You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Ruslan Dautkhanov (JIRA)" <ji...@apache.org> on 2018/11/07 16:34:00 UTC
[jira] [Updated] (SPARK-25958) error: [Errno 97] Address family not
supported by protocol in dataframe.take()
[ https://issues.apache.org/jira/browse/SPARK-25958?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Ruslan Dautkhanov updated SPARK-25958:
--------------------------------------
Description:
Following error happens on a heavy Spark job after 4 hours of runtime..
{code}
2018-11-06 14:35:56,604 - data_vault.py - ERROR - Exited with exception: [Errno 97] Address family not supported by protocol
Traceback (most recent call last):
File "/home/mwincek/svn/data_vault/data_vault.py", line 64, in data_vault
item.create_persistent_data()
File "/home/mwincek/svn/data_vault/src/table_recipe/amf_table_recipe.py", line 53, in create_persistent_data
single_obj.create_persistent_data()
File "/home/mwincek/svn/data_vault/src/table_processing/table_processing.py", line 21, in create_persistent_data
main_df = self.generate_dataframe_main()
File "/home/mwincek/svn/data_vault/src/table_processing/table_processing.py", line 98, in generate_dataframe_main
raw_disc_dv_df = self.get_raw_data_with_metadata_and_aggregation()
File "/home/mwincek/svn/data_vault/src/table_processing/satellite_binary_dates_table_processing.py", line 16, in get_raw_data_with_metadata_and_aggregation
main_df = self.get_dataframe_using_binary_date_aggregation_on_dataframe(input_df=raw_disc_dv_df)
File "/home/mwincek/svn/data_vault/src/table_processing/satellite_binary_dates_table_processing.py", line 60, in get_dataframe_using_binary_date_aggregation_on_dataframe
return_df = self.get_dataframe_from_binary_value_iteration(input_df)
File "/home/mwincek/svn/data_vault/src/table_processing/satellite_binary_dates_table_processing.py", line 136, in get_dataframe_from_binary_value_iteration
combine_df = self.get_dataframe_from_binary_value(input_df=input_df, binary_value=count)
File "/home/mwincek/svn/data_vault/src/table_processing/satellite_binary_dates_table_processing.py", line 154, in get_dataframe_from_binary_value
if len(results_of_filter_df.take(1)) == 0:
File "/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/sql/dataframe.py", line 504, in take
return self.limit(num).collect()
File "/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/sql/dataframe.py", line 467, in collect
return list(_load_from_socket(sock_info, BatchedSerializer(PickleSerializer())))
File "/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/rdd.py", line 148, in _load_from_socket
sock = socket.socket(af, socktype, proto)
File "/opt/cloudera/parcels/Anaconda/lib/python2.7/socket.py", line 191, in __init__
_sock = _realsocket(family, type, proto)
error: [Errno 97] Address family not supported by protocol
{code}
Looking at the failing line in lib/spark2/python/pyspark/rdd.py, line 148:
{code}
def _load_from_socket(sock_info, serializer):
port, auth_secret = sock_info
sock = None
# Support for both IPv4 and IPv6.
# On most of IPv6-ready systems, IPv6 will take precedence.
for res in socket.getaddrinfo("localhost", port, socket.AF_UNSPEC, socket.SOCK_STREAM):
af, socktype, proto, canonname, sa = res
sock = socket.socket(af, socktype, proto)
try:
sock.settimeout(15)
sock.connect(sa)
except socket.error:
sock.close()
sock = None
continue
break
if not sock:
raise Exception("could not open socket")
# The RDD materialization time is unpredicable, if we set a timeout for socket reading
# operation, it will very possibly fail. See SPARK-18281.
sock.settimeout(None)
sockfile = sock.makefile("rwb", 65536)
do_server_auth(sockfile, auth_secret)
# The socket will be automatically closed when garbage-collected.
return serializer.load_stream(sockfile)
{code}
the culprint is in lib/spark2/python/pyspark/rdd.py in this line
{code}
socket.getaddrinfo("localhost", port, socket.AF_UNSPEC, socket.SOCK_STREAM)
{code}
so the error "error: [Errno 97] *Address family* not supported by protocol"
seems to be caused by socket.AF_UNSPEC third option to the socket.getaddrinfo() call.
I tried to call similar socket.getaddrinfo call locally outside of PySpark and it worked fine.
RHEL 7.5.
was:
Following error happens on a heavy Spark job after 4 hours of runtime..
{code:python}
2018-11-06 14:35:56,604 - data_vault.py - ERROR - Exited with exception: [Errno 97] Address family not supported by protocol
Traceback (most recent call last):
File "/home/mwincek/svn/data_vault/data_vault.py", line 64, in data_vault
item.create_persistent_data()
File "/home/mwincek/svn/data_vault/src/table_recipe/amf_table_recipe.py", line 53, in create_persistent_data
single_obj.create_persistent_data()
File "/home/mwincek/svn/data_vault/src/table_processing/table_processing.py", line 21, in create_persistent_data
main_df = self.generate_dataframe_main()
File "/home/mwincek/svn/data_vault/src/table_processing/table_processing.py", line 98, in generate_dataframe_main
raw_disc_dv_df = self.get_raw_data_with_metadata_and_aggregation()
File "/home/mwincek/svn/data_vault/src/table_processing/satellite_binary_dates_table_processing.py", line 16, in get_raw_data_with_metadata_and_aggregation
main_df = self.get_dataframe_using_binary_date_aggregation_on_dataframe(input_df=raw_disc_dv_df)
File "/home/mwincek/svn/data_vault/src/table_processing/satellite_binary_dates_table_processing.py", line 60, in get_dataframe_using_binary_date_aggregation_on_dataframe
return_df = self.get_dataframe_from_binary_value_iteration(input_df)
File "/home/mwincek/svn/data_vault/src/table_processing/satellite_binary_dates_table_processing.py", line 136, in get_dataframe_from_binary_value_iteration
combine_df = self.get_dataframe_from_binary_value(input_df=input_df, binary_value=count)
File "/home/mwincek/svn/data_vault/src/table_processing/satellite_binary_dates_table_processing.py", line 154, in get_dataframe_from_binary_value
if len(results_of_filter_df.take(1)) == 0:
File "/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/sql/dataframe.py", line 504, in take
return self.limit(num).collect()
File "/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/sql/dataframe.py", line 467, in collect
return list(_load_from_socket(sock_info, BatchedSerializer(PickleSerializer())))
File "/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/rdd.py", line 148, in _load_from_socket
sock = socket.socket(af, socktype, proto)
File "/opt/cloudera/parcels/Anaconda/lib/python2.7/socket.py", line 191, in __init__
_sock = _realsocket(family, type, proto)
error: [Errno 97] Address family not supported by protocol
{code}
Looking at the failing line in lib/spark2/python/pyspark/rdd.py, line 148:
{code:python}
def _load_from_socket(sock_info, serializer):
port, auth_secret = sock_info
sock = None
# Support for both IPv4 and IPv6.
# On most of IPv6-ready systems, IPv6 will take precedence.
for res in socket.getaddrinfo("localhost", port, socket.AF_UNSPEC, socket.SOCK_STREAM):
af, socktype, proto, canonname, sa = res
sock = socket.socket(af, socktype, proto)
try:
sock.settimeout(15)
sock.connect(sa)
except socket.error:
sock.close()
sock = None
continue
break
if not sock:
raise Exception("could not open socket")
# The RDD materialization time is unpredicable, if we set a timeout for socket reading
# operation, it will very possibly fail. See SPARK-18281.
sock.settimeout(None)
sockfile = sock.makefile("rwb", 65536)
do_server_auth(sockfile, auth_secret)
# The socket will be automatically closed when garbage-collected.
return serializer.load_stream(sockfile)
{code}
the culprint is in the line
{code:python}
socket.getaddrinfo("localhost", port, socket.AF_UNSPEC, socket.SOCK_STREAM)
{code}
so the error "error: [Errno 97] *Address family* not supported by protocol"
seems to be caused by socket.AF_UNSPEC third option to the socket.getaddrinfo() call.
I tried to call similar socket.getaddrinfo call locally outside of PySpark and it worked fine.
RHEL 7.5.
> error: [Errno 97] Address family not supported by protocol in dataframe.take()
> ------------------------------------------------------------------------------
>
> Key: SPARK-25958
> URL: https://issues.apache.org/jira/browse/SPARK-25958
> Project: Spark
> Issue Type: New Feature
> Components: PySpark, Spark Core
> Affects Versions: 2.3.1, 2.3.2
> Reporter: Ruslan Dautkhanov
> Priority: Major
>
> Following error happens on a heavy Spark job after 4 hours of runtime..
> {code}
> 2018-11-06 14:35:56,604 - data_vault.py - ERROR - Exited with exception: [Errno 97] Address family not supported by protocol
> Traceback (most recent call last):
> File "/home/mwincek/svn/data_vault/data_vault.py", line 64, in data_vault
> item.create_persistent_data()
> File "/home/mwincek/svn/data_vault/src/table_recipe/amf_table_recipe.py", line 53, in create_persistent_data
> single_obj.create_persistent_data()
> File "/home/mwincek/svn/data_vault/src/table_processing/table_processing.py", line 21, in create_persistent_data
> main_df = self.generate_dataframe_main()
> File "/home/mwincek/svn/data_vault/src/table_processing/table_processing.py", line 98, in generate_dataframe_main
> raw_disc_dv_df = self.get_raw_data_with_metadata_and_aggregation()
> File "/home/mwincek/svn/data_vault/src/table_processing/satellite_binary_dates_table_processing.py", line 16, in get_raw_data_with_metadata_and_aggregation
> main_df = self.get_dataframe_using_binary_date_aggregation_on_dataframe(input_df=raw_disc_dv_df)
> File "/home/mwincek/svn/data_vault/src/table_processing/satellite_binary_dates_table_processing.py", line 60, in get_dataframe_using_binary_date_aggregation_on_dataframe
> return_df = self.get_dataframe_from_binary_value_iteration(input_df)
> File "/home/mwincek/svn/data_vault/src/table_processing/satellite_binary_dates_table_processing.py", line 136, in get_dataframe_from_binary_value_iteration
> combine_df = self.get_dataframe_from_binary_value(input_df=input_df, binary_value=count)
> File "/home/mwincek/svn/data_vault/src/table_processing/satellite_binary_dates_table_processing.py", line 154, in get_dataframe_from_binary_value
> if len(results_of_filter_df.take(1)) == 0:
> File "/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/sql/dataframe.py", line 504, in take
> return self.limit(num).collect()
> File "/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/sql/dataframe.py", line 467, in collect
> return list(_load_from_socket(sock_info, BatchedSerializer(PickleSerializer())))
> File "/opt/cloudera/parcels/SPARK2/lib/spark2/python/pyspark/rdd.py", line 148, in _load_from_socket
> sock = socket.socket(af, socktype, proto)
> File "/opt/cloudera/parcels/Anaconda/lib/python2.7/socket.py", line 191, in __init__
> _sock = _realsocket(family, type, proto)
> error: [Errno 97] Address family not supported by protocol
> {code}
> Looking at the failing line in lib/spark2/python/pyspark/rdd.py, line 148:
> {code}
> def _load_from_socket(sock_info, serializer):
> port, auth_secret = sock_info
> sock = None
> # Support for both IPv4 and IPv6.
> # On most of IPv6-ready systems, IPv6 will take precedence.
> for res in socket.getaddrinfo("localhost", port, socket.AF_UNSPEC, socket.SOCK_STREAM):
> af, socktype, proto, canonname, sa = res
> sock = socket.socket(af, socktype, proto)
> try:
> sock.settimeout(15)
> sock.connect(sa)
> except socket.error:
> sock.close()
> sock = None
> continue
> break
> if not sock:
> raise Exception("could not open socket")
> # The RDD materialization time is unpredicable, if we set a timeout for socket reading
> # operation, it will very possibly fail. See SPARK-18281.
> sock.settimeout(None)
> sockfile = sock.makefile("rwb", 65536)
> do_server_auth(sockfile, auth_secret)
> # The socket will be automatically closed when garbage-collected.
> return serializer.load_stream(sockfile)
> {code}
> the culprint is in lib/spark2/python/pyspark/rdd.py in this line
> {code}
> socket.getaddrinfo("localhost", port, socket.AF_UNSPEC, socket.SOCK_STREAM)
> {code}
> so the error "error: [Errno 97] *Address family* not supported by protocol"
> seems to be caused by socket.AF_UNSPEC third option to the socket.getaddrinfo() call.
> I tried to call similar socket.getaddrinfo call locally outside of PySpark and it worked fine.
> RHEL 7.5.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org