: {0}, ls_id: {1} on oceanbase.__all_virtual_log_stat no LEADER".format(tenant_id,
+                                                                                                          ls_id))
+                    step_next_tag = False
+
+            if step_next_tag is False:
+                self.verbose("step_next_tag is false")
+                return
+            record.add_record("start step3")
+            return
+
+
+        except Exception as e:
+            self.stdio.warn("execute_by_tenant_id:{0} Exception:{1}".format(tenant_id, e))
+
+    def execute_421(self):
+        try:
+            self.stdio.print("start execute_421")
+            if self.ob_connector is None:
+                self.stdio.error("ob_connector is None. please check conf")
+                return
+            # get data from __all_virtual_ha_diagnose
+            sql = "select * from oceanbase.__all_virtual_ha_diagnose;"
+            cursor = self.ob_connector.execute_sql_return_cursor_dictionary(sql)
+            diagnose_data = cursor.fetchall()
+            if diagnose_data is None or len(diagnose_data) <= 0:
+                self.stdio.warn("not found data on oceanbase.__all_virtual_ha_diagnose")
+                return
+            # get all tenant_id
+            tenant_ids = []
+            for data in diagnose_data:
+                tenant_ids.append(data["tenant_id"])
+            self.verbose("tenant_ids:{0}".format(tenant_ids))
+            # step1
+            ### tenant_diagnose_data:   [tenant_id] diagnose_data
+            tenant_diagnose_data = {}
+            for data in diagnose_data:
+                if tenant_diagnose_data.get(data["tenant_id"]) is None:
+                    tenant_diagnose_data[data["tenant_id"]] = [data]
+                else:
+                    tenant_data = tenant_diagnose_data.get(data["tenant_id"])
+                    tenant_data.append(data)
+                    tenant_diagnose_data[data["tenant_id"]] = tenant_data
+            self.verbose("tenant_diagnose_data:{0}".format(tenant_diagnose_data))
+            self.stdio.start_loading("no_leader scene start analyzing...")
+            for tenant_id in tenant_diagnose_data:
+                record_one_tenant=self.execute_421_no_leader_by_tenant_id(tenant_id, tenant_diagnose_data[tenant_id])
+                self.Result.records.append(record_one_tenant)
+            self.stdio.stop_loading('no_leader scene end')
+            return
+
+        except Exception as e:
+            raise RCAExecuteException("execute_421 execute error: {0}".format(e))
+
+    def execute_421_no_leader_by_tenant_id(self, tenant_id,diagnose_data):
+        record = RCA_ResultRecord()
+        try:
+            self.stdio.verbose("start execute_421_no_leader_by_tenant_id")
+            record.add_record("tenant_id: {0}.".format(tenant_id))
+            leader_nu={}
+            record.add_record("start step1")
+            for diagnose_data_by_tenant_id in diagnose_data:
+                if diagnose_data_by_tenant_id["election_role"].upper() == "LEADER":
+                    leader_nu[diagnose_data_by_tenant_id["ls_id"]] = leader_nu.get(
+                        diagnose_data_by_tenant_id["ls_id"], 0) + 1
+                else:
+                    leader_nu[diagnose_data_by_tenant_id["ls_id"]] = leader_nu.get(
+                        diagnose_data_by_tenant_id["ls_id"], 0)
+            record.add_record("all ls_id:{0}".format(list(leader_nu.keys())))
+            self.verbose("all ls_id:{0}".format(list(leader_nu.keys())))
+            scene_1_tag=True
+            for ls_id in leader_nu:
+                record.add_record("on ls_id: {1} ".format(tenant_id, ls_id))
+                self.verbose("on tenant_id: {0}, ls_id: {1} ".format(tenant_id, ls_id))
+                if leader_nu[ls_id] > 1:
+                    self.stdio.warn("the leader number > 1")
+                    record.add_record("the ls_id's leader number > 1")
+                    record.add_suggest(
+                        "tenant_id: {0}, ls_id: {1} .the ls_id's leader number > 1".format(tenant_id, ls_id))
+                    scene_1_tag = False
+                    continue
+                elif leader_nu[ls_id] == 0:
+                    self.stdio.warn(
+                        "the leader number = 0,The election layer is unable to select a new owner, and a common problem in this scenario is that the message delay is too large. You can continue to troubleshoot the problem of message delay or backlog in the log")
+                    record.add_suggest(
+                        "tenant_id: {0}, ls_id: {1} .the leader number = 0. The election layer is unable to select a new owner, and a common problem in this scenario is that the message delay is too large. You can continue to troubleshoot the problem of message delay or backlog in the log".format(
+                            tenant_id, ls_id))
+                    scene_1_tag = False
+                    continue
+                else:
+                    ## Normal
+                    self.verbose("Normal. The ls_id's leader number = 1")
+                    record.add_record("Normal. The ls_id's leader number = 1")
+
+            if scene_1_tag is False:
+                self.verbose("scene_1 is check")
+                return record
+
+            ## scene 2
+            record.add_record("start step2")
+            scene_2_tag = True
+            for tenant_diagnose_data_by_tenant_id in diagnose_data:
+                ls_id = tenant_diagnose_data_by_tenant_id["ls_id"]
+                record.add_record("on ls_id: {1} ".format(tenant_id, ls_id))
+                if tenant_diagnose_data_by_tenant_id["election_role"].upper() == "LEADER" and \
+                        tenant_diagnose_data_by_tenant_id["palf_role"].upper() != "LEADER" and \
+                        tenant_diagnose_data_by_tenant_id["palf_state"].upper() != "ACTIVE":
+                    self.stdio.warn(
+                        "tenant_id: {0}, ls_id: {1} on oceanbase.__all_virtual_ha_diagnose election_role is LEADER but palf_role is {2} and palf_state is {3}".format(
+                            tenant_id,
+                            ls_id,
+                            tenant_diagnose_data_by_tenant_id["palf_role"],
+                            tenant_diagnose_data_by_tenant_id["palf_state"]))
+                    record.add_record(
+                        "tenant_id: {0}, ls_id: {1} on oceanbase.__all_virtual_ha_diagnose election_role is LEADER but palf_role is {2} and palf_state is {3}".format(
+                            tenant_id,
+                            ls_id,
+                            tenant_diagnose_data_by_tenant_id["palf_role"],
+                            tenant_diagnose_data_by_tenant_id["palf_state"]))
+                    record.add_suggest(
+                        "tenant_id: {0}, ls_id: {1} on oceanbase.__all_virtual_ha_diagnose election_role is LEADER but palf_role is {2} and palf_state is {3}. The newly elected leader failed to take office in the palf layer, and the palf_state can be used to determine at which stage the palf failed to take office.".format(
+                            tenant_id,
+                            ls_id,
+                            tenant_diagnose_data_by_tenant_id["palf_role"],
+                            tenant_diagnose_data_by_tenant_id["palf_state"]))
+                    scene_2_tag = False
+                else:
+                    self.verbose(
+                        "tenant_id: {0}, ls_id: {1} on oceanbase.__all_virtual_ha_diagnose election_role is LEADER , palf_role is {2} and palf_state is {3}".format(
+                            tenant_id,
+                            ls_id,
+                            tenant_diagnose_data_by_tenant_id["palf_role"],
+                            tenant_diagnose_data_by_tenant_id["palf_state"]))
+                    record.add_record("Normal. Unable to find a replica where both election_role and palf_role are leaders, but log_handler_role is follower")
+                    continue
+            if scene_2_tag is False:
+                self.verbose("scene_2 is check")
+                return
+            ## scene 3
+            record.add_record("start step3")
+
+            for tenant_diagnose_data_by_tenant_id in diagnose_data:
+                record.add_record(
+                    "tenant_id: {0}, ls_id: {1} ".format(tenant_diagnose_data_by_tenant_id["tenant_id"],
+                                                         tenant_diagnose_data_by_tenant_id["ls_id"]))
+                if tenant_diagnose_data_by_tenant_id["election_role"].upper() == "LEADER" and \
+                        tenant_diagnose_data_by_tenant_id["palf_role"].upper() == "LEADER" and \
+                        tenant_diagnose_data_by_tenant_id["log_handler_role"].upper() == "follower":
+                    record.add_record("election_role:LEADER , palf_role: LEADER, log_handler_role: follower")
+                    log_handler_takeover_state = tenant_diagnose_data_by_tenant_id[
+                        "log_handler_takeover_state"].lower()
+                    record.add_record("log_handler_takeover_state: {0}".format(log_handler_takeover_state))
+                    if log_handler_takeover_state == "wait_replay_done":
+                        record.add_suggest(
+                            "Previous stuck waiting for replay steps. Please check the issue about replay")
+                    elif log_handler_takeover_state == "unknown":
+                        record.add_suggest(
+                            "Please check observe whether the remaining log streams of this tenant also have the issue of log handler failure in taking over")
+                    elif log_handler_takeover_state == "wait_rc_handler_done":
+                        log_handler_takeover_log_type = tenant_diagnose_data_by_tenant_id[
+                            "log_handler_takeover_log_type"]
+                        record.add_record(
+                            "log_handler_takeover_log_type: {0}".format(log_handler_takeover_log_type))
+                        record.add_suggest(
+                            "log_handler_takeover_log_type is {0}. Please report oceanbase's community".format(
+                                log_handler_takeover_log_type))
+                else:
+                    record.add_record("Normal.Unable to find a replica where the selection_role is a leader, but the palf_role and palf_state are not leaders or active, respectively")
+
+            if record.suggest_is_empty():
+                record.add_suggest("Normal. Not find the reason of the log handler failure in taking over.")
+        except Exception as e:
+            raise RCAExecuteException("tenant_id: {0}. execute_421_no_leader_by_tenant_id execute error: {1}".format(tenant_id,e))
+        finally:
+
+            return record
+
+
+
+
+    def check_election_leader_by_tenant_id(self, tenant_id):
+        try:
+            self.stdio.verbose("start check_election_leader_by_tenant_id")
+            self.gather_log.set_parameters("scope", "election")
+            self.gather_log.grep("T{0}_.*dump proposer info".format(tenant_id))
+            self.work_path = self.store_dir
+            logs_name = self.gather_log.execute()
+            if len(logs_name) == 0:
+                self.stdio.warn(
+                    "check_election_leader_by_tenant_id not found log about election_leader. tenant_id: {0}".format(
+                        tenant_id))
+                return ""
+            self.stdio.verbose(
+                "check_election_leader_by_tenant_id tenant_id: {0}, logs_name:{1}".format(tenant_id, logs_name))
+            for name in logs_name:
+                self.stdio.verbose("read the log file: {0}".format(name))
+                with open(name, 'rb') as file:
+                    file.seek(0, os.SEEK_END)
+                    file_length = file.tell()
+                    file.seek(max(file_length - 1024, 0), 0)
+                    lines = file.readlines()
+                    last_line = lines[-1].decode().strip()
+                    pattern = r'addr:"([^"]+)"'
+                    match = re.search(pattern, last_line)
+                    if match:
+                        return match.group(1)
+                    else:
+                        return ""
+        except Exception as e:
+            raise RCAExecuteException(
+                "check_election_leader_by_tenant_id: {1}. execute error: {0}".format(e, tenant_id))
+
+    def export_result(self):
+        super().export_result()
+
+    def get_scene_info(self):
+
+        return {"name": "log_error",
+                "info_en": "Troubleshooting log related issues. Currently supported scenes: no_leader.",
+                "info_cn": '日志相关问题排查。目前支持：无主场景。',
+                }
+
+
+log_error = LogErrorScene()
\ No newline at end of file
diff --git a/handler/rca/scene/major_hold_scene.py b/handler/rca/scene/major_hold_scene.py
index dee2ad5a..7ebfb93d 100644
--- a/handler/rca/scene/major_hold_scene.py
+++ b/handler/rca/scene/major_hold_scene.py
@@ -12,7 +12,7 @@
 
 """
 @time: 2024/1/2
-@file: major_hold.py
+@file: major_hold_scene.py
 @desc:
 """
 import json

From 54a44f1fb93248e6234ad949e41ec6dd52a9643f Mon Sep 17 00:00:00 2001
From: Teingi <jingshun.tq@antgroup.com>
Date: Mon, 22 Apr 2024 20:05:15 +0800
Subject: [PATCH 02/30] update README.md

---
 README-CN.md | 57 ++++++++++++++++++++++++++--------------------------
 README.md    | 55 +++++++++++++++++++++++++-------------------------
 2 files changed, 57 insertions(+), 55 deletions(-)

diff --git a/README-CN.md b/README-CN.md
index d14ecbcc..32e1cc0c 100644
--- a/README-CN.md
+++ b/README-CN.md
@@ -62,49 +62,50 @@ obdiag config -h <db_host> -u <sys_user> [-p password] [-P port]
 ```
 
 # obdiag 功能
+- 一键集群巡检
+- 一键诊断分析
+- 一键根因分析
+- 一键信息采集
 
-## obdiag 巡检功能
-- [一键巡检](./docs/check.md)
 
-## obdiag 一键场景化信息采集功能
-- [一键场景化信息采集](./docs/gather_scene.md)
+# 参与贡献
 
-## obdiag 一键信息采集功能
+obdiag 期望构建一个开放的社区，我们欢迎任何形式的贡献，您可以：
 
-- [一键收集OB日志](./docs/gather_ob_log.md)
-- [一键收集AWR报告](./docs/gather_awr.md)
-- [一键收集主机信息](./docs/gather_sysstat.md)
-- [一键收集slog/clog日志](./docs/gather_admin.md)
-- [一键收集火焰图信息](./docs/gather_perf.md)
-- [一键收集OB堆栈信息](./docs/gather_ob_stack.md)
-- [一键收集并行SQL的执行详情信息](./docs/gather_sql_plan_monitor.md)
-- [一键收集OBPROXY日志](./docs/gather_obproxy_log.md)
-- [一键收集AWR报告](./docs/gather_awr.md)
-- [一键收集全部诊断信息](./docs/gather_all.md)
+- 向我们提出一个[issue](https://github.com/oceanbase/oceanbase-diagnostic-tool/issues)。
+- 提交请求。
+
+- 通过 [Issues](https://github.com/oceanbase/oceanbase-diagnostic-tool/issues) 提交 bug。
+- 通过 [Discussion](https://github.com/oceanbase/oceanbase-diagnostic-tool/discussions) 参与或发起讨论。
+- 通过 [Pull requests](https://github.com/oceanbase/oceanbase-diagnostic-tool/pulls) 提交问题修复或者功能特性。
+- 加入 obdiag [SIG（兴趣小组)](https://oceanbase.yuque.com/org-wiki-obtech-vh7w9r/imzr6c/ixh8wb9d356at3hm)
 
-## obdiag 一键分析功能说明
-- [一键分析OB日志](./docs/analyze_ob_log.md)
-- [一键全链路诊断](./docs/analyze_flt_trace.md)
+# Roadmap Ahead
+
+| 版本 | 迭代周期 | Function | 
+|---------|---------------|---------|
+|1.6.0| 2024.01| <ul><li> 场景化信息采集 </li><li> 场景化根因分析 </li></ul> |
+|2.0.0|2024.03| <ul><li> context改造，场景化扩展能力增强 </li><li> 支持在线更新巡检、采集的task </li><li> 根因分析二期 </li></ul>|
+|2.1.0|2024.04| <ul><li> 根因分析场景扩展 </li><li> 新增 tabledump 采集 </li></ul>|
+|2.2.0|2024.05| <ul><li> 根因分析场景扩展 </li></ul>|
+|2.3.0|2024.06| <ul><li> 根因分析场景扩展 </li><li> 支持 SQL 诊断 </li></ul>|
+|2.4.0|2024.07| <ul><li> 根因分析场景扩展 </li><li> 适配两款内核的诊断工具 </li></ul>|
+|2.5.0|2024.08| <ul><li> 根因分析场景扩展 </li><li> 支持 OMS 诊断 </li></ul>|
+|3.0.0|2024.09| <ul><li> 根因分析场景扩展 </li><li> 服务化改造 </li></ul>|
+|3.1.0|2024.10| <ul><li> 根因分析场景扩展 </li><li> 支持巡检报告比对 </li></ul>|
+|3.2.0|2024.11| <ul><li> 根因分析场景扩展 </li><li> SQL 诊断二期，支持SQL问题的根因分析 </li></ul>|
+|3.3.0|2024.12| <ul><li> AI 化探索 </li></ul>|
 
-## obdiag 一键场景化根因分析功能
-- [一键场景化根因分析](./docs/rca.md)
 
 # 许可证
 
 OceanBase Diagnostic Tool 使用 [MulanPSL - 2.0](http://license.coscl.org.cn/MulanPSL2) 许可证。
 您可以免费复制及使用源代码。当您修改或分发源代码时，请遵守木兰协议。
 
-
-## 贡献
-
-我们热烈欢迎并高度赞赏您的贡献。您可以通过以下几种方式做出贡献：
-
-- 向我们提出一个[issue](https://github.com/oceanbase/oceanbase-diagnostic-tool/issues)。
-- 提交请求。
-
 ## 支持
 
 如果您在使用 OceanBase LogProxy 时遇到任何问题，欢迎联系我们寻求帮助：
 
 - [GitHub Issue](https://github.com/oceanbase/oceanbase-diagnostic-tool/issues)
 - [官方网站](https://www.oceanbase.com/docs/obdiag-cn)
+- obdiag SIG 微信号: obdiagsig
\ No newline at end of file
diff --git a/README.md b/README.md
index f5164359..ed373e1a 100644
--- a/README.md
+++ b/README.md
@@ -64,48 +64,49 @@ obdiag config -h <db_host> -u <sys_user> [-p password] [-P port]
 ```
 
 # obdiag Fuctions
+- One-click cluster inspection
+- One-click diagnostic analyze
+- One-click root cause analysis
+- One-click information collection
 
-## obdiag check Fuctions
-- [check](./docs/check.md)
+For more details, please refer to [Official docs](https://www.oceanbase.com/docs/obdiag-cn)
 
-## obdiag gather scene Fuctions
-- [gather scene](./docs/gather_scene.md)
+# Join the Contributing Community
 
-## obdiag gather Fuctions
+obdiag envisions an open community. We welcome your contributions in any form:
 
-- [gather log](./docs/gather_ob_log.md)
-- [gather sysstat](./docs/gather_sysstat.md)
-- [gather slog/clog](./docs/gather_admin.md)
-- [gather perf](./docs/gather_perf.md)
-- [gather obstack](./docs/gather_ob_stack.md)
-- [gather sql plan monitor](./docs/gather_sql_plan_monitor.md)
-- [gather obproxy_log](./docs/gather_obproxy_log.md)
-- [gather awr](./docs/gather_awr.md)
-- [gather all](./docs/gather_all.md)
+- Report bugs through [Issues](https://github.com/oceanbase/oceanbase-diagnostic-tool/issues).
+- Participate in or initiate discussions via [Discussion](https://github.com/oceanbase/oceanbase-diagnostic-tool/discussions).
+- Contribute bug fixes or new features through [Pull requests](https://github.com/oceanbase/oceanbase-diagnostic-tool/pulls).
+- Join the obdiag [SIG（Special Interest Group)](https://oceanbase.yuque.com/org-wiki-obtech-vh7w9r/imzr6c/ixh8wb9d356at3hm)
 
-## obdiag analyze Fuctions
-- [analyze log](./docs/analyze_ob_log.md)
-- [analyze flt trace log](./docs/analyze_flt_trace.md)
 
-## obdiag rca Fuctions
-- [rca](./docs/rca.md)
+
+# Roadmap Ahead
+
+| Version | Date | Function | 
+|---------|---------------|---------|
+|1.6.0| 2024.01| <ul><li> Scenario based fault information collection </li><li> Scenario based root cause analysis </li></ul> |
+|2.0.0|2024.03| <ul><li> Context Transformation, Enhanced Scene Expansion Capabilities</li><li> Support online updating of inspection and gather tasks </li><li>Root Cause Analysis Phase II Transformation </li></ul>|
+|2.1.0|2024.04| <ul><li> Root Cause Analysis Scenario Expansion </li><li> Gather tabledump </li></ul>|
+|2.2.0|2024.05| <ul><li> Root Cause Analysis Scenario Expansion </li></ul>|
+|2.3.0|2024.06| <ul><li> Root Cause Analysis Scenario Expansion </li><li> Support SQL Diagnosis </li></ul>|
+|2.4.0|2024.07| <ul><li> Root Cause Analysis Scenario Expansion </li><li> Adapting Two Additional Kernel Diagnostic Tools </li></ul>|
+|2.5.0|2024.08| <ul><li> Root Cause Analysis Scenario Expansion </li><li> Support OMS Diagnosis </li></ul>|
+|3.0.0|2024.09| <ul><li> Root Cause Analysis Scenario Expansion </li><li> Service-ification Transformation </li></ul>|
+|3.1.0|2024.10| <ul><li> Root Cause Analysis Scenario Expansion </li><li> Supporting Comparative Functionality for Patrol Inspection Reports </li></ul>|
+|3.2.0|2024.11| <ul><li> Root Cause Analysis Scenario Expansion </li><li> SQL Diagnosis Phase II, Supporting Root Cause Analysis for SQL problems </li></ul>|
+|3.3.0|2024.12| <ul><li> AI for obdiag </li></ul>|
 
 # Licencing
 OceanBase Database is under MulanPubL - 2.0 license. You can freely copy and use the source code. When you modify or
 distribute the source code, please obey the MulanPubL - 2.0 license.
 
-
-# Contributing
-
-Contributions are warmly welcomed and greatly appreciated. Here are a few ways you can contribute:
-
-- Raise us an [issue](https://github.com/oceanbase/oceanbase-diagnostic-tool/issues).
-- Submit Pull Requests.
-
 # Support
 
 In case you have any problems when using obdiag, welcome reach out for help:
 
 - [GitHub Issue](https://github.com/oceanbase/oceanbase-diagnostic-tool/issues)
 - [Official Website](https://www.oceanbase.com/docs/obdiag-cn)
+- obdiag SIG WeChat: obdiagsig
 

From 742cebc7ea30a917250919b6aa7e7e1c8e930105 Mon Sep 17 00:00:00 2001
From: Teingi <jingshun.tq@antgroup.com>
Date: Mon, 22 Apr 2024 20:06:28 +0800
Subject: [PATCH 03/30] update README.md

---
 README-CN.md | 1 -
 README.md    | 1 -
 2 files changed, 2 deletions(-)

diff --git a/README-CN.md b/README-CN.md
index 32e1cc0c..69bd71c0 100644
--- a/README-CN.md
+++ b/README-CN.md
@@ -78,7 +78,6 @@ obdiag 期望构建一个开放的社区，我们欢迎任何形式的贡献，
 - 通过 [Issues](https://github.com/oceanbase/oceanbase-diagnostic-tool/issues) 提交 bug。
 - 通过 [Discussion](https://github.com/oceanbase/oceanbase-diagnostic-tool/discussions) 参与或发起讨论。
 - 通过 [Pull requests](https://github.com/oceanbase/oceanbase-diagnostic-tool/pulls) 提交问题修复或者功能特性。
-- 加入 obdiag [SIG（兴趣小组)](https://oceanbase.yuque.com/org-wiki-obtech-vh7w9r/imzr6c/ixh8wb9d356at3hm)
 
 # Roadmap Ahead
 
diff --git a/README.md b/README.md
index ed373e1a..811be1f2 100644
--- a/README.md
+++ b/README.md
@@ -78,7 +78,6 @@ obdiag envisions an open community. We welcome your contributions in any form:
 - Report bugs through [Issues](https://github.com/oceanbase/oceanbase-diagnostic-tool/issues).
 - Participate in or initiate discussions via [Discussion](https://github.com/oceanbase/oceanbase-diagnostic-tool/discussions).
 - Contribute bug fixes or new features through [Pull requests](https://github.com/oceanbase/oceanbase-diagnostic-tool/pulls).
-- Join the obdiag [SIG（Special Interest Group)](https://oceanbase.yuque.com/org-wiki-obtech-vh7w9r/imzr6c/ixh8wb9d356at3hm)
 
 
 

From b4183acb5c93f3da2418661ffe40e583ff04eb6e Mon Sep 17 00:00:00 2001
From: Teingi <jingshun.tq@antgroup.com>
Date: Mon, 22 Apr 2024 20:08:38 +0800
Subject: [PATCH 04/30] update README.md

---
 README-CN.md | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/README-CN.md b/README-CN.md
index 69bd71c0..71135b50 100644
--- a/README-CN.md
+++ b/README-CN.md
@@ -71,10 +71,6 @@ obdiag config -h <db_host> -u <sys_user> [-p password] [-P port]
 # 参与贡献
 
 obdiag 期望构建一个开放的社区，我们欢迎任何形式的贡献，您可以：
-
-- 向我们提出一个[issue](https://github.com/oceanbase/oceanbase-diagnostic-tool/issues)。
-- 提交请求。
-
 - 通过 [Issues](https://github.com/oceanbase/oceanbase-diagnostic-tool/issues) 提交 bug。
 - 通过 [Discussion](https://github.com/oceanbase/oceanbase-diagnostic-tool/discussions) 参与或发起讨论。
 - 通过 [Pull requests](https://github.com/oceanbase/oceanbase-diagnostic-tool/pulls) 提交问题修复或者功能特性。

From 74f4a10afc5ae81501d9eadcbd879b6112f6887b Mon Sep 17 00:00:00 2001
From: Teingi <jingshun.tq@antgroup.com>
Date: Mon, 22 Apr 2024 20:10:36 +0800
Subject: [PATCH 05/30] update README.md

---
 README-CN.md | 2 +-
 README.md    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/README-CN.md b/README-CN.md
index 71135b50..c1df09de 100644
--- a/README-CN.md
+++ b/README-CN.md
@@ -77,7 +77,7 @@ obdiag 期望构建一个开放的社区，我们欢迎任何形式的贡献，
 
 # Roadmap Ahead
 
-| 版本 | 迭代周期 | Function | 
+| 版本 | 迭代周期 | 功能点 | 
 |---------|---------------|---------|
 |1.6.0| 2024.01| <ul><li> 场景化信息采集 </li><li> 场景化根因分析 </li></ul> |
 |2.0.0|2024.03| <ul><li> context改造，场景化扩展能力增强 </li><li> 支持在线更新巡检、采集的task </li><li> 根因分析二期 </li></ul>|
diff --git a/README.md b/README.md
index 811be1f2..c2b372ba 100644
--- a/README.md
+++ b/README.md
@@ -83,7 +83,7 @@ obdiag envisions an open community. We welcome your contributions in any form:
 
 # Roadmap Ahead
 
-| Version | Date | Function | 
+| Version | Iteration Period | Function | 
 |---------|---------------|---------|
 |1.6.0| 2024.01| <ul><li> Scenario based fault information collection </li><li> Scenario based root cause analysis </li></ul> |
 |2.0.0|2024.03| <ul><li> Context Transformation, Enhanced Scene Expansion Capabilities</li><li> Support online updating of inspection and gather tasks </li><li>Root Cause Analysis Phase II Transformation </li></ul>|

From 47aa6259aae6e126f0d5eb74d43917988ec360e8 Mon Sep 17 00:00:00 2001
From: Teingi <jingshun.tq@antgroup.com>
Date: Tue, 23 Apr 2024 19:15:04 +0800
Subject: [PATCH 06/30] update README

---
 README-CN.md |  6 ------
 README.md    | 10 +---------
 2 files changed, 1 insertion(+), 15 deletions(-)

diff --git a/README-CN.md b/README-CN.md
index c1df09de..f790fc7e 100644
--- a/README-CN.md
+++ b/README-CN.md
@@ -41,12 +41,6 @@ sh /usr/local/oceanbase-diagnostic-tool/init.sh
 ```
 
 ## 方式二：源码安装
-源码编译环境确保有如下依赖
-- gcc
-- wget
-- python-devel
-- mysql-devel
-
 源码安装需要在python >= 3.8的环境下进行
 
 ```shell
diff --git a/README.md b/README.md
index c2b372ba..54e4394c 100644
--- a/README.md
+++ b/README.md
@@ -41,15 +41,7 @@ sh /usr/local/oceanbase-diagnostic-tool/init.sh
 ```
 
 ## Method 2: Install obdiag by using the source code
-
-Before you install obdiag by using the source code, make sure that you have installed these dependencies:
-
-- gcc
-- wget
-- python-devel
-- mysql-devel
-
-To install obdiag on Python3.8, run these commands:
+To install obdiag on Python >= 3.8, run these commands:
 
 ```shell
 pip3 install -r requirements3.txt

From 44e0c65e08f4f47838cc066df406ef5533f3e346 Mon Sep 17 00:00:00 2001
From: Teingi <jingshun.tq@antgroup.com>
Date: Wed, 24 Apr 2024 14:46:04 +0800
Subject: [PATCH 07/30] close #177

---
 rpm/oceanbase-diagnostic-tool.spec | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/rpm/oceanbase-diagnostic-tool.spec b/rpm/oceanbase-diagnostic-tool.spec
index c5749ecc..f97038f5 100644
--- a/rpm/oceanbase-diagnostic-tool.spec
+++ b/rpm/oceanbase-diagnostic-tool.spec
@@ -80,5 +80,6 @@ find /usr/local/oceanbase-diagnostic-tool/obdiag -type f -exec chmod 644 {} \;
 ln -sf /usr/local/oceanbase-diagnostic-tool/obdiag /usr/bin/obdiag
 chmod +x /usr/local/oceanbase-diagnostic-tool/obdiag
 cp -rf /usr/local/oceanbase-diagnostic-tool/init_obdiag_cmd.sh /etc/profile.d/obdiag.sh
+sh /usr/local/oceanbase-diagnostic-tool/init.sh
 echo -e 'Please execute the following command to init obdiag:\n'
-echo -e '\033[32m source /usr/local/oceanbase-diagnostic-tool/init.sh \n \033[0m'
+echo -e '\033[32m source ~/.bashrc \n \033[0m'

From 58e5571207014f7be96434901ebf382a16e140a4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Wed, 24 Apr 2024 17:19:06 +0800
Subject: [PATCH 08/30] update check cases

---
 cmd.py                                        |  2 +
 .../ob_enable_plan_cache_bad_version.yaml     |  2 +-
 .../tasks/observer/cluster/sys_log_level.yaml | 23 +++++++++
 .../checker/tasks/observer/system/aio.yaml    |  4 +-
 .../tasks/observer/system/clock_source.yaml   | 11 ++++
 .../observer/system/dependent_software.yaml   |  9 +---
 .../tasks/observer/system/parameter.yaml      | 50 +++++++++----------
 .../system/parameter_ip_local_port_range.yaml |  6 +--
 .../observer/system/parameter_tcp_rmem.yaml   |  6 +--
 .../observer/system/parameter_tcp_wmem.yaml   |  6 +--
 .../observer/system/ulimit_parameter.yaml     |  8 +--
 handler/gather/gather_obproxy_log.py          |  2 +-
 handler/rca/rca_handler.py                    |  9 ++++
 handler/rca/scene/log_error_scene.py          |  5 +-
 14 files changed, 89 insertions(+), 54 deletions(-)
 create mode 100644 handler/checker/tasks/observer/cluster/sys_log_level.yaml
 create mode 100644 handler/checker/tasks/observer/system/clock_source.yaml

diff --git a/cmd.py b/cmd.py
index 986dec43..0c0fcfb1 100644
--- a/cmd.py
+++ b/cmd.py
@@ -322,6 +322,8 @@ def do_command(self):
             return False
         cmd = '%s %s' % (self.prev_cmd, base)
         ROOT_IO.track_limit += 1
+        if "main.py" in cmd:
+            telemetry.work_tag=False
         telemetry.push_cmd_info("cmd: {0}. args:{1}".format(cmd,args))
         return self.commands[base].init(cmd, args).do_command()
 
diff --git a/handler/checker/tasks/observer/cluster/ob_enable_plan_cache_bad_version.yaml b/handler/checker/tasks/observer/cluster/ob_enable_plan_cache_bad_version.yaml
index 13b957e8..77e6d8a3 100644
--- a/handler/checker/tasks/observer/cluster/ob_enable_plan_cache_bad_version.yaml
+++ b/handler/checker/tasks/observer/cluster/ob_enable_plan_cache_bad_version.yaml
@@ -6,6 +6,6 @@ task:
       sql: 'select name from oceanbase.__all_virtual_tenant_parameter_stat where name like "%ob_enable_plan_cache%" and value like "%true%";'
       result:
         set_value: ob_enable_plan_cache
-        verify: '[ -z "ob_enable_plan_cache" ]'
+        verify: '[ -z "$ob_enable_plan_cache" ]'
         err_msg: 'On this version, ob_enable_plan_cache suggestion to close'
 
diff --git a/handler/checker/tasks/observer/cluster/sys_log_level.yaml b/handler/checker/tasks/observer/cluster/sys_log_level.yaml
new file mode 100644
index 00000000..1d67338c
--- /dev/null
+++ b/handler/checker/tasks/observer/cluster/sys_log_level.yaml
@@ -0,0 +1,23 @@
+info: "Check sys_log_level ."
+task:
+  - version: "[4.0.0.0,*]"
+    steps:
+    - type: sql
+      sql: 'SELECT value FROM  oceanbase.__all_virtual_sys_parameter_stat where name  like "%syslog_level%";'
+      result:
+        set_value: sys_log_level
+        verify_type: equal
+        report_type: warning
+        verify: '[[ ${sys_log_level} == "WDIAG"]]'
+        err_msg: "on 4.x, the recommended value for sys_log_level is WDIAG"
+
+  - version: "[3.0.0,4.0.0.0)"
+    steps:
+    - type: sql
+      sql: 'SELECT value FROM  oceanbase.__all_virtual_sys_parameter_stat where name  like "%syslog_level%";'
+      result:
+        set_value: sys_log_level
+        verify_type: equal
+        report_type: warning
+        verify: '[[ ${sys_log_level} == "INFO"]]'
+        err_msg: "on 3.x, the recommended value for sys_log_level is INFO"
diff --git a/handler/checker/tasks/observer/system/aio.yaml b/handler/checker/tasks/observer/system/aio.yaml
index 6ad6adeb..d72b3369 100644
--- a/handler/checker/tasks/observer/system/aio.yaml
+++ b/handler/checker/tasks/observer/system/aio.yaml
@@ -11,11 +11,11 @@ task:
           set_value: aio_max_nr
           report_type: warning
           verify: "[ ${aio_max_nr} -ge 1048576 ]"
-          err_msg: 'fs.aio-max-nr : #{aio_max_nr} is a non recommended value, recommended value  need  >1048576'
+          err_msg: 'fs.aio-max-nr : #{aio_max_nr} . recommended: >1048576'
       - type: get_system_parameter
         parameter: fs.aio-nr
         result:
           set_value: aio_nr
           report_type: warning
           verify: "[ $((aio_max_nr - aio_nr)) -ge $((20000*${observer_nu})) ]"
-          err_msg: 'fs.aio-nr : #{aio_nr} is a non recommended value, recommended value  need  aio-max-nr - aio-nr>20000 * observer_num'
+          err_msg: 'fs.aio-nr : #{aio_nr} . recommended:  aio-max-nr - aio-nr>20000 * observer_num'
diff --git a/handler/checker/tasks/observer/system/clock_source.yaml b/handler/checker/tasks/observer/system/clock_source.yaml
new file mode 100644
index 00000000..e494f5d9
--- /dev/null
+++ b/handler/checker/tasks/observer/system/clock_source.yaml
@@ -0,0 +1,11 @@
+info: 'Check the type of clock_source is tsc'
+task:
+  - steps:
+      - type: ssh
+        ssh: "cat /sys/devices/system/clocksource/clocksource0/current_clocksource"
+        result:
+          set_value: clock_source
+          verify: "[ \"${clock_source}\" == \"tsc\" ]"
+          err_msg: 'clock_source: #{clock_source}. recommended: tsc. Uneven CPU utilization during pressure testing resulted in low TPS during pressure testing'
+
+
diff --git a/handler/checker/tasks/observer/system/dependent_software.yaml b/handler/checker/tasks/observer/system/dependent_software.yaml
index 5c0d64ae..c65c5996 100644
--- a/handler/checker/tasks/observer/system/dependent_software.yaml
+++ b/handler/checker/tasks/observer/system/dependent_software.yaml
@@ -35,11 +35,4 @@ task:
         set_value: transparent_hugepage_switch
         report_type: warning
         verify: '[ -n "${transparent_hugepage_switch}" ]'
-        err_msg: 'transparent_hugepage need retrun "[never]". Now , it is null.'
-    - type: ssh
-      ssh: "python --version 2>&1 | awk '{print $2}' | cut -d'.' -f1,2"
-      result:
-        set_value: python_version
-        report_type: warning
-        verify: '[ "2.7" == ${python_version} ]'
-        err_msg: 'python version need retrun 2.7.x'
\ No newline at end of file
+        err_msg: 'transparent_hugepage need retrun "[never]". Now , it is null.'
\ No newline at end of file
diff --git a/handler/checker/tasks/observer/system/parameter.yaml b/handler/checker/tasks/observer/system/parameter.yaml
index 6cb80c7e..5dc3bd3e 100644
--- a/handler/checker/tasks/observer/system/parameter.yaml
+++ b/handler/checker/tasks/observer/system/parameter.yaml
@@ -10,7 +10,7 @@ task:
         report_type: warning
         verify_type: between
         verify: "[2048,16384]"
-        err_msg: 'net.core.somaxconn : #{parameter} , which is not recommended. Set it within the range of  2048 ≤ value ≤ 16384'
+        err_msg: 'net.core.somaxconn : #{parameter}. recommended: 2048 ≤ value ≤ 16384.'
     - type: get_system_parameter
       parameter: net.core.netdev_max_backlog
       result:
@@ -18,7 +18,7 @@ task:
         report_type: warning
         verify_type: between
         verify: "[ 500 ,10000 ]"
-        err_msg: 'net.core.netdev_max_backlog  : #{parameter} , which is not recommended. Set it within the range of  500 ≤ value ≤ 10000'
+        err_msg: 'net.core.netdev_max_backlog: #{parameter}. recommended: 500 ≤ value ≤ 10000.'
     - type: get_system_parameter
       parameter: net.core.rmem_default
       result:
@@ -26,7 +26,7 @@ task:
         report_type: warning
         verify_type: between
         verify: "[ 65536 ,16777216 ]"
-        err_msg: 'net.core.rmem_default  : #{parameter} , which is not recommended. Set it within the range of  65536 ≤ value ≤ 16777216'
+        err_msg: 'net.core.rmem_default: #{parameter}. recommended: 65536 ≤ value ≤ 16777216.'
     - type: get_system_parameter
       parameter: net.core.wmem_default
       result:
@@ -34,7 +34,7 @@ task:
         report_type: warning
         verify_type: between
         verify: "[ 65536,16777216 ]"
-        err_msg: 'net.core.wmem_default  : #{parameter} , which is not recommended. Set it within the range of  65536 ≤ value ≤ 16777216'
+        err_msg: 'net.core.wmem_default: #{parameter}. recommended: 65536 ≤ value ≤ 16777216.'
     - type: get_system_parameter
       parameter: net.core.rmem_max
       result:
@@ -42,7 +42,7 @@ task:
         report_type: warning
         verify_type: between
         verify: "[ 8388608 ,16777216 ]"
-        err_msg: 'net.core.rmem_max : #{parameter} , which is not recommended. Set it within the range of  8388608 ≤ value ≤ 16777216'
+        err_msg: 'net.core.rmem_max : #{parameter}. recommended: 8388608 ≤ value ≤ 16777216.'
     - type: get_system_parameter
       parameter: net.core.wmem_max
       result:
@@ -50,7 +50,7 @@ task:
         report_type: warning
         verify_type: between
         verify: "[ 8388608,16777216 ]"
-        err_msg: 'net.core.wmem_max  : #{parameter} , which is not recommended. Set it within the range of  8388608 ≤ value ≤ 16777216'
+        err_msg: 'net.core.wmem_max: #{parameter}. recommended: 8388608 ≤ value ≤ 16777216.'
     - type: get_system_parameter
       parameter: net.ipv4.ip_forward
       result:
@@ -58,7 +58,7 @@ task:
         report_type: warning
         verify_type: equal
         verify: 0
-        err_msg: 'net.ipv4.ip_forward : #{parameter} , which is not recommended. Set it within the range of  0'
+        err_msg: 'net.ipv4.ip_forward : #{parameter}. recommended: 0.'
     - type: get_system_parameter
       parameter: net.ipv4.tcp_tw_recycle
       result:
@@ -66,7 +66,7 @@ task:
         report_type: warning
         verify_type: equal
         verify: 1
-        err_msg: 'net.ipv4.tcp_tw_recycle : #{parameter} , which is not recommended. Set it within the range of  1'
+        err_msg: 'net.ipv4.tcp_tw_recycle : #{parameter}. recommended: 1.'
 
     - type: get_system_parameter
       parameter: net.ipv4.conf.default.rp_filter
@@ -75,7 +75,7 @@ task:
         report_type: warning
         verify_type: equal
         verify: 1
-        err_msg: 'net.ipv4.conf.default.rp_filter : #{parameter} , which is not recommended. Set it within the range of  1'
+        err_msg: 'net.ipv4.conf.default.rp_filter : #{parameter}. recommended: 1.'
     - type: get_system_parameter
       parameter: net.ipv4.conf.default.accept_source_route
       result:
@@ -83,7 +83,7 @@ task:
         report_type: warning
         verify_type: equal
         verify: 0
-        err_msg: 'net.ipv4.conf.default.accept_source_route  : #{parameter} , which is not recommended. Set it within the range of  0'
+        err_msg: 'net.ipv4.conf.default.accept_source_route: #{parameter}. recommended: 0.'
     - type: get_system_parameter
       parameter: net.ipv4.tcp_syncookies
       result:
@@ -91,7 +91,7 @@ task:
         report_type: warning
         verify_type: equal
         verify: 1
-        err_msg: 'net.ipv4.tcp_syncookies  : #{parameter} , which is not recommended. Set it within the range of  1'
+        err_msg: 'net.ipv4.tcp_syncookies: #{parameter}. recommended: 1.'
     - type: get_system_parameter
       parameter: net.ipv4.tcp_max_syn_backlog
       result:
@@ -99,97 +99,97 @@ task:
         report_type: warning
         verify_type: between
         verify: "[1024,16384]"
-        err_msg: 'net.ipv4.tcp_max_syn_backlog : #{parameter} , which is not recommended. Set it within the range of  1024 ≤ value ≤ 16384'
+        err_msg: 'net.ipv4.tcp_max_syn_backlog : #{parameter}. recommended: 1024 ≤ value ≤ 16384.'
     - type: get_system_parameter
       parameter: net.ipv4.tcp_fin_timeout
       result:
         set_value: parameter
         report_type: warning
         verify: "[ 15 -le  ${parameter}  ] && [ ${parameter} -le 60 ]"
-        err_msg: 'net.ipv4.tcp_fin_timeout : #{parameter} , which is not recommended. Set it within the range of  15 ≤ value ≤ 60'
+        err_msg: 'net.ipv4.tcp_fin_timeout : #{parameter}. recommended: 15 ≤ value ≤ 60.'
     - type: get_system_parameter
       parameter: net.ipv4.tcp_tw_reuse
       result:
         set_value: parameter
         report_type: warning
         verify: "[ ${parameter} -eq 1 ]"
-        err_msg: 'net.ipv4.tcp_tw_reuse  : #{parameter} , which is not recommended. Set it within the range of  1'
+        err_msg: 'net.ipv4.tcp_tw_reuse: #{parameter}. recommended: 1'
     - type: get_system_parameter
       parameter: net.ipv4.tcp_slow_start_after_idle
       result:
         set_value: parameter
         report_type: warning
         verify: "[ ${parameter} -eq 0 ]"
-        err_msg: 'net.ipv4.tcp_slow_start_after_idle  : #{parameter} , which is not recommended. Set it within the range of  0'
+        err_msg: 'net.ipv4.tcp_slow_start_after_idle: #{parameter}. recommended: 0.'
     - type: get_system_parameter
       parameter: vm.swappiness
       result:
         set_value: parameter
         report_type: warning
         verify: "[ ${parameter} -eq 0 ]"
-        err_msg: 'vm.swappiness : #{parameter} , which is not recommended. Set it within the range of  0'
+        err_msg: 'vm.swappiness : #{parameter}. recommended: 0'
     - type: get_system_parameter
       parameter: vm.min_free_kbytes
       result:
         set_value: parameter
         report_type: warning
         verify: "[ 32768 -le  ${parameter}  ] && [ ${parameter} -le 2097152 ]"
-        err_msg: 'vm.min_free_kbytes : #{parameter} , which is not recommended. Set it within the range of  32768 ≤ value ≤ 2097152'
+        err_msg: 'vm.min_free_kbytes : #{parameter}. recommended: 32768 ≤ value ≤ 2097152.'
     - type: get_system_parameter
       parameter: vm.max_map_count
       result:
         set_value: parameter
         report_type: warning
         verify: "[ 327680  -le  ${parameter}  ] && [ ${parameter}  -le  1000000 ]"
-        err_msg: 'vm.max_map_count : #{parameter} , which is not recommended.Unreasonable vm.max_map_count configuration may cause serious memory leaks. Set it within the range of  327680 ≤ value ≤ 1000000 '
+        err_msg: 'vm.max_map_count : #{parameter}. recommended:327680 ≤ value ≤ 1000000.'
     - type: get_system_parameter
       parameter: vm.overcommit_memory
       result:
         set_value: parameter
         report_type: warning
         verify: "[ ${parameter} -eq 0 ]"
-        err_msg: 'vm.overcommit_memory : #{parameter} , which is not recommended. Set it within the range of  0 '
+        err_msg: 'vm.overcommit_memory : #{parameter}. recommended: 0.'
     - type: get_system_parameter
       parameter: vm.nr_hugepages
       result:
         set_value: parameter
         report_type: warning
         verify: "[ ${parameter} -eq 0 ]"
-        err_msg: 'vm.nr_hugepages : #{parameter} , which is not recommended. Set it within the range of  0 '
+        err_msg: 'vm.nr_hugepages : #{parameter}. recommended: 0'
     - type: get_system_parameter
       parameter: fs.aio-max-nr
       result:
         set_value: parameter
         report_type: warning
         verify: "[ 1048576  -le  ${parameter} ]"
-        err_msg: 'fs.aio-max-nr : #{parameter} is a non recommended value, recommended value : #{parameter} is ≥ 1048576'
+        err_msg: 'fs.aio-max-nr : #{parameter}. recommended: #{parameter} is ≥ 1048576.'
     - type: get_system_parameter
       parameter: kernel.numa_balancing
       result:
         set_value: parameter
         report_type: warning
         verify: "[ ${parameter} -eq 0 ]"
-        err_msg: 'kernel.numa_balancing : #{parameter} , which is not recommended. Set it within the range of  0 '
+        err_msg: 'kernel.numa_balancing : #{parameter}. recommended: 0.'
     - type: get_system_parameter
       parameter: vm.zone_reclaim_mode
       result:
         set_value: parameter
         report_type: warning
         verify: "[ ${parameter} -eq 0 ]"
-        err_msg: 'vm.zone_reclaim_mode : #{parameter} , which is not recommended. Set it within the range of  0 '
+        err_msg: 'vm.zone_reclaim_mode : #{parameter}. recommended: 0.'
     - type: get_system_parameter
       parameter: fs.file-max
       result:
         set_value: parameter
         report_type: warning
         verify: "[ 6573688  -le  ${parameter} ]"
-        err_msg: 'fs.file-max: #{parameter} is a non recommended value, recommended value : #{parameter} is ≥ 6573688'
+        err_msg: 'fs.file-max: #{parameter}. recommended: #{parameter} is ≥ 6573688.'
     - type: get_system_parameter
       parameter: fs.pipe-user-pages-soft
       result:
         set_value: parameter
         report_type: warning
         verify: "[ 0 -eq  ${parameter} ]"
-        err_msg: 'fs.pipe-user-pages-soft : #{parameter} is a non recommended value, recommended value  is 0'
+        err_msg: 'fs.pipe-user-pages-soft : #{parameter}. recommended: 0.'
 
 
diff --git a/handler/checker/tasks/observer/system/parameter_ip_local_port_range.yaml b/handler/checker/tasks/observer/system/parameter_ip_local_port_range.yaml
index 9a83b86a..29e41c99 100644
--- a/handler/checker/tasks/observer/system/parameter_ip_local_port_range.yaml
+++ b/handler/checker/tasks/observer/system/parameter_ip_local_port_range.yaml
@@ -8,7 +8,7 @@ task:
       result:
         set_value: ip_local_port_range
         verify: '[[ -n "$ip_local_port_range" && "$ip_local_port_range" != "-1" ]]'
-        err_msg: "ip_local_port_range is #{ip_local_port_range} . Please check net.ipv4.ip_local_port_range on your node"
+        err_msg: "ip_local_port_range : #{ip_local_port_range} . Please check net.ipv4.ip_local_port_range on your node"
     - type: ssh
       ssh: "echo \"#{ip_local_port_range}\" | awk '{print $1}'"
       result:
@@ -16,7 +16,7 @@ task:
         report_type: warning
         verify_type: equal
         verify: 3500
-        err_msg: 'ip_local_port_range_min : #{ip_local_port_range_min} is a non recommended value, recommended value is 3500'
+        err_msg: 'ip_local_port_range_min : #{ip_local_port_range_min}. recommended: 3500'
     - type: ssh
       ssh: "echo \"#{ip_local_port_range}\" | awk '{print $2}'"
       result:
@@ -24,4 +24,4 @@ task:
         report_type: warning
         verify_type: equal
         verify: 65535
-        err_msg: 'ip_local_port_range_max : #{ip_local_port_range_max} is a non recommended value, recommended value is 65535'
\ No newline at end of file
+        err_msg: 'ip_local_port_range_max : #{ip_local_port_range_max}. recommended: 65535'
\ No newline at end of file
diff --git a/handler/checker/tasks/observer/system/parameter_tcp_rmem.yaml b/handler/checker/tasks/observer/system/parameter_tcp_rmem.yaml
index 2cd140cd..9bc4a880 100644
--- a/handler/checker/tasks/observer/system/parameter_tcp_rmem.yaml
+++ b/handler/checker/tasks/observer/system/parameter_tcp_rmem.yaml
@@ -16,7 +16,7 @@ task:
         report_type: warning
         verify_type: between
         verify: "[4096,8192]"
-        err_msg: 'net.ipv4.tcp_rmem_min : #{tcp_rmem_min} is a non recommended value, recommended value is 4096 ≤ min ≤ 8192'
+        err_msg: 'net.ipv4.tcp_rmem_min : #{tcp_rmem_min}. recommended: 4096 ≤ min ≤ 8192'
     - type: ssh
       ssh: "echo \"#{tcp_rmem}\" | awk '{print $2}'"
       result:
@@ -24,7 +24,7 @@ task:
         report_type: warning
         verify_type: between
         verify: "[65536,131072]"
-        err_msg: 'net.ipv4.tcp_rmem_default : #{tcp_rmem_default}. net.ipv4.tcp_rmem_default from net.ipv4.tcp_rmem. It is a non recommended value, recommended value :is 65536 ≤ default≤ 131072'
+        err_msg: 'net.ipv4.tcp_rmem_default : #{tcp_rmem_default}. net.ipv4.tcp_rmem_default from net.ipv4.tcp_rmem. recommended: is 65536 ≤ default≤ 131072'
     - type: ssh
       ssh: "echo \"#{tcp_rmem}\" | awk '{print $3}'"
       result:
@@ -32,4 +32,4 @@ task:
         report_type: warning
         verify_type: between
         verify: "[8388608,16777216]"
-        err_msg: 'net.ipv4.tcp_rmem_max : #{tcp_rmem_max}. net.ipv4.tcp_rmem_max from net.ipv4.tcp_rmem. It is a non recommended value, recommended value is 65536 ≤ max≤ 131072'
+        err_msg: 'net.ipv4.tcp_rmem_max : #{tcp_rmem_max}. net.ipv4.tcp_rmem_max from net.ipv4.tcp_rmem. recommended: 65536 ≤ max≤ 131072'
diff --git a/handler/checker/tasks/observer/system/parameter_tcp_wmem.yaml b/handler/checker/tasks/observer/system/parameter_tcp_wmem.yaml
index 76eadaa9..9ed4a2fc 100644
--- a/handler/checker/tasks/observer/system/parameter_tcp_wmem.yaml
+++ b/handler/checker/tasks/observer/system/parameter_tcp_wmem.yaml
@@ -14,7 +14,7 @@ task:
         report_type: warning
         verify_type: between
         verify: "[4096,8192]"
-        err_msg: 'net.ipv4.tcp_wmem_min : #{tcp_wmem_min} is a non recommended value, recommended value is 4096 ≤ min ≤ 8192'
+        err_msg: 'net.ipv4.tcp_wmem_min : #{tcp_wmem_min}. recommended: 4096 ≤ min ≤ 8192'
     - type: ssh
       ssh: "echo \"#{tcp_wmem}\" | awk '{print $2}'"
       result:
@@ -22,7 +22,7 @@ task:
         report_type: warning
         verify_type: between
         verify: "[65536,131072]"
-        err_msg: 'net.ipv4.tcp_wmem_default : #{tcp_wmem_default} is a non recommended value, recommended value :is 65536 ≤ default≤ 131072'
+        err_msg: 'net.ipv4.tcp_wmem_default : #{tcp_wmem_default}. recommended: is 65536 ≤ default≤ 131072'
     - type: ssh
       ssh: "echo \"#{tcp_wmem}\" | awk '{print $3}'"
       result:
@@ -30,4 +30,4 @@ task:
         report_type: warning
         verify_type: between
         verify: "[8388608,16777216]"
-        err_msg: 'net.ipv4.tcp_wmem_max : #{tcp_wmem_max} is a non recommended value, recommended value is 65536 ≤ max≤ 131072'
+        err_msg: 'net.ipv4.tcp_wmem_max : #{tcp_wmem_max}. recommended: 65536 ≤ max≤ 131072'
diff --git a/handler/checker/tasks/observer/system/ulimit_parameter.yaml b/handler/checker/tasks/observer/system/ulimit_parameter.yaml
index 08eb0ea3..778259c5 100644
--- a/handler/checker/tasks/observer/system/ulimit_parameter.yaml
+++ b/handler/checker/tasks/observer/system/ulimit_parameter.yaml
@@ -8,21 +8,21 @@ task:
         set_value: parameter
         report_type: warning
         verify: "[ 'unlimited' == ${parameter} ]"
-        err_msg: 'On ip : #{remote_ip}, ulimit -c is #{parameter} . It is a non recommended value, and the recommended value is unlimited. Please refer to the official website document for the configuration method'
+        err_msg: 'On ip : #{remote_ip}, ulimit -c is #{parameter} . recommended: unlimited.'
     - type: ssh
       ssh: ulimit -u
       result:
         set_value: parameter
         report_type: warning
         verify: "[ '655360' == ${parameter} ]"
-        err_msg: 'On ip : #{remote_ip}, ulimit -u is #{parameter} . It is a non recommended value, and the recommended value is 655360. Please refer to the official website document for the configuration method'
+        err_msg: 'On ip : #{remote_ip}, ulimit -u is #{parameter} . recommended: 655360.'
     - type: ssh
       ssh: ulimit -s
       result:
         set_value: parameter
         report_type: warning
         verify: "[ 'unlimited' == ${parameter} ]"
-        err_msg: 'On ip : #{remote_ip}, ulimit -s is #{parameter} . It is a non recommended value, and the recommended value is unlimited. Please refer to the official website document for the configuration method'
+        err_msg: 'On ip : #{remote_ip}, ulimit -s is #{parameter} . recommended: unlimited.'
     - type: ssh
       ssh: ulimit -n
       result:
@@ -30,4 +30,4 @@ task:
         report_type: warning
         verify_type: equal
         verify: 655350
-        err_msg: 'On ip : #{remote_ip}, ulimit -n is #{parameter} . It is a non recommended value, and the recommended value is unlimited. Please refer to the official website document for the configuration method'
+        err_msg: 'On ip : #{remote_ip}, ulimit -n is #{parameter} . recommended: unlimited.'
diff --git a/handler/gather/gather_obproxy_log.py b/handler/gather/gather_obproxy_log.py
index 603097e0..dcf0b769 100644
--- a/handler/gather/gather_obproxy_log.py
+++ b/handler/gather/gather_obproxy_log.py
@@ -249,7 +249,7 @@ def __get_log_name(self, ssh_helper, node):
                 self.scope == "obproxy_limit" or self.scope == "obproxy_slow" or self.scope == "obproxy_diagnosis" or self.scope == "obproxy_error":
             get_obproxy_log = "ls -1 -F %s/*%s.*log* | awk -F '/' '{print $NF}'" % (log_path, self.scope)
         else:
-            get_obproxy_log = "ls -1 -F %s/obproxy.*log* %s/obproxy_error.*log* %s/obproxy_stat.*log* %s/obproxy_digest.*log* %s/obproxy_limit.*log* %s/obproxy_slow.*log* | awk -F '/' '{print $NF}'" % (log_path, log_path, log_path, log_path, log_path, log_path)
+            get_obproxy_log = "ls -1 -F %s/obproxy.*log* %s/obproxy_error.*log* %s/obproxy_stat.*log* %s/obproxy_digest.*log* %s/obproxy_limit.*log* %s/obproxy_slow.*log* %s/obproxy_diagnosis.*log*| awk -F '/' '{print $NF}'" % (log_path, log_path, log_path, log_path, log_path, log_path,log_path)
         if self.is_ssh:
             log_files = SshClient(self.stdio).run(ssh_helper, get_obproxy_log).strip()
         else:
diff --git a/handler/rca/rca_handler.py b/handler/rca/rca_handler.py
index 3a004891..94d4d017 100644
--- a/handler/rca/rca_handler.py
+++ b/handler/rca/rca_handler.py
@@ -252,6 +252,15 @@ def get_scene_info(self):
         raise Exception("rca ({0})  scene.get_scene_info() undefined".format(type(self).__name__))
     def export_result(self):
         return self.Result.export()
+    def get_all_tenants_id(self):
+        try:
+            if self.ob_connector is None:
+                raise Exception("ob_connector is None")
+            all_tenant_id_data=self.ob_connector.execute_sql("select tenant_id from oceanbase.__all_tenant;")[0]
+            return all_tenant_id_data
+        except Exception as e:
+            raise Exception("run rca's get_all_tenants_id. Exception: {0}".format(e))
+
 
 class Result:
 
diff --git a/handler/rca/scene/log_error_scene.py b/handler/rca/scene/log_error_scene.py
index 0973db65..39ab8929 100644
--- a/handler/rca/scene/log_error_scene.py
+++ b/handler/rca/scene/log_error_scene.py
@@ -12,7 +12,7 @@
 
 """
 @time: 2024/04/16
-@file: no_leader_scene.py
+@file: log_error_scene.py
 @desc:
 """
 import os
@@ -39,8 +39,6 @@ def init(self, context):
         if not (observer_version == "4.0.0.0" or StringUtils.compare_versions_greater(observer_version, "4.0.0.0")):
             self.stdio.error("observer version is {0}, which is less than 4.0.0.0.".format(observer_version))
             raise RCAInitException("observer version is {0}, which is less than 4.0.0.0.".format(observer_version))
-        # if self.ob_connector is None:
-        #     raise RCAInitException("ob_connector is None. Please check the NODES conf.")
         self.verbose("observer version is {0}.".format(observer_version))
         if self.ob_connector is None:
             raise RCAInitException("ob_connector is None. Please check the NODES conf.")
@@ -120,7 +118,6 @@ def execute_by_tenant_id(self, tenant_id, record):
             if step_next_tag is False:
                 self.verbose("step_next_tag is false")
                 return
-            record.add_record("start step3")
             return
 
 

From 7089ec3a2e03e6fb095d37bfc37b53dc97cd1615 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Wed, 24 Apr 2024 18:06:38 +0800
Subject: [PATCH 09/30] add check's cases about avx2

---
 .../tasks/observer/system/instruction_set_avx2.yaml   | 11 +++++++++++
 1 file changed, 11 insertions(+)
 create mode 100644 handler/checker/tasks/observer/system/instruction_set_avx2.yaml

diff --git a/handler/checker/tasks/observer/system/instruction_set_avx2.yaml b/handler/checker/tasks/observer/system/instruction_set_avx2.yaml
new file mode 100644
index 00000000..a17a1e00
--- /dev/null
+++ b/handler/checker/tasks/observer/system/instruction_set_avx2.yaml
@@ -0,0 +1,11 @@
+info: 'Check the flags of cpu'
+task:
+  - steps:
+      - type: ssh
+        ssh: "lscpu |grep Flags"
+        result:
+          set_value: cpu_flags
+          verify: " [[ $cpu_flags == *avx2* ]] "
+          err_msg: 'clock_source: #{clock_source}. recommended: tsc. Uneven CPU utilization during pressure testing resulted in low TPS during pressure testing'
+
+

From c81e94b6f8801a24f57a36180c8916ca53846257 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Wed, 24 Apr 2024 20:52:47 +0800
Subject: [PATCH 10/30] add check's cases about core_pattern tenant_number

---
 .../tasks/observer/cluster/tenant_number.yaml | 19 +++++++++++++++++++
 .../tasks/observer/system/core_pattern.yaml   | 11 +++++++++++
 2 files changed, 30 insertions(+)
 create mode 100644 handler/checker/tasks/observer/cluster/tenant_number.yaml
 create mode 100644 handler/checker/tasks/observer/system/core_pattern.yaml

diff --git a/handler/checker/tasks/observer/cluster/tenant_number.yaml b/handler/checker/tasks/observer/cluster/tenant_number.yaml
new file mode 100644
index 00000000..3c725440
--- /dev/null
+++ b/handler/checker/tasks/observer/cluster/tenant_number.yaml
@@ -0,0 +1,19 @@
+info: "Check the number of tenant"
+task:
+  - version: "[4.0.0.0,*]"
+    steps:
+    - type: sql
+      sql: 'select count(0)/2 from oceanbase.__all_tenant where tenant_id>1000;'
+      result:
+        set_value: tenant_nu
+        verify_type: max
+        verify: 100
+        err_msg: "The number of tenants: #{tenant_nu}.recommended: tenant_nu<50"
+    - type: sql
+      sql: 'select count(0)/2 from oceanbase.__all_tenant where tenant_id>1000;'
+      result:
+        set_value: tenant_nu
+        verify_type: max
+        report_type: warning
+        verify: 50
+        err_msg: "The number of tenants: #{tenant_nu}.recommended: tenant_nu<50"
\ No newline at end of file
diff --git a/handler/checker/tasks/observer/system/core_pattern.yaml b/handler/checker/tasks/observer/system/core_pattern.yaml
new file mode 100644
index 00000000..ba0e3f9a
--- /dev/null
+++ b/handler/checker/tasks/observer/system/core_pattern.yaml
@@ -0,0 +1,11 @@
+info: 'Check  kernel.core_pattern'
+task:
+  - steps:
+      - type: get_system_parameter
+        parameter: kernel.core_pattern
+        result:
+          set_value: core_pattern
+          verify: "[[ $core_pattern == *" "* ]]"
+          err_msg: 'clock_source: #{clock_source}. recommended: tsc. Uneven CPU utilization during pressure testing resulted in low TPS during pressure testing'
+
+

From f91d7515d486568c067dc3a9a72c96782adc49c3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Thu, 25 Apr 2024 10:22:53 +0800
Subject: [PATCH 11/30] fix check yaml

---
 handler/checker/tasks/observer/cluster/sys_log_level.yaml | 6 ++----
 handler/checker/tasks/observer/system/core_pattern.yaml   | 4 +---
 2 files changed, 3 insertions(+), 7 deletions(-)

diff --git a/handler/checker/tasks/observer/cluster/sys_log_level.yaml b/handler/checker/tasks/observer/cluster/sys_log_level.yaml
index 1d67338c..1063d34e 100644
--- a/handler/checker/tasks/observer/cluster/sys_log_level.yaml
+++ b/handler/checker/tasks/observer/cluster/sys_log_level.yaml
@@ -6,9 +6,8 @@ task:
       sql: 'SELECT value FROM  oceanbase.__all_virtual_sys_parameter_stat where name  like "%syslog_level%";'
       result:
         set_value: sys_log_level
-        verify_type: equal
         report_type: warning
-        verify: '[[ ${sys_log_level} == "WDIAG"]]'
+        verify: '[[ $sys_log_level == "WDIAG" ]]'
         err_msg: "on 4.x, the recommended value for sys_log_level is WDIAG"
 
   - version: "[3.0.0,4.0.0.0)"
@@ -17,7 +16,6 @@ task:
       sql: 'SELECT value FROM  oceanbase.__all_virtual_sys_parameter_stat where name  like "%syslog_level%";'
       result:
         set_value: sys_log_level
-        verify_type: equal
         report_type: warning
-        verify: '[[ ${sys_log_level} == "INFO"]]'
+        verify: '[[ $sys_log_level == "INFO" ]]'
         err_msg: "on 3.x, the recommended value for sys_log_level is INFO"
diff --git a/handler/checker/tasks/observer/system/core_pattern.yaml b/handler/checker/tasks/observer/system/core_pattern.yaml
index ba0e3f9a..a226347f 100644
--- a/handler/checker/tasks/observer/system/core_pattern.yaml
+++ b/handler/checker/tasks/observer/system/core_pattern.yaml
@@ -5,7 +5,5 @@ task:
         parameter: kernel.core_pattern
         result:
           set_value: core_pattern
-          verify: "[[ $core_pattern == *" "* ]]"
+          verify: '[[ $core_pattern == *" "* ]]'
           err_msg: 'clock_source: #{clock_source}. recommended: tsc. Uneven CPU utilization during pressure testing resulted in low TPS during pressure testing'
-
-

From c4940d3d8a763635b3e0ac5d3c03c50961795007 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Thu, 25 Apr 2024 11:54:26 +0800
Subject: [PATCH 12/30] update clock_source.yaml

---
 handler/checker/tasks/observer/system/clock_source.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/handler/checker/tasks/observer/system/clock_source.yaml b/handler/checker/tasks/observer/system/clock_source.yaml
index e494f5d9..ce9950a2 100644
--- a/handler/checker/tasks/observer/system/clock_source.yaml
+++ b/handler/checker/tasks/observer/system/clock_source.yaml
@@ -5,7 +5,7 @@ task:
         ssh: "cat /sys/devices/system/clocksource/clocksource0/current_clocksource"
         result:
           set_value: clock_source
-          verify: "[ \"${clock_source}\" == \"tsc\" ]"
+          verify: "[[ \"${clock_source}\" == \"tsc\" || \"${clock_source}\" == \"arch_sys_counter\" || \"${clock_source}\" == \"kvm-clock\" ]]"
           err_msg: 'clock_source: #{clock_source}. recommended: tsc. Uneven CPU utilization during pressure testing resulted in low TPS during pressure testing'
 
 

From 9db5d05774aa14109863f535f98e278438abe93d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Thu, 25 Apr 2024 14:45:36 +0800
Subject: [PATCH 13/30] update build_before

---
 handler/checker/tasks/observer_check_package.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/handler/checker/tasks/observer_check_package.yaml b/handler/checker/tasks/observer_check_package.yaml
index f0a6b356..4b8f132b 100644
--- a/handler/checker/tasks/observer_check_package.yaml
+++ b/handler/checker/tasks/observer_check_package.yaml
@@ -2,7 +2,7 @@ ad:
   info_en: "Test and inspection tasks"
   info_cn: "测试巡检任务"
   tasks:
-    - system.parameter
+    - system.*
 build_before:
   info_en: "Deployment environment check"
   info_cn: "部署环境检查"

From 41b1b3aaad3963ccbda4019a18a7fb14aad5cb78 Mon Sep 17 00:00:00 2001
From: Teingi <jingshun.tq@antgroup.com>
Date: Thu, 25 Apr 2024 15:14:09 +0800
Subject: [PATCH 14/30] update README

---
 README-CN.md | 22 +++++++++++-----------
 README.md    | 22 +++++++++++-----------
 2 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/README-CN.md b/README-CN.md
index f790fc7e..fe99b285 100644
--- a/README-CN.md
+++ b/README-CN.md
@@ -1,18 +1,18 @@
 <p align="center">
-    <a href="https://github.com/oceanbase/oceanbase-diagnostic-tool/blob/master/LICENSE">
+    <a href="https://github.com/oceanbase/obdiag/blob/master/LICENSE">
         <img alt="license" src="https://img.shields.io/badge/license-MulanPubL--2.0-blue" />
     </a>
-    <a href="https://github.com/oceanbase/oceanbase-diagnostic-tool/releases/latest">
-        <img alt="license" src="https://img.shields.io/badge/dynamic/json?color=blue&label=release&query=tag_name&url=https%3A%2F%2Fapi.github.com%2Frepos%2Foceanbase%2Foceanbase-diagnostic-tool%2Freleases%2Flatest" />
+    <a href="https://github.com/oceanbase/obdiag/releases/latest">
+        <img alt="license" src="https://img.shields.io/badge/dynamic/json?color=blue&label=release&query=tag_name&url=https%3A%2F%2Fapi.github.com%2Frepos%2Foceanbase%2Fobdiag%2Freleases%2Flatest" />
     </a>
     <a href="https://img.shields.io/badge/python%20-3.8.0%2B-blue.svg">
         <img alt="pyversions" src="https://img.shields.io/badge/python%20-3.8.0%2B-blue.svg" />
     </a>
-    <a href="https://github.com/oceanbase/oceanbase-diagnostic-tool">
-        <img alt="stars" src="https://img.shields.io/badge/dynamic/json?color=blue&label=stars&query=stargazers_count&url=https%3A%2F%2Fapi.github.com%2Frepos%2Foceanbase%2Foceanbase-diagnostic-tool" />
+    <a href="https://github.com/oceanbase/obdiag">
+        <img alt="stars" src="https://img.shields.io/badge/dynamic/json?color=blue&label=stars&query=stargazers_count&url=https%3A%2F%2Fapi.github.com%2Frepos%2Foceanbase%2Fobdiag" />
     </a>
-    <a href="https://github.com/oceanbase/oceanbase-diagnostic-tool">
-        <img alt="forks" src="https://img.shields.io/badge/dynamic/json?color=blue&label=forks&query=forks&url=https%3A%2F%2Fapi.github.com%2Frepos%2Foceanbase%2Foceanbase-diagnostic-tool" />
+    <a href="https://github.com/oceanbase/obdiag">
+        <img alt="forks" src="https://img.shields.io/badge/dynamic/json?color=blue&label=forks&query=forks&url=https%3A%2F%2Fapi.github.com%2Frepos%2Foceanbase%2Fobdiag" />
     </a>
     <a href="https://www.oceanbase.com/docs/obdiag-cn">
         <img alt="Chinese doc" src="https://img.shields.io/badge/文档-简体中文-blue" />
@@ -65,9 +65,9 @@ obdiag config -h <db_host> -u <sys_user> [-p password] [-P port]
 # 参与贡献
 
 obdiag 期望构建一个开放的社区，我们欢迎任何形式的贡献，您可以：
-- 通过 [Issues](https://github.com/oceanbase/oceanbase-diagnostic-tool/issues) 提交 bug。
-- 通过 [Discussion](https://github.com/oceanbase/oceanbase-diagnostic-tool/discussions) 参与或发起讨论。
-- 通过 [Pull requests](https://github.com/oceanbase/oceanbase-diagnostic-tool/pulls) 提交问题修复或者功能特性。
+- 通过 [Issues](https://github.com/oceanbase/obdiag/issues) 提交 bug。
+- 通过 [Discussion](https://github.com/oceanbase/obdiag/discussions) 参与或发起讨论。
+- 通过 [Pull requests](https://github.com/oceanbase/obdiag/pulls) 提交问题修复或者功能特性。
 
 # Roadmap Ahead
 
@@ -95,6 +95,6 @@ OceanBase Diagnostic Tool 使用 [MulanPSL - 2.0](http://license.coscl.org.cn/Mu
 
 如果您在使用 OceanBase LogProxy 时遇到任何问题，欢迎联系我们寻求帮助：
 
-- [GitHub Issue](https://github.com/oceanbase/oceanbase-diagnostic-tool/issues)
+- [GitHub Issue](https://github.com/oceanbase/obdiag/issues)
 - [官方网站](https://www.oceanbase.com/docs/obdiag-cn)
 - obdiag SIG 微信号: obdiagsig
\ No newline at end of file
diff --git a/README.md b/README.md
index 54e4394c..376402e1 100644
--- a/README.md
+++ b/README.md
@@ -1,20 +1,20 @@
 English | [中文版](README-CN.md)
 
 <p align="center">
-    <a href="https://github.com/oceanbase/oceanbase-diagnostic-tool/blob/master/LICENSE">
+    <a href="https://github.com/oceanbase/obdiag/blob/master/LICENSE">
         <img alt="license" src="https://img.shields.io/badge/license-MulanPubL--2.0-blue" />
     </a>
-    <a href="https://github.com/oceanbase/oceanbase-diagnostic-tool/releases/latest">
-        <img alt="license" src="https://img.shields.io/badge/dynamic/json?color=blue&label=release&query=tag_name&url=https%3A%2F%2Fapi.github.com%2Frepos%2Foceanbase%2Foceanbase-diagnostic-tool%2Freleases%2Flatest" />
+    <a href="https://github.com/oceanbase/obdiag/releases/latest">
+        <img alt="license" src="https://img.shields.io/badge/dynamic/json?color=blue&label=release&query=tag_name&url=https%3A%2F%2Fapi.github.com%2Frepos%2Foceanbase%2Fobdiag%2Freleases%2Flatest" />
     </a>
     <a href="https://img.shields.io/badge/python%20-3.8.0%2B-blue.svg">
         <img alt="pyversions" src="https://img.shields.io/badge/python%20-3.8.0%2B-blue.svg" />
     </a>
-    <a href="https://github.com/oceanbase/oceanbase-diagnostic-tool">
-        <img alt="stars" src="https://img.shields.io/badge/dynamic/json?color=blue&label=stars&query=stargazers_count&url=https%3A%2F%2Fapi.github.com%2Frepos%2Foceanbase%2Foceanbase-diagnostic-tool" />
+    <a href="https://github.com/oceanbase/obdiag">
+        <img alt="stars" src="https://img.shields.io/badge/dynamic/json?color=blue&label=stars&query=stargazers_count&url=https%3A%2F%2Fapi.github.com%2Frepos%2Foceanbase%2Fobdiag" />
     </a>
-    <a href="https://github.com/oceanbase/oceanbase-diagnostic-tool">
-        <img alt="forks" src="https://img.shields.io/badge/dynamic/json?color=blue&label=forks&query=forks&url=https%3A%2F%2Fapi.github.com%2Frepos%2Foceanbase%2Foceanbase-diagnostic-tool" />
+    <a href="https://github.com/oceanbase/obdiag">
+        <img alt="forks" src="https://img.shields.io/badge/dynamic/json?color=blue&label=forks&query=forks&url=https%3A%2F%2Fapi.github.com%2Frepos%2Foceanbase%2Fobdiag" />
     </a>
     <a href="https://www.oceanbase.com/docs/obdiag-cn">
         <img alt="Chinese doc" src="https://img.shields.io/badge/文档-简体中文-blue" />
@@ -67,9 +67,9 @@ For more details, please refer to [Official docs](https://www.oceanbase.com/docs
 
 obdiag envisions an open community. We welcome your contributions in any form:
 
-- Report bugs through [Issues](https://github.com/oceanbase/oceanbase-diagnostic-tool/issues).
-- Participate in or initiate discussions via [Discussion](https://github.com/oceanbase/oceanbase-diagnostic-tool/discussions).
-- Contribute bug fixes or new features through [Pull requests](https://github.com/oceanbase/oceanbase-diagnostic-tool/pulls).
+- Report bugs through [Issues](https://github.com/oceanbase/obdiag/issues).
+- Participate in or initiate discussions via [Discussion](https://github.com/oceanbase/obdiag/discussions).
+- Contribute bug fixes or new features through [Pull requests](https://github.com/oceanbase/obdiag/pulls).
 
 
 
@@ -97,7 +97,7 @@ distribute the source code, please obey the MulanPubL - 2.0 license.
 
 In case you have any problems when using obdiag, welcome reach out for help:
 
-- [GitHub Issue](https://github.com/oceanbase/oceanbase-diagnostic-tool/issues)
+- [GitHub Issue](https://github.com/oceanbase/obdiag/issues)
 - [Official Website](https://www.oceanbase.com/docs/obdiag-cn)
 - obdiag SIG WeChat: obdiagsig
 

From b42efafd5f25cd69089f27c22effdf93079e110c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Thu, 25 Apr 2024 18:07:51 +0800
Subject: [PATCH 15/30] test check

---
 handler/checker/check_handler.py             |  7 ++++-
 handler/checker/check_task.py                | 30 +++++++++++++++++---
 handler/checker/step/data_size.py            |  2 +-
 handler/checker/step/get_system_parameter.py |  2 +-
 handler/checker/step/sql.py                  |  4 +--
 handler/checker/step/ssh.py                  |  2 +-
 handler/checker/step/stepbase.py             | 11 +++----
 7 files changed, 43 insertions(+), 15 deletions(-)

diff --git a/handler/checker/check_handler.py b/handler/checker/check_handler.py
index c7477a52..7bd249f3 100644
--- a/handler/checker/check_handler.py
+++ b/handler/checker/check_handler.py
@@ -17,6 +17,8 @@
 """
 
 import os
+import time
+
 import yaml
 
 from common.ob_connector import OBConnector
@@ -229,6 +231,7 @@ def execute_one(self, task_name):
             raise CheckException("execute_one Exception : {0}".format(e))
 
     def execute(self):
+        start_time = time.time()
         try:
             self.stdio.verbose(
                 "execute_all_tasks. the number of tasks is {0} ,tasks is {1}".format(len(self.tasks.keys()),
@@ -244,4 +247,6 @@ def execute(self):
         except CheckrReportException as e:
             self.stdio.error("Report error :{0}".format(e))
         except Exception as e:
-            self.stdio.error("Internal error :{0}".format(e))
\ No newline at end of file
+            self.stdio.error("Internal error :{0}".format(e))
+        end_time = time.time()
+        print("Total cost time is {0} s".format((end_time - start_time)))
\ No newline at end of file
diff --git a/handler/checker/check_task.py b/handler/checker/check_task.py
index 9605bfcf..b8db28e8 100644
--- a/handler/checker/check_task.py
+++ b/handler/checker/check_task.py
@@ -15,6 +15,9 @@
 @file: check_task.py
 @desc:
 """
+import threading
+
+from common.ob_connector import OBConnector
 from handler.checker.check_exception import StepResultFailException, \
     StepExecuteFailException, StepResultFalseException, TaskException
 from handler.checker.step.stepbase import StepBase
@@ -39,15 +42,30 @@ def execute(self):
         self.stdio.verbose("task_base execute")
         steps_nu = filter_by_version(self.task, self.cluster, self.stdio)
         if steps_nu < 0:
-            self.stdio.warn("{0} Unadapted by version. SKIP".format(self.task['name']))
+            self.stdio.warn("Unadapted by version. SKIP")
             self.report.add("Unadapted by version. SKIP", "warning")
             return "Unadapted by version.SKIP"
         self.stdio.verbose("filter_by_version is return {0}".format(steps_nu))
         if len(self.nodes) == 0:
             raise Exception("node is not exist")
-
+        # TODO: 这里的逻辑需要优化，如果一个节点执行失败了，那么后续的步骤就不会被执行了。
+        work_threads = []
         for node in self.nodes:
+            obConnector = OBConnector(ip=self.cluster.get("db_host"),
+                                      port=self.cluster.get("db_port"),
+                                      username=self.cluster.get("tenant_sys").get("user"),
+                                      password=self.cluster.get("tenant_sys").get("password"),
+                                      stdio=self.stdio,
+                                      timeout=10000)
+            t = threading.Thread(target=self.execute_one_node, args=(steps_nu,node,obConnector))
+            work_threads.append(t)
+            t.start()
+        for t in work_threads:
+            t.join()
 
+        self.stdio.verbose("task execute end")
+    def execute_one_node(self,steps_nu,node,obConnector):
+        try:
             self.stdio.verbose("run task in node: {0}".format(StringUtils.node_cut_passwd_for_log(node)))
             steps = self.task[steps_nu]
             nu = 1
@@ -56,7 +74,7 @@ def execute(self):
                     self.stdio.verbose("step nu: {0}".format(nu))
                     if len(self.cluster) == 0:
                         raise Exception("cluster is not exist")
-                    step_run = StepBase(self.context, step, node, self.cluster, self.task_variable_dict)
+                    step_run = StepBase(self.context, step, node, self.cluster, self.task_variable_dict,obConnector)
                     self.stdio.verbose("step nu: {0} initted, to execute".format(nu))
                     step_run.execute(self.report)
                     self.task_variable_dict = step_run.update_task_variable_dict()
@@ -78,4 +96,8 @@ def execute(self):
 
                 self.stdio.verbose("step nu: {0} execute end ".format(nu))
                 nu = nu + 1
-        self.stdio.verbose("task execute end")
+        except Exception as e:
+            self.stdio.error("TaskBase execute Exception: {0}".format(e))
+            raise e
+
+
diff --git a/handler/checker/step/data_size.py b/handler/checker/step/data_size.py
index b8d0ff0c..66dc2ff9 100644
--- a/handler/checker/step/data_size.py
+++ b/handler/checker/step/data_size.py
@@ -23,7 +23,7 @@
 
 
 class DataSizeHandler:
-    def __init__(self,context, step, node, task_variable_dict):
+    def __init__(self,context, step, node, task_variable_dict,obConnector):
         self.context = context
         self.stdio = context.stdio
         self.stdio.verbose("init DataSizeHandler")
diff --git a/handler/checker/step/get_system_parameter.py b/handler/checker/step/get_system_parameter.py
index af3341c1..29713ee3 100644
--- a/handler/checker/step/get_system_parameter.py
+++ b/handler/checker/step/get_system_parameter.py
@@ -23,7 +23,7 @@
 
 
 class GetSystemParameterHandler:
-    def __init__(self,context, step, node, task_variable_dict):
+    def __init__(self,context, step, node, task_variable_dict,obConnector):
         self.context = context
         self.stdio = context.stdio
         self.stdio.verbose("init GetSystemParameterHandler")
diff --git a/handler/checker/step/sql.py b/handler/checker/step/sql.py
index c55c50a7..7d846626 100644
--- a/handler/checker/step/sql.py
+++ b/handler/checker/step/sql.py
@@ -23,7 +23,7 @@
 
 
 class StepSQLHandler:
-    def __init__(self,context, step, task_variable_dict):
+    def __init__(self,context, step, task_variable_dict,obConnector):
         try:
             self.context = context
             self.stdio = context.stdio
@@ -32,7 +32,7 @@ def __init__(self,context, step, task_variable_dict):
             self.tenant_mode = None
             self.sys_database = None
             self.database = None
-            self.ob_connector=self.context.get_variable('check_obConnector')
+            self.ob_connector=obConnector
             if self.ob_connector is None:
                 raise Exception("self.ob_connector is None.")
         except Exception as e:
diff --git a/handler/checker/step/ssh.py b/handler/checker/step/ssh.py
index 282477e2..4e4c6368 100644
--- a/handler/checker/step/ssh.py
+++ b/handler/checker/step/ssh.py
@@ -23,7 +23,7 @@
 
 
 class SshHandler:
-    def __init__(self,context, step, node, task_variable_dict):
+    def __init__(self,context, step, node, task_variable_dict,obConnector):
         self.context = context
         self.stdio = context.stdio
         self.ssh_report_value = None
diff --git a/handler/checker/step/stepbase.py b/handler/checker/step/stepbase.py
index 3ec68d8e..aa479251 100644
--- a/handler/checker/step/stepbase.py
+++ b/handler/checker/step/stepbase.py
@@ -27,7 +27,7 @@
 
 
 class StepBase(object):
-    def __init__(self, context, step, node, cluster, task_variable_dict):
+    def __init__(self, context, step, node, cluster, task_variable_dict,obConnector):
         self.context = context
         self.stdio = context.stdio
         self.step = step
@@ -35,6 +35,7 @@ def __init__(self, context, step, node, cluster, task_variable_dict):
         self.cluster = cluster
         self.task_variable_dict = {}
         self.task_variable_dict = task_variable_dict
+        self.obConnector=obConnector
 
     def execute(self, report):
         no_cluster_name_msg = "(Please set ob_cluster_name or obproxy_cluster_name)"
@@ -54,13 +55,13 @@ def execute(self, report):
             if "type" not in self.step:
                 raise StepExecuteFailException("Missing field :type")
             if self.step["type"] == "get_system_parameter":
-                handler = GetSystemParameterHandler(self.context, self.step, self.node, self.task_variable_dict)
+                handler = GetSystemParameterHandler(self.context, self.step, self.node, self.task_variable_dict,self.obConnector)
             elif self.step["type"] == "ssh":
-                handler = SshHandler(self.context, self.step, self.node, self.task_variable_dict)
+                handler = SshHandler(self.context, self.step, self.node, self.task_variable_dict,self.obConnector)
             elif self.step["type"] == "sql":
-                handler = StepSQLHandler(self.context, self.step, task_variable_dict=self.task_variable_dict)
+                handler = StepSQLHandler(self.context, self.step, task_variable_dict=self.task_variable_dict,obConnector=self.obConnector)
             elif self.step["type"] == "data_size":
-                handler = DataSizeHandler(self.context, self.step, self.cluster, self.task_variable_dict)
+                handler = DataSizeHandler(self.context, self.step, self.cluster, self.task_variable_dict,self.obConnector)
             else:
                 raise StepExecuteFailException("the type not support: {0}".format(self.step["type"]))
             self.stdio.verbose("task execute and result")

From 5fa5fef2ce0c8fa8706796e25c2b3a82d7ff96d4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Thu, 25 Apr 2024 20:55:23 +0800
Subject: [PATCH 16/30] test check

---
 handler/checker/check_handler.py              | 51 +++++++++++++++----
 handler/checker/step/sql.py                   |  6 ++-
 .../sysbench_free_test_memory_limit.yaml      |  2 +-
 3 files changed, 46 insertions(+), 13 deletions(-)

diff --git a/handler/checker/check_handler.py b/handler/checker/check_handler.py
index 7bd249f3..88622e4d 100644
--- a/handler/checker/check_handler.py
+++ b/handler/checker/check_handler.py
@@ -17,6 +17,7 @@
 """
 
 import os
+import queue
 import time
 
 import yaml
@@ -111,20 +112,15 @@ def __init__(self, context,  check_target_type="observer"):
         self.nodes=new_node
         self.version=get_version(self.nodes, self.check_target_type,self.cluster, self.stdio)
 
-        # add OBConnector
-        obConnector = None
+        # add OBConnectorPool
+        OBConnectorPool = None
         try:
-            if self.cluster is not None:
-                obConnector=OBConnector(ip=self.cluster.get("db_host"),
-                                                   port=self.cluster.get("db_port"),
-                                                   username=self.cluster.get("tenant_sys").get("user"),
-                                                   password=self.cluster.get("tenant_sys").get("password"),
-                                                   stdio=self.stdio,
-                                                   timeout=10000)
+            OBConnectorPool=checkOBConnectorPool(context,2,self.cluster)
+
         except Exception as e:
             self.stdio.warn("obConnector init error. Error info is {0}".format(e))
         finally:
-            self.context.set_variable('check_obConnector', obConnector)
+            self.context.set_variable('check_obConnector_pool', OBConnectorPool)
 
 
     def handle(self):
@@ -249,4 +245,37 @@ def execute(self):
         except Exception as e:
             self.stdio.error("Internal error :{0}".format(e))
         end_time = time.time()
-        print("Total cost time is {0} s".format((end_time - start_time)))
\ No newline at end of file
+        print("Total cost time is {0} s".format((end_time - start_time)))
+class checkOBConnectorPool:
+    def __init__(self,context, max_size, cluster):
+        self.max_size = max_size
+        self.cluster=cluster
+        self.connections = queue.Queue(maxsize=max_size)
+        self.stdio=context.stdio
+
+    def get_connection(self):
+        try:
+            if self.connections.qsize() == 0:
+                if self.connections.qsize() < self.max_size:
+                    conn = OBConnector(
+                        ip=self.cluster.get("db_host"),
+                        port=self.cluster.get("db_port"),
+                        username=self.cluster.get("tenant_sys").get("user"),
+                        password=self.cluster.get("tenant_sys").get("password"),
+                        stdio=self.stdio,
+                        timeout=10000
+                    )
+                    self.connections.put(conn)
+                else:
+                    conn = self.connections.get()
+            else:
+                conn = self.connections.get()
+            return conn
+        except Exception as e:
+            return None
+
+    def release_connection(self, conn):
+        if conn is not None:
+            self.connections.put(conn)
+        return
+
diff --git a/handler/checker/step/sql.py b/handler/checker/step/sql.py
index 7d846626..bf1311c8 100644
--- a/handler/checker/step/sql.py
+++ b/handler/checker/step/sql.py
@@ -32,7 +32,9 @@ def __init__(self,context, step, task_variable_dict,obConnector):
             self.tenant_mode = None
             self.sys_database = None
             self.database = None
-            self.ob_connector=obConnector
+            self.ob_connector_pool=self.context.get_variable('check_obConnector_pool',None)
+            if self.ob_connector_pool is not None:
+                self.ob_connector=self.ob_connector_pool.get_connection()
             if self.ob_connector is None:
                 raise Exception("self.ob_connector is None.")
         except Exception as e:
@@ -72,6 +74,8 @@ def execute(self):
         except Exception as e:
             self.stdio.error("StepSQLHandler execute Exception: {0}".format(e))
             raise StepExecuteFailException("StepSQLHandler execute Exception: {0}".format(e))
+        finally:
+            self.ob_connector_pool.release_connection(self.ob_connector)
 
     def update_step_variable_dict(self):
         return self.task_variable_dict
diff --git a/handler/checker/tasks/observer/sysbench/sysbench_free_test_memory_limit.yaml b/handler/checker/tasks/observer/sysbench/sysbench_free_test_memory_limit.yaml
index 661d93b7..63412cb6 100644
--- a/handler/checker/tasks/observer/sysbench/sysbench_free_test_memory_limit.yaml
+++ b/handler/checker/tasks/observer/sysbench/sysbench_free_test_memory_limit.yaml
@@ -30,7 +30,7 @@ task:
         set_value: result
         verify_type: between
         verify: "[80,100]"
-        err_msg: 'memory_limit/os_memory is #{result}%,is not between 80 and 100'
+        err_msg: 'memory_limit: #{memory_limit}. os_memory: #{os_memory}. memory_limit/os_memory is #{result}%,is not between 80% and 100%'
 
       # memory_size
     - type: sql

From 7300bac98ad7319da37c533db64e1741cf4bad56 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Sun, 28 Apr 2024 16:32:14 +0800
Subject: [PATCH 17/30] test check

---
 common/ob_connector.py                        | 14 ++++++-
 handler/checker/check_handler.py              | 38 ++++++++++---------
 handler/checker/check_task.py                 | 12 ++----
 handler/checker/step/data_size.py             |  2 +-
 handler/checker/step/get_system_parameter.py  |  2 +-
 handler/checker/step/sql.py                   |  2 +-
 handler/checker/step/ssh.py                   |  2 +-
 handler/checker/step/stepbase.py              |  8 ++--
 .../tasks/observer/cluster/deadlocks.yaml     |  3 +-
 .../tasks/observer/system/core_pattern.yaml   |  4 +-
 10 files changed, 48 insertions(+), 39 deletions(-)

diff --git a/common/ob_connector.py b/common/ob_connector.py
index 223eb915..b548b89e 100644
--- a/common/ob_connector.py
+++ b/common/ob_connector.py
@@ -20,7 +20,7 @@
 
 
 class OBConnector(object):
-    def __init__(self, ip, port, username, password=None, database=None, stdio=None, timeout=10,):
+    def __init__(self, ip, port, username, password=None, database=None, stdio=None, timeout=30,):
         self.ip = str(ip)
         self.port = int(port)
         self.username = str(username)
@@ -50,6 +50,18 @@ def _connect_db(self):
             self.stdio.verbose("connect databse ...")
         except mysql.Error as e:
             self.stdio.error("connect OB: {0}:{1} with user {2} failed, error:{3}".format(self.ip, self.port, self.username, e))
+            return
+        try:
+            ob_trx_timeout=self.timeout*1000000
+            self.execute_sql("SET SESSION ob_trx_timeout={0};".format(ob_trx_timeout))
+        except Exception as e:
+            self.stdio.warn("set ob_trx_timeout failed, error:{0}".format(e))
+        try:
+            ob_query_timeout=self.timeout*1000000
+            self.execute_sql("SET SESSION ob_query_timeout={0};".format(ob_query_timeout))
+        except Exception as e:
+            self.stdio.warn("set ob_query_timeout failed, error:{0}".format(e))
+
 
     def execute_sql(self, sql):
         if self.conn is None:
diff --git a/handler/checker/check_handler.py b/handler/checker/check_handler.py
index 88622e4d..ca967621 100644
--- a/handler/checker/check_handler.py
+++ b/handler/checker/check_handler.py
@@ -33,7 +33,6 @@
 from common.tool import YamlUtils
 from common.tool import StringUtils
 
-
 class CheckHandler:
 
     def __init__(self, context,  check_target_type="observer"):
@@ -113,8 +112,8 @@ def __init__(self, context,  check_target_type="observer"):
         self.version=get_version(self.nodes, self.check_target_type,self.cluster, self.stdio)
 
         # add OBConnectorPool
-        OBConnectorPool = None
         try:
+            global OBConnectorPool
             OBConnectorPool=checkOBConnectorPool(context,2,self.cluster)
 
         except Exception as e:
@@ -252,29 +251,32 @@ def __init__(self,context, max_size, cluster):
         self.cluster=cluster
         self.connections = queue.Queue(maxsize=max_size)
         self.stdio=context.stdio
+        self.stdio.verbose("obConnectorPool init success!")
+        try:
+            for i in range(max_size):
+                conn = OBConnector(
+                    ip=self.cluster.get("db_host"),
+                    port=self.cluster.get("db_port"),
+                    username=self.cluster.get("tenant_sys").get("user"),
+                    password=self.cluster.get("tenant_sys").get("password"),
+                    stdio=self.stdio,
+                    timeout=10000
+                )
+                self.connections.put(conn)
+            self.stdio.verbose("obConnectorPool init success!")
+        except Exception as e:
+            self.stdio.error("obConnectorPool init fail! err:".format(e))
+
 
     def get_connection(self):
         try:
-            if self.connections.qsize() == 0:
-                if self.connections.qsize() < self.max_size:
-                    conn = OBConnector(
-                        ip=self.cluster.get("db_host"),
-                        port=self.cluster.get("db_port"),
-                        username=self.cluster.get("tenant_sys").get("user"),
-                        password=self.cluster.get("tenant_sys").get("password"),
-                        stdio=self.stdio,
-                        timeout=10000
-                    )
-                    self.connections.put(conn)
-                else:
-                    conn = self.connections.get()
-            else:
-                conn = self.connections.get()
-            return conn
+            return self.connections.get()
         except Exception as e:
+            self.stdio.error("get connection fail! err:".format(e))
             return None
 
     def release_connection(self, conn):
+
         if conn is not None:
             self.connections.put(conn)
         return
diff --git a/handler/checker/check_task.py b/handler/checker/check_task.py
index b8db28e8..77e04310 100644
--- a/handler/checker/check_task.py
+++ b/handler/checker/check_task.py
@@ -51,20 +51,14 @@ def execute(self):
         # TODO: 这里的逻辑需要优化，如果一个节点执行失败了，那么后续的步骤就不会被执行了。
         work_threads = []
         for node in self.nodes:
-            obConnector = OBConnector(ip=self.cluster.get("db_host"),
-                                      port=self.cluster.get("db_port"),
-                                      username=self.cluster.get("tenant_sys").get("user"),
-                                      password=self.cluster.get("tenant_sys").get("password"),
-                                      stdio=self.stdio,
-                                      timeout=10000)
-            t = threading.Thread(target=self.execute_one_node, args=(steps_nu,node,obConnector))
+            t = threading.Thread(target=self.execute_one_node, args=(steps_nu,node))
             work_threads.append(t)
             t.start()
         for t in work_threads:
             t.join()
 
         self.stdio.verbose("task execute end")
-    def execute_one_node(self,steps_nu,node,obConnector):
+    def execute_one_node(self,steps_nu,node):
         try:
             self.stdio.verbose("run task in node: {0}".format(StringUtils.node_cut_passwd_for_log(node)))
             steps = self.task[steps_nu]
@@ -74,7 +68,7 @@ def execute_one_node(self,steps_nu,node,obConnector):
                     self.stdio.verbose("step nu: {0}".format(nu))
                     if len(self.cluster) == 0:
                         raise Exception("cluster is not exist")
-                    step_run = StepBase(self.context, step, node, self.cluster, self.task_variable_dict,obConnector)
+                    step_run = StepBase(self.context, step, node, self.cluster, self.task_variable_dict)
                     self.stdio.verbose("step nu: {0} initted, to execute".format(nu))
                     step_run.execute(self.report)
                     self.task_variable_dict = step_run.update_task_variable_dict()
diff --git a/handler/checker/step/data_size.py b/handler/checker/step/data_size.py
index 66dc2ff9..b8d0ff0c 100644
--- a/handler/checker/step/data_size.py
+++ b/handler/checker/step/data_size.py
@@ -23,7 +23,7 @@
 
 
 class DataSizeHandler:
-    def __init__(self,context, step, node, task_variable_dict,obConnector):
+    def __init__(self,context, step, node, task_variable_dict):
         self.context = context
         self.stdio = context.stdio
         self.stdio.verbose("init DataSizeHandler")
diff --git a/handler/checker/step/get_system_parameter.py b/handler/checker/step/get_system_parameter.py
index 29713ee3..af3341c1 100644
--- a/handler/checker/step/get_system_parameter.py
+++ b/handler/checker/step/get_system_parameter.py
@@ -23,7 +23,7 @@
 
 
 class GetSystemParameterHandler:
-    def __init__(self,context, step, node, task_variable_dict,obConnector):
+    def __init__(self,context, step, node, task_variable_dict):
         self.context = context
         self.stdio = context.stdio
         self.stdio.verbose("init GetSystemParameterHandler")
diff --git a/handler/checker/step/sql.py b/handler/checker/step/sql.py
index bf1311c8..6c0759ae 100644
--- a/handler/checker/step/sql.py
+++ b/handler/checker/step/sql.py
@@ -23,7 +23,7 @@
 
 
 class StepSQLHandler:
-    def __init__(self,context, step, task_variable_dict,obConnector):
+    def __init__(self,context, step, task_variable_dict):
         try:
             self.context = context
             self.stdio = context.stdio
diff --git a/handler/checker/step/ssh.py b/handler/checker/step/ssh.py
index 4e4c6368..282477e2 100644
--- a/handler/checker/step/ssh.py
+++ b/handler/checker/step/ssh.py
@@ -23,7 +23,7 @@
 
 
 class SshHandler:
-    def __init__(self,context, step, node, task_variable_dict,obConnector):
+    def __init__(self,context, step, node, task_variable_dict):
         self.context = context
         self.stdio = context.stdio
         self.ssh_report_value = None
diff --git a/handler/checker/step/stepbase.py b/handler/checker/step/stepbase.py
index aa479251..9eca253f 100644
--- a/handler/checker/step/stepbase.py
+++ b/handler/checker/step/stepbase.py
@@ -55,13 +55,13 @@ def execute(self, report):
             if "type" not in self.step:
                 raise StepExecuteFailException("Missing field :type")
             if self.step["type"] == "get_system_parameter":
-                handler = GetSystemParameterHandler(self.context, self.step, self.node, self.task_variable_dict,self.obConnector)
+                handler = GetSystemParameterHandler(self.context, self.step, self.node, self.task_variable_dict)
             elif self.step["type"] == "ssh":
-                handler = SshHandler(self.context, self.step, self.node, self.task_variable_dict,self.obConnector)
+                handler = SshHandler(self.context, self.step, self.node, self.task_variable_dict)
             elif self.step["type"] == "sql":
-                handler = StepSQLHandler(self.context, self.step, task_variable_dict=self.task_variable_dict,obConnector=self.obConnector)
+                handler = StepSQLHandler(self.context, self.step, task_variable_dict=self.task_variable_dict)
             elif self.step["type"] == "data_size":
-                handler = DataSizeHandler(self.context, self.step, self.cluster, self.task_variable_dict,self.obConnector)
+                handler = DataSizeHandler(self.context, self.step, self.cluster, self.task_variable_dict)
             else:
                 raise StepExecuteFailException("the type not support: {0}".format(self.step["type"]))
             self.stdio.verbose("task execute and result")
diff --git a/handler/checker/tasks/observer/cluster/deadlocks.yaml b/handler/checker/tasks/observer/cluster/deadlocks.yaml
index 201359da..690d0227 100644
--- a/handler/checker/tasks/observer/cluster/deadlocks.yaml
+++ b/handler/checker/tasks/observer/cluster/deadlocks.yaml
@@ -1,6 +1,7 @@
 info: "Check whether there is a deadlock."
 task:
   - version: "[4.0.0.0,*]"
+    execute_type: "one_node"
     steps:
     - type: sql
       sql: 'select count(0) from oceanbase.DBA_OB_DEADLOCK_EVENT_HISTORY;'
@@ -9,4 +10,4 @@ task:
         verify_type: equal
         report_type: warning
         verify: 0
-        err_msg: "There is a deadlock."
\ No newline at end of file
+        err_msg: "There is a deadlock. Please check on the oceanbase.DBA_OB_DEADLOCK_EVENT_HISTORY"
\ No newline at end of file
diff --git a/handler/checker/tasks/observer/system/core_pattern.yaml b/handler/checker/tasks/observer/system/core_pattern.yaml
index a226347f..a708a49a 100644
--- a/handler/checker/tasks/observer/system/core_pattern.yaml
+++ b/handler/checker/tasks/observer/system/core_pattern.yaml
@@ -5,5 +5,5 @@ task:
         parameter: kernel.core_pattern
         result:
           set_value: core_pattern
-          verify: '[[ $core_pattern == *" "* ]]'
-          err_msg: 'clock_source: #{clock_source}. recommended: tsc. Uneven CPU utilization during pressure testing resulted in low TPS during pressure testing'
+          verify: '[[ $core_pattern != *" "* ]]'
+          err_msg: 'kernel.core_pattern: #{core_pattern} , is not recommended for configuring functions other than the specified core path'

From 6590e26ca45ac36d9d02175284c08f38f1b94c90 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Sun, 28 Apr 2024 17:06:45 +0800
Subject: [PATCH 18/30] update check

---
 conf/inner_config.yml            | 1 -
 handler/checker/check_handler.py | 5 ++---
 handler/checker/check_task.py    | 1 -
 handler/checker/step/stepbase.py | 3 +--
 4 files changed, 3 insertions(+), 7 deletions(-)

diff --git a/conf/inner_config.yml b/conf/inner_config.yml
index 8c1e0845..f4bf9245 100644
--- a/conf/inner_config.yml
+++ b/conf/inner_config.yml
@@ -17,7 +17,6 @@ check:
   report:
     report_path: "./check_report/"
     export_type: table
-  package_file: "~/.obdiag/check/check_package.yaml"
   tasks_base_path: "~/.obdiag/check/tasks/"
 gather:
   scenes_base_path: "~/.obdiag/gather/tasks"
diff --git a/handler/checker/check_handler.py b/handler/checker/check_handler.py
index ca967621..cc5fdac5 100644
--- a/handler/checker/check_handler.py
+++ b/handler/checker/check_handler.py
@@ -113,13 +113,12 @@ def __init__(self, context,  check_target_type="observer"):
 
         # add OBConnectorPool
         try:
-            global OBConnectorPool
-            OBConnectorPool=checkOBConnectorPool(context,2,self.cluster)
+            obConnectorPool=checkOBConnectorPool(context,2,self.cluster)
 
         except Exception as e:
             self.stdio.warn("obConnector init error. Error info is {0}".format(e))
         finally:
-            self.context.set_variable('check_obConnector_pool', OBConnectorPool)
+            self.context.set_variable('check_obConnector_pool', obConnectorPool)
 
 
     def handle(self):
diff --git a/handler/checker/check_task.py b/handler/checker/check_task.py
index 77e04310..9a4476a4 100644
--- a/handler/checker/check_task.py
+++ b/handler/checker/check_task.py
@@ -71,7 +71,6 @@ def execute_one_node(self,steps_nu,node):
                     step_run = StepBase(self.context, step, node, self.cluster, self.task_variable_dict)
                     self.stdio.verbose("step nu: {0} initted, to execute".format(nu))
                     step_run.execute(self.report)
-                    self.task_variable_dict = step_run.update_task_variable_dict()
                     if "report_type" in step["result"] and step["result"]["report_type"] == "execution":
                         self.stdio.verbose("report_type stop this step")
                         return
diff --git a/handler/checker/step/stepbase.py b/handler/checker/step/stepbase.py
index 9eca253f..3ec68d8e 100644
--- a/handler/checker/step/stepbase.py
+++ b/handler/checker/step/stepbase.py
@@ -27,7 +27,7 @@
 
 
 class StepBase(object):
-    def __init__(self, context, step, node, cluster, task_variable_dict,obConnector):
+    def __init__(self, context, step, node, cluster, task_variable_dict):
         self.context = context
         self.stdio = context.stdio
         self.step = step
@@ -35,7 +35,6 @@ def __init__(self, context, step, node, cluster, task_variable_dict,obConnector)
         self.cluster = cluster
         self.task_variable_dict = {}
         self.task_variable_dict = task_variable_dict
-        self.obConnector=obConnector
 
     def execute(self, report):
         no_cluster_name_msg = "(Please set ob_cluster_name or obproxy_cluster_name)"

From 1fcabe416058642baf2d7766f7150449ab23c6c7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Sun, 28 Apr 2024 18:01:15 +0800
Subject: [PATCH 19/30] add check case

---
 handler/checker/check_handler.py                |  2 +-
 handler/checker/step/sql.py                     |  3 ++-
 .../checker/tasks/observer/bugs/bug_182.yaml    | 17 +++++++++++++++++
 3 files changed, 20 insertions(+), 2 deletions(-)
 create mode 100644 handler/checker/tasks/observer/bugs/bug_182.yaml

diff --git a/handler/checker/check_handler.py b/handler/checker/check_handler.py
index cc5fdac5..81f46cc9 100644
--- a/handler/checker/check_handler.py
+++ b/handler/checker/check_handler.py
@@ -113,7 +113,7 @@ def __init__(self, context,  check_target_type="observer"):
 
         # add OBConnectorPool
         try:
-            obConnectorPool=checkOBConnectorPool(context,2,self.cluster)
+            obConnectorPool=checkOBConnectorPool(context,3,self.cluster)
 
         except Exception as e:
             self.stdio.warn("obConnector init error. Error info is {0}".format(e))
diff --git a/handler/checker/step/sql.py b/handler/checker/step/sql.py
index 6c0759ae..b7194bdc 100644
--- a/handler/checker/step/sql.py
+++ b/handler/checker/step/sql.py
@@ -61,8 +61,9 @@ def execute(self):
             if data is None:
                 self.stdio.warn("sql result is None: {0}".format(self.step["sql"]))
             self.stdio.verbose("execute_sql result:{0}".format(data))
-            if len(data) == 0:
+            if len(data) == 0 or data is None:
                 self.stdio.warn("sql result is None: {0}".format(self.step["sql"]))
+                data=""
             else:
                 data = data[0][0]
             if data is None:
diff --git a/handler/checker/tasks/observer/bugs/bug_182.yaml b/handler/checker/tasks/observer/bugs/bug_182.yaml
new file mode 100644
index 00000000..5745b6cd
--- /dev/null
+++ b/handler/checker/tasks/observer/bugs/bug_182.yaml
@@ -0,0 +1,17 @@
+info: "OB has been upgraded to version 4.2.1, and some partition tables are executing DDL with error code -4109 and error message: Server state or role not the same as expected. github issue #182"
+task:
+  - version: "[4.0.0.0,*]"
+    steps:
+    - type: sql
+      sql: 'select tenant_id, table_id, table_name, database_id, table_type, load_type, def_type, rowkey_column_num, index_column_num, max_used_column_id, autoinc_column_id, auto_increment, read_only, rowkey_split_pos, compress_func_name, expire_condition, is_use_bloomfilter, comment, block_size, collation_type, data_table_id, index_status, tablegroup_id, progressive_merge_num, index_type, part_level, part_func_type, part_func_expr, part_num, sub_part_func_type, sub_part_func_expr, sub_part_num, schema_version, view_definition, view_check_option, view_is_updatable, index_using_type, parser_name, index_attributes_set, tablet_size, pctfree, partition_status, partition_schema_version, session_id, pk_comment, sess_active_time, row_store_type, store_format, duplicate_scope, progressive_merge_round, storage_format_version, table_mode, encryption, tablespace_id, sub_part_template_flags, dop, character_set_client, collation_connection, auto_part_size, auto_part, association_table_id, tablet_id, max_dependency_version, define_user_id, transition_point, b_transition_point, interval_range, b_interval_range, object_status, table_flags, truncate_version, 0 as is_deleted from OCEANBASE.__all_table
+EXCEPT select
+           t1.tenant_id, t1.table_id, t1.table_name, t1.database_id, t1.table_type, t1.load_type, t1.def_type, t1.rowkey_column_num, t1.index_column_num, t1.max_used_column_id, t1.autoinc_column_id, t1.auto_increment, t1.read_only, t1.rowkey_split_pos, t1.compress_func_name, t1.expire_condition, t1.is_use_bloomfilter, t1.comment, t1.block_size, t1.collation_type, t1.data_table_id, t1.index_status, t1.tablegroup_id, t1.progressive_merge_num, t1.index_type, t1.part_level, t1.part_func_type, t1.part_func_expr, t1.part_num, t1.sub_part_func_type, t1.sub_part_func_expr, t1.sub_part_num, t1.schema_version, t1.view_definition, t1.view_check_option, t1.view_is_updatable, t1.index_using_type, t1.parser_name, t1.index_attributes_set, t1.tablet_size, t1.pctfree, t1.partition_status, t1.partition_schema_version, t1.session_id, t1.pk_comment, t1.sess_active_time, t1.row_store_type, t1.store_format, t1.duplicate_scope, t1.progressive_merge_round, t1.storage_format_version, t1.table_mode, t1.encryption, t1.tablespace_id, t1.sub_part_template_flags, t1.dop, t1.character_set_client, t1.collation_connection, t1.auto_part_size, t1.auto_part, t1.association_table_id, t1.tablet_id, t1.max_dependency_version, t1.define_user_id, t1.transition_point, t1.b_transition_point, t1.interval_range, t1.b_interval_range, t1.object_status, t1.table_flags, t1.truncate_version, t1.is_deleted
+       from
+           OCEANBASE.__all_table_history t1
+               inner join (select t2.table_id,max(t2.schema_version) as schema_version from OCEANBASE.__all_table_history t2 group by t2.table_id)as t3
+                          on t1.table_id = t3.table_id and t1.schema_version = t3.schema_version and t1.is_deleted = 0;'
+      result:
+        set_value: error_table
+        report_type: warning
+        verify: '[ -z "$error_table" ]'
+        err_msg: "Some partition tables are inconsistent. Please get bug's on https://github.com/oceanbase/obdiag/issues/182"

From 2ffbeb8178089f3fb6e5688b3be429b8b3dcc137 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Sun, 28 Apr 2024 20:15:51 +0800
Subject: [PATCH 20/30] fix case

---
 handler/checker/check_handler.py                              | 4 +---
 handler/checker/tasks/observer/cluster/deadlocks.yaml         | 1 -
 .../observer/table/information_schema_tables_two_data.yaml    | 3 +--
 3 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/handler/checker/check_handler.py b/handler/checker/check_handler.py
index 81f46cc9..f225832c 100644
--- a/handler/checker/check_handler.py
+++ b/handler/checker/check_handler.py
@@ -225,7 +225,6 @@ def execute_one(self, task_name):
             raise CheckException("execute_one Exception : {0}".format(e))
 
     def execute(self):
-        start_time = time.time()
         try:
             self.stdio.verbose(
                 "execute_all_tasks. the number of tasks is {0} ,tasks is {1}".format(len(self.tasks.keys()),
@@ -242,8 +241,7 @@ def execute(self):
             self.stdio.error("Report error :{0}".format(e))
         except Exception as e:
             self.stdio.error("Internal error :{0}".format(e))
-        end_time = time.time()
-        print("Total cost time is {0} s".format((end_time - start_time)))
+
 class checkOBConnectorPool:
     def __init__(self,context, max_size, cluster):
         self.max_size = max_size
diff --git a/handler/checker/tasks/observer/cluster/deadlocks.yaml b/handler/checker/tasks/observer/cluster/deadlocks.yaml
index 690d0227..e05c7034 100644
--- a/handler/checker/tasks/observer/cluster/deadlocks.yaml
+++ b/handler/checker/tasks/observer/cluster/deadlocks.yaml
@@ -1,7 +1,6 @@
 info: "Check whether there is a deadlock."
 task:
   - version: "[4.0.0.0,*]"
-    execute_type: "one_node"
     steps:
     - type: sql
       sql: 'select count(0) from oceanbase.DBA_OB_DEADLOCK_EVENT_HISTORY;'
diff --git a/handler/checker/tasks/observer/table/information_schema_tables_two_data.yaml b/handler/checker/tasks/observer/table/information_schema_tables_two_data.yaml
index f6bce02c..76d450b7 100644
--- a/handler/checker/tasks/observer/table/information_schema_tables_two_data.yaml
+++ b/handler/checker/tasks/observer/table/information_schema_tables_two_data.yaml
@@ -1,4 +1,4 @@
-info: 'A table found two records in information_schema.tables. KBA-50000056'
+info: 'A table found two records in information_schema.tables.'
 task:
   - version: "[4.0.0.0,*]"
     steps:
@@ -6,7 +6,6 @@ task:
       sql: 'select count(0) from oceanbase.__all_virtual_table_stat where table_id = partition_id and (tenant_id,table_id) in (select tenant_id, table_id from oceanbase.__all_virtual_table where part_level != 0);'
       result:
         set_value: err_table_count
-        # report_type: warning
         verify_type: equal
         verify: 0
         err_msg: 'Find have table found two records in information_schema.tables. the number of err_table_count is : #{err_table_count}.  Please get more info by "select * from oceanbase.__all_virtual_table_stat where table_id = partition_id and (tenant_id,table_id) in (select tenant_id, table_id from oceanbase.__all_virtual_table where part_level != 0);". And you can by "delete from __all_table_stat where table_id=partition_id and table_id=${partition table table_id};" and "delete from __all_column_stat where table_id=partition_id and table_id=${partition table table_id};" to fix it.'

From 65132b43cf3abdf93739bf3eaa219b398cb77bd0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Mon, 29 Apr 2024 17:42:01 +0800
Subject: [PATCH 21/30] support ash

---
 cmd.py                              |  32 +++++
 common/ssh.py                       |  19 ++-
 conf/inner_config.yml               |   1 +
 config.py                           |   1 +
 core.py                             |  10 +-
 handler/gather/gather_ash_report.py | 193 ++++++++++++++++++++++++++++
 6 files changed, 251 insertions(+), 5 deletions(-)
 create mode 100644 handler/gather/gather_ash_report.py

diff --git a/cmd.py b/cmd.py
index 0c0fcfb1..071face0 100644
--- a/cmd.py
+++ b/cmd.py
@@ -562,6 +562,38 @@ def _do_command(self, obdiag):
         return obdiag.gather_function('gather_scenes_run', self.opts)
 
 
+class ObdiagGatherAshReportRunCommand(ObdiagOriginCommand):
+
+    def __init__(self):
+        super(ObdiagGatherAshReportRunCommand, self).__init__('run', 'gather ash report')
+        self.parser.add_option('--trace_id', type='string', help="The TRACE.ID of the SQL to be sampled, if left blank or filled with NULL, indicates that TRACE.ID is not restricted.")
+        self.parser.add_option('--sql_id', type='string', help="The SQL.ID, if left blank or filled with NULL, indicates that SQL.ID is not restricted.")
+        #WAIT_CLASS
+        self.parser.add_option('--wait_class', type='string',
+                               help='Report type.',default='TEXT')
+        self.parser.add_option('--report_type', type='string',
+                               help='Event types to be sampled.')
+        self.parser.add_option('--from', type='string',
+                               help="specify the start of the time range. format: 'yyyy-mm-dd hh:mm:ss'")
+        self.parser.add_option('--to', type='string',
+                               help="specify the end of the time range. format: 'yyyy-mm-dd hh:mm:ss'")
+        self.parser.add_option('--since', type='string',
+                               help="Specify time range that from 'n' [d]ays, 'n' [h]ours or 'n' [m]inutes. before to now. format: <n> <m|h|d>. example: 1h.",
+                               default='30m')
+        self.parser.add_option('--store_dir', type='string',
+                               help='the dir to store gather result, current dir by default.', default='./')
+
+        self.parser.add_option('-c', type='string', help='obdiag custom config',
+                               default=os.path.expanduser('~/.obdiag/config.yml'))
+
+    def init(self, cmd, args):
+        super(ObdiagGatherAshReportRunCommand, self).init(cmd, args)
+        return self
+
+    def _do_command(self, obdiag):
+        return obdiag.gather_function('gather_ash_report', self.opts)
+
+
 class ObdiagAnalyzeLogCommand(ObdiagOriginCommand):
 
     def __init__(self):
diff --git a/common/ssh.py b/common/ssh.py
index 9c18b6b2..f58b8994 100644
--- a/common/ssh.py
+++ b/common/ssh.py
@@ -811,7 +811,14 @@ def file_uploader(self, local_dir, remote_dir, stdio=None):
         except:
             stdio.exception("")
             stdio.verbose('Failed to get %s' % remote_dir)
-
+# TODO ENV_DISABLE_RSA_ALGORITHMS need get by context.inner_context
+ENV_DISABLE_RSA_ALGORITHMS=0
+def dis_rsa_algorithms(state=0):
+    """
+    Disable RSA algorithms in OpenSSH server.
+    """
+    global ENV_DISABLE_RSA_ALGORITHMS
+    ENV_DISABLE_RSA_ALGORITHMS=state
 class SshHelper(object):
     def __init__(self, is_ssh=None, host_ip=None, username=None, password=None, ssh_port=None, key_file=None,
                  node=None, stdio=None):
@@ -851,17 +858,21 @@ def __init__(self, is_ssh=None, host_ip=None, username=None, password=None, ssh_
             return
 
         if self.is_ssh:
+            self._disabled_rsa_algorithms=None
+            DISABLED_ALGORITHMS = dict(pubkeys=["rsa-sha2-512", "rsa-sha2-256"])
+            if ENV_DISABLE_RSA_ALGORITHMS == 1:
+                self._disabled_rsa_algorithms = DISABLED_ALGORITHMS
             self.ssh_type = "remote"
             if len(self.key_file) > 0:
                 try:
                     self._ssh_fd = paramiko.SSHClient()
                     self._ssh_fd.set_missing_host_key_policy(paramiko.client.AutoAddPolicy())
                     self._ssh_fd.load_system_host_keys()
-                    self._ssh_fd.connect(hostname=host_ip, username=username, key_filename=self.key_file, port=ssh_port)
+                    self._ssh_fd.connect(hostname=host_ip, username=username, key_filename=self.key_file, port=ssh_port,disabled_algorithms=self._disabled_rsa_algorithms)
                 except AuthenticationException:
                     self.password = input("Authentication failed, Input {0}@{1} password:\n".format(username, host_ip))
                     self.need_password = True
-                    self._ssh_fd.connect(hostname=host_ip, username=username, password=password, port=ssh_port)
+                    self._ssh_fd.connect(hostname=host_ip, username=username, password=password, port=ssh_port,disabled_algorithms=self._disabled_rsa_algorithms)
                 except Exception as e:
                     raise OBDIAGSSHConnException("ssh {0}@{1}: failed, exception:{2}".format(username, host_ip, e))
             else:
@@ -869,7 +880,7 @@ def __init__(self, is_ssh=None, host_ip=None, username=None, password=None, ssh_
                 self._ssh_fd.set_missing_host_key_policy(paramiko.client.AutoAddPolicy())
                 self._ssh_fd.load_system_host_keys()
                 self.need_password = True
-                self._ssh_fd.connect(hostname=host_ip, username=username, password=password, port=ssh_port)
+                self._ssh_fd.connect(hostname=host_ip, username=username, password=password, port=ssh_port,disabled_algorithms=self._disabled_rsa_algorithms)
 
     def ssh_exec_cmd(self, cmd):
         if self.ssh_type == "docker":
diff --git a/conf/inner_config.yml b/conf/inner_config.yml
index f4bf9245..9b3fdcd1 100644
--- a/conf/inner_config.yml
+++ b/conf/inner_config.yml
@@ -4,6 +4,7 @@ obdiag:
     config_backup_dir: ~/.obdiag/backup_conf
     file_number_limit: 20
     file_size_limit: 2G
+    dis_rsa_algorithms: 0
   logger:
     log_dir: ~/.obdiag/log
     log_filename: obdiag.log
diff --git a/config.py b/config.py
index fb01eb8d..d79fcb9c 100644
--- a/config.py
+++ b/config.py
@@ -64,6 +64,7 @@
                 'config_backup_dir': '~/.obdiag/backup_conf',
                 'file_number_limit': 20,
                 'file_size_limit': '2G',
+                'dis_rsa_algorithms':0,
             },
             'logger': {
                 'log_dir': '~/.obdiag/log',
diff --git a/core.py b/core.py
index b5d7dcf3..ef8c41c8 100644
--- a/core.py
+++ b/core.py
@@ -21,9 +21,10 @@
 from optparse import Values
 from copy import copy
 
+from handler.gather.gather_ash_report import GatherAshReportHandler
 from handler.rca.rca_handler import RCAHandler
 from handler.rca.rca_list import RcaScenesListHandler
-from common.ssh import SshClient, SshConfig
+from common.ssh import SshClient, SshConfig, dis_rsa_algorithms
 from context import HandlerContextNamespace, HandlerContext
 from config import ConfigManager, InnerConfigManager
 from err import CheckStatus, SUG_SSH_FAILED
@@ -67,6 +68,10 @@ def __init__(self, stdio=None, config_path=os.path.expanduser('~/.obdiag/config.
                 "basic") is not None and self.inner_config_manager.config.get("obdiag").get("basic").get(
                 "telemetry") is not None and self.inner_config_manager.config.get("obdiag").get("basic").get("telemetry") is False:
             telemetry.work_tag = False
+        if self.inner_config_manager.config.get("obdiag") is not None and self.inner_config_manager.config.get("obdiag").get(
+                "basic") is not None and self.inner_config_manager.config.get("obdiag").get("basic").get("dis_rsa_algorithms") is not None :
+            disable_rsa_algorithms=self.inner_config_manager.config.get("obdiag").get("basic").get("dis_rsa_algorithms")
+            dis_rsa_algorithms(disable_rsa_algorithms)
 
     def fork(self, cmds=None, options=None, stdio=None):
         new_obdiag = copy(self)
@@ -236,6 +241,9 @@ def gather_function(self, function_type, opt):
             elif function_type == 'gather_scenes_run':
                 handler = GatherSceneHandler(self.context)
                 return handler.handle()
+            elif function_type == 'gather_ash_report':
+                handler =GatherAshReportHandler(self.context)
+                return handler.handle()
             else:
                 self._call_stdio('error', 'Not support gather function: {0}'.format(function_type))
                 return False
diff --git a/handler/gather/gather_ash_report.py b/handler/gather/gather_ash_report.py
new file mode 100644
index 00000000..03135441
--- /dev/null
+++ b/handler/gather/gather_ash_report.py
@@ -0,0 +1,193 @@
+#!/usr/bin/env python
+# -*- coding: UTF-8 -*
+# Copyright (c) 2022 OceanBase
+# OceanBase Diagnostic Tool is licensed under Mulan PSL v2.
+# You can use this software according to the terms and conditions of the Mulan PSL v2.
+# You may obtain a copy of Mulan PSL v2 at:
+#          http://license.coscl.org.cn/MulanPSL2
+# THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND,
+# EITHER EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT,
+# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.
+# See the Mulan PSL v2 for more details.
+
+"""
+@time: 2024/4/28
+@file: gather_ash_report.py
+@desc:
+"""
+import datetime
+import os
+
+from common.ob_connector import OBConnector
+from common.obdiag_exception import OBDIAGFormatException, OBDIAGException
+from common.tool import DirectoryUtil, TimeUtils, Util
+from stdio import SafeStdio
+from colorama import Fore, Style
+
+
+class GatherAshReportHandler(SafeStdio):
+    def __init__(self, context, gather_pack_dir='./'):
+        super().__init__()
+        self.report_type = None
+        self.wait_class = None
+        self.sql_id = None
+        self.ash_report_file_name = None
+        self.from_time_str = None
+        self.to_time_str = None
+        self.ash_sql = None
+        self.trace_id = None
+        self.context = context
+        self.stdio = self.context.stdio
+        self.gather_pack_dir = gather_pack_dir
+        if self.context.get_variable("gather_timestamp", None) :
+            self.gather_timestamp=self.context.get_variable("gather_timestamp")
+        else:
+            self.gather_timestamp = TimeUtils.get_current_us_timestamp()
+        self.cluster = self.context.cluster_config
+        try:
+            self.obconn = OBConnector(
+                        ip=self.cluster.get("db_host"),
+                        port=self.cluster.get("db_port"),
+                        username=self.cluster.get("tenant_sys").get("user"),
+                        password=self.cluster.get("tenant_sys").get("password"),
+                        stdio=self.stdio,
+                        timeout=10000
+                    )
+        except Exception as e:
+            self.stdio.error("Failed to connect to database: {0}".format(e))
+            raise OBDIAGFormatException("Failed to connect to database: {0}".format(e))
+
+
+    def handle(self):
+        if not self.init_option():
+            self.stdio.error('init option failed')
+            return False
+        if not self.init_config():
+            self.stdio.error('init config failed')
+            return False
+        self.__init_variables()
+        self.__init_report_path()
+        self.__init_task_names()
+        self.execute()
+        self.__print_result()
+
+    def execute(self):
+        try:
+            self.stdio.verbose("execute_tasks. the number of tasks is {0} ,tasks is {1}".format(len(self.yaml_tasks.keys()), self.yaml_tasks.keys()))
+
+        except Exception as e:
+            self.stdio.error("Internal error :{0}".format(e))
+
+
+    def __init_report_path(self):
+        try:
+            self.report_path = os.path.join(self.gather_pack_dir, "gather_pack_{0}".format(TimeUtils.timestamp_to_filename_time(self.gather_timestamp), self.stdio))
+            self.stdio.verbose("Use {0} as pack dir.".format(self.report_path))
+            DirectoryUtil.mkdir(path=self.report_path, stdio=self.stdio)
+        except Exception as e:
+            self.stdio.error("init_report_path failed, error:{0}".format(e))
+
+    def __init_variables(self):
+        try:
+            self.variables = {
+                "observer_data_dir": self.ob_nodes[0].get("home_path") if self.ob_nodes and self.ob_nodes[0].get("home_path") else "",
+                "obproxy_data_dir": self.obproxy_nodes[0].get("home_path") if self.obproxy_nodes and self.obproxy_nodes[0].get("home_path") else "",
+                "from_time": self.from_time_str,
+                "to_time": self.to_time_str
+            }
+            self.stdio.verbose("gather scene variables: {0}".format(self.variables))
+        except Exception as e:
+            self.stdio.error("init gather scene variables failed, error: {0}".format(e))
+
+
+    def init_option(self):
+        options = self.context.options
+        from_option = Util.get_option(options, 'from')
+        to_option = Util.get_option(options, 'to')
+        store_dir_option = Util.get_option(options, 'store_dir',"./")
+        trace_id_option = Util.get_option(options, 'trace_id')
+        sql_id_option = Util.get_option(options, 'sql_id')
+        report_type_option = Util.get_option(options, 'report_type')
+        wait_class_option = Util.get_option(options, 'wait_class')
+
+        if from_option is not None and to_option is not None:
+            try:
+                from_timestamp = TimeUtils.parse_time_str(from_option)
+                to_timestamp = TimeUtils.parse_time_str(to_option)
+                self.from_time_str = from_option
+                self.to_time_str = to_option
+            except OBDIAGFormatException:
+                self.stdio.exception('Error: Datetime is invalid. Must be in format yyyy-mm-dd hh:mm:ss. from_datetime={0}, to_datetime={1}'.format(from_option, to_option))
+                return False
+            if to_timestamp <= from_timestamp:
+                self.stdio.exception('Error: from datetime is larger than to datetime, please check.')
+                return False
+        elif (from_option is None or to_option is None) and since_option is not None:
+            now_time = datetime.datetime.now()
+            self.to_time_str = (now_time + datetime.timedelta(minutes=1)).strftime('%Y-%m-%d %H:%M:%S')
+            self.from_time_str = (now_time - datetime.timedelta(seconds=TimeUtils.parse_time_length_to_sec(since_option))).strftime('%Y-%m-%d %H:%M:%S')
+            self.stdio.print('gather from_time: {0}, to_time: {1}'.format(self.from_time_str, self.to_time_str))
+        else:
+            self.stdio.warn('No time option provided, default processing is based on the last 30 minutes')
+            now_time = datetime.datetime.now()
+            self.to_time_str = (now_time + datetime.timedelta(minutes=1)).strftime('%Y-%m-%d %H:%M:%S')
+            if since_option:
+                self.from_time_str = (now_time - datetime.timedelta(seconds=TimeUtils.parse_time_length_to_sec(since_option))).strftime('%Y-%m-%d %H:%M:%S')
+            else:
+                self.from_time_str = (now_time - datetime.timedelta(minutes=30)).strftime('%Y-%m-%d %H:%M:%S')
+            self.stdio.print('gather from_time: {0}, to_time: {1}'.format(self.from_time_str, self.to_time_str))
+        if store_dir_option:
+            if not os.path.exists(os.path.abspath(store_dir_option)):
+                self.stdio.warn('warn: args --store_dir [{0}] incorrect: No such directory, Now create it'.format(os.path.abspath(store_dir_option)))
+                os.makedirs(os.path.abspath(store_dir_option))
+            self.gather_pack_dir = os.path.abspath(store_dir_option)
+        self.ash_sql="CALL DBMS_WORKLOAD_REPOSITORY.ASH_REPORT(  '{0}',  '{1}'".format(self.from_time_str, self.to_time_str)
+        if sql_id_option:
+            self.sql_id = sql_id_option
+            self.ash_sql = self.ash_sql + ", '{0}'".format(self.sql_id)
+        else:
+            self.ash_sql = self.ash_sql + ", NULL"
+        if trace_id_option:
+            self.trace_id = trace_id_option
+            self.ash_sql = self.ash_sql + ", '{0}'".format(self.trace_id)
+        else:
+            self.ash_sql = self.ash_sql + ", NULL"
+        if wait_class_option:
+            self.wait_class = wait_class_option
+            self.ash_sql = self.ash_sql + ", '{0}'".format(self.wait_class)
+        else:
+            self.ash_sql = self.ash_sql + ", NULL"
+        if report_type_option:
+            self.report_type = report_type_option
+            self.ash_sql = self.ash_sql + ", '{0}'".format(self.report_type)
+        else:
+            self.ash_sql = self.ash_sql + ", NULL"
+
+        try:
+            self.ash_sql = self.ash_sql + ");"
+            self.stdio.verbose("ash_sql: {0}".format(self.ash_sql))
+
+            ash_report_data=self.obconn.execute_sql(self.ash_sql)
+            if not ash_report_data or len(ash_report_data)==0:
+                self.stdio.error("ash report data is empty")
+                raise OBDIAGException("ash report data is empty")
+            ash_report=ash_report_data[0]
+
+            # save ash_report_data
+            self.ash_report_file_name="ash_report_{0}.txt".format(TimeUtils.timestamp_to_filename_time(self.gather_timestamp))
+
+            with open(self.report_path + "/"+self.ash_report_file_name, 'w') as f:
+                f.write(ash_report)
+        except Exception as e:
+            self.stdio.error("ash report gather failed, error message: {0}".format(e))
+            return False
+
+        return True
+
+    def __print_result(self):
+        self.stdio.print(Fore.YELLOW + "\nGather scene results stored in this directory: {0}\n".format(self.report_path + "/"+self.ash_report_file_name) + Style.RESET_ALL)
+
+
+
+
+

From 4d9210469d5307d497bf109501b5a5d2b2fcacf8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Mon, 29 Apr 2024 20:39:20 +0800
Subject: [PATCH 22/30] support ash

---
 cmd.py                              |  23 +++--
 common/ob_connector.py              |   9 ++
 handler/gather/gather_ash_report.py | 136 +++++++++++++---------------
 init_obdiag_cmd.sh                  |   2 +-
 4 files changed, 82 insertions(+), 88 deletions(-)

diff --git a/cmd.py b/cmd.py
index 071face0..3e8c9a0f 100644
--- a/cmd.py
+++ b/cmd.py
@@ -562,24 +562,23 @@ def _do_command(self, obdiag):
         return obdiag.gather_function('gather_scenes_run', self.opts)
 
 
-class ObdiagGatherAshReportRunCommand(ObdiagOriginCommand):
+class ObdiagGatherAshReportCommand(ObdiagOriginCommand):
 
     def __init__(self):
-        super(ObdiagGatherAshReportRunCommand, self).__init__('run', 'gather ash report')
-        self.parser.add_option('--trace_id', type='string', help="The TRACE.ID of the SQL to be sampled, if left blank or filled with NULL, indicates that TRACE.ID is not restricted.")
-        self.parser.add_option('--sql_id', type='string', help="The SQL.ID, if left blank or filled with NULL, indicates that SQL.ID is not restricted.")
-        #WAIT_CLASS
+        super(ObdiagGatherAshReportCommand, self).__init__('ash', 'gather ash report')
+        self.parser.add_option('--trace_id', type='string',
+                               help="The TRACE.ID of the SQL to be sampled, if left blank or filled with NULL, indicates that TRACE.ID is not restricted.")
+        self.parser.add_option('--sql_id', type='string',
+                               help="The SQL.ID, if left blank or filled with NULL, indicates that SQL.ID is not restricted.")
+        # WAIT_CLASS
         self.parser.add_option('--wait_class', type='string',
-                               help='Report type.',default='TEXT')
-        self.parser.add_option('--report_type', type='string',
                                help='Event types to be sampled.')
+        self.parser.add_option('--report_type', type='string',
+                               help='Report type, currently only supports text type.', default='TEXT')
         self.parser.add_option('--from', type='string',
                                help="specify the start of the time range. format: 'yyyy-mm-dd hh:mm:ss'")
         self.parser.add_option('--to', type='string',
                                help="specify the end of the time range. format: 'yyyy-mm-dd hh:mm:ss'")
-        self.parser.add_option('--since', type='string',
-                               help="Specify time range that from 'n' [d]ays, 'n' [h]ours or 'n' [m]inutes. before to now. format: <n> <m|h|d>. example: 1h.",
-                               default='30m')
         self.parser.add_option('--store_dir', type='string',
                                help='the dir to store gather result, current dir by default.', default='./')
 
@@ -587,7 +586,7 @@ def __init__(self):
                                default=os.path.expanduser('~/.obdiag/config.yml'))
 
     def init(self, cmd, args):
-        super(ObdiagGatherAshReportRunCommand, self).init(cmd, args)
+        super(ObdiagGatherAshReportCommand, self).init(cmd, args)
         return self
 
     def _do_command(self, obdiag):
@@ -600,7 +599,6 @@ def __init__(self):
         super(ObdiagAnalyzeLogCommand, self).__init__('log', 'Analyze oceanbase log from online observer machines or offline oceanbase log files')       
         self.parser.add_option('--from', type='string', help="specify the start of the time range. format: 'yyyy-mm-dd hh:mm:ss'")
         self.parser.add_option('--to', type='string', help="specify the end of the time range. format: 'yyyy-mm-dd hh:mm:ss'")
-        self.parser.add_option('--since', type='string', help="Specify time range that from 'n' [d]ays, 'n' [h]ours or 'n' [m]inutes. before to now. format: <n> <m|h|d>. example: 1h.", default='30m')
         self.parser.add_option('--scope', type='string', help="log type constrains, choices=[observer, election, rootservice, all]", default='all')
         self.parser.add_option('--grep', action="append", type='string', help="specify keywords constrain")
         self.parser.add_option('--log_level', type='string', help="oceanbase logs greater than or equal to this level will be analyze, choices=[DEBUG, TRACE, INFO, WDIAG, WARN, EDIAG, ERROR]")
@@ -745,6 +743,7 @@ def __init__(self):
         self.register_command(ObdiagGatherAwrCommand())
         self.register_command(ObdiagGatherObproxyLogCommand())
         self.register_command(ObdiagGatherSceneCommand())
+        self.register_command(ObdiagGatherAshReportCommand())
 
 
 class ObdiagGatherSceneCommand(MajorCommand):
diff --git a/common/ob_connector.py b/common/ob_connector.py
index b548b89e..e002c9e4 100644
--- a/common/ob_connector.py
+++ b/common/ob_connector.py
@@ -114,3 +114,12 @@ def execute_sql_pretty(self, sql):
         ret = from_db_cursor(cursor)
         cursor.close()
         return ret
+    def callproc(self, procname, args=()):
+        if self.conn is None:
+            self._connect_db()
+        else:
+            self.conn.ping(reconnect=True)
+        cursor = self.conn.cursor()
+        cursor.callproc(procname, args)
+        ret = cursor.fetchall()
+        return ret
diff --git a/handler/gather/gather_ash_report.py b/handler/gather/gather_ash_report.py
index 03135441..6bb6bcf3 100644
--- a/handler/gather/gather_ash_report.py
+++ b/handler/gather/gather_ash_report.py
@@ -39,45 +39,58 @@ def __init__(self, context, gather_pack_dir='./'):
         self.context = context
         self.stdio = self.context.stdio
         self.gather_pack_dir = gather_pack_dir
-        if self.context.get_variable("gather_timestamp", None) :
-            self.gather_timestamp=self.context.get_variable("gather_timestamp")
+        if self.context.get_variable("gather_timestamp", None):
+            self.gather_timestamp = self.context.get_variable("gather_timestamp")
         else:
             self.gather_timestamp = TimeUtils.get_current_us_timestamp()
         self.cluster = self.context.cluster_config
         try:
             self.obconn = OBConnector(
-                        ip=self.cluster.get("db_host"),
-                        port=self.cluster.get("db_port"),
-                        username=self.cluster.get("tenant_sys").get("user"),
-                        password=self.cluster.get("tenant_sys").get("password"),
-                        stdio=self.stdio,
-                        timeout=10000
-                    )
+                ip=self.cluster.get("db_host"),
+                port=self.cluster.get("db_port"),
+                username=self.cluster.get("tenant_sys").get("user"),
+                password=self.cluster.get("tenant_sys").get("password"),
+                stdio=self.stdio,
+                timeout=10000,
+                database="oceanbase"
+            )
         except Exception as e:
             self.stdio.error("Failed to connect to database: {0}".format(e))
             raise OBDIAGFormatException("Failed to connect to database: {0}".format(e))
 
-
     def handle(self):
         if not self.init_option():
             self.stdio.error('init option failed')
             return False
-        if not self.init_config():
-            self.stdio.error('init config failed')
-            return False
-        self.__init_variables()
         self.__init_report_path()
-        self.__init_task_names()
         self.execute()
         self.__print_result()
 
     def execute(self):
         try:
-            self.stdio.verbose("execute_tasks. the number of tasks is {0} ,tasks is {1}".format(len(self.yaml_tasks.keys()), self.yaml_tasks.keys()))
+            ash_report_arg = (self.from_time_str, self.to_time_str, self.sql_id, self.trace_id, self.wait_class, self.report_type)
+            self.stdio.verbose("ash report arg: {0}".format(ash_report_arg))
+            ash_report_data = self.obconn.callproc("DBMS_WORKLOAD_REPOSITORY.ASH_REPORT", args=ash_report_arg)
+            if not ash_report_data or len(ash_report_data) == 0:
+                self.stdio.error("ash report data is empty")
+                raise OBDIAGException("ash report data is empty")
+            ash_report = ash_report_data[0][0]
+            if len(ash_report) > 1:
+                self.stdio.verbose("ash report: \n{0}".format(ash_report))
+            else:
+                raise OBDIAGException("ash report data is empty")
 
-        except Exception as e:
-            self.stdio.error("Internal error :{0}".format(e))
+            # save ash_report_data
+            self.ash_report_file_name = "ash_report_{0}.txt".format(
+                TimeUtils.timestamp_to_filename_time(self.gather_timestamp))
+            self.ash_report_file_name=os.path.join(self.report_path, "result_summary.txt")
 
+            self.stdio.verbose("save ash report file name: {0}".format(self.ash_report_file_name))
+
+            with open(self.ash_report_file_name, 'w+') as f:
+                f.write(ash_report)
+        except Exception as e:
+            self.stdio.error("ash report gather failed, error message: {0}".format(e))
 
     def __init_report_path(self):
         try:
@@ -87,29 +100,19 @@ def __init_report_path(self):
         except Exception as e:
             self.stdio.error("init_report_path failed, error:{0}".format(e))
 
-    def __init_variables(self):
-        try:
-            self.variables = {
-                "observer_data_dir": self.ob_nodes[0].get("home_path") if self.ob_nodes and self.ob_nodes[0].get("home_path") else "",
-                "obproxy_data_dir": self.obproxy_nodes[0].get("home_path") if self.obproxy_nodes and self.obproxy_nodes[0].get("home_path") else "",
-                "from_time": self.from_time_str,
-                "to_time": self.to_time_str
-            }
-            self.stdio.verbose("gather scene variables: {0}".format(self.variables))
-        except Exception as e:
-            self.stdio.error("init gather scene variables failed, error: {0}".format(e))
 
 
     def init_option(self):
         options = self.context.options
         from_option = Util.get_option(options, 'from')
         to_option = Util.get_option(options, 'to')
-        store_dir_option = Util.get_option(options, 'store_dir',"./")
         trace_id_option = Util.get_option(options, 'trace_id')
         sql_id_option = Util.get_option(options, 'sql_id')
         report_type_option = Util.get_option(options, 'report_type')
         wait_class_option = Util.get_option(options, 'wait_class')
+        store_dir_option = Util.get_option(options, 'store_dir' )
 
+        since_option = "30m"
         if from_option is not None and to_option is not None:
             try:
                 from_timestamp = TimeUtils.parse_time_str(from_option)
@@ -117,77 +120,60 @@ def init_option(self):
                 self.from_time_str = from_option
                 self.to_time_str = to_option
             except OBDIAGFormatException:
-                self.stdio.exception('Error: Datetime is invalid. Must be in format yyyy-mm-dd hh:mm:ss. from_datetime={0}, to_datetime={1}'.format(from_option, to_option))
+                self.stdio.exception(
+                    'Error: Datetime is invalid. Must be in format yyyy-mm-dd hh:mm:ss. from_datetime={0}, to_datetime={1}'.format(
+                        from_option, to_option))
                 return False
             if to_timestamp <= from_timestamp:
                 self.stdio.exception('Error: from datetime is larger than to datetime, please check.')
                 return False
-        elif (from_option is None or to_option is None) and since_option is not None:
+        elif (from_option is None or to_option is None):
             now_time = datetime.datetime.now()
-            self.to_time_str = (now_time + datetime.timedelta(minutes=1)).strftime('%Y-%m-%d %H:%M:%S')
-            self.from_time_str = (now_time - datetime.timedelta(seconds=TimeUtils.parse_time_length_to_sec(since_option))).strftime('%Y-%m-%d %H:%M:%S')
+            self.to_time_str = (now_time + datetime.timedelta(minutes=0)).strftime('%Y-%m-%d %H:%M:%S')
+            self.from_time_str = (now_time - datetime.timedelta(
+                seconds=TimeUtils.parse_time_length_to_sec(since_option))).strftime('%Y-%m-%d %H:%M:%S')
             self.stdio.print('gather from_time: {0}, to_time: {1}'.format(self.from_time_str, self.to_time_str))
         else:
             self.stdio.warn('No time option provided, default processing is based on the last 30 minutes')
             now_time = datetime.datetime.now()
             self.to_time_str = (now_time + datetime.timedelta(minutes=1)).strftime('%Y-%m-%d %H:%M:%S')
-            if since_option:
-                self.from_time_str = (now_time - datetime.timedelta(seconds=TimeUtils.parse_time_length_to_sec(since_option))).strftime('%Y-%m-%d %H:%M:%S')
-            else:
-                self.from_time_str = (now_time - datetime.timedelta(minutes=30)).strftime('%Y-%m-%d %H:%M:%S')
+            self.from_time_str = (now_time - datetime.timedelta(minutes=30)).strftime('%Y-%m-%d %H:%M:%S')
             self.stdio.print('gather from_time: {0}, to_time: {1}'.format(self.from_time_str, self.to_time_str))
         if store_dir_option:
             if not os.path.exists(os.path.abspath(store_dir_option)):
-                self.stdio.warn('warn: args --store_dir [{0}] incorrect: No such directory, Now create it'.format(os.path.abspath(store_dir_option)))
+                self.stdio.warn('warn: args --store_dir [{0}] incorrect: No such directory, Now create it'.format(
+                    os.path.abspath(store_dir_option)))
                 os.makedirs(os.path.abspath(store_dir_option))
             self.gather_pack_dir = os.path.abspath(store_dir_option)
-        self.ash_sql="CALL DBMS_WORKLOAD_REPOSITORY.ASH_REPORT(  '{0}',  '{1}'".format(self.from_time_str, self.to_time_str)
         if sql_id_option:
             self.sql_id = sql_id_option
-            self.ash_sql = self.ash_sql + ", '{0}'".format(self.sql_id)
         else:
-            self.ash_sql = self.ash_sql + ", NULL"
+            self.sql_id = None
         if trace_id_option:
             self.trace_id = trace_id_option
-            self.ash_sql = self.ash_sql + ", '{0}'".format(self.trace_id)
         else:
-            self.ash_sql = self.ash_sql + ", NULL"
+            self.trace_id = None
+
+        if report_type_option:
+            self.report_type = report_type_option.strip()
+            if report_type_option.upper() != "TEXT":
+                self.stdio.error("Invalid argument for report type, Now just support TEXT")
+                return False
+        else:
+            self.report_type = None
         if wait_class_option:
             self.wait_class = wait_class_option
-            self.ash_sql = self.ash_sql + ", '{0}'".format(self.wait_class)
         else:
-            self.ash_sql = self.ash_sql + ", NULL"
-        if report_type_option:
-            self.report_type = report_type_option
-            self.ash_sql = self.ash_sql + ", '{0}'".format(self.report_type)
+            self.wait_class = None
+        if store_dir_option:
+            self.gather_pack_dir = store_dir_option
         else:
-            self.ash_sql = self.ash_sql + ", NULL"
-
-        try:
-            self.ash_sql = self.ash_sql + ");"
-            self.stdio.verbose("ash_sql: {0}".format(self.ash_sql))
-
-            ash_report_data=self.obconn.execute_sql(self.ash_sql)
-            if not ash_report_data or len(ash_report_data)==0:
-                self.stdio.error("ash report data is empty")
-                raise OBDIAGException("ash report data is empty")
-            ash_report=ash_report_data[0]
-
-            # save ash_report_data
-            self.ash_report_file_name="ash_report_{0}.txt".format(TimeUtils.timestamp_to_filename_time(self.gather_timestamp))
-
-            with open(self.report_path + "/"+self.ash_report_file_name, 'w') as f:
-                f.write(ash_report)
-        except Exception as e:
-            self.stdio.error("ash report gather failed, error message: {0}".format(e))
-            return False
+            self.gather_pack_dir = "./"
+        self.stdio.print("from_time: {0}, to_time: {1}, sql_id: {2}, trace_id: {3}, report_type: {4}, wait_class: {5}, store_dir: {6}".format(self.from_time_str, self.to_time_str, self.sql_id, self.trace_id, self.report_type, self.wait_class,self.gather_pack_dir))
 
         return True
 
     def __print_result(self):
-        self.stdio.print(Fore.YELLOW + "\nGather scene results stored in this directory: {0}\n".format(self.report_path + "/"+self.ash_report_file_name) + Style.RESET_ALL)
-
-
-
-
-
+        self.stdio.print(Fore.YELLOW + "\nGather scene results stored in this directory: {0}".format(
+           self.ash_report_file_name) + Style.RESET_ALL)
+        self.stdio.print("")
\ No newline at end of file
diff --git a/init_obdiag_cmd.sh b/init_obdiag_cmd.sh
index e9ea3d49..c896ecca 100644
--- a/init_obdiag_cmd.sh
+++ b/init_obdiag_cmd.sh
@@ -12,7 +12,7 @@ _obdiag_completion() {
             case "${COMP_WORDS[1]}" in
                 gather)
                     if [ "$COMP_CWORD" -eq 2 ]; then
-                        type_list="log clog slog plan_monitor stack perf sysstat obproxy_log all scene"
+                        type_list="log clog slog plan_monitor stack perf sysstat obproxy_log all scene ash"
                     elif [ "${COMP_WORDS[2]}" = "scene" ] && [ "$COMP_CWORD" -eq 3 ]; then
                         type_list="list run"
                     fi

From ac776ab295606371c141c926e0b166e3284b0f2a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Mon, 29 Apr 2024 20:47:30 +0800
Subject: [PATCH 23/30] support ash

---
 cmd.py                              |  2 +-
 handler/gather/gather_ash_report.py | 14 +++++++++-----
 2 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/cmd.py b/cmd.py
index 3e8c9a0f..69282bf1 100644
--- a/cmd.py
+++ b/cmd.py
@@ -565,7 +565,7 @@ def _do_command(self, obdiag):
 class ObdiagGatherAshReportCommand(ObdiagOriginCommand):
 
     def __init__(self):
-        super(ObdiagGatherAshReportCommand, self).__init__('ash', 'gather ash report')
+        super(ObdiagGatherAshReportCommand, self).__init__('ash', 'Gather ash report')
         self.parser.add_option('--trace_id', type='string',
                                help="The TRACE.ID of the SQL to be sampled, if left blank or filled with NULL, indicates that TRACE.ID is not restricted.")
         self.parser.add_option('--sql_id', type='string',
diff --git a/handler/gather/gather_ash_report.py b/handler/gather/gather_ash_report.py
index 6bb6bcf3..5e96b58f 100644
--- a/handler/gather/gather_ash_report.py
+++ b/handler/gather/gather_ash_report.py
@@ -28,6 +28,7 @@
 class GatherAshReportHandler(SafeStdio):
     def __init__(self, context, gather_pack_dir='./'):
         super().__init__()
+        self.result_summary_file_name = None
         self.report_type = None
         self.wait_class = None
         self.sql_id = None
@@ -83,12 +84,15 @@ def execute(self):
             # save ash_report_data
             self.ash_report_file_name = "ash_report_{0}.txt".format(
                 TimeUtils.timestamp_to_filename_time(self.gather_timestamp))
-            self.ash_report_file_name=os.path.join(self.report_path, "result_summary.txt")
-
-            self.stdio.verbose("save ash report file name: {0}".format(self.ash_report_file_name))
+            self.ash_report_file_name=os.path.join(self.report_path, self.ash_report_file_name)
 
             with open(self.ash_report_file_name, 'w+') as f:
                 f.write(ash_report)
+            self.stdio.print("save ash report file name:"+ Fore.YELLOW +"{0}".format(self.ash_report_file_name)+Style.RESET_ALL)
+            self.result_summary_file_name = os.path.join(self.report_path, "result_summary.txt")
+            with open(self.ash_report_file_name, 'w+') as f:
+                f.write(self.ash_report_file_name)
+
         except Exception as e:
             self.stdio.error("ash report gather failed, error message: {0}".format(e))
 
@@ -174,6 +178,6 @@ def init_option(self):
         return True
 
     def __print_result(self):
-        self.stdio.print(Fore.YELLOW + "\nGather scene results stored in this directory: {0}".format(
-           self.ash_report_file_name) + Style.RESET_ALL)
+        self.stdio.print(Fore.YELLOW + "\nGather ash_report results stored in this directory: {0}".format(
+           self.report_path) + Style.RESET_ALL)
         self.stdio.print("")
\ No newline at end of file

From ef08820033a6be1aff4f0bfde00517d764f85ed2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Tue, 30 Apr 2024 10:05:15 +0800
Subject: [PATCH 24/30] support ash

---
 cmd.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/cmd.py b/cmd.py
index 69282bf1..d3935ac8 100644
--- a/cmd.py
+++ b/cmd.py
@@ -605,6 +605,7 @@ def __init__(self):
         self.parser.add_option('--files', action="append", type='string', help="specify files")
         self.parser.add_option('--store_dir', type='string', help='the dir to store gather result, current dir by default.', default='./')
         self.parser.add_option('-c', type='string', help='obdiag custom config', default=os.path.expanduser('~/.obdiag/config.yml'))
+        self.parser.add_option('--since', type='string',help="Specify time range that from 'n' [d]ays, 'n' [h]ours or 'n' [m]inutes. before to now. format: <n> <m|h|d>. example: 1h.",default='30m')
 
     def init(self, cmd, args):
         super(ObdiagAnalyzeLogCommand, self).init(cmd, args)

From 1cfd7c187a89f09a83cb60a17498ef5909b0ce3e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Tue, 30 Apr 2024 10:25:43 +0800
Subject: [PATCH 25/30] ash's observer version must greater than 4.0.0.0

---
 handler/gather/gather_ash_report.py | 24 +++++++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

diff --git a/handler/gather/gather_ash_report.py b/handler/gather/gather_ash_report.py
index 5e96b58f..6f0d2977 100644
--- a/handler/gather/gather_ash_report.py
+++ b/handler/gather/gather_ash_report.py
@@ -18,9 +18,10 @@
 import datetime
 import os
 
+from common.command import get_observer_version, get_observer_version_by_sql
 from common.ob_connector import OBConnector
 from common.obdiag_exception import OBDIAGFormatException, OBDIAGException
-from common.tool import DirectoryUtil, TimeUtils, Util
+from common.tool import DirectoryUtil, TimeUtils, Util, StringUtils
 from stdio import SafeStdio
 from colorama import Fore, Style
 
@@ -45,6 +46,8 @@ def __init__(self, context, gather_pack_dir='./'):
         else:
             self.gather_timestamp = TimeUtils.get_current_us_timestamp()
         self.cluster = self.context.cluster_config
+
+        self.observer_nodes = self.context.cluster_config.get("servers")
         try:
             self.obconn = OBConnector(
                 ip=self.cluster.get("db_host"),
@@ -60,12 +63,31 @@ def __init__(self, context, gather_pack_dir='./'):
             raise OBDIAGFormatException("Failed to connect to database: {0}".format(e))
 
     def handle(self):
+        if not self.version_check():
+            self.stdio.error('version check failed')
+            return False
         if not self.init_option():
             self.stdio.error('init option failed')
             return False
         self.__init_report_path()
         self.execute()
         self.__print_result()
+    def version_check(self):
+        observer_version = ""
+        try:
+            observer_version = get_observer_version_by_sql(self.ob_cluster, self.stdio)
+        except Exception as e:
+            if len(self.observer_nodes) > 0:
+                observer_version = get_observer_version(True, self.observer_nodes[0]["ssher"],
+                                                            self.observer_nodes[0]["home_path"],self.stdio)
+            else:
+                self.stdio.warn("RCAHandler Failed to get observer version:{0}".format(e))
+        self.stdio.verbose("RCAHandler.init get observer version: {0}".format(observer_version))
+
+        if not (observer_version == "4.0.0.0" or StringUtils.compare_versions_greater(observer_version, "4.0.0.0")):
+            self.stdio.error("observer version: {0}, must greater than 4.0.0.0".format(observer_version))
+            return False
+        return True
 
     def execute(self):
         try:

From e0b3271b2dda7c82b95459b9ea41e7564802df33 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Tue, 30 Apr 2024 10:28:57 +0800
Subject: [PATCH 26/30] update format

---
 common/ob_connector.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/common/ob_connector.py b/common/ob_connector.py
index e002c9e4..948644a5 100644
--- a/common/ob_connector.py
+++ b/common/ob_connector.py
@@ -114,6 +114,7 @@ def execute_sql_pretty(self, sql):
         ret = from_db_cursor(cursor)
         cursor.close()
         return ret
+
     def callproc(self, procname, args=()):
         if self.conn is None:
             self._connect_db()

From fa4108b7574ff631d2b70c51d3e03059a64080c0 Mon Sep 17 00:00:00 2001
From: Teingi <jingshun.tq@antgroup.com>
Date: Tue, 30 Apr 2024 15:51:03 +0800
Subject: [PATCH 27/30] update README

---
 README-CN.md | 2 +-
 README.md    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/README-CN.md b/README-CN.md
index fe99b285..bbd70cd2 100644
--- a/README-CN.md
+++ b/README-CN.md
@@ -75,7 +75,7 @@ obdiag 期望构建一个开放的社区，我们欢迎任何形式的贡献，
 |---------|---------------|---------|
 |1.6.0| 2024.01| <ul><li> 场景化信息采集 </li><li> 场景化根因分析 </li></ul> |
 |2.0.0|2024.03| <ul><li> context改造，场景化扩展能力增强 </li><li> 支持在线更新巡检、采集的task </li><li> 根因分析二期 </li></ul>|
-|2.1.0|2024.04| <ul><li> 根因分析场景扩展 </li><li> 新增 tabledump 采集 </li></ul>|
+|2.1.0|2024.04| <ul><li> 根因分析场景扩展 </li><li> 新增 ash 报告 采集 </li></ul>|
 |2.2.0|2024.05| <ul><li> 根因分析场景扩展 </li></ul>|
 |2.3.0|2024.06| <ul><li> 根因分析场景扩展 </li><li> 支持 SQL 诊断 </li></ul>|
 |2.4.0|2024.07| <ul><li> 根因分析场景扩展 </li><li> 适配两款内核的诊断工具 </li></ul>|
diff --git a/README.md b/README.md
index 376402e1..203fa922 100644
--- a/README.md
+++ b/README.md
@@ -79,7 +79,7 @@ obdiag envisions an open community. We welcome your contributions in any form:
 |---------|---------------|---------|
 |1.6.0| 2024.01| <ul><li> Scenario based fault information collection </li><li> Scenario based root cause analysis </li></ul> |
 |2.0.0|2024.03| <ul><li> Context Transformation, Enhanced Scene Expansion Capabilities</li><li> Support online updating of inspection and gather tasks </li><li>Root Cause Analysis Phase II Transformation </li></ul>|
-|2.1.0|2024.04| <ul><li> Root Cause Analysis Scenario Expansion </li><li> Gather tabledump </li></ul>|
+|2.1.0|2024.04| <ul><li> Root Cause Analysis Scenario Expansion </li><li> Gather ash report </li></ul>|
 |2.2.0|2024.05| <ul><li> Root Cause Analysis Scenario Expansion </li></ul>|
 |2.3.0|2024.06| <ul><li> Root Cause Analysis Scenario Expansion </li><li> Support SQL Diagnosis </li></ul>|
 |2.4.0|2024.07| <ul><li> Root Cause Analysis Scenario Expansion </li><li> Adapting Two Additional Kernel Diagnostic Tools </li></ul>|

From 93cf3c9310092a080f853deced600869a20c5ab6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Mon, 6 May 2024 10:29:04 +0800
Subject: [PATCH 28/30] fix ash

---
 handler/gather/gather_ash_report.py | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/handler/gather/gather_ash_report.py b/handler/gather/gather_ash_report.py
index 6f0d2977..c445f263 100644
--- a/handler/gather/gather_ash_report.py
+++ b/handler/gather/gather_ash_report.py
@@ -21,6 +21,7 @@
 from common.command import get_observer_version, get_observer_version_by_sql
 from common.ob_connector import OBConnector
 from common.obdiag_exception import OBDIAGFormatException, OBDIAGException
+from common.ssh import SshHelper
 from common.tool import DirectoryUtil, TimeUtils, Util, StringUtils
 from stdio import SafeStdio
 from colorama import Fore, Style
@@ -41,6 +42,7 @@ def __init__(self, context, gather_pack_dir='./'):
         self.context = context
         self.stdio = self.context.stdio
         self.gather_pack_dir = gather_pack_dir
+        self.ob_cluster = self.context.cluster_config
         if self.context.get_variable("gather_timestamp", None):
             self.gather_timestamp = self.context.get_variable("gather_timestamp")
         else:
@@ -78,7 +80,8 @@ def version_check(self):
             observer_version = get_observer_version_by_sql(self.ob_cluster, self.stdio)
         except Exception as e:
             if len(self.observer_nodes) > 0:
-                observer_version = get_observer_version(True, self.observer_nodes[0]["ssher"],
+                ssher=SshHelper(self.observer_nodes[0]["ip"], self.observer_nodes[0]["ssh_port"], self.observer_nodes[0]["ssh_username"], self.observer_nodes[0]["ssh_password"])
+                observer_version = get_observer_version(True, ssher,
                                                             self.observer_nodes[0]["home_path"],self.stdio)
             else:
                 self.stdio.warn("RCAHandler Failed to get observer version:{0}".format(e))
@@ -110,9 +113,9 @@ def execute(self):
 
             with open(self.ash_report_file_name, 'w+') as f:
                 f.write(ash_report)
-            self.stdio.print("save ash report file name:"+ Fore.YELLOW +"{0}".format(self.ash_report_file_name)+Style.RESET_ALL)
+            self.stdio.print("save ash report file name: "+ Fore.YELLOW +"{0}".format(self.ash_report_file_name)+Style.RESET_ALL)
             self.result_summary_file_name = os.path.join(self.report_path, "result_summary.txt")
-            with open(self.ash_report_file_name, 'w+') as f:
+            with open(self.result_summary_file_name, 'w+') as f:
                 f.write(self.ash_report_file_name)
 
         except Exception as e:

From f5ab7cff610a8b35e9afe1acb19c668d357eb66a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Tue, 7 May 2024 16:26:29 +0800
Subject: [PATCH 29/30] fix rca

---
 handler/rca/rca_handler.py               |  7 ++-
 handler/rca/scene/lock_conflict_scene.py |  2 +-
 handler/rca/scene/major_hold_scene.py    | 73 ++++++++++++++----------
 3 files changed, 51 insertions(+), 31 deletions(-)

diff --git a/handler/rca/rca_handler.py b/handler/rca/rca_handler.py
index 94d4d017..6574c6b0 100644
--- a/handler/rca/rca_handler.py
+++ b/handler/rca/rca_handler.py
@@ -293,15 +293,20 @@ def export(self):
 
 
 class RCA_ResultRecord:
-    def __init__(self):
+    def __init__(self,stdio=None):
         self.records = []
         self.suggest = "The suggest: "
+        self.stdio = stdio
 
     def add_record(self, record):
         self.records.append(record)
+        if self.stdio is not None:
+            self.stdio.verbose("add record: {0}".format(record))
 
     def add_suggest(self, suggest):
         self.suggest += suggest
+        if self.stdio is not None:
+            self.stdio.verbose("add suggest: {0}".format(suggest))
     def suggest_is_empty(self):
         return self.suggest == "The suggest: "
 
diff --git a/handler/rca/scene/lock_conflict_scene.py b/handler/rca/scene/lock_conflict_scene.py
index 6e0ab71a..85206fc6 100644
--- a/handler/rca/scene/lock_conflict_scene.py
+++ b/handler/rca/scene/lock_conflict_scene.py
@@ -73,7 +73,7 @@ def __execute_4_2(self):
                     trans_record.add_record("wait_lock_trans_id is {0}".format(wait_lock_trans_id))
                     session_datas = cursor_by_trans_id.fetchall()
                     trans_record.add_record(
-                        "get SESSION_ID by wait_lock_trans_id:{0}. get data:{0}".format(trans_id, session_datas))
+                        "get SESSION_ID by wait_lock_trans_id:{0}. get data:{1}".format(trans_id, session_datas))
                     if len(session_datas) != 1:
                         trans_record.add_suggest("wait_lock_session_id is not get. The holding lock trans_id is {0}. You can resolve lock conflicts by killing this locked session, but this may cause business exceptions. Please use with caution.".format(trans_id))
                         continue
diff --git a/handler/rca/scene/major_hold_scene.py b/handler/rca/scene/major_hold_scene.py
index 7ebfb93d..55fed00c 100644
--- a/handler/rca/scene/major_hold_scene.py
+++ b/handler/rca/scene/major_hold_scene.py
@@ -52,7 +52,7 @@ def execute(self):
             COMPACTING_data = self.ob_connector.execute_sql(
                 'select * from oceanbase.CDB_OB_MAJOR_COMPACTION where IS_ERROR="YES";')
             if len(COMPACTING_data) == 0:
-                first_record.add_record("CDB_OB_MAJOR_COMPACTION is not exist IS_ERROR='YES'")
+                first_record.add_record("ON CDB_OB_MAJOR_COMPACTION WHERE IS_ERROR='YES', data is not exist")
             else:
                 need_tag = True
                 CDB_OB_MAJOR_COMPACTION_err_tenant_ids = []
@@ -177,22 +177,26 @@ def execute(self):
 
                 sql = "select * from oceanbase.GV$OB_COMPACTION_PROGRESS where TENANT_ID='{0}' and COMPACTION_SCN='{1}';".format(
                     err_tenant_id, global_broadcast_scn)
-                OB_COMPACTION_PROGRESS_data_global_broadcast_scn = self.ob_connector.execute_sql(sql)
-                file_name = "{0}/rca_major_hold_{1}_OB_COMPACTION_PROGRESS_data_global_broadcast_scn".format(
+                cursor = self.ob_connector.execute_sql_return_cursor_dictionary(sql)
+                OB_COMPACTION_PROGRESS_data_global_broadcast_scn_data = cursor.fetchall()
+                OB_COMPACTION_PROGRESS_data_global_broadcast_scn_json_data = json.dumps(OB_COMPACTION_PROGRESS_data_global_broadcast_scn_data, cls=DateTimeEncoder)
+                file_name = "{0}/rca_major_hold_{1}_OB_COMPACTION_PROGRESS_data_global_broadcast_scn.json".format(
                     self.local_path, err_tenant_id)
-                with open(file_name, 'w') as f:
-                    f.write(str(OB_COMPACTION_PROGRESS_data_global_broadcast_scn))
+                with open(file_name, 'w+') as f:
+                    f.write(str(OB_COMPACTION_PROGRESS_data_global_broadcast_scn_json_data))
                 tenant_record.add_record(
                     "tenant_id:{0} OB_COMPACTION_PROGRESS_data_global_broadcast_scn save on {1}".format(err_tenant_id,
                                                                                                         file_name))
 
                 sql = "select * from oceanbase.GV$OB_COMPACTION_PROGRESS where TENANT_ID='{0}' and COMPACTION_SCN='{1}';".format(
                     err_tenant_id, last_scn)
-                OB_COMPACTION_PROGRESS_data_last_scn = self.ob_connector.execute_sql(sql)
-                file_name = "{0}/rca_major_hold_{1}_OB_COMPACTION_PROGRESS_data_last_scn".format(
+                cursor = self.ob_connector.execute_sql_return_cursor_dictionary(sql)
+                OB_COMPACTION_PROGRESS_data_last_scn_data = cursor.fetchall()
+                OB_COMPACTION_PROGRESS_data_last_scn_json_data = json.dumps(OB_COMPACTION_PROGRESS_data_last_scn_data, cls=DateTimeEncoder)
+                file_name = "{0}/rca_major_hold_{1}_OB_COMPACTION_PROGRESS_data_last_scn.json".format(
                     self.local_path, err_tenant_id)
-                with open(file_name, 'w') as f:
-                    f.write(str(OB_COMPACTION_PROGRESS_data_last_scn))
+                with open(file_name, 'w+') as f:
+                    f.write(str(OB_COMPACTION_PROGRESS_data_last_scn_json_data))
                 tenant_record.add_record(
                     "tenant_id:{0} OB_COMPACTION_PROGRESS_data_last_scn save on {1}".format(err_tenant_id,
                                                                                             file_name))
@@ -233,19 +237,31 @@ def execute(self):
             try:
                 cursor = self.ob_connector.execute_sql_return_cursor_dictionary(
                     'select * from oceanbase.GV$OB_COMPACTION_SUGGESTIONS where tenant_id="{0}";'.format(err_tenant_id))
-                columns = [column[0] for column in cursor.description]
                 OB_COMPACTION_SUGGESTIONS_data = cursor.fetchall()
                 OB_COMPACTION_SUGGESTIONS_info = json.dumps(OB_COMPACTION_SUGGESTIONS_data, cls=DateTimeEncoder)
-                file_name = "{0}/rca_major_hold_{1}_OB_COMPACTION_SUGGESTIONS_info".format(
+                file_name = "{0}/rca_major_hold_{1}_OB_COMPACTION_SUGGESTIONS_info.json".format(
                     self.local_path, err_tenant_id)
-                with open(file_name, 'w') as f:
+                with open(file_name, 'w+') as f:
                     f.write(str(OB_COMPACTION_SUGGESTIONS_info))
                 tenant_record.add_record(
                     "tenant_id:{0} OB_COMPACTION_PROGRESS_data_last_scn save on {1}".format(err_tenant_id,
                                                                                             file_name))
 
             except Exception as e:
-                self.stdio.warn("MajorHoldScene execute 5 exception: {0}".format(e))
+                self.stdio.error("MajorHoldScene execute 5 exception: {0}".format(e))
+            #6
+            try:
+                # get oceanbase.__all_virtual_dag_warning_history status="RETRYED" type like "%MERGE%"
+                cursor=self.ob_connector.execute_sql_return_cursor_dictionary('SELECT * FROM oceanbase.__all_virtual_dag_warning_history WHERE tenant_id="{0}" AND status="RETRYED" AND type like "%MERGE%";'.format(err_tenant_id))
+                __all_virtual_dag_warning_history_data = cursor.fetchall()
+                file_name = "{0}/rca_major_hold_{0}_all_virtual_dag_warning_history.json".format(
+                    self.local_path, err_tenant_id)
+                __all_virtual_dag_warning_history_json_data = json.dumps(__all_virtual_dag_warning_history_data, cls=DateTimeEncoder)
+                with open(file_name, 'w+') as f:
+                    f.write(str(__all_virtual_dag_warning_history_json_data))
+                tenant_record.add_record("tenant_id:{0} all_virtual_dag_warning_history save on {1}".format(err_tenant_id,file_name))
+            except Exception as e:
+                self.stdio.error("MajorHoldScene execute 6 exception: {0}".format(e))
             tenant_record.add_suggest("send the {0} to the oceanbase community".format(self.local_path))
             self.Result.records.append(tenant_record)
 
@@ -255,14 +271,14 @@ def get_info__all_virtual_compaction_diagnose_info(self, tenant_record):
                 "SELECT * FROM oceanbase.__all_virtual_compaction_diagnose_info WHERE IS_ERROR = 'NO' OR IS_SUSPENDED = 'NO';")
             if len(COMPACTING_datas) == 0:
                 tenant_record.add_record(
-                    "sql:select * from oceanbase.__all_virtual_compaction_diagnose_info; no data")
+                    "ON oceanbase.__all_virtual_compaction_diagnose_info. No data WHERE IS_ERROR = 'NO' OR IS_SUSPENDED = 'NO';")
                 return
             else:
                 tenant_record.add_record(
                     "sql:select * from oceanbase.CDB_OB_MAJOR_COMPACTION where status=COMPACTING; "
                     "result:{0}".format(str(COMPACTING_datas)))
             for index, COMPACTING_data in COMPACTING_datas:
-                self.diagnose_info_switch(COMPACTING_data)
+                self.diagnose_info_switch(COMPACTING_data,tenant_record)
         except Exception as e:
             raise RCAExecuteException(
                 "MajorHoldScene execute get_info__all_virtual_compaction_diagnose_info exception: {0}".format(e))
@@ -288,7 +304,7 @@ def diagnose_info_switch(self, sql_data, tenant_record):
             log_name = "/tmp/rca_major_hold_schedule_medium_failed_{1}_{2}_{0}.txt".format(tenant_id, svr_ip,
                                                                                            svr_port)
             tenant_record.add_record(
-                "diagnose_info type is 'schedule medium failed'. time is {0},observer is {1}:{2},the log is {3}".format(
+                "diagnose_info type: 'schedule medium failed'. time is {0},observer is {1}:{2},the log is {3}".format(
                     create_time, svr_ip, svr_port, log_name))
             ssh_helper.ssh_exec_cmd(
                 'grep "schedule_medium_failed" {1}/log/observer.log* |grep -P  "\[\d+\]" -m 1 -o >{0}'.format(log_name,
@@ -309,12 +325,12 @@ def diagnose_info_switch(self, sql_data, tenant_record):
                     table_id, tenant_id))[0][7]
             if compaction_scn > global_broadcast_scn:
                 tenant_record.add_record(
-                    "diagnose_info type is error_no. error_no: {0}, err_trace: {1} , table_id:{2}, tenant_id:{3}, compaction_scn: {4}, global_broadcast_scn: {5}. compaction_scn>global_broadcast_scn".format(
+                    "diagnose_info type: error_no. error_no: {0}, err_trace: {1} , table_id:{2}, tenant_id:{3}, compaction_scn: {4}, global_broadcast_scn: {5}. compaction_scn>global_broadcast_scn".format(
                         err_no, err_trace, table_id, tenant_id, compaction_scn, global_broadcast_scn))
                 return
             else:
                 tenant_record.add_record(
-                    "diagnose_info type is error_no. error_no: {0}, err_trace:{1}, table_id:{2}, tenant_id:{3}, compaction_scn: {4}, global_broadcast_scn: {5}. compaction_scn<global_broadcast_scn".format(
+                    "diagnose_info type: error_no. error_no: {0}, err_trace:{1}, table_id:{2}, tenant_id:{3}, compaction_scn: {4}, global_broadcast_scn: {5}. compaction_scn<global_broadcast_scn".format(
                         err_no, err_trace, table_id, tenant_id, compaction_scn, global_broadcast_scn))
                 node = None
                 ssh_helper = None
@@ -343,7 +359,7 @@ def diagnose_info_switch(self, sql_data, tenant_record):
                 raise RCAExecuteException("can not find observer node by ip:{0}, port:{1}".format(svr_ip, svr_port))
 
             tenant_record.add_record(
-                "diagnose_info type is 'error_no'. time is {0},observer is {1}:{2},the log is {3}".format(
+                "diagnose_info type : 'error_no'. time is {0},observer is {1}:{2},the log is {3}".format(
                     create_time, svr_ip, svr_port, log_name))
             ssh_helper.ssh_exec_cmd('cat observer.log* |grep "{1}" > /tmp/{0}'.format(log_name, err_trace))
             ssh_helper.download(log_name, local_path=self.local_path)
@@ -354,7 +370,7 @@ def diagnose_info_switch(self, sql_data, tenant_record):
             cursor = self.ob_connector.execute_sql_return_cursor_dictionary(
                 "select * from oceanbase.__all_virtual_ls_info where tenant_id='{0}' and ls_id='{1}';".format(tenant_id,
                                                                                                               ls_id))
-            columns = [column[0] for column in cursor.description]
+            
             all_virtual_ls_info_data = cursor.fetchall()
             self.all_virtual_ls_info = json.dumps(all_virtual_ls_info_data, cls=DateTimeEncoder)
             tenant_record.add_record(
@@ -363,7 +379,7 @@ def diagnose_info_switch(self, sql_data, tenant_record):
                 "result:{0}".format(str(self.all_virtual_ls_info)))
             return
         elif "memtable can not create dag successfully" in diagnose_info:
-            tenant_record.add_record("diagnose_info type is memtable can not create dag successfully.")
+            tenant_record.add_record("diagnose_info type: memtable can not create dag successfully.")
 
             global_broadcast_scn = self.ob_connector.execute_sql(
                 "select * from oceanbase.CDB_OB_MAJOR_COMPACTION where TENANT_ID='{0}';".format(tenant_id))[0][3]
@@ -372,14 +388,14 @@ def diagnose_info_switch(self, sql_data, tenant_record):
                     table_id, tenant_id))[0][7]
             if compaction_scn > global_broadcast_scn:
                 tenant_record.add_record(
-                    "diagnose_info type is memtable can not create dag successfully.   table_id:{0}, tenant_id:{1}, compaction_scn: {2}, global_broadcast_scn: {3}. compaction_scn>global_broadcast_scn".format(
+                    "diagnose_info type: memtable can not create dag successfully.   table_id:{0}, tenant_id:{1}, compaction_scn: {2}, global_broadcast_scn: {3}. compaction_scn>global_broadcast_scn".format(
                         table_id, tenant_id, compaction_scn, global_broadcast_scn))
                 return
             else:
                 cursor = self.ob_connector.execute_sql_return_cursor_dictionary(
                     "select * from oceanbase.__all_virtual_dag_scheduler where svr_ip='{0}' and svr_port='{1}' and tenant_id='{2}';".format(
                         svr_ip, svr_port, tenant_id))
-                columns = [column[0] for column in cursor.description]
+                
                 all_virtual_ls_info_data = cursor.fetchall()
                 self.all_virtual_ls_info = json.dumps(all_virtual_ls_info_data, cls=DateTimeEncoder)
                 tenant_record.add_record(
@@ -390,11 +406,11 @@ def diagnose_info_switch(self, sql_data, tenant_record):
 
             return
         elif "medium wait for freeze" in diagnose_info or "major wait for freeze" in diagnose_info:
-            tenant_record.add_record("diagnose_info type is medium wait for freeze or major wait for freeze.")
+            tenant_record.add_record("diagnose_info type: medium wait for freeze or major wait for freeze.")
             cursor = self.ob_connector.execute_sql_return_cursor_dictionary(
                 "select * from oceanbase.__all_virtual_dag_scheduler where svr_ip='{0}' and svr_port='{1}' and tenant_id='{2}';".format(
                     svr_ip, svr_port, tenant_id))
-            columns = [column[0] for column in cursor.description]
+            
             all_virtual_ls_info_data = cursor.fetchall()
             self.all_virtual_ls_info = json.dumps(all_virtual_ls_info_data, cls=DateTimeEncoder)
             tenant_record.add_record(
@@ -404,11 +420,10 @@ def diagnose_info_switch(self, sql_data, tenant_record):
                 "result:{0}".format(str(self.all_virtual_ls_info)))
             return
         elif "major not schedule for long time" in diagnose_info:
-            tenant_record.add_record("diagnose_info type is major not schedule for long time")
+            tenant_record.add_record("diagnose_info type: ‘major not schedule for long time’")
             cursor = self.ob_connector.execute_sql_return_cursor_dictionary(
                 "select * from oceanbase.__all_virtual_tablet_compaction_info where svr_ip='{0}' and svr_port='{1}' and tenant_id='{2}' and ls_id='{3}' and tablet_id='{4}';".format(
                     svr_ip, svr_port, tenant_id, ls_id, table_id))
-            columns = [column[0] for column in cursor.description]
             all_virtual_ls_info_data = cursor.fetchall()
             all_virtual_tablet_compaction_info = json.dumps(all_virtual_ls_info_data, cls=DateTimeEncoder)
             tenant_record.add_record(
@@ -429,7 +444,7 @@ def diagnose_info_switch(self, sql_data, tenant_record):
                                                                                                      svr_ip,
                                                                                                      svr_port)
             tenant_record.add_record(
-                "diagnose_info type is 'major not schedule for long time'. time is {0},observer is {1}:{2},the log is {3}".format(
+                "diagnose_info type: 'major not schedule for long time'. time is {0},observer is {1}:{2},the log is {3}".format(
                     create_time, svr_ip, svr_port, log_name))
             thread_id = ssh_helper.ssh_exec_cmd(
                 'cat {0}/log/observer.log* |grep "MediumLoo" -m 1 |grep -P  "\[\d+\]" -m 1 -o | grep -oP "\d+"'.format(
@@ -441,7 +456,7 @@ def diagnose_info_switch(self, sql_data, tenant_record):
             ssh_helper.ssh_exec_cmd("rm -rf {0}".format(log_name))
 
         else:
-            tenant_record.add_record("diagnose_info type is Unknown.")
+            tenant_record.add_record("diagnose_info type: Unknown.")
 
     def export_result(self):
         return self.Result.export()

From 51a86fc0202b1664efccf76a625b24b4f0c725ff Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=B8=A0=E7=A3=8A?= <xuyan.wxy@oceanbase.com>
Date: Tue, 7 May 2024 18:03:58 +0800
Subject: [PATCH 30/30] fix rca

---
 handler/rca/scene/lock_conflict_scene.py | 62 +++++++++++++++++-------
 handler/rca/scene/major_hold_scene.py    |  2 +-
 2 files changed, 46 insertions(+), 18 deletions(-)

diff --git a/handler/rca/scene/lock_conflict_scene.py b/handler/rca/scene/lock_conflict_scene.py
index 85206fc6..97024ad4 100644
--- a/handler/rca/scene/lock_conflict_scene.py
+++ b/handler/rca/scene/lock_conflict_scene.py
@@ -15,18 +15,22 @@
 @file: lock_conflict_scene.py
 @desc:
 """
+import json
+
 from handler.rca.rca_exception import RCAInitException, RCANotNeedExecuteException
 from handler.rca.rca_handler import RcaScene, RCA_ResultRecord
-from common.tool import StringUtils
+from common.tool import StringUtils, DateTimeEncoder
 
 
 class LockConflictScene(RcaScene):
     def __init__(self):
         super().__init__()
+        self.local_path = ""
 
     def init(self, context):
         try:
             super().init(context)
+            self.local_path = context.get_variable('store_dir')
             if self.observer_version is None or len(self.observer_version.strip()) == 0 or self.observer_version == "":
                 raise Exception("observer version is None. Please check the NODES conf.")
         except Exception as e:
@@ -65,27 +69,51 @@ def __execute_4_2(self):
                     continue
                 else:
                     trans_id = OB_LOCKS_data['ID1']
-                    trans_record.add_record("holding lock trans_id is {0}".format(trans_id))
+                    trans_record.add_record("get holding_lock trans_id:{0}".format(trans_id))
+                    holding_lock_session_id=trans_id
+                    self.stdio.verbose("get holding lock SESSION_ID by trans_id:{0}".format(trans_id))
+                    cursor_by_trans_id = self.ob_connector.execute_sql_return_cursor_dictionary(
+                        'select * from oceanbase.V$OB_TRANSACTION_PARTICIPANTS where TX_ID="{0}";'.format(holding_lock_session_id))
+                    holding_lock_session_id_datas = cursor_by_trans_id.fetchall()
+                    holding_lock_session_id = "not get"
+                    if len(holding_lock_session_id_datas) == 1:
+                        holding_lock_session_id=holding_lock_session_id_datas[0].get("SESSION_ID")
+                    trans_record.add_record("get holding_lock_session_id:{0}".format(holding_lock_session_id))
+
                     wait_lock_trans_id=OB_LOCKS_data['TRANS_ID']
                     cursor_by_trans_id = self.ob_connector.execute_sql_return_cursor_dictionary(
                         'select * from oceanbase.V$OB_TRANSACTION_PARTICIPANTS where TX_ID="{0}";'.format(wait_lock_trans_id))
-                    self.stdio.verbose("get SESSION_ID by trans_id:{0}".format(trans_id))
                     trans_record.add_record("wait_lock_trans_id is {0}".format(wait_lock_trans_id))
-                    session_datas = cursor_by_trans_id.fetchall()
-                    trans_record.add_record(
-                        "get SESSION_ID by wait_lock_trans_id:{0}. get data:{1}".format(trans_id, session_datas))
-                    if len(session_datas) != 1:
-                        trans_record.add_suggest("wait_lock_session_id is not get. The holding lock trans_id is {0}. You can resolve lock conflicts by killing this locked session, but this may cause business exceptions. Please use with caution.".format(trans_id))
-                        continue
-                    if session_datas[0].get("SESSION_ID") is not None:
-                        trans_record.add_record("get SESSION_ID:{0}".format(session_datas[0].get("SESSION_ID")))
-                        trans_record.add_suggest("Sessions corresponding to lock transactions. The ID is {0}, "
-                                                 "which may be a lock conflict issue.You can be accessed through kill "
-                                                 "session to rollback the corresponding transaction with ID. Please "
-                                                 "note that this will result in corresponding transaction regression! "
-                                                 "".format(session_datas[0].get("SESSION_ID")))
+                    wait_lock_session_datas = cursor_by_trans_id.fetchall()
+                    wait_lock_session_id="not get"
+                    if len(wait_lock_session_datas) == 1:
+                        wait_lock_session_id=wait_lock_session_datas[0].get("SESSION_ID")
+                    trans_record.add_record("get wait_lock_session_id:{0}".format(wait_lock_session_datas[0].get("SESSION_ID")))
+                    self.stdio.verbose("get sql_info by holding_lock_session_id:{0}".format(holding_lock_session_id))
+                    # check SQL_AUDIT switch
+                    sql_info="not find"
+
+                    cursor_check_switch = self.ob_connector.execute_sql_return_cursor_dictionary("SHOW PARAMETERS LIKE '%enable_sql_audit%';")
+                    audit_switch_value = cursor_check_switch.fetchone().get('value')
+                    if audit_switch_value.strip().upper() == "TRUE":
+                        holding_lock_sql_info_cursor=self.ob_connector.execute_sql_return_cursor_dictionary(
+                            'SELECT * FROM oceanbase.v$OB_SQL_AUDIT where SID="{0}";'.format(holding_lock_session_id))
+                        holding_lock_sql_info= holding_lock_sql_info_cursor.fetchall()
+                        if len(holding_lock_sql_info)==0:
+                            trans_record.add_record("holding_lock_session_id: {0}; not find sql_info on v$OB_SQL_AUDIT".format(holding_lock_session_id))
+                        else:
+                            holding_lock_sql_info_json_data = json.dumps(holding_lock_sql_info, cls=DateTimeEncoder)
+                            file_name = "{0}/rca_holding_lock_sql_info_{1}.json".format(  self.local_path, holding_lock_session_id)
+                            with open(file_name, 'w+') as f:
+                                f.write(str(holding_lock_sql_info_json_data))
+                            trans_record.add_record(
+                                "holding_lock_session_id: {0}. holding_lock_sql_info save on {1}".format(holding_lock_session_id,
+                                    file_name))
+                            sql_info="save on {0}".format(file_name)
                     else:
-                        trans_record.add_record("wait_lock_session_id is not get. The holding lock trans_id is {0}. You can resolve lock conflicts by killing this locked session, but this may cause business exceptions. Please use with caution.".format(trans_id))
+                        self.stdio.verbose("SQL_AUDIT switch is False")
+                        trans_record.add_record("SQL_AUDIT switch is False. can't get sql_info")
+                    trans_record.add_suggest("holding_lock_session_id: {0}; wait_lock_session_id : {1}, sql_info: {2}. Lock conflicts can be ended by killing holding_lock_session_id or wait_lock_session_id".format(holding_lock_session_id,wait_lock_session_id,sql_info))
 
             except Exception as e:
                 trans_record.add_record("get SESSION_ID panic. OB_LOCKS_data:{0} error: {1}".format(OB_LOCKS_data, e))
diff --git a/handler/rca/scene/major_hold_scene.py b/handler/rca/scene/major_hold_scene.py
index 55fed00c..e72ecb14 100644
--- a/handler/rca/scene/major_hold_scene.py
+++ b/handler/rca/scene/major_hold_scene.py
@@ -31,7 +31,7 @@ def __init__(self):
     def init(self, context):
         try:
             super().init(context)
-            self.local_path = context.get_variable('result_path')
+            self.local_path = context.get_variable('store_dir')
 
             if self.observer_version is None:
                 raise Exception("obproxy version is None. Please check the NODES conf.")