def _freeze_script(fns, freeze_dict, python_cmd):
for fn in fns:
try:
hadoopy._runner._check_script(fn, files=glob.glob(os.path.dirname(fn) + '/*.py'), python_cmd=python_cmd)
except ValueError:
logging.warn('prefreeze: Skipping script[%s] as it could not be executed' % fn)
continue
logging.info('prefreeze: Freezing script[%s]' % fn)
if fn in freeze_dict:
continue
hadoopy.freeze_script(fn)
freeze_dict.update(hadoopy._freeze.FREEZE_CACHE)
def throughput_test(launcher):
output_path = '_hadoopy_bench/%f' % time.time()
v = 'blah'
kv = (v, {'client_time': time.time(),
'value_len': len(v),
'count': 0})
num_files = 3
num_kvs = 10000000
hadoopy.writetb(output_path + '/input/0', (kv for x in xrange(num_kvs)))
for x in range(1, num_files):
hadoopy.cp(output_path + '/input/0', output_path + '/input/%d' % x)
hadoopy.freeze_script('time_job.py') # Factor out Pyinstaller time
st = time.time()
launcher(output_path + '/input', output_path + '/output', 'time_job.py')
print((num_kvs * num_files) / (time.time() - st))
hadoopy.rmr(output_path)
def _freeze_script(script_path):
import hadoopy
if script_path not in _FROZEN_PATHS:
_FROZEN_PATHS[script_path] = hadoopy.freeze_script(script_path)
return _FROZEN_PATHS[script_path]
