Add ability to collect SQL Parameters in PyMsql plugin (#39)

README.md

@@ -58,6 +58,8 @@ Environment Variable | Description | Default
 | `SW_AGENT_AUTHENTICATION` | The authentication token to verify that the agent is trusted by the backend OAP, as for how to configure the backend, refer to [the yaml](https://github.com/apache/skywalking/blob/4f0f39ffccdc9b41049903cc540b8904f7c9728e/oap-server/server-bootstrap/src/main/resources/application.yml#L155-L158). | not set |
 | `SW_AGENT_LOGGING_LEVEL` | The logging level, could be one of `CRITICAL`, `FATAL`, `ERROR`, `WARN`(`WARNING`), `INFO`, `DEBUG` | `INFO` |
 | `SW_AGENT_DISABLE_PLUGINS` | The name patterns in CSV pattern, plugins whose name matches one of the pattern won't be installed | `''` |
+| `SW_MYSQL_TRACE_SQL_PARAMETERS` | Indicates whether to collect the sql parameters or not | `False` |
+| `SW_MYSQL_SQL_PARAMETERS_MAX_LENGTH` | The maximum length of the collected parameter, parameters longer than the specified length will be truncated | `512` |
 
 ## Supported Libraries
 

skywalking/config/__init__.py

@@ -26,6 +26,9 @@ protocol = (os.getenv('SW_AGENT_PROTOCOL') or 'grpc').lower()  # type: str
 authentication = os.getenv('SW_AGENT_AUTHENTICATION')  # type: str
 logging_level = os.getenv('SW_AGENT_LOGGING_LEVEL') or 'INFO'  # type: str
 disable_plugins = (os.getenv('SW_AGENT_DISABLE_PLUGINS') or '').split(',')  # type: List[str]
+mysql_trace_sql_parameters = True if os.getenv('SW_MYSQL_TRACE_SQL_PARAMETERS') and \
+                                     os.getenv('SW_MYSQL_TRACE_SQL_PARAMETERS') == 'True' else False  # type: bool
+mysql_sql_parameters_max_length = int(os.getenv('SW_MYSQL_SQL_PARAMETERS_MAX_LENGTH') or '512')  # type: int
 
 
 def init(

skywalking/plugins/sw_pymysql/__init__.py

@@ -15,8 +15,7 @@
 # limitations under the License.
 #
 import logging
-
-from skywalking import Layer, Component
+from skywalking import Layer, Component, config
 from skywalking.trace import tags
 from skywalking.trace.carrier import Carrier
 from skywalking.trace.context import get_context
@@ -47,6 +46,12 @@ def install():
                     span.tag(Tag(key=tags.DbInstance, val=this.connection.db.decode("utf-8")))
                     span.tag(Tag(key=tags.DbStatement, val=query))
 
+                    if config.mysql_trace_sql_parameters and args:
+                        parameter = ",".join([str(arg) for arg in args])
+                        max_len = config.mysql_sql_parameters_max_length
+                        parameter = parameter[0:max_len] + "..." if len(parameter) > max_len else parameter
+                        span.tag(Tag(key=tags.DbSqlParameters, val='[' + parameter + ']'))
+
                 except BaseException as e:
                     span.raised()
                     raise e

skywalking/trace/tags/__init__.py

@@ -26,3 +26,4 @@ HttpStatus = 'status.code'
 DbType = 'db.type'
 DbInstance = 'db.instance'
 DbStatement = 'db.statement'
+DbSqlParameters = 'db.sql.parameters'

tests/plugin/sw_pymysql/expected.data.yml

@@ -30,9 +30,11 @@ segmentItems:
               - key: db.type
                 value: mysql
               - key: db.instance
-                value: test
+                value: mysql
               - key: db.statement
-                value: select 1
+                value: 'select * from user where user = %s'
+              - key: db.sql.parameters
+                value: '[root]'
             startTime: gt 0
             endTime: gt 0
             componentId: 7003

tests/plugin/sw_pymysql/services/provider.py

@@ -22,6 +22,7 @@ from skywalking import agent, config
 if __name__ == '__main__':
     config.service_name = 'provider'
     config.logging_level = 'DEBUG'
+    config.mysql_trace_sql_parameters = True
     agent.start()
 
     from flask import Flask, jsonify
@@ -32,10 +33,10 @@ if __name__ == '__main__':
     @app.route("/users", methods=["POST", "GET"])
     def application():
         time.sleep(0.5)
-        connection = pymysql.connect(host='mysql', user='root', password='root', db='test', charset='utf8mb4')
+        connection = pymysql.connect(host='mysql', user='root', password='root', db='mysql', charset='utf8mb4')
         with connection.cursor() as cursor:
-            sql = "select 1"
-            cursor.execute(sql)
+            sql = "select * from user where user = %s"
+            cursor.execute(sql, ("root",))
 
         connection.close()