Closed AlJohri closed 5 years ago
I believe this was fixed in dask-yarn 0.6.1, which is compatible with distributed 2.0 and newer.
On Tue, Jul 2, 2019 at 7:37 PM Al Johri notifications@github.com wrote:
I was unable to copy and paste the stacktrace but here's a screenshot:
[image: Screen Shot 2019-07-02 at 8 36 40 PM] https://user-images.githubusercontent.com/2790092/60555136-2d318f80-9d09-11e9-8c26-f3bc2bb21a83.png
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/dask/dask-yarn/issues/77?email_source=notifications&email_token=AAKAOISCR74P2V7VOLT55EDP5PYFPA5CNFSM4H5A3XF2YY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4G5AKN7Q, or mute the thread https://github.com/notifications/unsubscribe-auth/AAKAOIXP7E5SAXOCLT67SH3P5PYFPANCNFSM4H5A3XFQ .
@TomAugspurger That's the version I'm on- same issue.
from dask_yarn import YarnCluster
from dask.distributed import Client
# Create a cluster in local deploy mode, to have access to the dashboard
cluster = YarnCluster(deploy_mode='local', worker_vcores=1, worker_memory="256MiB")
# Connect to the cluster
client = Client(cluster)
client.get_versions()
{'scheduler': {'host': (('python', '3.7.3.final.0'),
('python-bits', 64),
('OS', 'Linux'),
('OS-release', '4.14.104-78.84.amzn1.x86_64'),
('machine', 'x86_64'),
('processor', 'x86_64'),
('byteorder', 'little'),
('LC_ALL', 'None'),
('LANG', 'en_US.UTF-8'),
('LOCALE', 'en_US.UTF-8')),
'packages': {'required': (('dask', '2.0.0'),
('distributed', '2.0.1'),
('msgpack', '0.6.1'),
('cloudpickle', '1.2.1'),
('tornado', '6.0.3'),
('toolz', '0.9.0')),
'optional': (('numpy', '1.16.4'),
('pandas', '0.24.2'),
('bokeh', '1.2.0'),
('lz4', '2.1.10'),
('dask_ml', '1.0.0'),
('blosc', None))}},
'workers': {},
'client': {'host': [('python', '3.7.3.final.0'),
('python-bits', 64),
('OS', 'Linux'),
('OS-release', '4.14.104-78.84.amzn1.x86_64'),
('machine', 'x86_64'),
('processor', 'x86_64'),
('byteorder', 'little'),
('LC_ALL', 'None'),
('LANG', 'en_US.UTF-8'),
('LOCALE', 'en_US.UTF-8')],
'packages': {'required': [('dask', '2.0.0'),
('distributed', '2.0.1'),
('msgpack', '0.6.1'),
('cloudpickle', '1.2.1'),
('tornado', '6.0.3'),
('toolz', '0.9.0')],
'optional': [('numpy', '1.16.4'),
('pandas', '0.24.2'),
('bokeh', '1.2.0'),
('lz4', '2.1.10'),
('dask_ml', '1.0.0'),
('blosc', None)]}}}
cluster.scale(1)
tornado.application - ERROR - Exception in callback <function YarnCluster._widget.<locals>.update at 0x7f6fc8c92950>
Traceback (most recent call last):
File "/opt/python3/lib/python3.7/site-packages/tornado/ioloop.py", line 907, in _run
return self.callback()
File "/opt/python3/lib/python3.7/site-packages/dask_yarn/core.py", line 648, in update
status.value = self._widget_status()
File "/opt/python3/lib/python3.7/site-packages/dask_yarn/core.py", line 585, in _widget_status
cores = sum(w['ncores'] for w in workers.values())
File "/opt/python3/lib/python3.7/site-packages/dask_yarn/core.py", line 585, in <genexpr>
cores = sum(w['ncores'] for w in workers.values())
KeyError: 'ncores'
tornado.application - ERROR - Exception in callback <function YarnCluster._widget.<locals>.update at 0x7f6fc8c92950>
Traceback (most recent call last):
File "/opt/python3/lib/python3.7/site-packages/tornado/ioloop.py", line 907, in _run
return self.callback()
File "/opt/python3/lib/python3.7/site-packages/dask_yarn/core.py", line 648, in update
status.value = self._widget_status()
File "/opt/python3/lib/python3.7/site-packages/dask_yarn/core.py", line 585, in _widget_status
cores = sum(w['ncores'] for w in workers.values())
File "/opt/python3/lib/python3.7/site-packages/dask_yarn/core.py", line 585, in <genexpr>
cores = sum(w['ncores'] for w in workers.values())
KeyError: 'ncores'
And if I'm quick enough:
client.scheduler_info()['workers']
{'tcp://10.73.56.214:35797': {'type': 'Worker',
'id': 'tcp://10.73.56.214:35797',
'host': '10.73.56.214',
'resources': {},
'local_directory': '/mnt/yarn/usercache/hadoop/appcache/application_1562112156023_0010/container_1562112156023_0010_01_000004/dask-worker-space/worker-8jdl0grw',
'name': 'tcp://10.73.56.214:35797',
'nthreads': 1,
'memory_limit': 268435456,
'last_seen': 1562122681.500993,
'services': {},
'metrics': {'cpu': 2.0,
'memory': 40427520,
'time': 1562122680.9977098,
'read_bytes': 5693.9747349663585,
'write_bytes': 6715.667924125264,
'num_fds': 22,
'executing': 0,
'in_memory': 0,
'ready': 0,
'in_flight': 0,
'bandwidth': 100000000},
'nanny': 'tcp://10.73.56.214:39437'}}
cat /opt/python3/lib/python3.7/site-packages/dask_yarn/_version.py | grep '"version"'
"version": "0.6.1"
cat /opt/python3/lib/python3.7/site-packages/dask_yarn/core.py | grep ncores
cores = sum(w['ncores'] for w in workers.values())
Thanks for checking. I must have been thinking of a different library.
On Tue, Jul 2, 2019 at 10:00 PM Al Johri notifications@github.com wrote:
@TomAugspurger https://github.com/TomAugspurger That's the version I'm on- same issue.
from dask_yarn import YarnCluster from dask.distributed import Client
Create a cluster in local deploy mode, to have access to the dashboard
cluster = YarnCluster(deploy_mode='local', worker_vcores=1, worker_memory="256MiB")
Connect to the cluster
client = Client(cluster)
client.get_versions()
{'scheduler': {'host': (('python', '3.7.3.final.0'), ('python-bits', 64), ('OS', 'Linux'), ('OS-release', '4.14.104-78.84.amzn1.x86_64'), ('machine', 'x86_64'), ('processor', 'x86_64'), ('byteorder', 'little'), ('LC_ALL', 'None'), ('LANG', 'en_US.UTF-8'), ('LOCALE', 'en_US.UTF-8')), 'packages': {'required': (('dask', '2.0.0'), ('distributed', '2.0.1'), ('msgpack', '0.6.1'), ('cloudpickle', '1.2.1'), ('tornado', '6.0.3'), ('toolz', '0.9.0')), 'optional': (('numpy', '1.16.4'), ('pandas', '0.24.2'), ('bokeh', '1.2.0'), ('lz4', '2.1.10'), ('dask_ml', '1.0.0'), ('blosc', None))}}, 'workers': {}, 'client': {'host': [('python', '3.7.3.final.0'), ('python-bits', 64), ('OS', 'Linux'), ('OS-release', '4.14.104-78.84.amzn1.x86_64'), ('machine', 'x86_64'), ('processor', 'x86_64'), ('byteorder', 'little'), ('LC_ALL', 'None'), ('LANG', 'en_US.UTF-8'), ('LOCALE', 'en_US.UTF-8')], 'packages': {'required': [('dask', '2.0.0'), ('distributed', '2.0.1'), ('msgpack', '0.6.1'), ('cloudpickle', '1.2.1'), ('tornado', '6.0.3'), ('toolz', '0.9.0')], 'optional': [('numpy', '1.16.4'), ('pandas', '0.24.2'), ('bokeh', '1.2.0'), ('lz4', '2.1.10'), ('dask_ml', '1.0.0'), ('blosc', None)]}}}
cluster.scale(1)
tornado.application - ERROR - Exception in callback <function YarnCluster._widget.
.update at 0x7f6fc8c92950> Traceback (most recent call last): File "/opt/python3/lib/python3.7/site-packages/tornado/ioloop.py", line 907, in _run return self.callback() File "/opt/python3/lib/python3.7/site-packages/dask_yarn/core.py", line 648, in update status.value = self._widget_status() File "/opt/python3/lib/python3.7/site-packages/dask_yarn/core.py", line 585, in _widget_status cores = sum(w['ncores'] for w in workers.values()) File "/opt/python3/lib/python3.7/site-packages/dask_yarn/core.py", line 585, in cores = sum(w['ncores'] for w in workers.values()) KeyError: 'ncores' tornado.application - ERROR - Exception in callback <function YarnCluster._widget. .update at 0x7f6fc8c92950> Traceback (most recent call last): File "/opt/python3/lib/python3.7/site-packages/tornado/ioloop.py", line 907, in _run return self.callback() File "/opt/python3/lib/python3.7/site-packages/dask_yarn/core.py", line 648, in update status.value = self._widget_status() File "/opt/python3/lib/python3.7/site-packages/dask_yarn/core.py", line 585, in _widget_status cores = sum(w['ncores'] for w in workers.values()) File "/opt/python3/lib/python3.7/site-packages/dask_yarn/core.py", line 585, in cores = sum(w['ncores'] for w in workers.values()) KeyError: 'ncores' And if I'm quick enough:
client.scheduler_info()['workers']
{'tcp://10.73.56.214:35797': {'type': 'Worker', 'id': 'tcp://10.73.56.214:35797', 'host': '10.73.56.214', 'resources': {}, 'local_directory': '/mnt/yarn/usercache/hadoop/appcache/application_1562112156023_0010/container_1562112156023_0010_01_000004/dask-worker-space/worker-8jdl0grw', 'name': 'tcp://10.73.56.214:35797', 'nthreads': 1, 'memory_limit': 268435456, 'last_seen': 1562122681.500993, 'services': {}, 'metrics': {'cpu': 2.0, 'memory': 40427520, 'time': 1562122680.9977098, 'read_bytes': 5693.9747349663585, 'write_bytes': 6715.667924125264, 'num_fds': 22, 'executing': 0, 'in_memory': 0, 'ready': 0, 'in_flight': 0, 'bandwidth': 100000000}, 'nanny': 'tcp://10.73.56.214:39437'}}
cat /opt/python3/lib/python3.7/site-packages/dask_yarn/_version.py | grep '"version"'
"version": "0.6.1"
cat /opt/python3/lib/python3.7/site-packages/dask_yarn/core.py | grep ncores
cores = sum(w['ncores'] for w in workers.values())
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/dask/dask-yarn/issues/77?email_source=notifications&email_token=AAKAOIVMGMFRWWRE5SNER6LP5QI6VA5CNFSM4H5A3XF2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODZDDSWY#issuecomment-507918683, or mute the thread https://github.com/notifications/unsubscribe-auth/AAKAOIRNOJFRBCGUBXAJDDLP5QI6VANCNFSM4H5A3XFQ .
I was unable to copy and paste the stacktrace but here's a screenshot: