I am trying to get data from a Snowflake table into a Databricks spark dataframe. Here is my current code.
from pyspark.sql import SparkSession
from pyspark.sql.functions import *
from pyspark.sql.types import *
import pyspark.pandas as pypd
import pandas as pd
import re
options = {
"sfUrl": sfURL,
"sfUser": sfUser,
"sfPassword": sfPassword,
"sfDatabase": sfDatabase,
"sfSchema": sfSchema,
"sfWarehouse": sfWarehouse,
"sfRole": sfRole
}
pydf = spark.read \
.format("snowflake") \
.options(**options) \
.option("query",
$QUERY) \
.load()
Everything up to this point loads just fine, but when I run pydf.show()
to see the table, I get this error:
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID 3) (ip-10-52-231-139.ec2.internal executor driver): net.snowflake.client.jdbc.SnowflakeSQLLoggedException: JDBC driver internal error: Max retry reached for the download of #chunk0 (Total chunks: 2) retry=10, error=net.snowflake.client.jdbc.SnowflakeSQLLoggedException: JDBC driver encountered communication error. Message: Received close_notify during handshake.
And here is a truncated traceback:
Py4JJavaError Traceback (most recent call last)
File <command-3910608059704003>, line 1
----> 1 pydf.show()
File /databricks/spark/python/pyspark/instrumentation_utils.py:48, in _wrap_function.<locals>.wrapper(*args, **kwargs)
46 start = time.perf_counter()
47 try:
---> 48 res = func(*args, **kwargs)
49 logger.log_success(
50 module_name, class_name, function_name, time.perf_counter() - start, signature
51 )
52 return res
File /databricks/spark/python/pyspark/sql/dataframe.py:934, in DataFrame.show(self, n, truncate, vertical)
928 raise PySparkTypeError(
929 error_class="NOT_BOOL",
930 message_parameters={"arg_name": "vertical", "arg_type": type(vertical).__name__},
931 )
933 if isinstance(truncate, bool) and truncate:
--> 934 print(self._jdf.showString(n, 20, vertical))
935 else:
936 try:
File /databricks/spark/python/lib/py4j-0.10.9.7-src.zip/py4j/java_gateway.py:1322, in JavaMember.__call__(self, *args)
1316 command = proto.CALL_COMMAND_NAME +\
1317 self.command_header +\
1318 args_command +\
1319 proto.END_COMMAND_PART
1321 answer = self.gateway_client.send_command(command)
-> 1322 return_value = get_return_value(
1323 answer, self.gateway_client, self.target_id, self.name)
1325 for temp_arg in temp_args:
1326 if hasattr(temp_arg, "_detach"):
File /databricks/spark/python/pyspark/errors/exceptions/captured.py:188, in capture_sql_exception.<locals>.deco(*a, **kw)
186 def deco(*a: Any, **kw: Any) -> Any:
187 try:
--> 188 return f(*a, **kw)
189 except Py4JJavaError as e:
190 converted = convert_exception(e.java_exception)
File /databricks/spark/python/lib/py4j-0.10.9.7-src.zip/py4j/protocol.py:326, in get_return_value(answer, gateway_client, target_id, name)
324 value = OUTPUT_CONVERTER[type](answer[2:], gateway_client)
325 if answer[1] == REFERENCE_TYPE:
--> 326 raise Py4JJavaError(
327 "An error occurred while calling {0}{1}{2}.\n".
328 format(target_id, ".", name), value)
329 else:
330 raise Py4JError(
331 "An error occurred while calling {0}{1}{2}. Trace:\n{3}\n".
332 format(target_id, ".", name, value))
Py4JJavaError: An error occurred while calling o710.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID 3) (ip-10-52-231-139.ec2.internal executor driver): net.snowflake.client.jdbc.SnowflakeSQLLoggedException: JDBC driver internal error: Max retry reached for the download of #chunk0 (Total chunks: 2) retry=10, error=net.snowflake.client.jdbc.SnowflakeSQLLoggedException: JDBC driver encountered communication error. Message: Received close_notify during handshake.
...
Caused by: javax.net.ssl.SSLProtocolException: Received close_notify during handshake
...
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:3578)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:3510)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:3499)
...
Caused by: net.snowflake.client.jdbc.SnowflakeSQLLoggedException: JDBC driver internal error: Max retry reached for the download of #chunk0 (Total chunks: 2) retry=10, error=net.snowflake.client.jdbc.SnowflakeSQLLoggedException: JDBC driver encountered communication error. Message: Received close_notify during handshake.
...
Caused by: javax.net.ssl.SSLProtocolException: Received close_notify during handshake
...
My code worked fine three weeks ago, but all of a sudden it just stopped working. I am using i3.4xlarge, and I am using the Databricks runtime version "13.3 LTS (includes Apache Spark 3.4.1, Scala 2.12)", and it is unity catalog enabled and is using photon acceleration. I really, cannot tell what's going wrong here. Do I need to use a more updated compute, or a larger box?