def test_upload_job_files(self, get_remote, get_raw_binary):
main_names = ["main1", "main2", "main3"]
lib_names = ["lib1", "lib2", "lib3"]
def make_data_objects(*args):
objs = []
for name in args:
m = mock.Mock()
m.name = name
objs.append(m)
return objs
job = mock.Mock()
job.name = "job"
job.mains = make_data_objects(*main_names)
job.libs = make_data_objects(*lib_names)
# This is to mock "with remote.get_remote(instance) as r"
remote_instance = mock.Mock()
get_remote.return_value.__enter__ = mock.Mock(
return_value=remote_instance)
get_raw_binary.return_value = "data"
paths = job_utils.upload_job_files("where",
"/somedir",
job,
libs_subdir=False)
self.assertEqual(paths,
["/somedir/" + n for n in main_names + lib_names])
for path in paths:
remote_instance.write_file_to.assert_any_call(path, "data")
remote_instance.write_file_to.reset_mock()
paths = job_utils.upload_job_files("where",
"/somedir",
job,
libs_subdir=True)
remote_instance.execute_command.assert_called_with(
"mkdir -p /somedir/libs")
expected = ["/somedir/" + n for n in main_names]
expected += ["/somedir/libs/" + n for n in lib_names]
self.assertEqual(paths, expected)
for path in paths:
remote_instance.write_file_to.assert_any_call(path, "data")
def test_upload_job_files(self, get_remote, get_raw_binary):
main_names = ["main1", "main2", "main3"]
lib_names = ["lib1", "lib2", "lib3"]
def make_data_objects(*args):
objs = []
for name in args:
m = mock.Mock()
m.name = name
objs.append(m)
return objs
job = mock.Mock()
job.name = "job"
job.mains = make_data_objects(*main_names)
job.libs = make_data_objects(*lib_names)
# This is to mock "with remote.get_remote(instance) as r"
remote_instance = mock.Mock()
get_remote.return_value.__enter__ = mock.Mock(
return_value=remote_instance)
get_raw_binary.return_value = "data"
paths = job_utils.upload_job_files(
"where", "/somedir", job, libs_subdir=False)
self.assertEqual(paths,
["/somedir/" + n for n in main_names + lib_names])
for path in paths:
remote_instance.write_file_to.assert_any_call(path, "data")
remote_instance.write_file_to.reset_mock()
paths = job_utils.upload_job_files(
"where", "/somedir", job, libs_subdir=True)
remote_instance.execute_command.assert_called_with(
"mkdir -p /somedir/libs")
expected = ["/somedir/" + n for n in main_names]
expected += ["/somedir/libs/" + n for n in lib_names]
self.assertEqual(paths, expected)
for path in paths:
remote_instance.write_file_to.assert_any_call(path, "data")
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_workflow_dir(oozie_server, job, hdfs_user)
job_utils.upload_job_files(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)
return oozie_job_id
def run_job(self, job_execution):
ctx = context.ctx()
job = conductor.job_get(ctx, job_execution.job_id)
proxy_configs = job_execution.job_configs.get('proxy_configs')
# 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)
paths = job_utils.upload_job_files(master,
wf_dir,
job,
libs_subdir=False,
proxy_configs=proxy_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]
# 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)
# The rest of the paths will be passed with --jars
additional_jars = ",".join(paths)
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")
job_class = job_execution.job_configs.configs["edp.java.main_class"]
# TODO(tmckay): we need to clean up wf_dirs on long running clusters
# TODO(tmckay): probably allow for general options to spark-submit
args = " ".join(job_execution.job_configs.get('args', []))
# The redirects of stdout and stderr will preserve output in the wf_dir
cmd = "%s %s --class %s %s --master spark://%s:%s %s" % (
spark_submit, app_jar, job_class, additional_jars, host, port,
args)
# If an exception is raised here, the job_manager will mark
# the job failed and log the exception
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)
# 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)
paths = job_utils.upload_job_files(master, wf_dir, job,
libs_subdir=False)
# 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]
# 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)
# The rest of the paths will be passed with --jars
additional_jars = ",".join(paths)
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")
job_class = job_execution.job_configs.configs["edp.java.main_class"]
# TODO(tmckay): we need to clean up wf_dirs on long running clusters
# TODO(tmckay): probably allow for general options to spark-submit
args = " ".join(job_execution.job_configs.get('args', []))
# The redirects of stdout and stderr will preserve output in the wf_dir
cmd = "%s %s --class %s %s --master spark://%s:%s %s" % (
spark_submit,
app_jar,
job_class,
additional_jars,
host,
port,
args)
# If an exception is raised here, the job_manager will mark
# the job failed and log the exception
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 = %s, "
"stdout = %s" % (ret, stdout))
