Warning: file_get_contents(/data/phpspider/zhask/data//catemap/2/ssis/2.json): failed to open stream: No such file or directory in /data/phpspider/zhask/libs/function.php on line 167

Warning: Invalid argument supplied for foreach() in /data/phpspider/zhask/libs/tag.function.php on line 1116

Notice: Undefined index: in /data/phpspider/zhask/libs/function.php on line 180

Warning: array_chunk() expects parameter 1 to be array, null given in /data/phpspider/zhask/libs/function.php on line 181
Apache spark 调用其他笔记本时Databricks笔记本超时错误:com.Databricks.WorkflowException:java.net.SocketTimeoutException:读取超时_Apache Spark_Apache Spark Sql_Databricks_Socket Timeout Exception - Fatal编程技术网

Apache spark 调用其他笔记本时Databricks笔记本超时错误:com.Databricks.WorkflowException:java.net.SocketTimeoutException:读取超时

Apache spark 调用其他笔记本时Databricks笔记本超时错误:com.Databricks.WorkflowException:java.net.SocketTimeoutException:读取超时,apache-spark,apache-spark-sql,databricks,socket-timeout-exception,Apache Spark,Apache Spark Sql,Databricks,Socket Timeout Exception,我有一个主笔记本,称为一系列其他笔记本。每个笔记本在增量表上执行合并,以更新或插入新记录 当我运行带有作业群集的主笔记本时,一个名为“药物”的笔记本因超时错误而失败。当我用交互式集群运行药物笔记本时,它通过了 作业和交互式群集具有如下所示的相同设置: 有什么问题吗?spark驱动程序日志中的标准错误如下所示: --------------------------------------------------------------------------- Py4JJavaError

我有一个主笔记本,称为一系列其他笔记本。每个笔记本在增量表上执行合并,以更新或插入新记录

当我运行带有作业群集的主笔记本时,一个名为“药物”的笔记本因超时错误而失败。当我用交互式集群运行药物笔记本时,它通过了

作业和交互式群集具有如下所示的相同设置:

有什么问题吗?spark驱动程序日志中的标准错误如下所示:

---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<command-3958057957970596> in <module>()
      1 #Run CDMMedications
----> 2 dbutils.notebook.run("CDMMedications", 0, {"TheScope":TheScope, "TheKey":TheKey, "StorageAccount":StorageAccount, "FileSystem":FileSystem, "Database":Database})

/local_disk0/tmp/1565905071244-0/dbutils.py in run(self, path, timeout_seconds, arguments, _NotebookHandler__databricks_internal_cluster_spec)
    134                 arguments,
    135                 __databricks_internal_cluster_spec,
--> 136                 self.shell.currentJobGroup)
    137 
    138         def __repr__(self):

/databricks/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py in __call__(self, *args)
   1255         answer = self.gateway_client.send_command(command)
   1256         return_value = get_return_value(
-> 1257             answer, self.gateway_client, self.target_id, self.name)
   1258 
   1259         for temp_arg in temp_args:

/databricks/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
     61     def deco(*a, **kw):
     62         try:
---> 63             return f(*a, **kw)
     64         except py4j.protocol.Py4JJavaError as e:
     65             s = e.java_exception.toString()

/databricks/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    326                 raise Py4JJavaError(
    327                     "An error occurred while calling {0}{1}{2}.\n".
--> 328                     format(target_id, ".", name), value)
    329             else:
    330                 raise Py4JError(

Py4JJavaError: An error occurred while calling o779._run.
: com.databricks.WorkflowException: java.net.SocketTimeoutException: Read timed out
    at com.databricks.workflow.WorkflowDriver.run(WorkflowDriver.scala:75)
    at com.databricks.dbutils_v1.impl.NotebookUtilsImpl.run(NotebookUtilsImpl.scala:90)
    at com.databricks.dbutils_v1.impl.NotebookUtilsImpl._run(NotebookUtilsImpl.scala:69)
    at sun.reflect.GeneratedMethodAccessor605.invoke(Unknown Source)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:380)
    at py4j.Gateway.invoke(Gateway.java:295)
    at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
    at py4j.commands.CallCommand.execute(CallCommand.java:79)
    at py4j.GatewayConnection.run(GatewayConnection.java:251)
    at java.lang.Thread.run(Thread.java:748)
Caused by: java.net.SocketTimeoutException: Read timed out
    at java.net.SocketInputStream.socketRead0(Native Method)
    at java.net.SocketInputStream.socketRead(SocketInputStream.java:116)
    at java.net.SocketInputStream.read(SocketInputStream.java:171)
    at java.net.SocketInputStream.read(SocketInputStream.java:141)
    at sun.security.ssl.InputRecord.readFully(InputRecord.java:465)
    at sun.security.ssl.InputRecord.read(InputRecord.java:503)
    at sun.security.ssl.SSLSocketImpl.readRecord(SSLSocketImpl.java:975)
    at sun.security.ssl.SSLSocketImpl.readDataRecord(SSLSocketImpl.java:933)
    at sun.security.ssl.AppInputStream.read(AppInputStream.java:105)
    at org.apache.http.impl.io.SessionInputBufferImpl.streamRead(SessionInputBufferImpl.java:137)
    at org.apache.http.impl.io.SessionInputBufferImpl.fillBuffer(SessionInputBufferImpl.java:153)
    at org.apache.http.impl.io.SessionInputBufferImpl.readLine(SessionInputBufferImpl.java:282)
    at org.apache.http.impl.conn.DefaultHttpResponseParser.parseHead(DefaultHttpResponseParser.java:138)
    at org.apache.http.impl.conn.DefaultHttpResponseParser.parseHead(DefaultHttpResponseParser.java:56)
    at org.apache.http.impl.io.AbstractMessageParser.parse(AbstractMessageParser.java:259)
    at org.apache.http.impl.DefaultBHttpClientConnection.receiveResponseHeader(DefaultBHttpClientConnection.java:163)
    at org.apache.http.impl.conn.CPoolProxy.receiveResponseHeader(CPoolProxy.java:165)
    at org.apache.http.protocol.HttpRequestExecutor.doReceiveResponse(HttpRequestExecutor.java:273)
    at org.apache.http.protocol.HttpRequestExecutor.execute(HttpRequestExecutor.java:125)
    at org.apache.http.impl.execchain.MainClientExec.execute(MainClientExec.java:272)
    at org.apache.http.impl.execchain.ProtocolExec.execute(ProtocolExec.java:185)
    at org.apache.http.impl.execchain.RetryExec.execute(RetryExec.java:89)
    at org.apache.http.impl.execchain.RedirectExec.execute(RedirectExec.java:111)
    at org.apache.http.impl.client.InternalHttpClient.doExecute(InternalHttpClient.java:185)
    at org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:72)
    at com.databricks.common.client.RawDBHttpClient.httpRequestInternal(DBHttpClient.scala:498)
    at com.databricks.common.client.RawDBHttpClient.entityEnclosingRequestInternal(DBHttpClient.scala:489)
    at com.databricks.common.client.RawDBHttpClient.postInternal(DBHttpClient.scala:420)
    at com.databricks.common.client.RawDBHttpClient.postJson(DBHttpClient.scala:283)
    at com.databricks.common.client.DBHttpClient.postJson(DBHttpClient.scala:200)
    at com.databricks.workflow.SimpleJobsSessionClient.createNotebookJob(JobsSessionClient.scala:160)
    at com.databricks.workflow.ReliableJobsSessionClient$$anonfun$createNotebookJob$1.apply$mcJ$sp(JobsSessionClient.scala:249)
    at com.databricks.workflow.ReliableJobsSessionClient$$anonfun$createNotebookJob$1.apply(JobsSessionClient.scala:249)
    at com.databricks.workflow.ReliableJobsSessionClient$$anonfun$createNotebookJob$1.apply(JobsSessionClient.scala:249)
    at com.databricks.common.client.DBHttpClient$.retryWithDeadline(DBHttpClient.scala:133)
    at com.databricks.workflow.ReliableJobsSessionClient.withRetry(JobsSessionClient.scala:313)
    at com.databricks.workflow.ReliableJobsSessionClient.createNotebookJob(JobsSessionClient.scala:248)
    at com.databricks.workflow.WorkflowDriver.run0(WorkflowDriver.scala:93)
    at com.databricks.workflow.WorkflowDriver.run(WorkflowDriver.scala:61)
    ... 12 more
---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<command-3615515772639167> in <module>()
      1 #Run CDMLoad
----> 2 dbutils.notebook.run("CDMLoads/CDMLoad",0,{"TheScope":TheScope,"TheKey":TheKey,"StorageAccount":StorageAccount, "FileSystem":FileSystem, "Database":Database})

/local_disk0/tmp/1565905071244-0/dbutils.py in run(self, path, timeout_seconds, arguments, _NotebookHandler__databricks_internal_cluster_spec)
    134                 arguments,
    135                 __databricks_internal_cluster_spec,
--> 136                 self.shell.currentJobGroup)
    137 
    138         def __repr__(self):

/databricks/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py in __call__(self, *args)
   1255         answer = self.gateway_client.send_command(command)
   1256         return_value = get_return_value(
-> 1257             answer, self.gateway_client, self.target_id, self.name)
   1258 
   1259         for temp_arg in temp_args:

/databricks/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
     61     def deco(*a, **kw):
     62         try:
---> 63             return f(*a, **kw)
     64         except py4j.protocol.Py4JJavaError as e:
     65             s = e.java_exception.toString()

/databricks/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    326                 raise Py4JJavaError(
    327                     "An error occurred while calling {0}{1}{2}.\n".
--> 328                     format(target_id, ".", name), value)
    329             else:
    330                 raise Py4JError(

Py4JJavaError: An error occurred while calling o866._run.
: com.databricks.WorkflowException: com.databricks.NotebookExecutionException: FAILED
    at com.databricks.workflow.WorkflowDriver.run(WorkflowDriver.scala:75)
    at com.databricks.dbutils_v1.impl.NotebookUtilsImpl.run(NotebookUtilsImpl.scala:90)
    at com.databricks.dbutils_v1.impl.NotebookUtilsImpl._run(NotebookUtilsImpl.scala:69)
    at sun.reflect.GeneratedMethodAccessor605.invoke(Unknown Source)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:380)
    at py4j.Gateway.invoke(Gateway.java:295)
    at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
    at py4j.commands.CallCommand.execute(CallCommand.java:79)
    at py4j.GatewayConnection.run(GatewayConnection.java:251)
    at java.lang.Thread.run(Thread.java:748)
Caused by: com.databricks.NotebookExecutionException: FAILED
    at com.databricks.workflow.WorkflowDriver.run0(WorkflowDriver.scala:118)
    at com.databricks.workflow.WorkflowDriver.run(WorkflowDriver.scala:61)
    ... 12 more
---------------------------------------------------------------------------
Py4JJavaError回溯(最近一次调用)
在()
1#运行CDM指示
---->2 dbutils.notebook.run(“cdm指示”,0,{“TheScope”:TheScope,“TheKey”:TheKey,“StorageAccount”:StorageAccount,“FileSystem”:FileSystem,“Database”:Database})
/本地\u disk0/tmp/1565905071244-0/dbutils.py处于运行状态(self、path、timeout\u seconds、参数、\u notebookshandler\u databricks\u internal\u cluster\u spec)
134个论点,
135 uu数据块u内部u集群u规范,
-->136 self.shell.currentJobGroup)
137
138定义报告(自我):
/调用中的databricks/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py(self,*args)
1255 answer=self.gateway\u client.send\u命令(command)
1256返回值=获取返回值(
->1257应答,self.gateway_客户端,self.target_id,self.name)
1258
1259对于临时参数中的临时参数:
/deco中的databricks/spark/python/pyspark/sql/utils.py(*a,**kw)
61 def装饰(*a,**千瓦):
62尝试:
--->63返回f(*a,**kw)
64除py4j.protocol.Py4JJavaError外的其他错误为e:
65 s=e.java_exception.toString()
/获取返回值(应答、网关客户端、目标id、名称)中的databricks/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py
326 raise Py4JJavaError(
327“调用{0}{1}{2}时出错。\n”。
-->328格式(目标id,“.”,名称),值)
329其他:
330升起Py4JError(
Py4JJavaError:调用o779时出错。\u运行。
:com.databricks.WorkflowException:java.net.SocketTimeoutException:读取超时
在com.databricks.workflow.WorkflowDriver.run(WorkflowDriver.scala:75)上
在com.databricks.dbutils_v1.impl.NotebookUtilsImpl.run(NotebookUtilsImpl.scala:90)
在com.databricks.dbutils_v1.impl.NotebookUtilsImpl._运行(NotebookUtilsImpl.scala:69)
位于sun.reflect.GeneratedMethodAccessor605.invoke(未知源)
在sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)中
位于java.lang.reflect.Method.invoke(Method.java:498)
位于py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
位于py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:380)
在py4j.Gateway.invoke处(Gateway.java:295)
位于py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
在py4j.commands.CallCommand.execute(CallCommand.java:79)
在py4j.GatewayConnection.run处(GatewayConnection.java:251)
运行(Thread.java:748)
原因:java.net.SocketTimeoutException:读取超时
位于java.net.SocketInputStream.socketRead0(本机方法)
位于java.net.SocketInputStream.socketRead(SocketInputStream.java:116)
位于java.net.SocketInputStream.read(SocketInputStream.java:171)
位于java.net.SocketInputStream.read(SocketInputStream.java:141)
位于sun.security.ssl.InputRecord.readfull(InputRecord.java:465)
位于sun.security.ssl.InputRecord.read(InputRecord.java:503)
位于sun.security.ssl.SSLSocketImpl.readRecord(SSLSocketImpl.java:975)
位于sun.security.ssl.SSLSocketImpl.readDataRecord(SSLSocketImpl.java:933)
位于sun.security.ssl.AppInputStream.read(AppInputStream.java:105)
位于org.apache.http.impl.io.SessionInputBufferImpl.streamRead(SessionInputBufferImpl.java:137)
位于org.apache.http.impl.io.SessionInputBufferImpl.fillBuffer(SessionInputBufferImpl.java:153)
位于org.apache.http.impl.io.SessionInputBufferImpl.readLine(SessionInputBufferImpl.java:282)
位于org.apache.http.impl.conn.DefaultHttpResponseParser.parseHead(DefaultHttpResponseParser.java:138)
位于org.apache.http.impl.conn.DefaultHttpResponseParser.parseHead(DefaultHttpResponseParser.java:56)
位于org.apache.http.impl.io.AbstractMessageParser.parse(AbstractMessageParser.java:259)
位于org.apache.http.impl.DefaultBHttpClientConnection.receiveResponseHeader(DefaultBHttpClientConnection.java:163)
位于org.apache.http.impl.conn.CPoolProxy.receiveResponseHeader(CPoolProxy.java:165)
位于org.apache.http.protocol.HttpRequestExecutor.doReceiverResponse(HttpRequestExecutor.java:273)
位于org.apache.http.protocol.HttpRequestExecutor.execute(HttpRequestExecutor.java:125)
位于org.apache.http.impl.execchain.MainClientExec.execute(MainClientExec.java:272)
位于org.apache.http.impl.execchain.ProtocolExec.execute(ProtocolExec.java:185)
位于org.apache.http.impl.execchain.RetryExec.execute(RetryExec.java:89)
位于org.apache.http.impl.execchain.RedirectExec.execute(RedirectExec.java:111)
位于org.apache.http.impl.client.InternalHttpClient.doExecute(InternalHttpClient.java:185)
在org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:72)
位于com.databricks.common.client.RawDBHttpClient.httpRequestInternal(DBHttpClient.scala:498)
位于com.databricks.common.client.RawDBHttpClient.entityEnclosingRequestInternal(DBHttpClient.scala:489)
位于com.databricks.common.client.RawDBHttpClient.postInternal(DBHttpClient.scala:420)
位于com.databricks.common.client.RawDBHttpClient.postJson(DBHttpClient.scala:283)
位于com.databricks.common.client.DBHttpClient.postJso
dbutils.notebook.run("CDMMedications", 0, {"TheScope":TheScope, 
"TheKey":TheKey, "StorageAccount":StorageAccount, 
"FileSystem":FileSystem, "Database":Database})