def run_job(self, job_execution):
ctx = context.ctx()
job = conductor.job_get(ctx, job_execution.job_id)
input_source, output_source = job_utils.get_data_sources(
job_execution, job)
# Updated_job_configs will be a copy of job_execution.job_configs with
# any name or uuid references to data_sources resolved to paths
# assuming substitution is enabled.
# If substitution is not enabled then updated_job_configs will
# just be a reference to job_execution.job_configs to avoid a copy.
# Additional_sources will be a list of any data_sources found.
additional_sources, updated_job_configs = (
job_utils.resolve_data_source_references(
job_execution.job_configs))
proxy_configs = updated_job_configs.get('proxy_configs')
configs = updated_job_configs.get('configs', {})
for data_source in [input_source, output_source] + additional_sources:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(self.cluster, data_source)
break
hdfs_user = self.get_hdfs_user()
# TODO(tmckay): this should probably be "get_namenode"
# but that call does not exist in the oozie engine api now.
oozie_server = self.get_oozie_server(self.cluster)
wf_dir = self._create_hdfs_workflow_dir(oozie_server, job)
self._upload_job_files_to_hdfs(oozie_server, wf_dir, job, configs,
proxy_configs)
wf_xml = workflow_factory.get_workflow_xml(job, self.cluster,
updated_job_configs,
input_source, output_source,
hdfs_user)
path_to_workflow = self._upload_workflow_file(oozie_server, wf_dir,
wf_xml, hdfs_user)
job_params = self._get_oozie_job_params(hdfs_user, path_to_workflow)
client = self._get_client()
oozie_job_id = client.add_job(x.create_hadoop_xml(job_params),
job_execution)
job_execution = conductor.job_execution_get(ctx, job_execution.id)
if job_execution.info['status'] == edp.JOB_STATUS_TOBEKILLED:
return (None, edp.JOB_STATUS_KILLED, None)
client.run_job(job_execution, oozie_job_id)
try:
status = client.get_job_status(job_execution,
oozie_job_id)['status']
except Exception:
status = None
return (oozie_job_id, status, None)
def run_job(job_execution):
ctx = context.ctx()
cluster = conductor.cluster_get(ctx, job_execution.cluster_id)
if cluster.status != 'Active':
return job_execution
job = conductor.job_get(ctx, job_execution.job_id)
if not edp.compare_job_type(job.type, edp.JOB_TYPE_JAVA):
input_source = conductor.data_source_get(ctx, job_execution.input_id)
output_source = conductor.data_source_get(ctx, job_execution.output_id)
else:
input_source = None
output_source = None
#TODO(nprivalova): should be removed after all features implemented
validate(input_source, output_source, job)
for data_source in [input_source, output_source]:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(cluster, data_source)
hdfs_user = _get_hdfs_user(cluster)
oozie_server = _get_oozie_server(cluster)
wf_dir = create_workflow_dir(oozie_server, job, hdfs_user)
upload_job_files(oozie_server, wf_dir, job, hdfs_user)
creator = workflow_factory.get_creator(job)
wf_xml = creator.get_workflow_xml(cluster, job_execution,
input_source, output_source)
path_to_workflow = upload_workflow_file(oozie_server,
wf_dir, wf_xml, hdfs_user)
rm_path = _get_resource_manager_path(cluster)
nn_path = cluster['info']['HDFS']['NameNode']
client = o.OozieClient(cluster['info']['JobFlow']['Oozie'] + "/oozie/",
_get_oozie_server(cluster))
job_parameters = {"jobTracker": rm_path,
"nameNode": nn_path,
"user.name": hdfs_user,
"oozie.wf.application.path":
"%s%s" % (nn_path, path_to_workflow),
"oozie.use.system.libpath": "true"}
oozie_job_id = client.add_job(x.create_hadoop_xml(job_parameters),
job_execution)
job_execution = conductor.job_execution_update(ctx, job_execution,
{'oozie_job_id':
oozie_job_id,
'start_time':
datetime.datetime.now()})
client.run_job(job_execution, oozie_job_id)
return job_execution
def run_job(job_execution):
ctx = context.ctx()
cluster = conductor.cluster_get(ctx, job_execution.cluster_id)
if cluster.status != 'Active':
return job_execution
job = conductor.job_get(ctx, job_execution.job_id)
if not edp.compare_job_type(job.type, 'Java'):
input_source = conductor.data_source_get(ctx, job_execution.input_id)
output_source = conductor.data_source_get(ctx, job_execution.output_id)
else:
input_source = None
output_source = None
#TODO(nprivalova): should be removed after all features implemented
validate(input_source, output_source, job)
for data_source in [input_source, output_source]:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(cluster, data_source)
hdfs_user = _get_hdfs_user(cluster)
oozie_server = _get_oozie_server(cluster)
wf_dir = create_workflow_dir(oozie_server, job, hdfs_user)
upload_job_files(oozie_server, wf_dir, job, hdfs_user)
creator = workflow_factory.get_creator(job)
wf_xml = creator.get_workflow_xml(cluster, job_execution,
input_source, output_source)
path_to_workflow = upload_workflow_file(oozie_server,
wf_dir, wf_xml, hdfs_user)
rm_path = _get_resource_manager_path(cluster)
nn_path = cluster['info']['HDFS']['NameNode']
client = o.OozieClient(cluster['info']['JobFlow']['Oozie'] + "/oozie/",
_get_oozie_server(cluster))
job_parameters = {"jobTracker": rm_path,
"nameNode": nn_path,
"user.name": hdfs_user,
"oozie.wf.application.path":
"%s%s" % (nn_path, path_to_workflow),
"oozie.use.system.libpath": "true"}
oozie_job_id = client.add_job(x.create_hadoop_xml(job_parameters),
job_execution)
job_execution = conductor.job_execution_update(ctx, job_execution,
{'oozie_job_id':
oozie_job_id,
'start_time':
datetime.datetime.now()})
client.run_job(job_execution, oozie_job_id)
return job_execution
def test_configure_cluster_for_hdfs(self, mock_helper, mock_get, mock_six):
inst = mock.MagicMock()
inst.remote = mock.MagicMock()
mock_six.return_value = 111
str1 = '/tmp/etc-hosts-update.111'
str2 = ('cat /tmp/etc-hosts-update.111 /etc/hosts | sort | uniq > '
'/tmp/etc-hosts.111 && cat /tmp/etc-hosts.111 > '
'/etc/hosts && rm -f /tmp/etc-hosts.111 '
'/tmp/etc-hosts-update.111')
mock_get.return_value = [inst]
helper.configure_cluster_for_hdfs(self.cluster, "www.host.ru")
inst.remote.assert_has_calls(
[mock.call(), mock.call().__enter__(),
mock.call().__enter__().write_file_to(str1, mock_helper()),
mock.call().__enter__().execute_command(str2, run_as_root=True),
mock.call().__exit__(None, None, None)])
def test_configure_cluster_for_hdfs(self, mock_helper, mock_get, mock_six):
inst = mock.MagicMock()
inst.remote = mock.MagicMock()
mock_six.return_value = 111
str1 = '/tmp/etc-hosts-update.111'
str2 = ('cat /tmp/etc-hosts-update.111 /etc/hosts | sort | uniq > '
'/tmp/etc-hosts.111 && cat /tmp/etc-hosts.111 > '
'/etc/hosts && rm -f /tmp/etc-hosts.111 '
'/tmp/etc-hosts-update.111')
mock_get.return_value = [inst]
helper.configure_cluster_for_hdfs(self.cluster, "www.host.ru")
inst.remote.assert_has_calls(
[mock.call(), mock.call().__enter__(),
mock.call().__enter__().write_file_to(str1, mock_helper()),
mock.call().__enter__().execute_command(str2, run_as_root=True),
mock.call().__exit__(None, None, None)])
def run_job(self, job_execution):
ctx = context.ctx()
job = conductor.job_get(ctx, job_execution.job_id)
input_source, output_source = job_utils.get_data_sources(job_execution,
job)
proxy_configs = job_execution.job_configs.get('proxy_configs')
for data_source in [input_source, output_source]:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(self.cluster, data_source)
break
hdfs_user = self.get_hdfs_user()
# TODO(tmckay): this should probably be "get_namenode"
# but that call does not exist in the oozie engine api now.
oozie_server = self.get_oozie_server(self.cluster)
wf_dir = self._create_hdfs_workflow_dir(oozie_server, job)
self._upload_job_files_to_hdfs(oozie_server, wf_dir, job,
proxy_configs)
wf_xml = workflow_factory.get_workflow_xml(
job, self.cluster, job_execution, input_source, output_source,
hdfs_user)
path_to_workflow = self._upload_workflow_file(oozie_server, wf_dir,
wf_xml, hdfs_user)
job_params = self._get_oozie_job_params(hdfs_user,
path_to_workflow)
client = self._get_client()
oozie_job_id = client.add_job(x.create_hadoop_xml(job_params),
job_execution)
job_execution = conductor.job_execution_get(ctx, job_execution.id)
if job_execution.info['status'] == edp.JOB_STATUS_TOBEKILLED:
return (None, edp.JOB_STATUS_KILLED, None)
client.run_job(job_execution, oozie_job_id)
try:
status = client.get_job_status(job_execution,
oozie_job_id)['status']
except Exception:
status = None
return (oozie_job_id, status, None)
def run_job(self, job_execution):
ctx = context.ctx()
job = conductor.job_get(ctx, job_execution.job_id)
input_source, output_source = job_utils.get_data_sources(job_execution,
job)
for data_source in [input_source, output_source]:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(self.cluster, data_source)
break
hdfs_user = self.plugin.get_hdfs_user()
# TODO(tmckay): this should probably be "get_namenode"
# but that call does not exist in the plugin api now.
# However, other engines may need it.
oozie_server = self.plugin.get_oozie_server(self.cluster)
wf_dir = job_utils.create_hdfs_workflow_dir(oozie_server,
job, hdfs_user)
job_utils.upload_job_files_to_hdfs(oozie_server, wf_dir,
job, hdfs_user)
wf_xml = workflow_factory.get_workflow_xml(
job, self.cluster, job_execution, input_source, output_source)
path_to_workflow = self._upload_workflow_file(oozie_server, wf_dir,
wf_xml, hdfs_user)
job_params = self._get_oozie_job_params(hdfs_user,
path_to_workflow)
client = self._get_client()
oozie_job_id = client.add_job(x.create_hadoop_xml(job_params),
job_execution)
client.run_job(job_execution, oozie_job_id)
try:
status = client.get_job_status(job_execution,
oozie_job_id)['status']
except Exception:
status = None
return (oozie_job_id, status, None)
def _run_job(job_execution_id):
ctx = context.ctx()
job_execution = conductor.job_execution_get(ctx, job_execution_id)
cluster = conductor.cluster_get(ctx, job_execution.cluster_id)
if cluster.status != 'Active':
return
job_execution = _update_job_execution_extra(job_execution, cluster)
job = conductor.job_get(ctx, job_execution.job_id)
input_source, output_source = _get_data_sources(job_execution, job)
for data_source in [input_source, output_source]:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(cluster, data_source)
plugin = _get_plugin(cluster)
hdfs_user = plugin.get_hdfs_user()
oozie_server = plugin.get_oozie_server(cluster)
wf_dir = create_workflow_dir(oozie_server, job, hdfs_user)
upload_job_files(oozie_server, wf_dir, job, hdfs_user)
wf_xml = workflow_factory.get_workflow_xml(
job, cluster, job_execution, input_source, output_source)
path_to_workflow = upload_workflow_file(oozie_server,
wf_dir, wf_xml, hdfs_user)
client = _create_oozie_client(cluster)
job_params = _get_oozie_job_params(cluster, hdfs_user, path_to_workflow)
oozie_job_id = client.add_job(x.create_hadoop_xml(job_params),
job_execution)
job_execution = conductor.job_execution_update(
ctx, job_execution, {'oozie_job_id': oozie_job_id,
'start_time': datetime.datetime.now()})
client.run_job(job_execution, oozie_job_id)
def run_job(self, job_execution):
ctx = context.ctx()
job = conductor.job_get(ctx, job_execution.job_id)
indep_params = {}
data_source_urls = {}
additional_sources, updated_job_configs = (
job_utils.resolve_data_source_references(
job_execution.job_configs, job_execution.id, data_source_urls)
)
job_execution = conductor.job_execution_update(
ctx, job_execution, {"data_source_urls": data_source_urls})
for data_source in additional_sources:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(self.cluster, data_source)
break
# It is needed in case we are working with Spark plugin
self.plugin_params['master'] = (
self.plugin_params['master'] % {'host': self.master.hostname()})
# TODO(tmckay): wf_dir should probably be configurable.
# The only requirement is that the dir is writable by the image user
wf_dir = job_utils.create_workflow_dir(self.master, '/tmp/spark-edp',
job, job_execution.id, "700")
paths, builtin_paths = self._upload_job_files(
self.master, wf_dir, job, updated_job_configs)
# We can shorten the paths in this case since we'll run out of wf_dir
paths = [os.path.basename(p) for p in paths]
builtin_paths = [os.path.basename(p) for p in builtin_paths]
# TODO(tmckay): for now, paths[0] is always assumed to be the app
# jar and we generate paths in order (mains, then libs).
# When we have a Spark job type, we can require a "main" and set
# the app jar explicitly to be "main"
indep_params["app_jar"] = paths.pop(0)
indep_params["job_class"] = (
updated_job_configs["configs"]["edp.java.main_class"])
# If we uploaded builtins then we are using a wrapper jar. It will
# be the first one on the builtin list and the original app_jar needs
# to be added to the 'additional' jars
if builtin_paths:
indep_params["wrapper_jar"] = builtin_paths.pop(0)
indep_params["wrapper_class"] = (
'org.openstack.sahara.edp.SparkWrapper')
wrapper_xml = self._upload_wrapper_xml(self.master,
wf_dir,
updated_job_configs)
indep_params["wrapper_args"] = "%s %s" % (
wrapper_xml, indep_params["job_class"])
indep_params["addnl_jars"] = ",".join(
[indep_params["app_jar"]] + paths + builtin_paths)
else:
indep_params["addnl_jars"] = ",".join(paths)
# All additional jars are passed with the --jars option
if indep_params["addnl_jars"]:
indep_params["addnl_jars"] = (
" --jars " + indep_params["addnl_jars"])
# Launch the spark job using spark-submit and deploy_mode = client
# TODO(tmckay): we need to clean up wf_dirs on long running clusters
# TODO(tmckay): probably allow for general options to spark-submit
indep_params["args"] = updated_job_configs.get('args', [])
indep_params["args"] = " ".join([su.inject_swift_url_suffix(arg)
for arg in indep_params["args"]])
if indep_params.get("args"):
indep_params["args"] = (" " + indep_params["args"])
mutual_dict = self.plugin_params.copy()
mutual_dict.update(indep_params)
if mutual_dict.get("wrapper_jar"):
# Substrings which may be empty have spaces
# embedded if they are non-empty
cmd = (
'%(spark-user)s%(spark-submit)s%(driver-class-path)s'
' --class %(wrapper_class)s%(addnl_jars)s'
' --master %(master)s'
' --deploy-mode %(deploy-mode)s'
' %(wrapper_jar)s %(wrapper_args)s%(args)s') % dict(
mutual_dict)
else:
cmd = (
'%(spark-user)s%(spark-submit)s'
' --class %(job_class)s%(addnl_jars)s'
' --master %(master)s'
' --deploy-mode %(deploy-mode)s'
' %(app_jar)s%(args)s') % dict(
mutual_dict)
job_execution = conductor.job_execution_get(ctx, job_execution.id)
if job_execution.info['status'] == edp.JOB_STATUS_TOBEKILLED:
return (None, edp.JOB_STATUS_KILLED, None)
# If an exception is raised here, the job_manager will mark
# the job failed and log the exception
# The redirects of stdout and stderr will preserve output in the wf_dir
with remote.get_remote(self.master) as r:
# Upload the command launch script
launch = os.path.join(wf_dir, "launch_command")
r.write_file_to(launch, self._job_script())
r.execute_command("chmod u+rwx,g+rx,o+rx %s" % wf_dir)
r.execute_command("chmod +x %s" % launch)
ret, stdout = r.execute_command(
"cd %s; ./launch_command %s > /dev/null 2>&1 & echo $!"
% (wf_dir, cmd))
if ret == 0:
# Success, we'll add the wf_dir in job_execution.extra and store
# pid@instance_id as the job id
# We know the job is running so return "RUNNING"
return (stdout.strip() + "@" + self.master.id,
edp.JOB_STATUS_RUNNING,
{'spark-path': wf_dir})
# Hmm, no execption but something failed.
# Since we're using backgrounding with redirect, this is unlikely.
raise e.EDPError(_("Spark job execution failed. Exit status = "
"%(status)s, stdout = %(stdout)s") %
{'status': ret, 'stdout': stdout})
def run_job(self, job_execution):
ctx = context.ctx()
job = conductor.job_get(ctx, job_execution.job_id)
additional_sources, updated_job_configs = (
job_utils.resolve_data_source_references(job_execution.job_configs)
)
for data_source in additional_sources:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(self.cluster, data_source)
break
# We'll always run the driver program on the master
master = plugin_utils.get_instance(self.cluster, "master")
# TODO(tmckay): wf_dir should probably be configurable.
# The only requirement is that the dir is writable by the image user
wf_dir = job_utils.create_workflow_dir(master, '/tmp/spark-edp', job,
job_execution.id, "700")
paths, builtin_paths = self._upload_job_files(
master, wf_dir, job, updated_job_configs)
# We can shorten the paths in this case since we'll run out of wf_dir
paths = [os.path.basename(p) for p in paths]
builtin_paths = [os.path.basename(p) for p in builtin_paths]
# TODO(tmckay): for now, paths[0] is always assumed to be the app
# jar and we generate paths in order (mains, then libs).
# When we have a Spark job type, we can require a "main" and set
# the app jar explicitly to be "main"
app_jar = paths.pop(0)
job_class = updated_job_configs["configs"]["edp.java.main_class"]
# If we uploaded builtins then we are using a wrapper jar. It will
# be the first one on the builtin list and the original app_jar needs
# to be added to the 'additional' jars
if builtin_paths:
wrapper_jar = builtin_paths.pop(0)
wrapper_class = 'org.openstack.sahara.edp.SparkWrapper'
wrapper_xml = self._upload_wrapper_xml(master,
wf_dir,
updated_job_configs)
wrapper_args = "%s %s" % (wrapper_xml, job_class)
additional_jars = ",".join([app_jar] + paths + builtin_paths)
else:
wrapper_jar = wrapper_class = wrapper_args = ""
additional_jars = ",".join(paths)
# All additional jars are passed with the --jars option
if additional_jars:
additional_jars = " --jars " + additional_jars
# Launch the spark job using spark-submit and deploy_mode = client
host = master.hostname()
port = c_helper.get_config_value("Spark", "Master port", self.cluster)
spark_submit = os.path.join(
c_helper.get_config_value("Spark",
"Spark home",
self.cluster),
"bin/spark-submit")
# TODO(tmckay): we need to clean up wf_dirs on long running clusters
# TODO(tmckay): probably allow for general options to spark-submit
args = updated_job_configs.get('args', [])
args = " ".join([su.inject_swift_url_suffix(arg) for arg in args])
if args:
args = " " + args
if wrapper_jar and wrapper_class:
# Substrings which may be empty have spaces
# embedded if they are non-empty
cmd = (
'%(spark_submit)s%(driver_cp)s'
' --class %(wrapper_class)s%(addnl_jars)s'
' --master spark://%(host)s:%(port)s'
' %(wrapper_jar)s %(wrapper_args)s%(args)s') % (
{
"spark_submit": spark_submit,
"driver_cp": self.get_driver_classpath(),
"wrapper_class": wrapper_class,
"addnl_jars": additional_jars,
"host": host,
"port": port,
"wrapper_jar": wrapper_jar,
"wrapper_args": wrapper_args,
"args": args
})
else:
cmd = (
'%(spark_submit)s --class %(job_class)s%(addnl_jars)s'
' --master spark://%(host)s:%(port)s %(app_jar)s%(args)s') % (
{
"spark_submit": spark_submit,
"job_class": job_class,
"addnl_jars": additional_jars,
"host": host,
"port": port,
"app_jar": app_jar,
"args": args
})
job_execution = conductor.job_execution_get(ctx, job_execution.id)
if job_execution.info['status'] == edp.JOB_STATUS_TOBEKILLED:
return (None, edp.JOB_STATUS_KILLED, None)
# If an exception is raised here, the job_manager will mark
# the job failed and log the exception
# The redirects of stdout and stderr will preserve output in the wf_dir
with remote.get_remote(master) as r:
# Upload the command launch script
launch = os.path.join(wf_dir, "launch_command")
r.write_file_to(launch, self._job_script())
r.execute_command("chmod +x %s" % launch)
ret, stdout = r.execute_command(
"cd %s; ./launch_command %s > /dev/null 2>&1 & echo $!"
% (wf_dir, cmd))
if ret == 0:
# Success, we'll add the wf_dir in job_execution.extra and store
# pid@instance_id as the job id
# We know the job is running so return "RUNNING"
return (stdout.strip() + "@" + master.id,
edp.JOB_STATUS_RUNNING,
{'spark-path': wf_dir})
# Hmm, no execption but something failed.
# Since we're using backgrounding with redirect, this is unlikely.
raise e.EDPError(_("Spark job execution failed. Exit status = "
"%(status)s, stdout = %(stdout)s") %
{'status': ret, 'stdout': stdout})
def run_job(self, job_execution):
ctx = context.ctx()
job = conductor.job_get(ctx, job_execution.job_id)
indep_params = {}
data_source_urls = {}
additional_sources, updated_job_configs = (
job_utils.resolve_data_source_references(job_execution.job_configs,
job_execution.id,
data_source_urls))
job_execution = conductor.job_execution_update(
ctx, job_execution, {"data_source_urls": data_source_urls})
for data_source in additional_sources:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(self.cluster, data_source)
break
# It is needed in case we are working with Spark plugin
self.plugin_params['master'] = (self.plugin_params['master'] % {
'host': self.master.hostname()
})
# TODO(tmckay): wf_dir should probably be configurable.
# The only requirement is that the dir is writable by the image user
wf_dir = job_utils.create_workflow_dir(self.master, '/tmp/spark-edp',
job, job_execution.id, "700")
paths, builtin_paths = self._upload_job_files(self.master, wf_dir, job,
updated_job_configs)
# We can shorten the paths in this case since we'll run out of wf_dir
paths = [os.path.basename(p) for p in paths]
builtin_paths = [os.path.basename(p) for p in builtin_paths]
# TODO(tmckay): for now, paths[0] is always assumed to be the app
# jar and we generate paths in order (mains, then libs).
# When we have a Spark job type, we can require a "main" and set
# the app jar explicitly to be "main"
indep_params["app_jar"] = paths.pop(0)
indep_params["job_class"] = (
updated_job_configs["configs"]["edp.java.main_class"])
# If we uploaded builtins then we are using a wrapper jar. It will
# be the first one on the builtin list and the original app_jar needs
# to be added to the 'additional' jars
if builtin_paths:
indep_params["wrapper_jar"] = builtin_paths.pop(0)
indep_params["wrapper_class"] = (
'org.openstack.sahara.edp.SparkWrapper')
wrapper_xml = self._upload_wrapper_xml(self.master, wf_dir,
updated_job_configs)
indep_params["wrapper_args"] = "%s %s" % (
wrapper_xml, indep_params["job_class"])
indep_params["addnl_files"] = wrapper_xml
indep_params["addnl_jars"] = ",".join(
[indep_params["wrapper_jar"]] + paths + builtin_paths)
else:
indep_params["addnl_jars"] = ",".join(paths)
# All additional jars are passed with the --jars option
if indep_params["addnl_jars"]:
indep_params["addnl_jars"] = (" --jars " +
indep_params["addnl_jars"])
# Launch the spark job using spark-submit and deploy_mode = client
# TODO(tmckay): we need to clean up wf_dirs on long running clusters
# TODO(tmckay): probably allow for general options to spark-submit
indep_params["args"] = updated_job_configs.get('args', [])
indep_params["args"] = " ".join(
[su.inject_swift_url_suffix(arg) for arg in indep_params["args"]])
if indep_params.get("args"):
indep_params["args"] = (" " + indep_params["args"])
mutual_dict = self.plugin_params.copy()
mutual_dict.update(indep_params)
if mutual_dict.get("wrapper_jar"):
# Substrings which may be empty have spaces
# embedded if they are non-empty
cmd = ('%(spark-user)s%(spark-submit)s%(driver-class-path)s'
' --files %(addnl_files)s'
' --class %(wrapper_class)s%(addnl_jars)s'
' --master %(master)s'
' --deploy-mode %(deploy-mode)s'
' %(app_jar)s %(wrapper_args)s%(args)s') % dict(mutual_dict)
else:
cmd = ('%(spark-user)s%(spark-submit)s'
' --class %(job_class)s%(addnl_jars)s'
' --master %(master)s'
' --deploy-mode %(deploy-mode)s'
' %(app_jar)s%(args)s') % dict(mutual_dict)
job_execution = conductor.job_execution_get(ctx, job_execution.id)
if job_execution.info['status'] == edp.JOB_STATUS_TOBEKILLED:
return (None, edp.JOB_STATUS_KILLED, None)
# If an exception is raised here, the job_manager will mark
# the job failed and log the exception
# The redirects of stdout and stderr will preserve output in the wf_dir
with remote.get_remote(self.master) as r:
# Upload the command launch script
launch = os.path.join(wf_dir, "launch_command")
r.write_file_to(launch, self._job_script())
r.execute_command("chmod u+rwx,g+rx,o+rx %s" % wf_dir)
r.execute_command("chmod +x %s" % launch)
ret, stdout = r.execute_command(
"cd %s; ./launch_command %s > /dev/null 2>&1 & echo $!" %
(wf_dir, cmd))
if ret == 0:
# Success, we'll add the wf_dir in job_execution.extra and store
# pid@instance_id as the job id
# We know the job is running so return "RUNNING"
return (stdout.strip() + "@" + self.master.id,
edp.JOB_STATUS_RUNNING, {
'spark-path': wf_dir
})
# Hmm, no execption but something failed.
# Since we're using backgrounding with redirect, this is unlikely.
raise e.EDPError(
_("Spark job execution failed. Exit status = "
"%(status)s, stdout = %(stdout)s") % {
'status': ret,
'stdout': stdout
})
def run_job(self, job_execution):
ctx = context.ctx()
job = conductor.job_get(ctx, job_execution.job_id)
# This will be a dictionary of tuples, (native_url, runtime_url)
# keyed by data_source id
data_source_urls = {}
additional_sources, updated_job_configs = (
job_utils.resolve_data_source_references(job_execution.job_configs,
job_execution.id,
data_source_urls,
self.cluster))
job_execution = conductor.job_execution_update(
ctx, job_execution,
{"data_source_urls": job_utils.to_url_dict(data_source_urls)})
# Now that we've recorded the native urls, we can switch to the
# runtime urls
data_source_urls = job_utils.to_url_dict(data_source_urls,
runtime=True)
for data_source in additional_sources:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(self.cluster, data_source)
break
# It is needed in case we are working with Spark plugin
self.plugin_params['master'] = (self.plugin_params['master'] % {
'host': self.master.hostname()
})
# TODO(tmckay): wf_dir should probably be configurable.
# The only requirement is that the dir is writable by the image user
wf_dir = job_utils.create_workflow_dir(self.master, '/tmp/spark-edp',
job, job_execution.id, "700")
paths, builtin_paths = self._upload_job_files(self.master, wf_dir, job,
updated_job_configs)
# We can shorten the paths in this case since we'll run out of wf_dir
paths = [
os.path.basename(p) if p.startswith(wf_dir) else p for p in paths
]
builtin_paths = [os.path.basename(p) for p in builtin_paths]
cmd = self._build_command(wf_dir, paths, builtin_paths,
updated_job_configs)
job_execution = conductor.job_execution_get(ctx, job_execution.id)
if job_execution.info['status'] == edp.JOB_STATUS_TOBEKILLED:
return (None, edp.JOB_STATUS_KILLED, None)
# If an exception is raised here, the job_manager will mark
# the job failed and log the exception
# The redirects of stdout and stderr will preserve output in the wf_dir
with remote.get_remote(self.master) as r:
# Upload the command launch script
launch = os.path.join(wf_dir, "launch_command")
r.write_file_to(launch, self._job_script())
r.execute_command("chmod u+rwx,g+rx,o+rx %s" % wf_dir)
r.execute_command("chmod +x %s" % launch)
ret, stdout = r.execute_command(
"cd %s; ./launch_command %s > /dev/null 2>&1 & echo $!" %
(wf_dir, cmd))
if ret == 0:
# Success, we'll add the wf_dir in job_execution.extra and store
# pid@instance_id as the job id
# We know the job is running so return "RUNNING"
return (stdout.strip() + "@" + self.master.id,
edp.JOB_STATUS_RUNNING, {
'spark-path': wf_dir
})
# Hmm, no execption but something failed.
# Since we're using backgrounding with redirect, this is unlikely.
raise e.EDPError(
_("Spark job execution failed. Exit status = "
"%(status)s, stdout = %(stdout)s") % {
'status': ret,
'stdout': stdout
})
def run_job(self, job_execution):
ctx = context.ctx()
job = conductor.job_get(ctx, job_execution.job_id)
additional_sources, updated_job_configs = (
job_utils.resolve_data_source_references(
job_execution.job_configs))
for data_source in additional_sources:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(self.cluster, data_source)
break
# We'll always run the driver program on the master
master = plugin_utils.get_instance(self.cluster, "master")
# TODO(tmckay): wf_dir should probably be configurable.
# The only requirement is that the dir is writable by the image user
wf_dir = job_utils.create_workflow_dir(master, '/tmp/spark-edp', job,
job_execution.id, "700")
paths, builtin_paths = self._upload_job_files(master, wf_dir, job,
updated_job_configs)
# We can shorten the paths in this case since we'll run out of wf_dir
paths = [os.path.basename(p) for p in paths]
builtin_paths = [os.path.basename(p) for p in builtin_paths]
# TODO(tmckay): for now, paths[0] is always assumed to be the app
# jar and we generate paths in order (mains, then libs).
# When we have a Spark job type, we can require a "main" and set
# the app jar explicitly to be "main"
app_jar = paths.pop(0)
job_class = updated_job_configs["configs"]["edp.java.main_class"]
# If we uploaded builtins then we are using a wrapper jar. It will
# be the first one on the builtin list and the original app_jar needs
# to be added to the 'additional' jars
if builtin_paths:
wrapper_jar = builtin_paths.pop(0)
wrapper_class = 'org.openstack.sahara.edp.SparkWrapper'
wrapper_xml = self._upload_wrapper_xml(master, wf_dir,
updated_job_configs)
wrapper_args = "%s %s" % (wrapper_xml, job_class)
additional_jars = ",".join([app_jar] + paths + builtin_paths)
else:
wrapper_jar = wrapper_class = wrapper_args = ""
additional_jars = ",".join(paths)
# All additional jars are passed with the --jars option
if additional_jars:
additional_jars = " --jars " + additional_jars
# Launch the spark job using spark-submit and deploy_mode = client
host = master.hostname()
port = c_helper.get_config_value("Spark", "Master port", self.cluster)
spark_submit = os.path.join(
c_helper.get_config_value("Spark", "Spark home", self.cluster),
"bin/spark-submit")
# TODO(tmckay): we need to clean up wf_dirs on long running clusters
# TODO(tmckay): probably allow for general options to spark-submit
args = updated_job_configs.get('args', [])
args = " ".join([su.inject_swift_url_suffix(arg) for arg in args])
if args:
args = " " + args
if wrapper_jar and wrapper_class:
# Substrings which may be empty have spaces
# embedded if they are non-empty
cmd = ('%(spark_submit)s%(driver_cp)s'
' --class %(wrapper_class)s%(addnl_jars)s'
' --master spark://%(host)s:%(port)s'
' %(wrapper_jar)s %(wrapper_args)s%(args)s') % (
{
"spark_submit": spark_submit,
"driver_cp": self.get_driver_classpath(),
"wrapper_class": wrapper_class,
"addnl_jars": additional_jars,
"host": host,
"port": port,
"wrapper_jar": wrapper_jar,
"wrapper_args": wrapper_args,
"args": args
})
else:
cmd = ('%(spark_submit)s --class %(job_class)s%(addnl_jars)s'
' --master spark://%(host)s:%(port)s %(app_jar)s%(args)s'
) % ({
"spark_submit": spark_submit,
"job_class": job_class,
"addnl_jars": additional_jars,
"host": host,
"port": port,
"app_jar": app_jar,
"args": args
})
job_execution = conductor.job_execution_get(ctx, job_execution.id)
if job_execution.info['status'] == edp.JOB_STATUS_TOBEKILLED:
return (None, edp.JOB_STATUS_KILLED, None)
# If an exception is raised here, the job_manager will mark
# the job failed and log the exception
# The redirects of stdout and stderr will preserve output in the wf_dir
with remote.get_remote(master) as r:
# Upload the command launch script
launch = os.path.join(wf_dir, "launch_command")
r.write_file_to(launch, self._job_script())
r.execute_command("chmod +x %s" % launch)
ret, stdout = r.execute_command(
"cd %s; ./launch_command %s > /dev/null 2>&1 & echo $!" %
(wf_dir, cmd))
if ret == 0:
# Success, we'll add the wf_dir in job_execution.extra and store
# pid@instance_id as the job id
# We know the job is running so return "RUNNING"
return (stdout.strip() + "@" + master.id, edp.JOB_STATUS_RUNNING, {
'spark-path': wf_dir
})
# Hmm, no execption but something failed.
# Since we're using backgrounding with redirect, this is unlikely.
raise e.EDPError(
_("Spark job execution failed. Exit status = "
"%(status)s, stdout = %(stdout)s") % {
'status': ret,
'stdout': stdout
})
def run_job(self, job_execution):
ctx = context.ctx()
job = conductor.job_get(ctx, job_execution.job_id)
# This will be a dictionary of tuples, (native_url, runtime_url)
# keyed by data_source id
data_source_urls = {}
additional_sources, updated_job_configs = (
job_utils.resolve_data_source_references(job_execution.job_configs,
job_execution.id,
data_source_urls,
self.cluster)
)
job_execution = conductor.job_execution_update(
ctx, job_execution,
{"data_source_urls": job_utils.to_url_dict(data_source_urls)})
# Now that we've recorded the native urls, we can switch to the
# runtime urls
data_source_urls = job_utils.to_url_dict(data_source_urls,
runtime=True)
for data_source in additional_sources:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(self.cluster, data_source)
break
# It is needed in case we are working with Spark plugin
self.plugin_params['master'] = (
self.plugin_params['master'] % {'host': self.master.hostname()})
# TODO(tmckay): wf_dir should probably be configurable.
# The only requirement is that the dir is writable by the image user
wf_dir = job_utils.create_workflow_dir(self.master, '/tmp/spark-edp',
job, job_execution.id, "700")
paths, builtin_paths = self._upload_job_files(
self.master, wf_dir, job, updated_job_configs)
# We can shorten the paths in this case since we'll run out of wf_dir
paths = [os.path.basename(p) if p.startswith(wf_dir) else p
for p in paths]
builtin_paths = [os.path.basename(p) for p in builtin_paths]
cmd = self._build_command(wf_dir, paths, builtin_paths,
updated_job_configs)
job_execution = conductor.job_execution_get(ctx, job_execution.id)
if job_execution.info['status'] == edp.JOB_STATUS_TOBEKILLED:
return (None, edp.JOB_STATUS_KILLED, None)
# If an exception is raised here, the job_manager will mark
# the job failed and log the exception
# The redirects of stdout and stderr will preserve output in the wf_dir
with remote.get_remote(self.master) as r:
# Upload the command launch script
launch = os.path.join(wf_dir, "launch_command")
r.write_file_to(launch, self._job_script())
r.execute_command("chmod u+rwx,g+rx,o+rx %s" % wf_dir)
r.execute_command("chmod +x %s" % launch)
ret, stdout = r.execute_command(
"cd %s; ./launch_command %s > /dev/null 2>&1 & echo $!"
% (wf_dir, cmd))
if ret == 0:
# Success, we'll add the wf_dir in job_execution.extra and store
# pid@instance_id as the job id
# We know the job is running so return "RUNNING"
return (stdout.strip() + "@" + self.master.id,
edp.JOB_STATUS_RUNNING,
{'spark-path': wf_dir})
# Hmm, no execption but something failed.
# Since we're using backgrounding with redirect, this is unlikely.
raise e.EDPError(_("Spark job execution failed. Exit status = "
"%(status)s, stdout = %(stdout)s") %
{'status': ret, 'stdout': stdout})
def run_job(self, job_execution):
ctx = context.ctx()
# This will be a dictionary of tuples, (native_url, runtime_url)
# keyed by data_source id
data_source_urls = {}
job = conductor.job_get(ctx, job_execution.job_id)
input_source, output_source = job_utils.get_data_sources(
job_execution, job, data_source_urls, self.cluster)
# Updated_job_configs will be a copy of job_execution.job_configs with
# any name or uuid references to data_sources resolved to paths
# assuming substitution is enabled.
# If substitution is not enabled then updated_job_configs will
# just be a reference to job_execution.job_configs to avoid a copy.
# Additional_sources will be a list of any data_sources found.
additional_sources, updated_job_configs = (
job_utils.resolve_data_source_references(job_execution.job_configs,
job_execution.id,
data_source_urls,
self.cluster)
)
job_execution = conductor.job_execution_update(
ctx, job_execution,
{"data_source_urls": job_utils.to_url_dict(data_source_urls)})
# Now that we've recorded the native urls, we can switch to the
# runtime urls
data_source_urls = job_utils.to_url_dict(data_source_urls,
runtime=True)
proxy_configs = updated_job_configs.get('proxy_configs')
configs = updated_job_configs.get('configs', {})
use_hbase_lib = configs.get('edp.hbase_common_lib', {})
# Extract all the 'oozie.' configs so that they can be set in the
# job properties file. These are config values for Oozie itself,
# not the job code
oozie_params = {}
for k in list(configs):
if k.startswith('oozie.'):
oozie_params[k] = configs[k]
for data_source in [input_source, output_source] + additional_sources:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(
self.cluster, data_source_urls[data_source.id])
break
external_hdfs_urls = self._resolve_external_hdfs_urls(
job_execution.job_configs)
for url in external_hdfs_urls:
h.configure_cluster_for_hdfs(self.cluster, url)
hdfs_user = self.get_hdfs_user()
# TODO(tmckay): this should probably be "get_namenode"
# but that call does not exist in the oozie engine api now.
oozie_server = self.get_oozie_server(self.cluster)
wf_dir = self._create_hdfs_workflow_dir(oozie_server, job)
self._upload_job_files_to_hdfs(oozie_server, wf_dir, job, configs,
proxy_configs)
wf_xml = workflow_factory.get_workflow_xml(
job, self.cluster, updated_job_configs,
input_source, output_source,
hdfs_user, data_source_urls)
path_to_workflow = self._upload_workflow_file(oozie_server, wf_dir,
wf_xml, hdfs_user)
job_params = self._get_oozie_job_params(hdfs_user,
path_to_workflow,
oozie_params,
use_hbase_lib)
client = self._get_client()
oozie_job_id = client.add_job(x.create_hadoop_xml(job_params),
job_execution)
job_execution = conductor.job_execution_get(ctx, job_execution.id)
if job_execution.info['status'] == edp.JOB_STATUS_TOBEKILLED:
return (None, edp.JOB_STATUS_KILLED, None)
conductor.job_execution_update(
context.ctx(), job_execution.id,
{'info': {'status': edp.JOB_STATUS_READYTORUN},
'engine_job_id': oozie_job_id})
client.run_job(job_execution, oozie_job_id)
try:
status = client.get_job_info(job_execution, oozie_job_id)['status']
except Exception:
status = None
return (oozie_job_id, status, None)
def run_job(self, job_execution):
ctx = context.ctx()
# This will be a dictionary of tuples, (native_url, runtime_url)
# keyed by data_source id
data_source_urls = {}
job = conductor.job_get(ctx, job_execution.job_id)
input_source, output_source = job_utils.get_data_sources(
job_execution, job, data_source_urls, self.cluster)
# Updated_job_configs will be a copy of job_execution.job_configs with
# any name or uuid references to data_sources resolved to paths
# assuming substitution is enabled.
# If substitution is not enabled then updated_job_configs will
# just be a reference to job_execution.job_configs to avoid a copy.
# Additional_sources will be a list of any data_sources found.
additional_sources, updated_job_configs = (
job_utils.resolve_data_source_references(job_execution.job_configs,
job_execution.id,
data_source_urls,
self.cluster)
)
job_execution = conductor.job_execution_update(
ctx, job_execution,
{"data_source_urls": job_utils.to_url_dict(data_source_urls)})
# Now that we've recorded the native urls, we can switch to the
# runtime urls
data_source_urls = job_utils.to_url_dict(data_source_urls,
runtime=True)
proxy_configs = updated_job_configs.get('proxy_configs')
configs = updated_job_configs.get('configs', {})
use_hbase_lib = configs.get('edp.hbase_common_lib', {})
# Extract all the 'oozie.' configs so that they can be set in the
# job properties file. These are config values for Oozie itself,
# not the job code
oozie_params = {}
for k in list(configs):
if k.startswith('oozie.'):
oozie_params[k] = configs[k]
for data_source in [input_source, output_source] + additional_sources:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(
self.cluster, data_source_urls[data_source.id])
break
external_hdfs_urls = self._resolve_external_hdfs_urls(
job_execution.job_configs)
for url in external_hdfs_urls:
h.configure_cluster_for_hdfs(self.cluster, url)
hdfs_user = self.get_hdfs_user()
# TODO(tmckay): this should probably be "get_namenode"
# but that call does not exist in the oozie engine api now.
oozie_server = self.get_oozie_server(self.cluster)
wf_dir = self._create_hdfs_workflow_dir(oozie_server, job)
self._upload_job_files_to_hdfs(oozie_server, wf_dir, job, configs,
proxy_configs)
wf_xml = workflow_factory.get_workflow_xml(
job, self.cluster, updated_job_configs,
input_source, output_source,
hdfs_user, data_source_urls)
path_to_workflow = self._upload_workflow_file(oozie_server, wf_dir,
wf_xml, hdfs_user)
job_params = self._get_oozie_job_params(hdfs_user,
path_to_workflow,
oozie_params,
use_hbase_lib)
client = self._get_client()
oozie_job_id = client.add_job(x.create_hadoop_xml(job_params),
job_execution)
job_execution = conductor.job_execution_get(ctx, job_execution.id)
if job_execution.info['status'] == edp.JOB_STATUS_TOBEKILLED:
return (None, edp.JOB_STATUS_KILLED, None)
conductor.job_execution_update(
context.ctx(), job_execution.id,
{'info': {'status': edp.JOB_STATUS_READYTORUN},
'engine_job_id': oozie_job_id})
client.run_job(job_execution, oozie_job_id)
try:
status = client.get_job_status(job_execution,
oozie_job_id)['status']
except Exception:
status = None
return (oozie_job_id, status, None)
def _prepare_run_job(self, job_execution):
ctx = context.ctx()
# This will be a dictionary of tuples, (native_url, runtime_url)
# keyed by data_source id
data_source_urls = {}
prepared_job_params = {}
job = conductor.job_get(ctx, job_execution.job_id)
input_source, output_source = job_utils.get_data_sources(
job_execution, job, data_source_urls, self.cluster)
# Updated_job_configs will be a copy of job_execution.job_configs with
# any name or uuid references to data_sources resolved to paths
# assuming substitution is enabled.
# If substitution is not enabled then updated_job_configs will
# just be a reference to job_execution.job_configs to avoid a copy.
# Additional_sources will be a list of any data_sources found.
additional_sources, updated_job_configs = (
job_utils.resolve_data_source_references(job_execution.job_configs,
job_execution.id,
data_source_urls,
self.cluster)
)
job_execution = conductor.job_execution_update(
ctx, job_execution,
{"data_source_urls": job_utils.to_url_dict(data_source_urls)})
# Now that we've recorded the native urls, we can switch to the
# runtime urls
data_source_urls = job_utils.to_url_dict(data_source_urls,
runtime=True)
proxy_configs = updated_job_configs.get('proxy_configs')
configs = updated_job_configs.get('configs', {})
use_hbase_lib = configs.get('edp.hbase_common_lib', {})
# Extract all the 'oozie.' configs so that they can be set in the
# job properties file. These are config values for Oozie itself,
# not the job code
oozie_params = {}
for k in list(configs):
if k.startswith('oozie.'):
oozie_params[k] = configs[k]
for data_source in [input_source, output_source] + additional_sources:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(
self.cluster, data_source_urls[data_source.id])
break
external_hdfs_urls = self._resolve_external_hdfs_urls(
job_execution.job_configs)
for url in external_hdfs_urls:
h.configure_cluster_for_hdfs(self.cluster, url)
hdfs_user = self.get_hdfs_user()
# TODO(tmckay): this should probably be "get_namenode"
# but that call does not exist in the oozie engine api now.
oozie_server = self.get_oozie_server(self.cluster)
wf_dir = self._create_hdfs_workflow_dir(oozie_server, job)
self._upload_job_files_to_hdfs(oozie_server, wf_dir, job, configs,
proxy_configs)
wf_xml = workflow_factory.get_workflow_xml(
job, self.cluster, updated_job_configs,
input_source, output_source,
hdfs_user, data_source_urls)
path_to_workflow = self._upload_workflow_file(oozie_server, wf_dir,
wf_xml, hdfs_user)
prepared_job_params['context'] = ctx
prepared_job_params['hdfs_user'] = hdfs_user
prepared_job_params['path_to_workflow'] = path_to_workflow
prepared_job_params['use_hbase_lib'] = use_hbase_lib
prepared_job_params['job_execution'] = job_execution
prepared_job_params['oozie_params'] = oozie_params
prepared_job_params['wf_dir'] = wf_dir
prepared_job_params['oozie_server'] = oozie_server
return prepared_job_params
def prepare_cluster(self, data_source, cluster, **kwargs):
runtime_url = kwargs.pop('runtime_url')
h.configure_cluster_for_hdfs(cluster, runtime_url)
def run_job(job_execution_id):
ctx = context.ctx()
job_execution = conductor.job_execution_get(ctx,
job_execution_id)
cluster = conductor.cluster_get(ctx, job_execution.cluster_id)
if cluster.status != 'Active':
return
if CONF.use_namespaces and not CONF.use_floating_ips:
plugin = plugin_base.PLUGINS.get_plugin(cluster.plugin_name)
oozie = plugin.get_oozie_server(cluster)
info = oozie.remote().get_neutron_info()
extra = job_execution.extra.copy()
extra['neutron'] = info
job_execution = conductor.job_execution_update(ctx,
job_execution_id,
{'extra': extra})
job = conductor.job_get(ctx, job_execution.job_id)
if not edp.compare_job_type(job.type, edp.JOB_TYPE_JAVA):
input_source = conductor.data_source_get(ctx, job_execution.input_id)
output_source = conductor.data_source_get(ctx, job_execution.output_id)
else:
input_source = None
output_source = None
for data_source in [input_source, output_source]:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(cluster, data_source)
hdfs_user = _get_hdfs_user(cluster)
oozie_server = _get_oozie_server(cluster)
wf_dir = create_workflow_dir(oozie_server, job, hdfs_user)
upload_job_files(oozie_server, wf_dir, job, hdfs_user)
creator = workflow_factory.get_creator(job)
wf_xml = creator.get_workflow_xml(cluster, job_execution,
input_source, output_source)
path_to_workflow = upload_workflow_file(oozie_server,
wf_dir, wf_xml, hdfs_user)
plugin = plugin_base.PLUGINS.get_plugin(cluster.plugin_name)
rm_path = plugin.get_resource_manager_uri(cluster)
nn_path = plugin.get_name_node_uri(cluster)
client = _create_oozie_client(cluster)
job_parameters = {"jobTracker": rm_path,
"nameNode": nn_path,
"user.name": hdfs_user,
"oozie.wf.application.path":
"%s%s" % (nn_path, path_to_workflow),
"oozie.use.system.libpath": "true"}
oozie_job_id = client.add_job(x.create_hadoop_xml(job_parameters),
job_execution)
job_execution = conductor.job_execution_update(ctx, job_execution,
{'oozie_job_id':
oozie_job_id,
'start_time':
datetime.datetime.now()})
client.run_job(job_execution, oozie_job_id)
def run_job(self, job_execution):
ctx = context.ctx()
data_source_urls = {}
job = conductor.job_get(ctx, job_execution.job_id)
input_source, output_source = job_utils.get_data_sources(job_execution, job, data_source_urls)
# Updated_job_configs will be a copy of job_execution.job_configs with
# any name or uuid references to data_sources resolved to paths
# assuming substitution is enabled.
# If substitution is not enabled then updated_job_configs will
# just be a reference to job_execution.job_configs to avoid a copy.
# Additional_sources will be a list of any data_sources found.
additional_sources, updated_job_configs = job_utils.resolve_data_source_references(
job_execution.job_configs, job_execution.id, data_source_urls
)
job_execution = conductor.job_execution_update(ctx, job_execution, {"data_source_urls": data_source_urls})
proxy_configs = updated_job_configs.get("proxy_configs")
configs = updated_job_configs.get("configs", {})
use_hbase_lib = configs.get("edp.hbase_common_lib", {})
# Extract all the 'oozie.' configs so that they can be set in the
# job properties file. These are config values for Oozie itself,
# not the job code
oozie_params = {}
for k in list(configs):
if k.startswith("oozie."):
oozie_params[k] = configs[k]
for data_source in [input_source, output_source] + additional_sources:
if data_source and data_source.type == "hdfs":
h.configure_cluster_for_hdfs(self.cluster, data_source_urls[data_source.id])
break
hdfs_user = self.get_hdfs_user()
# TODO(tmckay): this should probably be "get_namenode"
# but that call does not exist in the oozie engine api now.
oozie_server = self.get_oozie_server(self.cluster)
wf_dir = self._create_hdfs_workflow_dir(oozie_server, job)
self._upload_job_files_to_hdfs(oozie_server, wf_dir, job, configs, proxy_configs)
wf_xml = workflow_factory.get_workflow_xml(
job, self.cluster, updated_job_configs, input_source, output_source, hdfs_user, data_source_urls
)
path_to_workflow = self._upload_workflow_file(oozie_server, wf_dir, wf_xml, hdfs_user)
job_params = self._get_oozie_job_params(hdfs_user, path_to_workflow, oozie_params, use_hbase_lib)
client = self._get_client()
oozie_job_id = client.add_job(x.create_hadoop_xml(job_params), job_execution)
job_execution = conductor.job_execution_get(ctx, job_execution.id)
if job_execution.info["status"] == edp.JOB_STATUS_TOBEKILLED:
return (None, edp.JOB_STATUS_KILLED, None)
client.run_job(job_execution, oozie_job_id)
try:
status = client.get_job_status(job_execution, oozie_job_id)["status"]
except Exception:
status = None
return (oozie_job_id, status, None)
def _prepare_run_job(self, job_execution):
ctx = context.ctx()
# This will be a dictionary of tuples, (native_url, runtime_url)
# keyed by data_source id
data_source_urls = {}
prepared_job_params = {}
job = conductor.job_get(ctx, job_execution.job_id)
input_source, output_source = job_utils.get_data_sources(
job_execution, job, data_source_urls, self.cluster)
# Updated_job_configs will be a copy of job_execution.job_configs with
# any name or uuid references to data_sources resolved to paths
# assuming substitution is enabled.
# If substitution is not enabled then updated_job_configs will
# just be a reference to job_execution.job_configs to avoid a copy.
# Additional_sources will be a list of any data_sources found.
additional_sources, updated_job_configs = (
job_utils.resolve_data_source_references(job_execution.job_configs,
job_execution.id,
data_source_urls,
self.cluster)
)
job_execution = conductor.job_execution_update(
ctx, job_execution,
{"data_source_urls": job_utils.to_url_dict(data_source_urls)})
# Now that we've recorded the native urls, we can switch to the
# runtime urls
data_source_urls = job_utils.to_url_dict(data_source_urls,
runtime=True)
proxy_configs = updated_job_configs.get('proxy_configs')
configs = updated_job_configs.get('configs', {})
use_hbase_lib = configs.get('edp.hbase_common_lib', {})
# Extract all the 'oozie.' configs so that they can be set in the
# job properties file. These are config values for Oozie itself,
# not the job code
oozie_params = {}
for k in list(configs):
if k.startswith('oozie.'):
oozie_params[k] = configs[k]
for data_source in [input_source, output_source] + additional_sources:
if data_source and data_source.type == 'hdfs':
h.configure_cluster_for_hdfs(
self.cluster, data_source_urls[data_source.id])
break
external_hdfs_urls = self._resolve_external_hdfs_urls(
job_execution.job_configs)
for url in external_hdfs_urls:
h.configure_cluster_for_hdfs(self.cluster, url)
hdfs_user = self.get_hdfs_user()
# TODO(tmckay): this should probably be "get_namenode"
# but that call does not exist in the oozie engine api now.
oozie_server = self.get_oozie_server(self.cluster)
wf_dir = self._create_hdfs_workflow_dir(oozie_server, job)
self._upload_job_files_to_hdfs(oozie_server, wf_dir, job, configs,
proxy_configs)
wf_xml = workflow_factory.get_workflow_xml(
job, self.cluster, updated_job_configs,
input_source, output_source,
hdfs_user, data_source_urls)
path_to_workflow = self._upload_workflow_file(oozie_server, wf_dir,
wf_xml, hdfs_user)
prepared_job_params['context'] = ctx
prepared_job_params['hdfs_user'] = hdfs_user
prepared_job_params['path_to_workflow'] = path_to_workflow
prepared_job_params['use_hbase_lib'] = use_hbase_lib
prepared_job_params['job_execution'] = job_execution
prepared_job_params['oozie_params'] = oozie_params
prepared_job_params['wf_dir'] = wf_dir
prepared_job_params['oozie_server'] = oozie_server
return prepared_job_params
