Merge pull request #94 from Teingi/master

1.6.0 release

README-CN.md

@@ -19,7 +19,7 @@
     </a>
 </p>
 
-# Oceanbase Diagnostic Tool (obdiag)
+# OceanBase Diagnostic Tool (obdiag)
 OceanBase Diagnostic Tool (obdiag) 是一款专门OceanBase打造的敏捷诊断工具，功能包括诊断信息收集、分析、巡检，可以在OceanBase集群不同的部署模式下（OCP，OBD或用户根据文档手工部署）实现一键执行。
 
 # 安装 obdiag
@@ -60,13 +60,17 @@ obdiag config -h <db_host> -u <sys_user> [-p password] [-P port]
 ## 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)
+
 ## obdiag 一键信息采集功能
 
 - [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)
@@ -76,6 +80,9 @@ obdiag config -h <db_host> -u <sys_user> [-p password] [-P port]
 - [一键分析OB日志](./docs/analyze_ob_log.md)
 - [一键全链路诊断](./docs/analyze_flt_trace.md)
 
+## 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。

README.md

@@ -21,8 +21,7 @@ English | [中文版](README-CN.md)
     </a>
 </p>
 
-
-# Oceanbase Diagnostic Tool (obdiag)
+# OceanBase Diagnostic Tool (obdiag)
 OceanBase Diagnostic Tool (obdiag) is is a quick diagnostic tool for open-source OceanBase software. The features include gather\analyze\check OceanBase Diagnostic information. It can be executed with one click in different deployment modes of OceanBase clusters (OCP, OBD, or manually deployed by users according to documentation).
 
 # Install obdiag
@@ -64,6 +63,9 @@ obdiag config -h <db_host> -u <sys_user> [-p password] [-P port]
 ## obdiag check Fuctions
 - [check](./docs/check.md)
 
+## obdiag gather scene Fuctions
+- [gather scene](./docs/gather_scene.md)
+
 ## obdiag gather Fuctions
 
 - [gather log](./docs/gather_ob_log.md)
@@ -80,6 +82,9 @@ obdiag config -h <db_host> -u <sys_user> [-p password] [-P port]
 - [analyze log](./docs/analyze_ob_log.md)
 - [analyze flt trace log](./docs/analyze_flt_trace.md)
 
+## obdiag rca Fuctions
+- [rca](./docs/rca.md)
+
 # 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.

clean_all_result.sh

@@ -1,3 +1,4 @@
 rm -rf ./gather_pack_*
 rm -rf ./analyze_pack_*
-rm -rf ./analyze_flt_result*
+rm -rf ./analyze_flt_result*
+rm -rf ./check_report

common/command.py

@@ -336,7 +336,7 @@ def get_observer_version(is_ssh, ssh_helper, ob_install_dir):
                 ob_version_info = SshClient().run_get_stderr(ssh_helper, cmd)
             else:
                 ob_version_info = LocalClient().run_get_stderr(cmd)
-            logger.info("get observer version with LD_LIBRARY_PATH,cmd:{0}, result:{1}".format(cmd,ob_version_info))
+            logger.info("get observer version with LD_LIBRARY_PATH,cmd:{0}".format(cmd))
             if "REVISION" not in ob_version_info:
                 raise Exception("Please check conf about observer,{0}".format(ob_version_info))
             ob_version = re.findall(r'[(]OceanBase.CE\s(.+?)[)]', ob_version_info)[0]
@@ -355,7 +355,7 @@ def get_obproxy_version(is_ssh, ssh_helper, obproxy_install_dir):
         obproxy_version_info = SshClient().run_get_stderr(ssh_helper, cmd)
     else:
         obproxy_version_info = LocalClient().run_get_stderr(cmd)
-    logger.info("get obproxy version, run cmd = [{0}] ".format(cmd))
+    logger.debug("get obproxy version, run cmd = [{0}] ".format(cmd))
     if obproxy_version_info is not None:
         ob_version = re.findall(r'[(]OceanBase.(.+? +?)[)]', obproxy_version_info)
         if len(ob_version) > 0:
@@ -367,7 +367,7 @@ def get_obproxy_version(is_ssh, ssh_helper, obproxy_install_dir):
                 obproxy_version_info = SshClient().run_get_stderr(ssh_helper, cmd)
             else:
                 obproxy_version_info = LocalClient().run_get_stderr(cmd)
-            logger.info("get obproxy version with LD_LIBRARY_PATH,cmd:{0}, result:{1}".format(cmd,obproxy_version_info))
+            logger.debug("get obproxy version with LD_LIBRARY_PATH,cmd:{0}, result:{1}".format(cmd,obproxy_version_info))
             if "REVISION" not in obproxy_version_info:
                 raise Exception("Please check conf about proxy,{0}".format(obproxy_version_info))
             pattern = r"(\d+\.\d+\.\d+\.\d+)"

common/constant.py

@@ -91,8 +91,19 @@ def __setattr__(self, name, value):
     "tasks_base_path": "~/.obdiag/tasks/"
   }
 }
+
+const.OBDIAG_GATHER_DEFAULT_CONFIG = {
+  "gather": {
+    "cases_base_path": "~/.obdiag/gather/tasks"
+  }
+}
+
+const.OBDIAG_RCA_DEFAULT_CONFIG = {
+    "rca": {
+        "result_path": "./rca/",
+    }
+}
 const.OBDIAG_TELEMETRY_FILE_NAME = os.path.expanduser("~/.obdiag/.obdiag_telemetry.txt")
 const.TELEMETRY_CONTENT_REPORTER = "obdiag"
 const.TELEMETRY_URL = "openwebapi.oceanbase.com"
 const.TELEMETRY_PATH = "/api/web/oceanbase/report"
-

common/ob_connector.py

@@ -37,15 +37,18 @@ def init(self):
             logger.exception(e)
 
     def _connect_db(self):
-        logger.debug("connect OB: {0}:{1} with user {2}".format(self.ip, self.port, self.username))
-        self.conn = mysql.connect(
-            host=self.ip,
-            port=self.port,
-            user=self.username,
-            passwd=self.password,
-            connect_timeout=30,
-        )
-        logger.debug("connect databse ...")
+        try:
+            logger.debug("connect OB: {0}:{1} with user {2}".format(self.ip, self.port, self.username))
+            self.conn = mysql.connect(
+                host=self.ip,
+                port=self.port,
+                user=self.username,
+                passwd=self.password,
+                connect_timeout=30,
+            )
+            logger.debug("connect databse ...")
+        except mysql.Error as e:
+            logger.error("connect OB: {0}:{1} with user {2} failed, error:{3}".format(self.ip, self.port, self.username, e))
 
     def execute_sql(self, sql):
         if self.conn is None:
@@ -58,6 +61,18 @@ def execute_sql(self, sql):
         cursor.close()
         return ret
 
+    def execute_sql_return_columns_and_data(self, sql):
+        if self.conn is None:
+            self._connect_db()
+        else:
+            self.conn.ping(reconnect=True)
+        cursor = self.conn.cursor()
+        cursor.execute(sql)
+        column_names = [col[0] for col in cursor.description]
+        ret = cursor.fetchall()
+        cursor.close()
+        return column_names, ret
+
     def execute_sql_return_cursor_dictionary(self, sql):
         if self.conn is None:
             self._connect_db()

common/obdiag_exception.py

@@ -118,4 +118,4 @@ def __repr__(self):
         return '%s %s' % (self.msg, self.obj is not None and pprint.pformat(self.obj) or '')
 
     def __str__(self):
-        return repr(self)
+        return repr(self)

common/scene.py

@@ -0,0 +1,100 @@
+#!/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: 2024/01/16
+@file: scene.py
+@desc:
+"""
+
+
+from common.logger import logger
+from utils.shell_utils import SshHelper
+from utils.version_utils import compare_versions_greater
+from common.command import get_observer_version, get_obproxy_version
+
+def filter_by_version(scene, cluster):
+    try:
+        steps = scene
+        steps_nu = 0
+        # get observer version
+        if "version" not in cluster or cluster["version"] == "":
+            return steps_nu
+        for now_steps in steps:
+            if "version" in now_steps:
+                steps_versions = now_steps["version"]
+                if not isinstance(steps_versions, str):
+                    logger.error("filter_by_version steps_version Exception : {0}".format("the type of version is not string"))
+                    raise Exception("filter_by_version steps_version Exception : {0}".format("the type of version is not string"))
+                version_real = cluster["version"]
+                logger.info("version_int is {0} steps_versions is {1}".format(version_real, steps_versions))
+
+                steps_versions = steps_versions.replace(" ", "")
+                steps_versions = steps_versions[1:-1]
+                steps_versions_list = steps_versions.split(",")
+                minVersion = steps_versions_list[0]
+                maxVersion = steps_versions_list[1]
+                # min
+                if minVersion == "*":
+                    minVersion = "-1"
+                if maxVersion == "*":
+                    maxVersion = "999"
+                if compare_versions_greater(version_real, minVersion) and compare_versions_greater(maxVersion, version_real):
+                    break
+            else:
+                logger.info("not version in now_steps")
+                break
+            steps_nu = steps_nu + 1
+        if steps_nu > len(steps) - 1:
+            logger.warning("not version in this scene")
+            return -1
+        return steps_nu
+    except Exception as e:
+        logger.error("filter_by_version Exception : {0}".format(e))
+        raise Exception("filter_by_version Exception : {0}".format(e))
+
+def get_version(nodes, type):
+    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("user"), node.get("password"), node.get("port"), node.get("private_key"), node)
+        if type == "observer":
+            version = get_observer_version(True, ssh, nodes[0]["home_path"])
+        elif type == "obproxy":
+            version = get_obproxy_version(True, ssh, nodes[0]["home_path"])
+        return version
+    except Exception as e:
+        logger.error("can't get version, Exception: {0}".format(e))
+        raise Exception("can't get version, Exception: {0}".format(e))
+
+def get_obproxy_and_ob_version(obproxy_nodes, nodes, type):
+    try:
+        if type == "observer" or type == "other":
+            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("user"), node.get("password"), node.get("port"), node.get("private_key"), node)
+            version = get_observer_version(True, ssh, nodes[0]["home_path"])
+        elif type == "obproxy":
+            if len(nodes) < 1:
+                raise Exception("input obproxy nodes is empty, please check your config")
+            node = obproxy_nodes[0]
+            ssh = SshHelper(True, node.get("ip"), node.get("user"), node.get("password"), node.get("port"), node.get("private_key"), node)
+            version = get_obproxy_version(True, ssh, nodes[0]["home_path"])
+        else:
+            raise Exception(
+                "type is {0} . No func to get the version".format(type))
+        return version
+    except Exception as e:
+        logger.error("can't get version, Exception: {0}".format(e))
+        raise Exception("can't get version, Exception: {0}".format(e))

conf/inner_config.yml

@@ -17,4 +17,8 @@ check:
     report_path: "./check_report/"
     export_type: table
   package_file: "~/.obdiag/check_package.yaml"
-  tasks_base_path: "~/.obdiag/tasks/"
+  tasks_base_path: "~/.obdiag/tasks/"
+gather:
+  scenes_base_path: "~/.obdiag/gather/tasks"
+rca:
+  result_path: "./rca/"

docs/check.md

@@ -23,18 +23,18 @@ observer  ->check_package.yaml
 obproxy   ->obproxy_check_package.yaml
 
 
-Example1:
+Example:
 obdiag check --cases= ad
 obdiag check --obproxy_cases= proxy
 obdiag check --cases=ad --obproxy_cases=proxy
 ```
 
 ### 关联持久化参数：
-持久化参数主要是部分日常不会修改的参数，依赖于conf/config.yml
+持久化参数主要是部分日常不会修改的参数，依赖于conf/inner_config.yml
 
 若使用rpm方式进行安装，config.yml位于
 ```shell script
-/user/local/oceanbase-diagnostic-tool/conf/config.yml
+/user/local/oceanbase-diagnostic-tool/conf/inner_config.yml
 ```
 
 check功能所关联的配置项在"CHECK"下，基本上的参数均无需变更或更改频率较低

docs/gather_all.md

@@ -74,6 +74,17 @@ Summary:
 | 192.168.2.12   | Completed | 42.152K | 6 s    | gather_pack_20220729170856/sysstat_192.168.2.12_20220729170856.zip   |
 +----------------+-----------+---------+--------+----------------------------------------------------------------------+
 
+
+# observer当前的堆栈信息
+Summary:
++----------------+-----------+---------+--------+-----------------------------------------------------------------------+
+| Node           | Status    | Size    | Time   | PackPath                                                              |
++================+===========+=========+========+=======================================================================+
+| 192.168.2.11   | Completed | 22.693K | 13 s   | gather_pack_20220729170902/obstack2_192.168.2.11_20220729170902.zip   |
++----------------+-----------+---------+--------+-----------------------------------------------------------------------+
+| 192.168.2.12  | Completed | 19.902K | 13 s   | gather_pack_20220729170902/obstack2_192.168.2.12_20220729170902.zip    |
++----------------+-----------+---------+--------+-----------------------------------------------------------------------+
+
 Gather Perf Summary:
 +----------------+-----------+----------+--------+-------------------------------------------------------------------+
 | Node           | Status    | Size     | Time   | PackPath                                                          |

docs/gather_awr.md

@@ -23,7 +23,7 @@ optional arguments:
   --cluster_name cluster_name
                         cluster name.
 
-Example: obdiag gather awr --cluster_name demo1 --from 2022-06-16 18:25:00 --to 2022-06-16 18:30:00
+Example: obdiag gather awr --from 2022-06-16 18:25:00 --to 2022-06-16 18:30:00
 
 ```
 
@@ -33,6 +33,6 @@ Gather AWR Summary:
 +-----------+-----------+--------+--------+----------------------------------------------------------------------------------------+
 | Cluster   | Status    | Size   | Time   | PackPath                                                                               |
 +===========+===========+========+========+========================================================================================+
-| demo1     | Completed | 4.602M | 29 s   | gather_pack_20220627005659/OBAWR_obcluster_jingshun_20220625160100_20220625180100.html |
+| demo1     | Completed | 4.602M | 29 s   | gather_pack_20220627005659/OBAWR_obcluster_demo1_20220625160100_20220625180100.html    |
 +-----------+-----------+--------+--------+----------------------------------------------------------------------------------------+
 ```

docs/gather_ob_stack.md

@@ -0,0 +1,23 @@
+## gather stack命令
+
+收集observer的堆栈信息
+```
+$ obdiag gather stack [-h]
+
+Example: obdiag gather stack
+```
+
+执行结果
+```shell script
+Example: obdiag gather stack
+
+Summary:
++----------------+-----------+---------+--------+-----------------------------------------------------------------------+
+| Node           | Status    | Size    | Time   | PackPath                                                              |
++================+===========+=========+========+=======================================================================+
+| 192.168.2.11   | Completed | 19.926K | 10 s   | gather_pack_20220729163951/obstack2_192.168.2.11_20220729163951.zip   |
++----------------+-----------+---------+--------+-----------------------------------------------------------------------+
+| 192.168.2.12   | Completed | 22.803K | 12 s   | gather_pack_20220729163951/obstack2_192.168.2.11_20220729163951.zip   |
++----------------+-----------+---------+--------+-----------------------------------------------------------------------+
+
+```