def run(self):
"""Run the Hive job on EMR cluster
"""
# copy the data source to a new object
# (Hive deletes/moves the original)
copy_s3_file(self.input_path, self.data_path)
# and create the hive script
self._generate_and_upload_hive_script()
logger.info("Waiting {} seconds for S3 eventual consistency".format(
self.s3_sync_wait_time))
time.sleep(self.s3_sync_wait_time)
# TODO more options like setting aws region
conn = EmrConnection(self.aws_access_key_id,
self.aws_secret_access_key)
setup_step = InstallHiveStep(self.hive_version)
run_step = HiveStep(self.job_name, self.script_path)
jobid = conn.run_jobflow(
self.job_name,
self.log_path,
action_on_failure='CANCEL_AND_WAIT',
master_instance_type=self.master_instance_type,
slave_instance_type=self.slave_instance_type,
ami_version=self.ami_version,
num_instances=self.num_instances)
conn.add_jobflow_steps(jobid, [setup_step, run_step])
self._wait_for_job_to_complete(conn, jobid)
logger.info("Output file is in: {0}".format(self.output_path))
def add_steps(cluster_id, key): try: emr_connection = EmrConnection() emr_connection.add_jobflow_steps(cluster_id, get_steps(key, key)) return True except Exception, e: return False
def run(self):
"""Run the Hive job on EMR cluster
"""
# copy the data source to a new object
# (Hive deletes/moves the original)
copy_s3_file(self.input_path, self.data_path)
# and create the hive script
self._generate_and_upload_hive_script()
logger.info("Waiting {} seconds for S3 eventual consistency".format(
self.s3_sync_wait_time))
time.sleep(self.s3_sync_wait_time)
# TODO more options like setting aws region
conn = EmrConnection(self.aws_access_key_id,
self.aws_secret_access_key)
setup_step = InstallHiveStep(self.hive_version)
run_step = HiveStep(self.job_name, self.script_path)
cluster_id = conn.run_jobflow(
self.job_name,
self.log_path,
action_on_failure='CANCEL_AND_WAIT',
master_instance_type=self.master_instance_type,
slave_instance_type=self.slave_instance_type,
ami_version=self.ami_version,
num_instances=self.num_instances,
job_flow_role=self.iam_instance_profile,
service_role=self.iam_service_role)
conn.add_jobflow_steps(cluster_id, [setup_step, run_step])
logger.info("Job started on cluster {0}".format(cluster_id))
self._wait_for_job_to_complete(conn, cluster_id)
logger.info("Output file is in: {0}".format(self.output_path))
def main(argv):
# load the config
config = ConfigParser()
config.read(os.path.join(os.path.split(argv[0])[0] if not None else '','config.ini'))
# load AWS config
awsConfig = ConfigParser()
awsConfig.read(config.get('Common','aws'))
aws_access_key = awsConfig.get('AWS','aws_access_key')
aws_secret_key = awsConfig.get('AWS','aws_secret_key')
event_bucket = awsConfig.get('AWS','event_bucket')
output_bucket = awsConfig.get('AWS','emr_output_bucket')
script_bucket = awsConfig.get('AWS','script_bucket')
jobId = argv[1]
emrConnection = EmrConnection(aws_access_key, aws_secret_key)
s3Connection = S3Connection(aws_access_key, aws_secret_key)
# clean s3 output
bucket = s3Connection.get_bucket(output_bucket)
for key in bucket.get_all_keys(prefix=BUCKET_KEY):
bucket.delete_key(key)
step = StreamingStep(name='Foursquare event deduper',
mapper='s3://%s/dedup_mapper.py foursquare' % script_bucket,
reducer='s3://%s/dedup_reducer.py' % script_bucket,
input='s3://%s/normalized' % event_bucket,
output='s3://%s/%s' % (output_bucket,BUCKET_KEY),
action_on_failure='CONTINUE')
emrConnection.add_jobflow_steps(jobId, step)
print 'Successfully started streaming steps'
class EmrJarRuntime(ZetRuntime):
def __init__(self, spec_filename="spec.json"):
import boto
from boto.emr.connection import EmrConnection, RegionInfo
# super(ZetRuntime, self).__init__()
# TODO
self.settings = get_settings_from_file(spec_filename)
p = self.settings.Param
self.s3_conn = boto.connect_s3(p.AWS_ACCESS_KEY_ID, p.AWS_ACCESS_KEY_SECRET)
self.s3_bucket = self.s3_conn.get_bucket(p.S3_BUCKET)
self.region = p.AWS_Region
self.emr_conn = EmrConnection(p.AWS_ACCESS_KEY_ID, p.AWS_ACCESS_KEY_SECRET,
region = RegionInfo(name = self.region,
endpoint = self.region + '.elasticmapreduce.amazonaws.com'))
self.job_flow_id = p.EMR_jobFlowId
def get_s3_working_dir(self, path=""):
ps = self.settings
glb_vars = ps.GlobalParam
return os.path.join('zetjob', glb_vars['userName'], "job%s" % glb_vars['jobId'], "blk%s" % glb_vars['blockId'], path)
def execute(self, jar_path, args):
from boto.emr.step import JarStep
s3_jar_path = s3_upload(self.s3_bucket, self.get_s3_working_dir(jar_path), jar_path)
# s3_jar_path = "s3://run-jars/jar/mahout-core-1.0-SNAPSHOT-job.jar"
print("Uploading jar to s3 : %s -> %s" % (jar_path, s3_jar_path))
print("Add jobflow step")
step = JarStep(name='cl_filter', jar=s3_jar_path, step_args=args)
self.emr_conn.add_jobflow_steps(self.job_flow_id, steps=[step])
print("Waiting jobflow step done")
emr_wait_job(self.emr_conn, self.job_flow_id)
class Rankmaniac:
"""
(wrapper class)
This class presents a simple wrapper around the AWS SDK. It strives
to provide all the functionality required to run map-reduce
(Hadoop) on Amazon. This way the students do not need to worry about
learning the API for Amazon S3 and EMR, and instead can focus on
computing pagerank quickly!
"""
DefaultRegionName = 'us-west-2'
DefaultRegionEndpoint = 'elasticmapreduce.us-west-2.amazonaws.com'
def __init__(self, team_id, access_key, secret_key,
bucket='cs144students'):
"""
(constructor)
Creates a new instance of the Rankmaniac class for a specific
team using the provided credentials.
Arguments:
team_id <str> the team identifier, which may be
differ slightly from the actual team
name.
access_key <str> the AWS access key identifier.
secret_key <str> the AWS secret acess key.
Keyword arguments:
bucket <str> the S3 bucket name.
"""
region = RegionInfo(None, self.DefaultRegionName,
self.DefaultRegionEndpoint)
self._s3_bucket = bucket
self._s3_conn = S3Connection(access_key, secret_key)
self._emr_conn = EmrConnection(access_key, secret_key, region=region)
self.team_id = team_id
self.job_id = None
self._reset()
self._num_instances = 1
def _reset(self):
"""
Resets the internal state of the job and submission.
"""
self._iter_no = 0
self._infile = None
self._last_outdir = None
self._last_process_step_iter_no = -1
self._is_done = False
def __del__(self):
"""
(destructor)
Terminates the map-reduce job if any, and closes the connections
to Amazon S3 and EMR.
"""
if self.job_id is not None:
self.terminate()
self._s3_conn.close()
self._emr_conn.close()
def __enter__(self):
"""
Used for `with` syntax. Simply returns this instance since the
set-up has all been done in the constructor.
"""
return self
def __exit__(self, type, value, traceback):
"""
Refer to __del__().
"""
self.__del__()
return False # do not swallow any exceptions
def upload(self, indir='data'):
"""
Uploads the local data to Amazon S3 under the configured bucket
and key prefix (the team identifier). This way the code can be
accessed by Amazon EMR to compute pagerank.
Keyword arguments:
indir <str> the base directory from which to
upload contents.
Special notes:
This method only uploads **files** in the specified
directory. It does not scan through subdirectories.
WARNING! This method removes all previous (or ongoing)
submission results, so it is unsafe to call while a job is
already running (and possibly started elsewhere).
"""
if self.job_id is not None:
raise RankmaniacError('A job is already running.')
bucket = self._s3_conn.get_bucket(self._s3_bucket)
# Clear out current bucket contents for team
keys = bucket.list(prefix=self._get_keyname())
bucket.delete_keys(keys)
for filename in os.listdir(indir):
relpath = os.path.join(indir, filename)
if os.path.isfile(relpath):
keyname = self._get_keyname(filename)
key = bucket.new_key(keyname)
key.set_contents_from_filename(relpath)
def set_infile(self, filename):
"""
Sets the data file to use for the first iteration of the
pagerank step in the map-reduce job.
"""
if self.job_id is not None:
raise RankmaniacError('A job is already running.')
self._infile = filename
def do_iter(self, pagerank_mapper, pagerank_reducer,
process_mapper, process_reducer,
pagerank_output=None, process_output=None,
num_pagerank_mappers=1, num_pagerank_reducers=1):
"""
Adds a pagerank step and a process step to the current job.
"""
num_process_mappers = 1
num_process_reducers = 1
if self._iter_no == 0:
pagerank_input = self._infile
elif self._iter_no > 0:
pagerank_input = self._last_outdir
if pagerank_output is None:
pagerank_output = self._get_default_outdir('pagerank')
# Output from the pagerank step becomes input to process step
process_input = pagerank_output
if process_output is None:
process_output = self._get_default_outdir('process')
pagerank_step = self._make_step(pagerank_mapper, pagerank_reducer,
pagerank_input, pagerank_output,
num_pagerank_mappers,
num_pagerank_reducers)
process_step = self._make_step(process_mapper, process_reducer,
process_input, process_output,
num_process_mappers,
num_process_reducers)
steps = [pagerank_step, process_step]
if self.job_id is None:
self._submit_new_job(steps)
else:
self._emr_conn.add_jobflow_steps(self.job_id, steps)
# Store `process_output` directory so it can be used in
# subsequent iteration
self._last_outdir = process_output
self._iter_no += 1
def is_done(self):
"""
Returns `True` if the map-reduce job is done, and `False`
otherwise.
For all process-step output files that have not been fetched,
gets the first part of the output file, and checks whether its
contents begins with the string 'FinalRank'.
Special notes:
WARNING! The usage of this method in your code requires that
that you used the default output directories in all calls
to do_iter().
"""
# Cache the result so we can return immediately without hitting
# any of the Amazon APIs
if self._is_done:
return True
iter_no = self._get_last_process_step_iter_no()
if iter_no < 0:
return False
while self._last_process_step_iter_no < iter_no:
self._last_process_step_iter_no += 1
i = self._last_process_step_iter_no
outdir = self._get_default_outdir('process', iter_no=i)
keyname = self._get_keyname(outdir, 'part-00000')
bucket = self._s3_conn.get_bucket(self._s3_bucket)
key = Key(bucket=bucket, name=keyname)
contents = key.next() # get first chunk of the output file
if contents.startswith('FinalRank'):
self._is_done = True # cache result
break
return self._is_done
def is_alive(self):
"""
Checks whether the jobflow has completed, failed, or been
terminated.
Special notes:
WARNING! This method should only be called **after**
is_done() in order to be able to distinguish between the
cases where the map-reduce job has outputted 'FinalRank'
on its final iteration and has a 'COMPLETED' state.
"""
jobflow = self.describe()
if jobflow.state in ('COMPLETED', 'FAILED', 'TERMINATED'):
return False
return True
def terminate(self):
"""
Terminates a running map-reduce job.
"""
if not self.job_id:
raise RankmaniacError('No job is running.')
self._emr_conn.terminate_jobflow(self.job_id)
self.job_id = None
self._reset()
def download(self, outdir='results'):
"""
Downloads the results from Amazon S3 to the local directory.
Keyword arguments:
outdir <str> the base directory to which to
download contents.
Special notes:
This method downloads all keys (files) from the configured
bucket for this particular team. It creates subdirectories
as needed.
"""
bucket = self._s3_conn.get_bucket(self._s3_bucket)
keys = bucket.list(prefix=self._get_keyname())
for key in keys:
keyname = key.name
# Ignore folder keys
if '$' not in keyname:
suffix = keyname.split('/')[1:] # removes team identifier
filename = os.path.join(outdir, *suffix)
dirname = os.path.dirname(filename)
if not os.path.exists(dirname):
os.makedirs(dirname)
key.get_contents_to_filename(filename)
def describe(self):
"""
Gets the current map-reduce job details.
Returns a boto.emr.emrobject.JobFlow object.
Special notes:
The JobFlow object has the following relevant fields.
state <str> the state of the job flow,
either COMPLETED
| FAILED
| TERMINATED
| RUNNING
| SHUTTING_DOWN
| STARTING
| WAITING
steps <list(boto.emr.emrobject.Step)>
a list of the step details in the workflow.
The Step object has the following relevant fields.
state <str> the state of the step.
startdatetime <str> the start time of the
job.
enddatetime <str> the end time of the job.
WARNING! Amazon has an upper-limit on the frequency with
which you can call this method; we have had success with
calling it at most once every 10 seconds.
"""
if not self.job_id:
raise RankmaniacError('No job is running.')
return self._emr_conn.describe_jobflow(self.job_id)
def _get_last_process_step_iter_no(self):
"""
Returns the most recently process-step of the job flow that has
been completed.
"""
steps = self.describe().steps
i = 1
while i < len(steps):
step = steps[i]
if step.state != 'COMPLETED':
break
i += 2
return i / 2 - 1
def _get_default_outdir(self, name, iter_no=None):
"""
Returns the default output directory, which is 'iter_no/name/'.
"""
if iter_no is None:
iter_no = self._iter_no
# Return iter_no/name/ **with** the trailing slash
return '%s/%s/' % (iter_no, name)
def _submit_new_job(self, steps):
"""
Submits a new job to run on Amazon EMR.
"""
if self.job_id is not None:
raise RankmaniacError('A job is already running.')
job_name = self._make_name()
num_instances = self._num_instances
log_uri = self._get_s3_team_uri('job_logs')
self.job_id = self._emr_conn.run_jobflow(name=job_name,
steps=steps,
num_instances=num_instances,
log_uri=log_uri)
def _make_step(self, mapper, reducer, input, output,
num_mappers=1, num_reducers=1):
"""
Returns a new step that runs the specified mapper and reducer,
reading from the specified input and writing to the specified
output.
"""
bucket = self._s3_conn.get_bucket(self._s3_bucket)
# Clear out current bucket/output contents for team
keys = bucket.list(prefix=self._get_keyname(output))
bucket.delete_keys(keys)
step_name = self._make_name()
step_args = ['-jobconf', 'mapred.map.tasks=%d' % (num_mappers),
'-jobconf', 'mapred.reduce.tasks=%d' % (num_reducers)]
return StreamingStep(name=step_name,
step_args=step_args,
mapper=self._get_s3_team_uri(mapper),
reducer=self._get_s3_team_uri(reducer),
input=self._get_s3_team_uri(input),
output=self._get_s3_team_uri(output))
def _make_name(self):
return strftime('%%s %m-%d-%Y %H:%M:%S', localtime()) % (self.team_id)
def _get_keyname(self, *args):
"""
Returns the key name to use in the grading bucket (for the
particular team).
'team_id/...'
"""
return '%s/%s' % (self.team_id, '/'.join(args))
def _get_s3_team_uri(self, *args):
"""
Returns the Amazon S3 URI for the team submissions.
"""
return 's3n://%s/%s' % (self._s3_bucket, self._get_keyname(*args))
class Rankmaniac:
"""
(wrapper class)
This class presents a simple wrapper around the AWS SDK. It strives
to provide all the functionality required to run map-reduce
(Hadoop) on Amazon. This way the students do not need to worry about
learning the API for Amazon S3 and EMR, and instead can focus on
computing pagerank quickly!
"""
DefaultRegionName = 'us-west-2'
DefaultRegionEndpoint = 'elasticmapreduce.us-west-2.amazonaws.com'
def __init__(self,
team_id,
access_key,
secret_key,
bucket='cs144students'):
"""
(constructor)
Creates a new instance of the Rankmaniac class for a specific
team using the provided credentials.
Arguments:
team_id <str> the team identifier, which may be
differ slightly from the actual team
name.
access_key <str> the AWS access key identifier.
secret_key <str> the AWS secret acess key.
Keyword arguments:
bucket <str> the S3 bucket name.
"""
region = RegionInfo(None, self.DefaultRegionName,
self.DefaultRegionEndpoint)
self._s3_bucket = bucket
self._s3_conn = S3Connection(access_key, secret_key)
self._emr_conn = EmrConnection(access_key, secret_key, region=region)
self.team_id = team_id
self.job_id = None
self._reset()
self._num_instances = 1
def _reset(self):
"""
Resets the internal state of the job and submission.
"""
self._iter_no = 0
self._infile = None
self._last_outdir = None
self._last_process_step_iter_no = -1
self._is_done = False
def __del__(self):
"""
(destructor)
Terminates the map-reduce job if any, and closes the connections
to Amazon S3 and EMR.
"""
if self.job_id is not None:
self.terminate()
self._s3_conn.close()
self._emr_conn.close()
def __enter__(self):
"""
Used for `with` syntax. Simply returns this instance since the
set-up has all been done in the constructor.
"""
return self
def __exit__(self, type, value, traceback):
"""
Refer to __del__().
"""
self.__del__()
return False # do not swallow any exceptions
def upload(self, indir='data'):
"""
Uploads the local data to Amazon S3 under the configured bucket
and key prefix (the team identifier). This way the code can be
accessed by Amazon EMR to compute pagerank.
Keyword arguments:
indir <str> the base directory from which to
upload contents.
Special notes:
This method only uploads **files** in the specified
directory. It does not scan through subdirectories.
WARNING! This method removes all previous (or ongoing)
submission results, so it is unsafe to call while a job is
already running (and possibly started elsewhere).
"""
if self.job_id is not None:
raise RankmaniacError('A job is already running.')
bucket = self._s3_conn.get_bucket(self._s3_bucket)
# Clear out current bucket contents for team
keys = bucket.list(prefix=self._get_keyname())
bucket.delete_keys(keys)
for filename in os.listdir(indir):
relpath = os.path.join(indir, filename)
if os.path.isfile(relpath):
keyname = self._get_keyname(filename)
key = bucket.new_key(keyname)
key.set_contents_from_filename(relpath)
def set_infile(self, filename):
"""
Sets the data file to use for the first iteration of the
pagerank step in the map-reduce job.
"""
if self.job_id is not None:
raise RankmaniacError('A job is already running.')
self._infile = filename
def do_iter(self,
pagerank_mapper,
pagerank_reducer,
process_mapper,
process_reducer,
pagerank_output=None,
process_output=None,
num_pagerank_mappers=1,
num_pagerank_reducers=1):
"""
Adds a pagerank step and a process step to the current job.
"""
num_process_mappers = 1
num_process_reducers = 1
if self._iter_no == 0:
pagerank_input = self._infile
elif self._iter_no > 0:
pagerank_input = self._last_outdir
if pagerank_output is None:
pagerank_output = self._get_default_outdir('pagerank')
# Output from the pagerank step becomes input to process step
process_input = pagerank_output
if process_output is None:
process_output = self._get_default_outdir('process')
pagerank_step = self._make_step(pagerank_mapper, pagerank_reducer,
pagerank_input, pagerank_output,
num_pagerank_mappers,
num_pagerank_reducers)
process_step = self._make_step(process_mapper, process_reducer,
process_input, process_output,
num_process_mappers,
num_process_reducers)
steps = [pagerank_step, process_step]
if self.job_id is None:
self._submit_new_job(steps)
else:
self._emr_conn.add_jobflow_steps(self.job_id, steps)
# Store `process_output` directory so it can be used in
# subsequent iteration
self._last_outdir = process_output
self._iter_no += 1
def is_done(self):
"""
Returns `True` if the map-reduce job is done, and `False`
otherwise.
For all process-step output files that have not been fetched,
gets the first part of the output file, and checks whether its
contents begins with the string 'FinalRank'.
Special notes:
WARNING! The usage of this method in your code requires that
that you used the default output directories in all calls
to do_iter().
"""
# Cache the result so we can return immediately without hitting
# any of the Amazon APIs
if self._is_done:
return True
iter_no = self._get_last_process_step_iter_no()
if iter_no < 0:
return False
while self._last_process_step_iter_no < iter_no:
self._last_process_step_iter_no += 1
i = self._last_process_step_iter_no
outdir = self._get_default_outdir('process', iter_no=i)
keyname = self._get_keyname(outdir, 'part-00000')
bucket = self._s3_conn.get_bucket(self._s3_bucket)
key = Key(bucket=bucket, name=keyname)
contents = key.next() # get first chunk of the output file
if contents.startswith('FinalRank'):
self._is_done = True # cache result
break
return self._is_done
def is_alive(self):
"""
Checks whether the jobflow has completed, failed, or been
terminated.
Special notes:
WARNING! This method should only be called **after**
is_done() in order to be able to distinguish between the
cases where the map-reduce job has outputted 'FinalRank'
on its final iteration and has a 'COMPLETED' state.
"""
jobflow = self.describe()
if jobflow.state in ('COMPLETED', 'FAILED', 'TERMINATED'):
return False
return True
def terminate(self):
"""
Terminates a running map-reduce job.
"""
if not self.job_id:
raise RankmaniacError('No job is running.')
self._emr_conn.terminate_jobflow(self.job_id)
self.job_id = None
self._reset()
def download(self, outdir='results'):
"""
Downloads the results from Amazon S3 to the local directory.
Keyword arguments:
outdir <str> the base directory to which to
download contents.
Special notes:
This method downloads all keys (files) from the configured
bucket for this particular team. It creates subdirectories
as needed.
"""
bucket = self._s3_conn.get_bucket(self._s3_bucket)
keys = bucket.list(prefix=self._get_keyname())
for key in keys:
keyname = key.name
# Ignore folder keys
if '$' not in keyname:
suffix = keyname.split('/')[1:] # removes team identifier
filename = os.path.join(outdir, *suffix)
dirname = os.path.dirname(filename)
if not os.path.exists(dirname):
os.makedirs(dirname)
key.get_contents_to_filename(filename)
def describe(self):
"""
Gets the current map-reduce job details.
Returns a boto.emr.emrobject.JobFlow object.
Special notes:
The JobFlow object has the following relevant fields.
state <str> the state of the job flow,
either COMPLETED
| FAILED
| TERMINATED
| RUNNING
| SHUTTING_DOWN
| STARTING
| WAITING
steps <list(boto.emr.emrobject.Step)>
a list of the step details in the workflow.
The Step object has the following relevant fields.
state <str> the state of the step.
startdatetime <str> the start time of the
job.
enddatetime <str> the end time of the job.
WARNING! Amazon has an upper-limit on the frequency with
which you can call this method; we have had success with
calling it at most once every 10 seconds.
"""
if not self.job_id:
raise RankmaniacError('No job is running.')
return self._emr_conn.describe_jobflow(self.job_id)
def _get_last_process_step_iter_no(self):
"""
Returns the most recently process-step of the job flow that has
been completed.
"""
steps = self.describe().steps
i = 1
while i < len(steps):
step = steps[i]
if step.state != 'COMPLETED':
break
i += 2
return i / 2 - 1
def _get_default_outdir(self, name, iter_no=None):
"""
Returns the default output directory, which is 'iter_no/name/'.
"""
if iter_no is None:
iter_no = self._iter_no
# Return iter_no/name/ **with** the trailing slash
return '%s/%s/' % (iter_no, name)
def _submit_new_job(self, steps):
"""
Submits a new job to run on Amazon EMR.
"""
if self.job_id is not None:
raise RankmaniacError('A job is already running.')
job_name = self._make_name()
num_instances = self._num_instances
log_uri = self._get_s3_team_uri('job_logs')
self.job_id = self._emr_conn.run_jobflow(name=job_name,
steps=steps,
num_instances=num_instances,
log_uri=log_uri)
def _make_step(self,
mapper,
reducer,
input,
output,
num_mappers=1,
num_reducers=1):
"""
Returns a new step that runs the specified mapper and reducer,
reading from the specified input and writing to the specified
output.
"""
bucket = self._s3_conn.get_bucket(self._s3_bucket)
# Clear out current bucket/output contents for team
keys = bucket.list(prefix=self._get_keyname(output))
bucket.delete_keys(keys)
step_name = self._make_name()
step_args = [
'-jobconf',
'mapred.map.tasks=%d' % (num_mappers), '-jobconf',
'mapred.reduce.tasks=%d' % (num_reducers)
]
return StreamingStep(name=step_name,
step_args=step_args,
mapper=self._get_s3_team_uri(mapper),
reducer=self._get_s3_team_uri(reducer),
input=self._get_s3_team_uri(input),
output=self._get_s3_team_uri(output))
def _make_name(self):
return strftime('%%s %m-%d-%Y %H:%M:%S', localtime()) % (self.team_id)
def _get_keyname(self, *args):
"""
Returns the key name to use in the grading bucket (for the
particular team).
'team_id/...'
"""
return '%s/%s' % (self.team_id, '/'.join(args))
def _get_s3_team_uri(self, *args):
"""
Returns the Amazon S3 URI for the team submissions.
"""
return 's3n://%s/%s' % (self._s3_bucket, self._get_keyname(*args))
class EmrHiveRuntime(HiveRuntime):
def __init__(self, spec_filename="spec.json"):
import boto
from boto.emr.connection import EmrConnection, RegionInfo
super(HiveRuntime, self).__init__(spec_filename)
p = self.settings.Param
self.s3_conn = boto.connect_s3(p.AWS_ACCESS_KEY_ID, p.AWS_ACCESS_KEY_SECRET)
self.s3_bucket = self.s3_conn.get_bucket(p.S3_BUCKET)
self.region = p.AWS_Region
self.emr_conn = EmrConnection(p.AWS_ACCESS_KEY_ID, p.AWS_ACCESS_KEY_SECRET,
region = RegionInfo(name = self.region,
endpoint = self.region + '.elasticmapreduce.amazonaws.com'))
self.job_flow_id = p.EMR_jobFlowId
def get_s3_working_dir(self, path=""):
ps = self.settings
glb_vars = ps.GlobalParam
return os.path.join('zetjob', glb_vars['userName'], "job%s" % glb_vars['jobId'], "blk%s" % glb_vars['blockId'], path)
def get_emr_job_name(self):
ps = self.settings
glb_vars = ps.GlobalParam
return os.path.join('zetjob', glb_vars['userName'], "job%s" % glb_vars['jobId'], "blk%s" % glb_vars['blockId'])
def s3_upload_dir(self, local_dir):
print("EmrHiveRuntime.s3_uploader()")
print("s3_upload_dir :::: %s" % local_dir)
s3_upload_dir = self.get_s3_working_dir(local_dir)
ext_files = [f for f in sorted(os.listdir(local_dir)) if os.path.isfile(os.path.join(local_dir,f))]
for f in ext_files:
f_local = os.path.join(local_dir, f)
f_remote = os.path.join(s3_upload_dir, local_dir, f)
f_remote_full = os.path.join("s3://", self.s3_bucket.name, f_remote)
print("S3 Upload :: %s ====> %s" % (f_local, s3_upload_dir))
print("S3 remote_full :: %s" % f_remote_full)
yield s3_upload(self.s3_bucket, f_remote, f_local)
def files_uploader(self, local_dir):
return self.s3_upload_dir(local_dir)
def clean_s3_working_dir(self):
s3_working_dir = self.get_s3_working_dir()
if not s3_delete(self.s3_bucket, s3_working_dir):
# TODO : refactor to 'HiveException'
raise Exception("Can not clean s3 path : %s" % s3_working_dir)
def clean_working_dir(self):
self.clean_s3_working_dir()
def emr_execute_hive(self, s3_hive_script):
from boto.emr.step import HiveStep
hive_step = HiveStep(name=self.get_emr_job_name(), hive_file=s3_hive_script)
self.emr_conn.add_jobflow_steps(self.job_flow_id, steps=[hive_step])
emr_wait_job(self.emr_conn, self.job_flow_id)
def execute(self, main_hive_script, generated_hive_script=None):
self.clean_working_dir()
hive_script_local = self.generate_script(main_hive_script, generated_hive_script)
s3_working_dir = self.get_s3_working_dir()
hive_script_remote = os.path.join(s3_working_dir, os.path.basename(hive_script_local))
hive_script_remote_full = s3_upload(self.s3_bucket, hive_script_remote, hive_script_local)
print(hive_script_remote_full)
print("EmrHiveRuntime.execute()")
self.emr_execute_hive(hive_script_remote_full)
def main(argv):
# load the config
config = ConfigParser()
config.read(os.path.join(os.path.split(argv[0])[0] if not None else '','config.ini'))
# load AWS config
awsConfig = ConfigParser()
awsConfig.read(config.get('Common','aws'))
aws_access_key = awsConfig.get('AWS','aws_access_key')
aws_secret_key = awsConfig.get('AWS','aws_secret_key')
event_bucket = awsConfig.get('AWS','event_bucket')
output_bucket = awsConfig.get('AWS','emr_output_bucket')
script_bucket = awsConfig.get('AWS','script_bucket')
jobId = argv[1]
emrConnection = EmrConnection(aws_access_key, aws_secret_key)
s3Connection = S3Connection(aws_access_key, aws_secret_key)
# clean s3 output
bucket = s3Connection.get_bucket(output_bucket)
for key in bucket.get_all_keys(prefix=DEDUPED_EVENTS_KEY):
bucket.delete_key(key)
step = StreamingStep(name='Twitter event deduper',
mapper='s3://%s/dedup_mapper.py twitter' % script_bucket,
reducer='s3://%s/dedup_reducer.py' % script_bucket,
input='s3://%s/normalized' % event_bucket,
output='s3://%s/%s' % (output_bucket,DEDUPED_EVENTS_KEY),
action_on_failure='CONTINUE')
emrConnection.add_jobflow_steps(jobId, step)
# clean s3 output
bucket = s3Connection.get_bucket(output_bucket)
for key in bucket.get_all_keys(prefix=EVENTS_KEY):
bucket.delete_key(key)
step = StreamingStep(name='Twitter 30-day Retweet Min/Max Analyzer',
mapper='s3://%s/30d_age_mapper.py' % script_bucket,
reducer='s3://%s/twitter_minmax_reducer.py' % script_bucket,
input='s3://%s/%s' % (output_bucket,DEDUPED_EVENTS_KEY),
output='s3://%s/%s' % (output_bucket,EVENTS_KEY),
action_on_failure='CONTINUE')
emrConnection.add_jobflow_steps(jobId, step)
# clean s3 output
bucket = s3Connection.get_bucket(output_bucket)
for key in bucket.get_all_keys(prefix=SUMMARY_KEY):
bucket.delete_key(key)
step = StreamingStep(name='Twitter Highlighter',
mapper='s3://%s/twitter_highlight_mapper.py' % script_bucket,
reducer='s3://%s/twitter_highlight_reducer.py' % script_bucket,
input='s3://%s/%s' % (output_bucket,EVENTS_KEY),
output='s3://%s/%s' % (output_bucket,SUMMARY_KEY),
action_on_failure='CONTINUE')
emrConnection.add_jobflow_steps(jobId, step)
print 'Successfully started twitter streaming steps'
class EmrManager(object):
# Default constructor of the class. Uses default parameters if not provided.
def __init__(self, parameters):
try:
self.region_name = parameters["region_name"]
self.access_key = parameters["access_key"]
self.secret_key = parameters["secret_key"]
self.ec2_keypair_name = parameters["ec2_keypair_name"]
self.base_bucket = parameters["base_bucket"]
self.log_dir = parameters["log_dir"]
self.emr_status_wait = parameters["emr_status_wait"]
self.step_status_wait = parameters["step_status_wait"]
self.emr_cluster_name = parameters["emr_cluster_name"]
except:
logging.error("Something went wrong initializing EmrManager")
sys.exit()
# Establishing EmrConnection
self.connection = EmrConnection(self.access_key, self.secret_key,
region=RegionInfo(name=self.region_name,
endpoint=self.region_name + '.elasticmapreduce.amazonaws.com'))
self.log_bucket_name = self.base_bucket + self.log_dir
#Method for launching the EMR cluster
def launch_cluster(self, master_type, slave_type, num_instances, ami_version):
try:
#Launching the cluster
cluster_id = self.connection.run_jobflow(
self.emr_cluster_name,
self.log_bucket_name,
ec2_keyname=self.ec2_keypair_name,
keep_alive=True,
action_on_failure = 'CANCEL_AND_WAIT',
master_instance_type=master_type,
slave_instance_type=slave_type,
num_instances=num_instances,
ami_version=ami_version)
logging.info("Launching cluster: " + cluster_id + ". Please be patient. Check the status of your cluster in your AWS Console")
# Checking the state of EMR cluster
state = self.connection.describe_jobflow(cluster_id).state
while state != u'COMPLETED' and state != u'SHUTTING_DOWN' and state != u'FAILED' and state != u'WAITING':
#sleeping to recheck for status.
time.sleep(int(self.emr_status_wait))
state = self.connection.describe_jobflow(cluster_id).state
logging.info("Creating cluster " + cluster_id + ". Status: " + state)
if state == u'SHUTTING_DOWN' or state == u'FAILED':
logging.error("Launching EMR cluster failed")
return "ERROR"
#Check if the state is WAITING. Then launch the next steps
if state == u'WAITING':
#Finding the master node dns of EMR cluster
master_dns = self.connection.describe_jobflow(cluster_id).masterpublicdnsname
logging.info("Launched EMR Cluster Successfully with cluster id:" + cluster_id)
logging.info("Master node DNS of EMR " + master_dns)
return cluster_id
except:
logging.error("Launching EMR cluster failed")
return "FAILED"
# run scripting step in cluster
def run_scripting_step(self, cluster_id, name, script_path):
try:
step = ScriptRunnerStep(name=name,
step_args=[script_path],
action_on_failure="CONTINUE")
return self._run_step(cluster_id, step)
except:
logging.error("Running scripting step in cluster " + cluster_id + " failed.")
return "FAILED"
# run streaming step in cluster
def run_streaming_step(self, cluster_id, name, mapper_path, reducer_path, input_path, output_path):
try:
# bundle files with the job
files = []
if mapper_path != "NONE":
files.append(mapper_path)
mapper_path = mapper_path.split("/")[-1]
if reducer_path != "NONE":
files.append(reducer_path)
reducer_path = reducer_path.split("/")[-1]
# build streaming step
logging.debug("Launching streaming step with mapper: " + mapper_path + " reducer: " + reducer_path + " and files: " + str(files))
step = StreamingStep(name=name,
step_args=["-files"] + files,
mapper=mapper_path,
reducer=reducer_path,
input=input_path,
output=output_path,
action_on_failure="CONTINUE")
return self._run_step(cluster_id, step)
except:
logging.error("Running streaming step in cluster " + cluster_id + " failed.")
return "FAILED"
# run mapreduce jar step in cluster
def run_jar_step(self, cluster_id, name, jar_path, class_name, input_path, output_path):
try:
# build streaming step
logging.debug("Launching jar step with jar: " + jar_path + " class name: " + class_name + " input: " + input_path + " and output: " + output_path)
step = JarStep(name=name,
jar=jar_path,
step_args= [class_name,
input_path,
output_path])
return self._run_step(cluster_id, step)
except:
logging.error("Running jar step in cluster " + cluster_id + " failed.")
return "FAILED"
def _run_step(self, cluster_id, step):
step_list = self.connection.add_jobflow_steps(cluster_id, [step])
step_id = step_list.stepids[0].value
logging.info("Starting step " + step_id + " in cluster " + cluster_id + ". Please be patient. Check the progress of the job in your AWS Console")
# Checking the state of the step
state = self._find_step_state(cluster_id, step_id)
while state != u'NOT_FOUND' and state != u'ERROR' and state != u'FAILED' and state!=u'COMPLETED':
#sleeping to recheck for status.
time.sleep(int(self.step_status_wait))
state = self._find_step_state(cluster_id, step_id)
logging.info("Starting step " + step_id + " in cluster " + cluster_id + ". Status: " + state)
if state == u'FAILED':
logging.error("Step " + step_id + " failed in cluster: " + cluster_id)
return "FAILED"
if state == u'NOT_FOUND':
logging.error("Step " + step_id + " could not be found in cluster: " + cluster_id)
return "NOT_FOUND"
if state == u'ERROR':
logging.error("Step " + step_id + " produced an error in _find_step_state in cluster: " + cluster_id)
return "ERROR"
#Check if the state is WAITING. Then launch the next steps
if state == u'COMPLETED':
#Finding the master node dns of EMR cluster
logging.info("Step " + step_id + " succesfully completed in cluster: " + cluster_id)
return step_id
def _find_step_state(self, cluster_id, step_id):
try:
step_summary_list = self.connection.list_steps(cluster_id)
for step_summary in step_summary_list.steps:
if step_summary.id == step_id:
return step_summary.status.state
return "NOT_FOUND"
except:
return "ERROR"
#Method for terminating the EMR cluster
def terminate_cluster(self, cluster_id):
self.connection.terminate_jobflow(cluster_id)
class EMRCluster(object):
'''Representation of an EMR cluster.
TODO: add bridge to boto interface for unit test.
'''
emr_status_delay = 10 # in sec
emr_status_max_delay = 60 # in sec
emr_status_max_error = 30 # number of errors
emr_max_idle = 10 * 60 # 10 min (in sec)
rate_limit_lock = RateLimitLock()
def __init__(self, prop):
'''Constructor, initialize EMR connection.'''
self.prop = prop
self.conn = EmrConnection(self.prop.ec2.key, self.prop.ec2.secret)
self.jobid = None
self.retry = 0
self.level = 0
self.last_update = -1
@property
def priority(self):
'''The priority used in EMRManager.
The lower value, the higher priority.
'''
with EMRCluster.rate_limit_lock:
if self.jobid is None:
return 1
return 0
def get_instance_groups(self):
'''Get instance groups to start a cluster.
It calculates the price with self.level, which indicates the
price upgrades from the original price.
'''
instance_groups = []
for group in self.prop.emr.instance_groups:
(num, group_name, instance_type) = group
level = max(0,
min(self.level,
len(self.prop.emr.price_upgrade_rate) -
1)) # 0 <= level < len(...)
bprice = self.prop.emr.prices[
instance_type] * self.prop.emr.price_upgrade_rate[level]
name = '%s-%s@%f' % (group_name, 'SPOT', bprice)
# Use on-demand instance if prices are zero.
if bprice > 0:
ig = InstanceGroup(num, group_name, instance_type, 'SPOT',
name, '%.3f' % bprice)
else:
ig = InstanceGroup(num, group_name, instance_type, 'ON_DEMAND',
name)
instance_groups.append(ig)
return instance_groups
def get_bootstrap_actions(self):
'''Get list of bootstrap actions from property'''
actions = []
for bootstrap_action in self.prop.emr.bootstrap_actions:
assert len(bootstrap_action
) >= 2, 'Wrong bootstrap action definition: ' + str(
bootstrap_action)
actions.append(
BootstrapAction(bootstrap_action[0], bootstrap_action[1],
bootstrap_action[2:]))
return actions
@synchronized
def start(self):
'''Start a EMR cluster.'''
# emr.project_name is required
if self.prop.emr.project_name is None:
raise ValueError('emr.project_name is not set')
self.last_update = time.time()
with EMRCluster.rate_limit_lock:
self.jobid = self.conn.run_jobflow(
name=self.prop.emr.cluster_name,
ec2_keyname=self.prop.emr.keyname,
log_uri=self.prop.emr.log_uri,
ami_version=self.prop.emr.ami_version,
bootstrap_actions=self.get_bootstrap_actions(),
keep_alive=True,
action_on_failure='CONTINUE',
api_params={'VisibleToAllUsers': 'true'},
instance_groups=self.get_instance_groups())
message('Job flow created: %s', self.jobid)
# Tag EC2 instances to allow future analysis
tags = {
'FlowControl': 'Briefly',
'Project': self.prop.emr.project_name
}
if self.prop.emr.tags is not None:
assert isinstance(self.prop.emr.tags, dict)
tags = dict(tags.items() + self.prop.emr.tags.items())
self.conn.add_tags(self.jobid, tags)
@synchronized
def terminate(self, level_upgrade=0):
'''Terminate this EMR cluster.'''
if self.jobid is None:
return
self.level += level_upgrade # upgrade to another price level
message('Terminate jobflow: %s', self.jobid)
for i in range(3):
try:
with EMRCluster.rate_limit_lock:
self.conn.terminate_jobflow(self.jobid)
break
except Exception as e:
message('Unable to terminate job flow: %s', self.jobid)
message(traceback.format_exc())
# We have to set jobid as None to create new cluster;
# otherwise, run_steps will keep launching jobs on the bad cluster.
self.jobid = None
def is_idle(self):
'''Check if this EMR cluster is idle?'''
return (not self.jobid is None) and (
(time.time() - self.last_update) > self.emr_max_idle)
def get_steps(self, node):
'''Get the jar step from the node.'''
step = JarStep(name=node.config.sub(node.config.emr.step_name,
node_hash=node.hash()),
main_class=node.config.main_class,
jar=node.config.hadoop.jar,
action_on_failure='CONTINUE',
step_args=node.process_args(*node.config.args))
return [step]
def get_step_index(self, step_id):
'''Get the index of a step given step_id (1 based)'''
steps = [
step.id
for step in reversed(self.conn.list_steps(self.jobid).steps)
if step.status is not None
]
# revert the index since latest step is on top of the list
return steps.index(step_id) + 1
def run_steps(self, node, wait=True):
'''Main loop to execute a node.
It will block until step complete or failure, and will raise
exception for failures so that the step will be retried.
TODO: add timeouts for each step?
TODO: dynamic increase cluster size?
'''
if not self.jobid:
self.start()
try:
with EMRCluster.rate_limit_lock:
# Here we just add single step. And get the step_id for fallowing checks.
step_id = self.conn.add_jobflow_steps(
self.jobid, self.get_steps(node)).stepids[0].value
assert step_id is not None
except Exception as e:
node.log('Unable to add jobflow steps: %s', node.hash())
node.log('%s', traceback.format_exc())
raise HadoopFailure()
status_error_counter = 0
step_status = 'PENDING'
step_index = None
step_start = time.time()
# notify the node with status.
node.notify_status('Running on EMR: %s', self.jobid)
while wait and step_status in ['PENDING', 'RUNNING']:
try:
# wait first for the status turning to 'RUNNING' from 'WAITING'. Exponential delay for errors.
# Cap delay to a predefined limit.
delay = min(self.emr_status_delay * (2**status_error_counter),
self.emr_status_max_delay)
time.sleep(delay)
# Keep current cluster alive.
self.last_update = time.time()
# Get current cluster status. May raise exception due to EMR request throttle.
cluster_state = self.conn.describe_cluster(
self.jobid).status.state
if step_index is None:
step_index = self.get_step_index(step_id)
node.log('Step #: %d', step_index)
node.log('Log URI: %s/%s/steps/%d/',
node.config.emr.log_uri, self.jobid, step_index)
step_status = self.conn.describe_step(self.jobid,
step_id).status.state
status_error_counter = 0 # reset counter
node.log("%s: %s %s", self.jobid, cluster_state, step_status)
if cluster_state in [
'TERMINATING', 'TERMINATED', 'TERMINATED_WITH_ERRORS'
]: # cluster kill (maybe due to spot price), upgrade.
self.terminate(1)
break
if (
time.time() - step_start
) > node.config.emr.step_timeout: # Step running too long? EMR cluster idle.
node.log('Step running too long. Restart with new cluster')
self.terminate()
break
except KeyboardInterrupt:
raise
except Exception as e:
node.log('EMR loop exception: %d error(s)',
status_error_counter)
status_error_counter += 1
if status_error_counter > self.emr_status_max_error:
self.terminate()
node.log('Too many errors in EMR loop')
node.log('Exception: %s', traceback.format_exc())
raise
if step_status != 'COMPLETED':
raise HadoopFailure()
def main(argv):
# load the config
config = ConfigParser()
config.read(os.path.join(os.path.split(argv[0])[0] if not None else '','config.ini'))
# load AWS config
awsConfig = ConfigParser()
awsConfig.read(config.get('Common','aws'))
aws_access_key = awsConfig.get('AWS','aws_access_key')
aws_secret_key = awsConfig.get('AWS','aws_secret_key')
event_bucket = awsConfig.get('AWS','event_bucket')
output_bucket = awsConfig.get('AWS','emr_output_bucket')
script_bucket = awsConfig.get('AWS','script_bucket')
jobId = argv[1]
emrConnection = EmrConnection(aws_access_key, aws_secret_key)
s3Connection = S3Connection(aws_access_key, aws_secret_key)
# clean s3 output
bucket = s3Connection.get_bucket(output_bucket)
for key in bucket.get_all_keys(prefix=DEDUPED_EVENTS_KEY):
bucket.delete_key(key)
step = StreamingStep(name='Foursquare event deduper',
mapper='s3://%s/dedup_mapper.py foursquare' % script_bucket,
reducer='s3://%s/dedup_reducer.py' % script_bucket,
input='s3://%s/normalized' % event_bucket,
output='s3://%s/%s' % (output_bucket,DEDUPED_EVENTS_KEY),
action_on_failure='CONTINUE')
emrConnection.add_jobflow_steps(jobId, step)
# clean s3 output
bucket = s3Connection.get_bucket(output_bucket)
for key in bucket.get_all_keys(prefix=AGGREGATED_KEY):
bucket.delete_key(key)
step = StreamingStep(name='Foursquare 30-day Collector',
mapper='s3://%s/foursquare_30d_mapper.py' % script_bucket,
reducer='s3://%s/identity_reducer.py' % script_bucket,
input='s3://%s/%s' % (output_bucket,DEDUPED_EVENTS_KEY),
output='s3://%s/%s' % (output_bucket,EVENTS_KEY),
action_on_failure='CONTINUE')
emrConnection.add_jobflow_steps(jobId, step)
# clean s3 output
bucket = s3Connection.get_bucket(output_bucket)
for key in bucket.get_all_keys(prefix=EVENTS_KEY):
bucket.delete_key(key)
step = StreamingStep(name='Foursquare Venue Aggregator',
mapper='s3://%s/identity_mapper.py' % script_bucket,
reducer='s3://%s/foursquare_checkin_aggregator_reducer.py' % script_bucket,
input='s3://%s/%s' % (output_bucket,EVENTS_KEY),
output='s3://%s/%s' % (output_bucket,AGGREGATED_KEY),
action_on_failure='CONTINUE')
emrConnection.add_jobflow_steps(jobId, step)
# clean s3 output
bucket = s3Connection.get_bucket(output_bucket)
for key in bucket.get_all_keys(prefix=MINMAX_KEY):
bucket.delete_key(key)
step = StreamingStep(name='Foursquare Min/Max Analyzer',
mapper='s3://%s/identity_mapper.py' % script_bucket,
reducer='s3://%s/foursquare_minmax_reducer.py' % script_bucket,
input='s3://%s/%s' % (output_bucket,AGGREGATED_KEY),
output='s3://%s/%s' % (output_bucket,MINMAX_KEY),
action_on_failure='CONTINUE')
emrConnection.add_jobflow_steps(jobId, step)
# clean s3 output
bucket = s3Connection.get_bucket(output_bucket)
for key in bucket.get_all_keys(prefix=SUMMARY_KEY):
bucket.delete_key(key)
step = StreamingStep(name='Foursquare Highlighter',
mapper='s3://%s/identity_mapper.py' % script_bucket,
reducer='s3://%s/foursquare_highlight_reducer.py' % script_bucket,
input='s3://%s/%s' % (output_bucket,MINMAX_KEY),
output='s3://%s/%s' % (output_bucket,SUMMARY_KEY),
action_on_failure='CONTINUE')
emrConnection.add_jobflow_steps(jobId, step)
print 'Successfully started foursquare streaming steps'
class EmrClient(object):
# The Hadoop version to use
HADOOP_VERSION = '1.0.3'
# The AMI version to use
AMI_VERSION = '2.4.7'
# Interval to wait between polls to EMR cluster in seconds
CLUSTER_OPERATION_RESULTS_POLLING_SECONDS = 10
# Timeout for EMR creation and ramp up in seconds
CLUSTER_OPERATION_RESULTS_TIMEOUT_SECONDS = 60 * 30
def __init__(self,
region_name='us-east-1',
aws_access_key_id=None,
aws_secret_access_key=None):
# If the access key is not specified, get it from the luigi config.cfg file
if not aws_access_key_id:
aws_access_key_id = luigi.configuration.get_config().get(
'aws', 'aws_access_key_id')
if not aws_secret_access_key:
aws_secret_access_key = luigi.configuration.get_config().get(
'aws', 'aws_secret_access_key')
# Create the region in which to run
region_endpoint = u'elasticmapreduce.%s.amazonaws.com' % (region_name)
region = RegionInfo(name=region_name, endpoint=region_endpoint)
self.emr_connection = EmrConnection(
aws_access_key_id=aws_access_key_id,
aws_secret_access_key=aws_secret_access_key,
region=region)
def launch_emr_cluster(
self,
cluster_name,
log_uri,
ec2_keyname=None,
master_type='m1.small',
core_type='m1.small',
num_instances=2,
hadoop_version='1.0.3',
ami_version='2.4.7',
):
# TODO Remove
# install_pig_step = InstallPigStep()
jobflow_id = self.emr_connection.run_jobflow(
name=cluster_name,
log_uri=log_uri,
ec2_keyname=ec2_keyname,
master_instance_type=master_type,
slave_instance_type=core_type,
num_instances=num_instances,
keep_alive=True,
enable_debugging=True,
hadoop_version=EmrClient.HADOOP_VERSION,
steps=[],
ami_version=EmrClient.AMI_VERSION)
# Log important information
status = self.emr_connection.describe_jobflow(jobflow_id)
logger.info('Creating new cluster %s with following details' %
status.name)
logger.info('jobflow ID:\t%s' % status.jobflowid)
logger.info('Log URI:\t%s' % status.loguri)
logger.info('Master Instance Type:\t%s' % status.masterinstancetype)
# A cluster of size 1 does not have any slave instances
if hasattr(status, 'slaveinstancetype'):
logger.info('Slave Instance Type:\t%s' % status.slaveinstancetype)
logger.info('Number of Instances:\t%s' % status.instancecount)
logger.info('Hadoop Version:\t%s' % status.hadoopversion)
logger.info('AMI Version:\t%s' % status.amiversion)
logger.info('Keep Alive:\t%s' % status.keepjobflowalivewhennosteps)
return self._poll_until_cluster_ready(jobflow_id)
def add_pig_step(self,
jobflow_id,
pig_file,
name='Pig Script',
pig_versions='latest',
pig_args=[]):
pig_step = PigStep(
name=name,
pig_file=pig_file,
pig_versions=pig_versions,
pig_args=pig_args,
# action_on_failure='CONTINUE',
)
self.emr_connection.add_jobflow_steps(jobflow_id, [pig_step])
# Poll until the cluster is done working
return self._poll_until_cluster_ready(jobflow_id)
def shutdown_emr_cluster(self, jobflow_id):
self.emr_connection.terminate_jobflow(jobflow_id)
return self._poll_until_cluster_shutdown(jobflow_id)
def get_jobflow_id(self):
# Get the id of the cluster that is WAITING for work
return self.emr_connection.list_clusters(
cluster_states=['WAITING']).clusters[0].id
def get_master_dns(self):
"""
Get the master node's public address
"""
# Get the jobflow ID
jobflow_id = self.get_master_dns()
# Use the jobflow ID to get the status
status = self.emr_connection.describe_jobflow(jobflow_id)
# Return the master's public dns
return status.masterpublicdnsname
def _poll_until_cluster_ready(self, jobflow_id):
start_time = time.time()
is_cluster_ready = False
while (not is_cluster_ready) and (
time.time() - start_time <
EmrClient.CLUSTER_OPERATION_RESULTS_TIMEOUT_SECONDS):
# Get the state
state = self.emr_connection.describe_jobflow(jobflow_id).state
if state == u'WAITING':
logger.info('Cluster intialized and is WAITING for work')
is_cluster_ready = True
elif (state == u'COMPLETED') or \
(state == u'SHUTTING_DOWN') or \
(state == u'FAILED') or \
(state == u'TERMINATED'):
logger.error('Error starting cluster; status: %s' % state)
# Poll until cluster shutdown
self._poll_until_cluster_shutdown(jobflow_id)
raise RuntimeError('Error, cluster failed to start')
else:
logger.debug('Cluster state: %s' % state)
time.sleep(EmrClient.CLUSTER_OPERATION_RESULTS_POLLING_SECONDS)
if not is_cluster_ready:
# TODO shutdown cluster
raise RuntimeError(
'Timed out waiting for EMR cluster to be active')
return jobflow_id
def _poll_until_cluster_shutdown(self, jobflow_id):
start_time = time.time()
is_cluster_shutdown = False
while (not is_cluster_shutdown) and (
time.time() - start_time <
EmrClient.CLUSTER_OPERATION_RESULTS_TIMEOUT_SECONDS):
# Get the state
state = self.emr_connection.describe_jobflow(jobflow_id).state
if (state == u'TERMINATED') or (state == u'COMPLETED'):
logger.info('Cluster successfully shutdown with status: %s' %
state)
return False
elif state == u'FAILED':
logger.error('Cluster shutdown with FAILED status')
return False
else:
logger.debug('Cluster state: %s' % state)
time.sleep(EmrClient.CLUSTER_OPERATION_RESULTS_POLLING_SECONDS)
if not is_cluster_shutdown:
# TODO shutdown cluster
raise RuntimeError(
'Timed out waiting for EMR cluster to shut down')
return True
class Rankmaniac:
'''Rankmaniac Wrapper
This class provides a simple wrapper around the Amazon Web Services SDK.
It should provide all the functionality required in terms of MapReduce,
so students don't need to worry about learning the EMR and S3 API.
'''
def __init__(self, team_id, access_key, secret_key):
'''Rankmaniac class constructor
Creates a new instance of the Rankmaniac Wrapper for a specific
team.
Arguments:
team_id string the team ID.
access_key string AWS access key.
secret_key string AWS secret key.
'''
self.s3_bucket = 'cs144caltech'
self.team_id = team_id
self.emr_conn = EmrConnection(access_key, secret_key)
self.s3_conn = S3Connection(access_key, secret_key)
self.job_id = None
def __del__(self):
if self.job_id:
self.terminate_job()
def submit_job(self,
mapper,
reducer,
input,
output,
num_map=1,
num_reduce=1):
'''Submit a new MapReduce job
Submits a new MapReduce job with a single step. To add more steps,
call add_step. To terminate this job, call terminate_job.
Arguments:
mapper string path to the mapper, relative to
your data directory.
reducer string path to the reducer, relative to
your data directory.
input string path to the input data, relative to
your data directory. To specify a
directory as input, ensure your path
contains a trailing /.
output string path to the desired output directory.
num_map int number of map tasks for this job.
num_reduce int number of reduce tasks for this job.
'''
if self.job_id:
raise Exception('There currently already exists a running job.')
job_name = self._make_name()
step = self._make_step(mapper, reducer, input, output, num_map,
num_reduce)
self.job_id = \
self.emr_conn.run_jobflow(name=job_name,
steps=[step],
num_instances=1,
log_uri=self._get_s3_url() + 'job_logs',
keep_alive=True)
def terminate_job(self):
'''Terminate a running MapReduce job
Stops the current running job.
'''
if not self.job_id:
raise Exception('No job is running.')
self.emr_conn.terminate_jobflow(self.job_id)
self.job_id = None
def get_job(self):
'''Gets the running job details
Returns:
JobFlow object with relevant fields:
state string the state of the job flow, either
COMPLETED | FAILED | TERMINATED
RUNNING | SHUTTING_DOWN | STARTING
WAITING | BOOTSTRAPPING
steps list(Step) a list of the step details in the
workflow. A Step has the relevant
fields:
status string
startdatetime string
enddatetime string
Note: Amazon has an upper-limit on the frequency with which you can
call this function; we have had success with calling it one
every 10 seconds.
'''
if not self.job_id:
raise Exception('No job is running.')
return self.emr_conn.describe_jobflow(self.job_id)
def add_step(self,
mapper,
reducer,
input,
output,
num_map=1,
num_reduce=1):
'''Add a step to an existing job
Adds a new step to an already running job flow.
Note: any given job flow can support up to 256 steps. To workaround
this limitation, you can always choose to submit a new job
once the current job completes.
Arguments:
mapper string path to the mapper, relative to
your data directory.
reducer string path to the reducer, relative to
your data directory.
input string path to the input data, relative to
your data directory. To specify a
directory as input, ensure your path
contains a trailing /.
output string path to the desired output directory.
'''
if not self.job_id:
raise Exception('No job is running.')
step = self._make_step(mapper, reducer, input, output, num_map,
num_reduce)
self.emr_conn.add_jobflow_steps(self.job_id, [step])
def upload(self, in_dir='data'):
'''Upload local data to S3
Uploads the files in the specified directory to S3, where it can be
used by Elastic MapReduce.
Note: this method only uploads files in the root of in_dir. It does
NOT scan through subdirectories.
Arguments:
in_dir string optional, defaults to 'data'. Uses
this directory as the base directory
from which to upload.
'''
bucket = self.s3_conn.get_bucket(self.s3_bucket)
keys = bucket.list(prefix='%s/' % self.team_id)
bucket.delete_keys(map(lambda k: k.name, keys))
to_upload = [(os.path.join(in_dir, file_name),
os.path.join(self.team_id, file_name))
for file_name in os.listdir(in_dir)
if os.path.isfile(os.path.join(in_dir, file_name))]
for l, r in to_upload:
key = Key(bucket)
key.key = r
key.set_contents_from_filename(l)
def download(self, out_dir='data'):
'''Download S3 data to local directory
Downloads S3 data to the specified directory.
Note: this method DOES download the entire directory hierarchy as
given by S3. It will create subdirectories as needed.
Arguments:
out_dir string optional, defaults to 'data'. Downloads
files to this directory.
'''
bucket = self.s3_conn.get_bucket(self.s3_bucket)
keys = bucket.list(prefix='%s/' % self.team_id)
for key in keys:
fp = os.path.join(out_dir, '/'.join(key.name.split('/')[1:]))
fp_dir = os.path.dirname(fp)
if os.path.exists(fp):
os.remove(fp)
elif not os.path.exists(fp_dir):
os.makedirs(fp_dir)
key.get_contents_to_filename(fp)
def _make_name(self):
return '%s-%s' % (self.team_id,
strftime('%m-%d-%Y %H:%M:%s', localtime()))
def _make_step(self, mapper, reducer, input, output, nm=1, nr=1):
job_name = self._make_name()
team_s3 = self._get_s3_url()
bucket = self.s3_conn.get_bucket(self.s3_bucket)
keys = bucket.list(prefix='%s/%s' % (self.team_id, output))
bucket.delete_keys(map(lambda k: k.name, keys))
return \
StreamingStep(name=job_name,
step_args=
['-jobconf', 'mapred.map.tasks=%d' % nm,
'-jobconf', 'mapred.reduce.tasks=%d' % nr],
mapper=team_s3 + mapper,
reducer=team_s3 + reducer,
input=team_s3 + input,
output=team_s3 + output)
def _get_s3_url(self):
return 's3n://%s/%s/' % (self.s3_bucket, self.team_id)
class EmrClient(object):
# The Hadoop version to use
HADOOP_VERSION = '1.0.3'
# The AMI version to use
AMI_VERSION = '2.4.7'
# Interval to wait between polls to EMR cluster in seconds
CLUSTER_OPERATION_RESULTS_POLLING_SECONDS = 10
# Timeout for EMR creation and ramp up in seconds
CLUSTER_OPERATION_RESULTS_TIMEOUT_SECONDS = 60 * 30
def __init__(self, region_name='us-east-1', aws_access_key_id=None, aws_secret_access_key=None):
# If the access key is not specified, get it from the luigi config.cfg file
if not aws_access_key_id:
aws_access_key_id = luigi.configuration.get_config().get('aws', 'aws_access_key_id')
if not aws_secret_access_key:
aws_secret_access_key = luigi.configuration.get_config().get('aws', 'aws_secret_access_key')
# Create the region in which to run
region_endpoint = u'elasticmapreduce.%s.amazonaws.com' % (region_name)
region = RegionInfo(name=region_name, endpoint=region_endpoint)
self.emr_connection = EmrConnection(aws_access_key_id=aws_access_key_id,
aws_secret_access_key=aws_secret_access_key,
region=region)
def launch_emr_cluster(self, cluster_name, log_uri, ec2_keyname=None, master_type='m1.small', core_type='m1.small', num_instances=2, hadoop_version='1.0.3', ami_version='2.4.7', ):
# TODO Remove
# install_pig_step = InstallPigStep()
jobflow_id = self.emr_connection.run_jobflow(name=cluster_name,
log_uri=log_uri,
ec2_keyname=ec2_keyname,
master_instance_type=master_type,
slave_instance_type=core_type,
num_instances=num_instances,
keep_alive=True,
enable_debugging=True,
hadoop_version=EmrClient.HADOOP_VERSION,
steps=[],
ami_version=EmrClient.AMI_VERSION)
# Log important information
status = self.emr_connection.describe_jobflow(jobflow_id)
logger.info('Creating new cluster %s with following details' % status.name)
logger.info('jobflow ID:\t%s' % status.jobflowid)
logger.info('Log URI:\t%s' % status.loguri)
logger.info('Master Instance Type:\t%s' % status.masterinstancetype)
# A cluster of size 1 does not have any slave instances
if hasattr(status, 'slaveinstancetype'):
logger.info('Slave Instance Type:\t%s' % status.slaveinstancetype)
logger.info('Number of Instances:\t%s' % status.instancecount)
logger.info('Hadoop Version:\t%s' % status.hadoopversion)
logger.info('AMI Version:\t%s' % status.amiversion)
logger.info('Keep Alive:\t%s' % status.keepjobflowalivewhennosteps)
return self._poll_until_cluster_ready(jobflow_id)
def add_pig_step(self, jobflow_id, pig_file, name='Pig Script', pig_versions='latest', pig_args=[]):
pig_step = PigStep(name=name,
pig_file=pig_file,
pig_versions=pig_versions,
pig_args=pig_args,
# action_on_failure='CONTINUE',
)
self.emr_connection.add_jobflow_steps(jobflow_id, [pig_step])
# Poll until the cluster is done working
return self._poll_until_cluster_ready(jobflow_id)
def shutdown_emr_cluster(self, jobflow_id):
self.emr_connection.terminate_jobflow(jobflow_id)
return self._poll_until_cluster_shutdown(jobflow_id)
def get_jobflow_id(self):
# Get the id of the cluster that is WAITING for work
return self.emr_connection.list_clusters(cluster_states=['WAITING']).clusters[0].id
def get_master_dns(self):
"""
Get the master node's public address
"""
# Get the jobflow ID
jobflow_id = self.get_master_dns()
# Use the jobflow ID to get the status
status = self.emr_connection.describe_jobflow(jobflow_id)
# Return the master's public dns
return status.masterpublicdnsname
def _poll_until_cluster_ready(self, jobflow_id):
start_time = time.time()
is_cluster_ready = False
while (not is_cluster_ready) and (time.time() - start_time < EmrClient.CLUSTER_OPERATION_RESULTS_TIMEOUT_SECONDS):
# Get the state
state = self.emr_connection.describe_jobflow(jobflow_id).state
if state == u'WAITING':
logger.info('Cluster intialized and is WAITING for work')
is_cluster_ready = True
elif (state == u'COMPLETED') or \
(state == u'SHUTTING_DOWN') or \
(state == u'FAILED') or \
(state == u'TERMINATED'):
logger.error('Error starting cluster; status: %s' % state)
# Poll until cluster shutdown
self._poll_until_cluster_shutdown(jobflow_id)
raise RuntimeError('Error, cluster failed to start')
else:
logger.debug('Cluster state: %s' % state)
time.sleep(EmrClient.CLUSTER_OPERATION_RESULTS_POLLING_SECONDS)
if not is_cluster_ready:
# TODO shutdown cluster
raise RuntimeError('Timed out waiting for EMR cluster to be active')
return jobflow_id
def _poll_until_cluster_shutdown(self, jobflow_id):
start_time = time.time()
is_cluster_shutdown = False
while (not is_cluster_shutdown) and (time.time() - start_time < EmrClient.CLUSTER_OPERATION_RESULTS_TIMEOUT_SECONDS):
# Get the state
state = self.emr_connection.describe_jobflow(jobflow_id).state
if (state == u'TERMINATED') or (state == u'COMPLETED'):
logger.info('Cluster successfully shutdown with status: %s' % state)
return False
elif state == u'FAILED':
logger.error('Cluster shutdown with FAILED status')
return False
else:
logger.debug('Cluster state: %s' % state)
time.sleep(EmrClient.CLUSTER_OPERATION_RESULTS_POLLING_SECONDS)
if not is_cluster_shutdown:
# TODO shutdown cluster
raise RuntimeError('Timed out waiting for EMR cluster to shut down')
return True
class Rankmaniac:
'''Rankmaniac Wrapper
This class provides a simple wrapper around the Amazon Web Services SDK.
It should provide all the functionality required in terms of MapReduce,
so students don't need to worry about learning the EMR and S3 API.
'''
def __init__(self, team_id, access_key, secret_key):
'''Rankmaniac class constructor
Creates a new instance of the Rankmaniac Wrapper for a specific
team.
Arguments:
team_id string the team ID.
access_key string AWS access key.
secret_key string AWS secret key.
'''
self.s3_bucket = 'cs144caltech'
self.team_id = team_id
self.emr_conn = EmrConnection(access_key, secret_key)
self.s3_conn = S3Connection(access_key, secret_key)
self.job_id = None
def __del__(self):
if self.job_id:
self.terminate_job()
def submit_job(self, mapper, reducer, input, output, num_map=1,
num_reduce=1):
'''Submit a new MapReduce job
Submits a new MapReduce job with a single step. To add more steps,
call add_step. To terminate this job, call terminate_job.
Arguments:
mapper string path to the mapper, relative to
your data directory.
reducer string path to the reducer, relative to
your data directory.
input string path to the input data, relative to
your data directory. To specify a
directory as input, ensure your path
contains a trailing /.
output string path to the desired output directory.
num_map int number of map tasks for this job.
num_reduce int number of reduce tasks for this job.
'''
if self.job_id:
raise Exception('There currently already exists a running job.')
job_name = self._make_name()
step = self._make_step(mapper, reducer, input, output, num_map,
num_reduce)
self.job_id = \
self.emr_conn.run_jobflow(name=job_name,
steps=[step],
num_instances=1,
log_uri=self._get_s3_url() + 'job_logs',
keep_alive=True)
def terminate_job(self):
'''Terminate a running MapReduce job
Stops the current running job.
'''
if not self.job_id:
raise Exception('No job is running.')
self.emr_conn.terminate_jobflow(self.job_id)
self.job_id = None
def get_job(self):
'''Gets the running job details
Returns:
JobFlow object with relevant fields:
state string the state of the job flow, either
COMPLETED | FAILED | TERMINATED
RUNNING | SHUTTING_DOWN | STARTING
WAITING | BOOTSTRAPPING
steps list(Step) a list of the step details in the
workflow. A Step has the relevant
fields:
status string
startdatetime string
enddatetime string
Note: Amazon has an upper-limit on the frequency with which you can
call this function; we have had success with calling it one
every 10 seconds.
'''
if not self.job_id:
raise Exception('No job is running.')
return self.emr_conn.describe_jobflow(self.job_id)
def add_step(self, mapper, reducer, input, output, num_map=1,
num_reduce=1):
'''Add a step to an existing job
Adds a new step to an already running job flow.
Note: any given job flow can support up to 256 steps. To workaround
this limitation, you can always choose to submit a new job
once the current job completes.
Arguments:
mapper string path to the mapper, relative to
your data directory.
reducer string path to the reducer, relative to
your data directory.
input string path to the input data, relative to
your data directory. To specify a
directory as input, ensure your path
contains a trailing /.
output string path to the desired output directory.
'''
if not self.job_id:
raise Exception('No job is running.')
step = self._make_step(mapper, reducer, input, output, num_map,
num_reduce)
self.emr_conn.add_jobflow_steps(self.job_id, [step])
def upload(self, in_dir='data'):
'''Upload local data to S3
Uploads the files in the specified directory to S3, where it can be
used by Elastic MapReduce.
Note: this method only uploads files in the root of in_dir. It does
NOT scan through subdirectories.
Arguments:
in_dir string optional, defaults to 'data'. Uses
this directory as the base directory
from which to upload.
'''
bucket = self.s3_conn.get_bucket(self.s3_bucket)
keys = bucket.list(prefix='%s/' % self.team_id)
bucket.delete_keys(map(lambda k: k.name, keys))
to_upload = [
(os.path.join(in_dir, file_name),
os.path.join(self.team_id, file_name))
for file_name in os.listdir(in_dir)
if os.path.isfile(os.path.join(in_dir, file_name))]
for l, r in to_upload:
key = Key(bucket)
key.key = r
key.set_contents_from_filename(l)
def download(self, out_dir='data'):
'''Download S3 data to local directory
Downloads S3 data to the specified directory.
Note: this method DOES download the entire directory hierarchy as
given by S3. It will create subdirectories as needed.
Arguments:
out_dir string optional, defaults to 'data'. Downloads
files to this directory.
'''
bucket = self.s3_conn.get_bucket(self.s3_bucket)
keys = bucket.list(prefix='%s/' % self.team_id)
for key in keys:
fp = os.path.join(out_dir, '/'.join(key.name.split('/')[1:]))
fp_dir = os.path.dirname(fp)
if os.path.exists(fp):
os.remove(fp)
elif not os.path.exists(fp_dir):
os.makedirs(fp_dir)
key.get_contents_to_filename(fp)
def _make_name(self):
return '%s-%s' % (self.team_id,
strftime('%m-%d-%Y %H:%M:%s', localtime()))
def _make_step(self, mapper, reducer, input, output, nm=1, nr=1):
job_name = self._make_name()
team_s3 = self._get_s3_url()
bucket = self.s3_conn.get_bucket(self.s3_bucket)
keys = bucket.list(prefix='%s/%s' % (self.team_id, output))
bucket.delete_keys(map(lambda k: k.name, keys))
return \
StreamingStep(name=job_name,
step_args=
['-jobconf', 'mapred.map.tasks=%d' % nm,
'-jobconf', 'mapred.reduce.tasks=%d' % nr],
mapper=team_s3 + mapper,
reducer=team_s3 + reducer,
input=team_s3 + input,
output=team_s3 + output)
def _get_s3_url(self):
return 's3n://%s/%s/' % (self.s3_bucket, self.team_id)