def test_to_url_dict(self):
data_source_urls = {'1': ('1_native', '1_runtime'),
'2': ('2_native', '2_runtime')}
self.assertItemsEqual({'1': '1_native',
'2': '2_native'},
job_utils.to_url_dict(data_source_urls))
self.assertItemsEqual({'1': '1_runtime',
'2': '2_runtime'},
job_utils.to_url_dict(data_source_urls,
runtime=True))
def test_to_url_dict(self):
data_source_urls = {'1': ('1_native', '1_runtime'),
'2': ('2_native', '2_runtime')}
self.assertItemsEqual({'1': '1_native',
'2': '2_native'},
job_utils.to_url_dict(data_source_urls))
self.assertItemsEqual({'1': '1_runtime',
'2': '2_runtime'},
job_utils.to_url_dict(data_source_urls,
runtime=True))
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)
job_utils.prepare_cluster_for_ds(additional_sources,
self.cluster, updated_job_configs,
data_source_urls)
# 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)
# 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)
# We'll always run the driver program on the master
master = plugin_utils.get_instance(self.cluster, "nimbus")
# 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/storm-edp', job,
job_execution.id, "700")
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]
app_jar = paths.pop(0)
job_class = updated_job_configs["configs"]["edp.java.main_class"]
topology_name = self._generate_topology_name(job.name)
# Launch the storm job using storm jar
host = master.hostname()
args = updated_job_configs.get('args', [])
args = " ".join([arg for arg in args])
if args:
args = " " + args
cmd = (
'%(storm_jar)s -c nimbus.host=%(host)s %(job_jar)s '
'%(main_class)s %(topology_name)s%(args)s' % (
{
"storm_jar": "/usr/local/storm/bin/storm jar",
"main_class": job_class,
"job_jar": app_jar,
"host": host,
"topology_name": topology_name,
"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
# topology_name@instance_id as the job id
# We know the job is running so return "RUNNING"
return (topology_name + "@" + master.id,
edp.JOB_STATUS_RUNNING,
{'storm-path': wf_dir})
# Hmm, no execption but something failed.
# Since we're using backgrounding with redirect, this is unlikely.
raise e.EDPError(_("Storm 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()
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()
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)
job_utils.prepare_cluster_for_ds(additional_sources, self.cluster,
updated_job_configs, data_source_urls)
# We'll always run the driver program on the master
master = plugin_utils.get_instance(self.cluster, "nimbus")
# 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/storm-edp', job,
job_execution.id, "700")
paths = self._upload_job_files(master, wf_dir, job,
updated_job_configs)
topology_name = self._set_topology_name(job_execution, job.name)
# Launch the storm job using storm jar
host = master.hostname()
cmd = self._build_command(paths, updated_job_configs, host,
topology_name)
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)
ret, stdout = self._execute_remote_job(master, wf_dir, cmd)
if ret == 0:
# Success, we'll add the wf_dir in job_execution.extra and store
# topology_name@instance_id as the job id
# We know the job is running so return "RUNNING"
return (topology_name + "@" + master.id, edp.JOB_STATUS_RUNNING, {
'storm-path': wf_dir
})
# Hmm, no execption but something failed.
# Since we're using backgrounding with redirect, this is unlikely.
raise e.EDPError(
_("Storm job execution failed. Exit status = "
"%(status)s, stdout = %(stdout)s") % {
'status': ret,
'stdout': stdout
})
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_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 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)
job_utils.prepare_cluster_for_ds(additional_sources,
self.cluster, updated_job_configs,
data_source_urls)
# We'll always run the driver program on the master
master = plugin_utils.get_instance(self.cluster, "nimbus")
# 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/storm-edp', job,
job_execution.id, "700")
paths = self._upload_job_files(master, wf_dir, job,
updated_job_configs)
topology_name = self._set_topology_name(job_execution, job.name)
# Launch the storm job using storm jar
host = master.hostname()
cmd = self._build_command(paths, updated_job_configs, host,
topology_name)
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)
ret, stdout = self._execute_remote_job(master, wf_dir, cmd)
if ret == 0:
# Success, we'll add the wf_dir in job_execution.extra and store
# topology_name@instance_id as the job id
# We know the job is running so return "RUNNING"
return (topology_name + "@" + master.id,
edp.JOB_STATUS_RUNNING,
{'storm-path': wf_dir})
# Hmm, no execption but something failed.
# Since we're using backgrounding with redirect, this is unlikely.
raise e.EDPError(_("Storm job execution failed. Exit status = "
"%(status)s, stdout = %(stdout)s") %
{'status': ret, 'stdout': stdout})
