%matplotlib inline
import pandas as pd
import socket
host = socket.getfqdn()
from core import load, zoom, calc, save,plots,monitor
#reload funcs after updating ./core/*.py
import importlib
importlib.reload(load)
importlib.reload(zoom)
importlib.reload(calc)
importlib.reload(save)
importlib.reload(plots)
importlib.reload(monitor)
<module 'core.monitor' from '/ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/core/monitor.py'>
If you submit the job with job scheduler; below are list of enviroment variable one can pass
local : if True run dask local cluster, if not true, put number of workers setted in the 'local' if no 'local ' given, local will be setted automatically to 'True'
%env ychunk='2', #%env tchunk='2'
controls chunk. 'False' sets no modification from original netcdf file's chunk.
ychunk=10 will group the original netcdf file to 10 by 10
tchunk=1 will chunk the time coordinate one by one
%env file_exp=
'file_exp': Which 'experiment' name is it? this corresopnds to intake catalog name without path and .yaml
#%env year=
for Validation, this correspoinds to path/year/month 's year for monitoring, this corresponids to 'date' having means do all files in the monitoring directory setting it as 0[0-9] &1[0-9]& [2-3][0-9], the job can be separated in three lots. For DELTA experiment, year corresponds to really 'year'
%env month=
for monitoring this corresponds to file path path-XIOS.{month}/
For DELTA experiment, year corresponds to really 'month'
proceed saving? True or False , Default is setted as True
proceed plotting? True or False , Default is setted as True
proceed computation? or just load computed result? True or False , Default is setted as True
save output file used for plotting
using kerchunked file -> False, not using kerhcunk -> True
name of control file to be used for computation/plots/save/ We have number of M_xxx.csv
Monitor.sh calls M_MLD_2D
and AWTD.sh, Fluxnet.sh, Siconc.sh, IceClim.sh, FWC_SSH.sh, Integrals.sh , Sections.sh
M_AWTMD
M_Fluxnet
M_Ice_quantities
M_IceClim M_IceConce M_IceThick
M_FWC_2D M_FWC_integrals M_FWC_SSH M_SSH_anomaly
M_Mean_temp_velo M_Mooring
M_Sectionx M_Sectiony
%%time
# 'savefig': Do we save output in html? or not. keep it true.
savefig=True
client,cluster,control,catalog_url,month,year,daskreport,outputpath = load.set_control(host)
!mkdir -p $outputpath
!mkdir -p $daskreport
client
local True using host= irene5113.c-irene.mg1.tgcc.ccc.cea.fr starting dask cluster on local= True workers 16 10000000000 rome local cluster starting This code is running on irene5113.c-irene.mg1.tgcc.ccc.cea.fr using SEDNA_DELTA_MONITOR file experiment, read from ../lib/SEDNA_DELTA_MONITOR.yaml on year= 2012 on month= 03 outputpath= ../results/SEDNA_DELTA_MONITOR/ daskreport= ../results/dask/6419602irene5113.c-irene.mg1.tgcc.ccc.cea.fr_SEDNA_DELTA_MONITOR_03M_Ice_quantities/ CPU times: user 582 ms, sys: 154 ms, total: 736 ms Wall time: 23.5 s
Client-9e380ec1-13e4-11ed-90fb-080038b981cb
Connection method: Cluster object | Cluster type: distributed.LocalCluster |
Dashboard: http://127.0.0.1:8787/status |
8ded29c2
Dashboard: http://127.0.0.1:8787/status | Workers: 16 |
Total threads: 128 | Total memory: 251.06 GiB |
Status: running | Using processes: True |
Scheduler-96c758bf-8d14-442a-a8c5-96e21c679524
Comm: tcp://127.0.0.1:41899 | Workers: 16 |
Dashboard: http://127.0.0.1:8787/status | Total threads: 128 |
Started: Just now | Total memory: 251.06 GiB |
Comm: tcp://127.0.0.1:37634 | Total threads: 8 |
Dashboard: http://127.0.0.1:39554/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:38236 | |
Local directory: /tmp/dask-worker-space/worker-dz_xsqdh |
Comm: tcp://127.0.0.1:36549 | Total threads: 8 |
Dashboard: http://127.0.0.1:35118/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:45211 | |
Local directory: /tmp/dask-worker-space/worker-hq371ltw |
Comm: tcp://127.0.0.1:38824 | Total threads: 8 |
Dashboard: http://127.0.0.1:43750/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:42431 | |
Local directory: /tmp/dask-worker-space/worker-blz4z0wm |
Comm: tcp://127.0.0.1:40853 | Total threads: 8 |
Dashboard: http://127.0.0.1:42112/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:33247 | |
Local directory: /tmp/dask-worker-space/worker-tqvm8o54 |
Comm: tcp://127.0.0.1:40593 | Total threads: 8 |
Dashboard: http://127.0.0.1:46467/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:45196 | |
Local directory: /tmp/dask-worker-space/worker-ufohh8ee |
Comm: tcp://127.0.0.1:45983 | Total threads: 8 |
Dashboard: http://127.0.0.1:42970/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:33626 | |
Local directory: /tmp/dask-worker-space/worker-ne22j7w7 |
Comm: tcp://127.0.0.1:35125 | Total threads: 8 |
Dashboard: http://127.0.0.1:45594/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:43807 | |
Local directory: /tmp/dask-worker-space/worker-cvyrg2bn |
Comm: tcp://127.0.0.1:43335 | Total threads: 8 |
Dashboard: http://127.0.0.1:34679/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:41607 | |
Local directory: /tmp/dask-worker-space/worker-cveg23yc |
Comm: tcp://127.0.0.1:41550 | Total threads: 8 |
Dashboard: http://127.0.0.1:32889/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:43053 | |
Local directory: /tmp/dask-worker-space/worker-sk_6vj7t |
Comm: tcp://127.0.0.1:46212 | Total threads: 8 |
Dashboard: http://127.0.0.1:33868/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:38582 | |
Local directory: /tmp/dask-worker-space/worker-g2g0u4gw |
Comm: tcp://127.0.0.1:33129 | Total threads: 8 |
Dashboard: http://127.0.0.1:35517/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:44099 | |
Local directory: /tmp/dask-worker-space/worker-6fh4weu_ |
Comm: tcp://127.0.0.1:38996 | Total threads: 8 |
Dashboard: http://127.0.0.1:42218/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:41961 | |
Local directory: /tmp/dask-worker-space/worker-zpp4f1r6 |
Comm: tcp://127.0.0.1:33012 | Total threads: 8 |
Dashboard: http://127.0.0.1:41728/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:37669 | |
Local directory: /tmp/dask-worker-space/worker-je2tgnut |
Comm: tcp://127.0.0.1:40740 | Total threads: 8 |
Dashboard: http://127.0.0.1:33020/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:36672 | |
Local directory: /tmp/dask-worker-space/worker-itc7z3c_ |
Comm: tcp://127.0.0.1:42226 | Total threads: 8 |
Dashboard: http://127.0.0.1:36453/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:43645 | |
Local directory: /tmp/dask-worker-space/worker-qerbpoxf |
Comm: tcp://127.0.0.1:45412 | Total threads: 8 |
Dashboard: http://127.0.0.1:42113/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:37922 | |
Local directory: /tmp/dask-worker-space/worker-vxi40qp4 |
df=load.controlfile(control)
#Take out 'later' tagged computations
#df=df[~df['Value'].str.contains('later')]
df
Value | Inputs | Equation | Zone | Plot | Colourmap | MinMax | Unit | Oldname | Unnamed: 10 | |
---|---|---|---|---|---|---|---|---|---|---|
Ice_quantities | param.e1te2t,icemod.sivelo,icemod.sivolu,icemo... | calc.Ice_quant(data) | ALL | Ice_intquant | None | (0,20) | cm s^(-1) | I-2 |
Each computation consists of
%%time
import os
calcswitch=os.environ.get('calc', 'True')
lazy=os.environ.get('lazy','False' )
loaddata=((df.Inputs != '').any())
print('calcswitch=',calcswitch,'df.Inputs != nothing',loaddata, 'lazy=',lazy)
data = load.datas(catalog_url,df.Inputs,month,year,daskreport,lazy=lazy) if ((calcswitch=='True' )*loaddata) else 0
data
calcswitch= True df.Inputs != nothing True lazy= True ../lib/SEDNA_DELTA_MONITOR.yaml using param_xios reading ../lib/SEDNA_DELTA_MONITOR.yaml using param_xios reading <bound method DataSourceBase.describe of sources: param_xios: args: combine: nested concat_dim: y urlpath: /ccc/work/cont003/gen7420/odakatin/CONFIGS/SEDNA/SEDNA-I/SEDNA_Domain_cfg_Tgt_20210423_tsh10m_L1/param_f32/x_*.nc xarray_kwargs: compat: override coords: minimal data_vars: minimal parallel: true description: SEDNA NEMO parameters from MPI output nav_lon lat fails driver: intake_xarray.netcdf.NetCDFSource metadata: catalog_dir: /ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/../lib/ > {'name': 'param_xios', 'container': 'xarray', 'plugin': ['netcdf'], 'driver': ['netcdf'], 'description': 'SEDNA NEMO parameters from MPI output nav_lon lat fails', 'direct_access': 'forbid', 'user_parameters': [{'name': 'path', 'description': 'file coordinate', 'type': 'str', 'default': '/ccc/work/cont003/gen7420/odakatin/CONFIGS/SEDNA/MESH/SEDNA_mesh_mask_Tgt_20210423_tsh10m_L1/param'}], 'metadata': {}, 'args': {'urlpath': '/ccc/work/cont003/gen7420/odakatin/CONFIGS/SEDNA/SEDNA-I/SEDNA_Domain_cfg_Tgt_20210423_tsh10m_L1/param_f32/x_*.nc', 'combine': 'nested', 'concat_dim': 'y'}} 0 read icemod ['siconc', 'sivelo', 'sivolu'] lazy= True using load_data_xios reading icemod using load_data_xios reading {'name': 'data_xios', 'container': 'xarray', 'plugin': ['netcdf'], 'driver': ['netcdf'], 'description': 'SEDNA NEMO outputs from different xios server', 'direct_access': 'forbid', 'user_parameters': [{'name': 'path', 'description': 'name of config', 'type': 'str', 'default': '/ccc/scratch/cont003/gen7420/talandel/SEDNA/SEDNA-DELTA-S/SPLIT/1d'}, {'name': 'fileexp', 'description': 'name of config', 'type': 'str', 'default': 'SEDNA-DELTA'}, {'name': 'month', 'description': 'running number 2 digit', 'type': 'str', 'default': '02'}, {'name': 'freq', 'description': '1d or 1m', 'type': 'str', 'default': '1d'}, {'name': 'year', 'description': 'last digits of yearmonthdate.', 'type': 'str', 'default': '2012'}, {'name': 'file', 'description': 'file name', 'type': 'str', 'default': 'icemod'}, {'name': 'eio', 'description': 'xios mpi number', 'type': 'str', 'default': '0[0-5][0-9][0-9]'}], 'metadata': {}, 'args': {'urlpath': '{{path}}/{{year}}/{{month}}/*{{file}}_*_{{eio}}.nc', 'combine': 'nested', 'concat_dim': 'time_counter,x,y'}} took 127.13639807701111 seconds 0 merging icemod ['siconc', 'sivelo', 'sivolu'] param nav_lon will be included in data param e1te2t will be included in data param mask2d will be included in data param nav_lat will be included in data CPU times: user 1min 25s, sys: 5.87 s, total: 1min 30s Wall time: 2min 31s
<xarray.Dataset> Dimensions: (t: 31, y: 6540, x: 6560) Coordinates: * t (t) object 2012-03-01 12:00:00 ... 2012-03-31 12:00:00 * y (y) int64 1 2 3 4 5 6 7 ... 6535 6536 6537 6538 6539 6540 * x (x) int64 1 2 3 4 5 6 7 ... 6555 6556 6557 6558 6559 6560 nav_lat (y, x) float32 dask.array<chunksize=(13, 6560), meta=np.ndarray> nav_lon (y, x) float32 dask.array<chunksize=(13, 6560), meta=np.ndarray> time_centered (t) object dask.array<chunksize=(31,), meta=np.ndarray> e1te2t (y, x) float64 dask.array<chunksize=(13, 6560), meta=np.ndarray> mask2d (y, x) bool dask.array<chunksize=(13, 6560), meta=np.ndarray> Data variables: siconc (t, y, x) float32 dask.array<chunksize=(31, 6540, 6560), meta=np.ndarray> sivelo (t, y, x) float32 dask.array<chunksize=(31, 6540, 6560), meta=np.ndarray> sivolu (t, y, x) float32 dask.array<chunksize=(31, 6540, 6560), meta=np.ndarray> Attributes: (12/26) name: /ccc/scratch/cont003/ra5563/talandel/ONGOING-RUN... description: ice variables title: ice variables Conventions: CF-1.6 timeStamp: 2022-Jan-19 12:40:23 GMT uuid: 7def6cc3-6d0d-4c8a-814c-8b4c39428c94 ... ... start_date: 20090101 output_frequency: 1d CONFIG: SEDNA CASE: DELTA history: Thu Jan 20 11:43:59 2022: ncks -4 -L 1 SEDNA-DEL... NCO: netCDF Operators version 4.9.1 (Homepage = http:...
%%time
monitor.auto(df,data,savefig,daskreport,outputpath,file_exp='SEDNA'
)
#calc= True #save= True #plot= False Value='Ice_quantities' Zone='ALL' Plot='Ice_intquant' cmap='None' clabel='cm s^(-1)' clim= (0, 20) outputpath='../results/SEDNA_DELTA_MONITOR/' nc_outputpath='../nc_results/SEDNA_DELTA_MONITOR/' filename='SEDNA_Ice_intquant_ALL_Ice_quantities' data=monitor.optimize_dataset(data) #3 Start computing data= calc.Ice_quant(data) monitor.optimize_dataset(data) add optimise here once otimise can recognise
<xarray.Dataset> Dimensions: (t: 31) Coordinates: * t (t) object 2012-03-01 12:00:00 ... 2012-03-31 12:00:00 time_centered (t) object dask.array<chunksize=(31,), meta=np.ndarray> Data variables: Ice volume (t) float64 dask.array<chunksize=(31,), meta=np.ndarray> Ice area (t) float64 dask.array<chunksize=(31,), meta=np.ndarray> Ice extent (t) float64 dask.array<chunksize=(31,), meta=np.ndarray> Ice drift (t) float64 dask.array<chunksize=(31,), meta=np.ndarray>
#4 Saving SEDNA_Ice_intquant_ALL_Ice_quantities data=save.datas(data,plot=Plot,path=nc_outputpath,filename=filename) start saving data saving data in a csv file ../nc_results/SEDNA_DELTA_MONITOR/SEDNA_Ice_intquant_ALL_Ice_quantities2012-03-01_2012-03-31.nc
2022-08-04 13:03:33,729 - distributed.worker_memory - WARNING - Worker tcp://127.0.0.1:33012 (pid=135504) exceeded 99% memory budget. Restarting... 2022-08-04 13:03:34,493 - distributed.nanny - WARNING - Restarting worker 2022-08-04 13:04:04,028 - distributed.worker_memory - WARNING - Worker tcp://127.0.0.1:40740 (pid=135530) exceeded 99% memory budget. Restarting... 2022-08-04 13:04:04,606 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:40740 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46926 remote=tcp://127.0.0.1:40740>: Stream is closed 2022-08-04 13:04:04,618 - distributed.worker - ERROR - failed during get data with tcp://127.0.0.1:46212 -> tcp://127.0.0.1:40740 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/tornado/iostream.py", line 867, in _read_to_buffer bytes_read = self.read_from_fd(buf) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/tornado/iostream.py", line 1140, in read_from_fd return self.socket.recv_into(buf, len(buf)) ConnectionResetError: [Errno 104] Connection reset by peer The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1692, in get_data response = await comm.read(deserializers=serializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 142, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc.__class__.__name__}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) local=tcp://127.0.0.1:46212 remote=tcp://127.0.0.1:41756>: ConnectionResetError: [Errno 104] Connection reset by peer 2022-08-04 13:04:04,615 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:40740 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46748 remote=tcp://127.0.0.1:40740>: Stream is closed 2022-08-04 13:04:04,616 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:40740 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46774 remote=tcp://127.0.0.1:40740>: Stream is closed 2022-08-04 13:04:04,623 - distributed.nanny - WARNING - Restarting worker 2022-08-04 13:04:04,616 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:40740 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46698 remote=tcp://127.0.0.1:40740>: Stream is closed 2022-08-04 13:04:04,618 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:40740 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46804 remote=tcp://127.0.0.1:40740>: Stream is closed 2022-08-04 13:04:04,618 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:40740 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46808 remote=tcp://127.0.0.1:40740>: Stream is closed 2022-08-04 13:04:04,618 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:40740 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46806 remote=tcp://127.0.0.1:40740>: Stream is closed 2022-08-04 13:04:04,618 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:40740 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46802 remote=tcp://127.0.0.1:40740>: Stream is closed 2022-08-04 13:04:04,618 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:40740 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46811 remote=tcp://127.0.0.1:40740>: Stream is closed 2022-08-04 13:04:04,618 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:40740 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46798 remote=tcp://127.0.0.1:40740>: Stream is closed 2022-08-04 13:04:04,618 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:40740 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46796 remote=tcp://127.0.0.1:40740>: Stream is closed 2022-08-04 13:04:04,619 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:40740 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46816 remote=tcp://127.0.0.1:40740>: Stream is closed 2022-08-04 13:04:04,618 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:40740 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46814 remote=tcp://127.0.0.1:40740>: Stream is closed 2022-08-04 13:04:04,618 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:40740 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46800 remote=tcp://127.0.0.1:40740>: Stream is closed 2022-08-04 13:04:04,618 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:40740 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46810 remote=tcp://127.0.0.1:40740>: Stream is closed 2022-08-04 13:04:14,529 - distributed.worker_memory - WARNING - Worker tcp://127.0.0.1:45983 (pid=135509) exceeded 99% memory budget. Restarting... 2022-08-04 13:04:15,110 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45983 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:50052 remote=tcp://127.0.0.1:45983>: Stream is closed 2022-08-04 13:04:15,119 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45983 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:50158 remote=tcp://127.0.0.1:45983>: Stream is closed 2022-08-04 13:04:15,119 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45983 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:50114 remote=tcp://127.0.0.1:45983>: Stream is closed 2022-08-04 13:04:15,122 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45983 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:50216 remote=tcp://127.0.0.1:45983>: Stream is closed 2022-08-04 13:04:15,122 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45983 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:49990 remote=tcp://127.0.0.1:45983>: Stream is closed 2022-08-04 13:04:15,122 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45983 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:50270 remote=tcp://127.0.0.1:45983>: Stream is closed 2022-08-04 13:04:15,122 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45983 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:50258 remote=tcp://127.0.0.1:45983>: Stream is closed 2022-08-04 13:04:15,122 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45983 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:50268 remote=tcp://127.0.0.1:45983>: Stream is closed 2022-08-04 13:04:15,122 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45983 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:50262 remote=tcp://127.0.0.1:45983>: Stream is closed 2022-08-04 13:04:15,122 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45983 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:50272 remote=tcp://127.0.0.1:45983>: Stream is closed 2022-08-04 13:04:15,122 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45983 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:50266 remote=tcp://127.0.0.1:45983>: Stream is closed 2022-08-04 13:04:15,122 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45983 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:50264 remote=tcp://127.0.0.1:45983>: Stream is closed 2022-08-04 13:04:15,122 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45983 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:50260 remote=tcp://127.0.0.1:45983>: Stream is closed 2022-08-04 13:04:15,122 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45983 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:50254 remote=tcp://127.0.0.1:45983>: Stream is closed 2022-08-04 13:04:15,127 - distributed.nanny - WARNING - Restarting worker 2022-08-04 13:04:15,122 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45983 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:50256 remote=tcp://127.0.0.1:45983>: Stream is closed 2022-08-04 13:04:28,634 - distributed.worker_memory - WARNING - Worker tcp://127.0.0.1:36877 (pid=136307) exceeded 99% memory budget. Restarting... 2022-08-04 13:04:29,352 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36877 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:47588 remote=tcp://127.0.0.1:36877>: Stream is closed 2022-08-04 13:04:29,358 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36877 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:47652 remote=tcp://127.0.0.1:36877>: Stream is closed 2022-08-04 13:04:29,358 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36877 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:47650 remote=tcp://127.0.0.1:36877>: Stream is closed 2022-08-04 13:04:29,358 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36877 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:47662 remote=tcp://127.0.0.1:36877>: Stream is closed 2022-08-04 13:04:29,358 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36877 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:47654 remote=tcp://127.0.0.1:36877>: Stream is closed 2022-08-04 13:04:29,358 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36877 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:47646 remote=tcp://127.0.0.1:36877>: Stream is closed 2022-08-04 13:04:29,358 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36877 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:47660 remote=tcp://127.0.0.1:36877>: Stream is closed 2022-08-04 13:04:29,358 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36877 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:47638 remote=tcp://127.0.0.1:36877>: Stream is closed 2022-08-04 13:04:29,358 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36877 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:47658 remote=tcp://127.0.0.1:36877>: Stream is closed 2022-08-04 13:04:29,358 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36877 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:47656 remote=tcp://127.0.0.1:36877>: Stream is closed 2022-08-04 13:04:29,358 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36877 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:47648 remote=tcp://127.0.0.1:36877>: Stream is closed 2022-08-04 13:04:29,360 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36877 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:47644 remote=tcp://127.0.0.1:36877>: Stream is closed 2022-08-04 13:04:29,363 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36877 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:47636 remote=tcp://127.0.0.1:36877>: Stream is closed 2022-08-04 13:04:29,497 - distributed.nanny - WARNING - Restarting worker 2022-08-04 13:04:31,242 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36877 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:47642 remote=tcp://127.0.0.1:36877>: Stream is closed 2022-08-04 13:04:31,242 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36877 Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 233, in read n = await stream.read_into(chunk) tornado.iostream.StreamClosedError: Stream is closed The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 1983, in gather_dep response = await get_data_from_worker( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2725, in get_data_from_worker return await retry_operation(_get_data, operation="get_data_from_worker") File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 383, in retry_operation return await retry( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils_comm.py", line 368, in retry return await coro() File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/worker.py", line 2705, in _get_data response = await send_recv( File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 918, in send_recv response = await comm.read(deserializers=deserializers) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 239, in read convert_stream_closed_error(self, e) File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 144, in convert_stream_closed_error raise CommClosedError(f"in {obj}: {exc}") from exc distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:47640 remote=tcp://127.0.0.1:36877>: Stream is closed 2022-08-04 13:04:33,228 - distributed.worker_memory - WARNING - Worker tcp://127.0.0.1:34630 (pid=136365) exceeded 99% memory budget. Restarting... 2022-08-04 13:04:34,021 - distributed.nanny - WARNING - Restarting worker 2022-08-04 13:04:36,528 - distributed.worker_memory - WARNING - Worker tcp://127.0.0.1:41550 (pid=135491) exceeded 99% memory budget. Restarting... 2022-08-04 13:04:37,282 - distributed.nanny - WARNING - Restarting worker 2022-08-04 13:04:40,529 - distributed.worker_memory - WARNING - Worker tcp://127.0.0.1:42381 (pid=136430) exceeded 99% memory budget. Restarting... 2022-08-04 13:04:41,290 - distributed.nanny - WARNING - Restarting worker 2022-08-04 13:04:44,929 - distributed.worker_memory - WARNING - Worker tcp://127.0.0.1:45611 (pid=136399) exceeded 99% memory budget. Restarting... 2022-08-04 13:04:45,718 - distributed.nanny - WARNING - Restarting worker 2022-08-04 13:04:48,928 - distributed.worker_memory - WARNING - Worker tcp://127.0.0.1:40547 (pid=136493) exceeded 99% memory budget. Restarting... 2022-08-04 13:04:49,725 - distributed.nanny - WARNING - Restarting worker 2022-08-04 13:04:55,133 - distributed.worker_memory - WARNING - Worker tcp://127.0.0.1:40593 (pid=135494) exceeded 99% memory budget. Restarting... 2022-08-04 13:04:55,804 - distributed.nanny - WARNING - Restarting worker
--------------------------------------------------------------------------- KilledWorker Traceback (most recent call last) File <timed eval>:1, in <module> File /ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/core/monitor.py:89, in auto(df, val, savefig, daskreport, outputpath, file_exp) 87 print('data=save.datas(data,plot=Plot,path=nc_outputpath,filename=filename)' ) 88 with performance_report(filename=daskreport+"_save_"+step.Value+".html"): ---> 89 save.datas(data,plot=Plot,path=nc_outputpath,filename=filename) 90 # 5. Plot 91 if plotswitch=='True': File /ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/core/save.py:16, in datas(data, plot, path, filename) 14 print('start saving data' ) 15 if 'int' in plot: ---> 16 savedfile=integral(data,path,filename) 17 print('save computed data at',savedfile,'completed') 18 elif 'Mooring' in plot: File /ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/core/save.py:87, in integral(data, path, filename) 85 print('saving data in a csv file',filesave) 86 #data[filename]=data ---> 87 data.to_netcdf(filesave,mode='w') 88 return filesave File /ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/xarray/core/dataset.py:1882, in Dataset.to_netcdf(self, path, mode, format, group, engine, encoding, unlimited_dims, compute, invalid_netcdf) 1879 encoding = {} 1880 from ..backends.api import to_netcdf -> 1882 return to_netcdf( # type: ignore # mypy cannot resolve the overloads:( 1883 self, 1884 path, 1885 mode=mode, 1886 format=format, 1887 group=group, 1888 engine=engine, 1889 encoding=encoding, 1890 unlimited_dims=unlimited_dims, 1891 compute=compute, 1892 multifile=False, 1893 invalid_netcdf=invalid_netcdf, 1894 ) File /ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/xarray/backends/api.py:1219, in to_netcdf(dataset, path_or_file, mode, format, group, engine, encoding, unlimited_dims, compute, multifile, invalid_netcdf) 1216 if multifile: 1217 return writer, store -> 1219 writes = writer.sync(compute=compute) 1221 if isinstance(target, BytesIO): 1222 store.sync() File /ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/xarray/backends/common.py:168, in ArrayWriter.sync(self, compute) 162 import dask.array as da 164 # TODO: consider wrapping targets with dask.delayed, if this makes 165 # for any discernible difference in perforance, e.g., 166 # targets = [dask.delayed(t) for t in self.targets] --> 168 delayed_store = da.store( 169 self.sources, 170 self.targets, 171 lock=self.lock, 172 compute=compute, 173 flush=True, 174 regions=self.regions, 175 ) 176 self.sources = [] 177 self.targets = [] File /ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/dask/array/core.py:1229, in store(***failed resolving arguments***) 1227 elif compute: 1228 store_dsk = HighLevelGraph(layers, dependencies) -> 1229 compute_as_if_collection(Array, store_dsk, map_keys, **kwargs) 1230 return None 1232 else: File /ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/dask/base.py:342, in compute_as_if_collection(cls, dsk, keys, scheduler, get, **kwargs) 340 schedule = get_scheduler(scheduler=scheduler, cls=cls, get=get) 341 dsk2 = optimization_function(cls)(dsk, keys, **kwargs) --> 342 return schedule(dsk2, keys, **kwargs) File /ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/client.py:3001, in Client.get(self, dsk, keys, workers, allow_other_workers, resources, sync, asynchronous, direct, retries, priority, fifo_timeout, actors, **kwargs) 2999 should_rejoin = False 3000 try: -> 3001 results = self.gather(packed, asynchronous=asynchronous, direct=direct) 3002 finally: 3003 for f in futures.values(): File /ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/client.py:2175, in Client.gather(self, futures, errors, direct, asynchronous) 2173 else: 2174 local_worker = None -> 2175 return self.sync( 2176 self._gather, 2177 futures, 2178 errors=errors, 2179 direct=direct, 2180 local_worker=local_worker, 2181 asynchronous=asynchronous, 2182 ) File /ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils.py:338, in SyncMethodMixin.sync(self, func, asynchronous, callback_timeout, *args, **kwargs) 336 return future 337 else: --> 338 return sync( 339 self.loop, func, *args, callback_timeout=callback_timeout, **kwargs 340 ) File /ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils.py:405, in sync(loop, func, callback_timeout, *args, **kwargs) 403 if error: 404 typ, exc, tb = error --> 405 raise exc.with_traceback(tb) 406 else: 407 return result File /ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/utils.py:378, in sync.<locals>.f() 376 future = asyncio.wait_for(future, callback_timeout) 377 future = asyncio.ensure_future(future) --> 378 result = yield future 379 except Exception: 380 error = sys.exc_info() File /ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/tornado/gen.py:762, in Runner.run(self) 759 exc_info = None 761 try: --> 762 value = future.result() 763 except Exception: 764 exc_info = sys.exc_info() File /ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/client.py:2038, in Client._gather(self, futures, errors, direct, local_worker) 2036 exc = CancelledError(key) 2037 else: -> 2038 raise exception.with_traceback(traceback) 2039 raise exc 2040 if errors == "skip": KilledWorker: ("('where-bf71e6c28c758f28d2125456376c8801', 0, 0, 0)", <WorkerState 'tcp://127.0.0.1:40547', name: 8, status: closed, memory: 0, processing: 2>)