%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'>
# 'month': = 'JOBID' almost month but not really,
# If you submit the job with job scheduler, above
#below are list of enviroment variable one can pass
#%env local='2"
# 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 control=FWC_SSH
# name of control file to be used for computation/plots/save/
#%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.
#%env month=
# for monitoring this corresponds to file path path-XIOS.{month}/
#
#%env save= proceed saving? True or False , Default is setted as True
#%env plot= proceed plotting? True or False , Default is setted as True
#%env calc= proceed computation? or just load computed result? True or False , Default is setted as True
#%env save=False
%%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= irene4045.c-irene.mg1.tgcc.ccc.cea.fr starting dask cluster on local= True workers 16 10000000000 False not local in tgcc rome local cluster starting This code is running on irene4045.c-irene.mg1.tgcc.ccc.cea.fr using SEDNA_ALPHA_MONITOR file experiment, read from ../lib/SEDNA_ALPHA_MONITOR.yaml on year= * on month= 23 outputpath= ../results/SEDNA_ALPHA_MONITOR/23/ daskreport= ../results/dask/2530524irene4045.c-irene.mg1.tgcc.ccc.cea.fr_SEDNA_ALPHA_MONITOR_23IceThickness/ CPU times: user 327 ms, sys: 236 ms, total: 563 ms Wall time: 9.06 s
Client
|
Cluster
|
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 | |
---|---|---|---|---|---|---|---|---|---|---|
IceThickness | icemod.sivolu | (data.sivolu.where(data.sivolu >0)).to_dataset... | ALL | maps | Spectral | (0,5) | m | M-4 |
Each computation consists of
%%time
import os
calcswitch=os.environ.get('calc', 'True')
loaddata=((df.Inputs != '').any())
print('calcswitch=',calcswitch,'df.Inputs != nothing',loaddata)
data = load.datas(catalog_url,df.Inputs,month,year,daskreport) if ((calcswitch=='True' )*loaddata) else 0
data
calcswitch= True df.Inputs != nothing True ../lib/SEDNA_ALPHA_MONITOR.yaml using param_xios reading ../lib/SEDNA_ALPHA_MONITOR.yaml using param_xios reading <bound method DataSourceBase.describe of sources: param_xios: args: combine: by_coords 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': 'by_coords', 'concat_dim': 'y'}} 0 read icemod ['sivolu'] using load_data_xios reading icemod using load_data_xios reading <bound method DataSourceBase.describe of sources: data_xios: args: combine: by_coords concat_dim: time_counter,x,y urlpath: /ccc/scratch/cont003/gen7420/talandel/ONGOING-RUNS/SEDNA-ALPHA-XIOS.23/SEDNA-ALPHA_1d_icemod_*_0[0-5][0-9][0-9].nc xarray_kwargs: compat: override coords: minimal data_vars: minimal drop_variables: !!set botpres: null deptht_bounds: null depthu_bounds: null iicestru: null iicestrv: null intstrx: null intstry: null mldkz5: null rhop_sig0: null siages: null sidive: null sisali: null sishea: null sistre: null sitemp: null snthic: null snvolu: null sometauy: null sozotaux: null time_centered_bounds: null time_counter_bounds: null utau_atmoce: null utau_iceoce: null uwspd10: null vtau_atmoce: null vtau_iceoce: null vwspd10: null parallel: true preprocess: !!python/name:core.load.prep '' description: SEDNA NEMO outputs from different xios server driver: intake_xarray.netcdf.NetCDFSource metadata: catalog_dir: /ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/../lib/ > took 401.5782685279846 seconds 0 merging icemod ['sivolu'] param nav_lat will be included in data param mask2d will be included in data param nav_lon will be included in data sum_num (13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12) start rechunking with (130, 122, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 48) end of y_rechunk CPU times: user 3min 36s, sys: 31.6 s, total: 4min 8s Wall time: 6min 55s
<xarray.Dataset> Dimensions: (t: 31, x: 6560, y: 6540) Coordinates: nav_lat (y, x) float32 dask.array<chunksize=(130, 6560), meta=np.ndarray> nav_lon (y, x) float32 dask.array<chunksize=(130, 6560), meta=np.ndarray> * t (t) object 2004-07-01 12:00:00 ... 2004-07-31 12:00:00 * y (y) int64 1 2 3 4 5 6 7 8 ... 6534 6535 6536 6537 6538 6539 6540 * x (x) int64 1 2 3 4 5 6 7 8 ... 6554 6555 6556 6557 6558 6559 6560 mask2d (y, x) bool dask.array<chunksize=(130, 6560), meta=np.ndarray> Data variables: sivolu (t, y, x) float32 dask.array<chunksize=(1, 130, 6560), meta=np.ndarray> Attributes: name: /ccc/scratch/cont003/gen7420/talandel/ONGOING-RU... description: ice variables title: ice variables Conventions: CF-1.6 timeStamp: 2021-Aug-04 15:32:27 GMT uuid: be0d49a1-d456-4e73-a33e-e553bcdcaa0a ibegin: 0 ni: 6560 jbegin: 0 nj: 13 DOMAIN_number_total: 544 DOMAIN_number: 0 DOMAIN_dimensions_ids: [2 3] DOMAIN_size_global: [6560 6540] DOMAIN_size_local: [6560 13] DOMAIN_position_first: [1 1] DOMAIN_position_last: [6560 13] DOMAIN_halo_size_start: [0 0] DOMAIN_halo_size_end: [0 0] DOMAIN_type: box start_date: 20030101 output_frequency: 1d CONFIG: SEDNA CASE: ALPHA
|
|
array([cftime.DatetimeNoLeap(2004, 7, 1, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 2, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 3, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 4, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 5, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 6, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 7, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 8, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 9, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 10, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 11, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 12, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 13, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 14, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 15, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 16, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 17, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 18, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 19, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 20, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 21, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 22, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 23, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 24, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 25, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 26, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 27, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 28, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 29, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 30, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 31, 12, 0, 0, 0)], dtype=object)
array([ 1, 2, 3, ..., 6538, 6539, 6540])
array([ 1, 2, 3, ..., 6558, 6559, 6560])
|
|
%%time
monitor.auto(df,data,savefig,daskreport,outputpath,file_exp='SEDNA'
)
#calc= True #save= True #plot= False Zone='ALL' Value='IceThickness' cmap='Spectral' clabel='m' clim= (0, 5) outputpath='../results/SEDNA_ALPHA_MONITOR/23/' nc_outputpath='../nc_results/SEDNA_ALPHA_MONITOR/23/' filename='SEDNA_maps_ALL_IceThickness' #3 Start computing dtaa= (data.sivolu.where(data.sivolu >0)).to_dataset(name='sivolu').chunk({ 't': -1 }).unify_chunks()
<xarray.Dataset> Dimensions: (t: 31, x: 6560, y: 6540) Coordinates: nav_lat (y, x) float32 dask.array<chunksize=(130, 6560), meta=np.ndarray> nav_lon (y, x) float32 dask.array<chunksize=(130, 6560), meta=np.ndarray> * t (t) object 2004-07-01 12:00:00 ... 2004-07-31 12:00:00 * y (y) int64 1 2 3 4 5 6 7 8 ... 6534 6535 6536 6537 6538 6539 6540 * x (x) int64 1 2 3 4 5 6 7 8 ... 6554 6555 6556 6557 6558 6559 6560 mask2d (y, x) bool dask.array<chunksize=(130, 6560), meta=np.ndarray> Data variables: sivolu (t, y, x) float32 dask.array<chunksize=(31, 130, 6560), meta=np.ndarray>
|
|
array([cftime.DatetimeNoLeap(2004, 7, 1, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 2, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 3, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 4, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 5, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 6, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 7, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 8, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 9, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 10, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 11, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 12, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 13, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 14, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 15, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 16, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 17, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 18, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 19, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 20, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 21, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 22, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 23, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 24, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 25, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 26, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 27, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 28, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 29, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 30, 12, 0, 0, 0), cftime.DatetimeNoLeap(2004, 7, 31, 12, 0, 0, 0)], dtype=object)
array([ 1, 2, 3, ..., 6538, 6539, 6540])
array([ 1, 2, 3, ..., 6558, 6559, 6560])
|
|
#4 Saving SEDNA_maps_ALL_IceThickness dtaa=save.datas(data,plot=Plot,path=nc_outputpath,filename=filename) start saving data saving data in a file t (31,) 0 slice(0, 31, None)
distributed.nanny - WARNING - Restarting worker distributed.nanny - WARNING - Restarting worker distributed.nanny - WARNING - Restarting worker distributed.nanny - WARNING - Restarting worker distributed.nanny - WARNING - Restarting worker distributed.nanny - WARNING - Restarting worker distributed.nanny - WARNING - Restarting worker distributed.core - ERROR - Exception while handling op heartbeat_worker Traceback (most recent call last): File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/core.py", line 496, in handle_comm result = handler(comm, **msg) File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in heartbeat_worker parent._tasks[key]: duration for key, duration in executing.items() File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in <dictcomp> parent._tasks[key]: duration for key, duration in executing.items() KeyError: "('create_eachfile-026fd1972dcb056178ad56f271fab5e1', 0, 0, 52)" distributed.core - ERROR - Exception while handling op heartbeat_worker Traceback (most recent call last): File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/core.py", line 496, in handle_comm result = handler(comm, **msg) File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in heartbeat_worker parent._tasks[key]: duration for key, duration in executing.items() File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in <dictcomp> parent._tasks[key]: duration for key, duration in executing.items() KeyError: "('open_dataset-concatenate-ba9268119c3d5d45ffa60d45413dfbaa', 21, 49, 0)" distributed.core - ERROR - Exception while handling op heartbeat_worker Traceback (most recent call last): File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/core.py", line 496, in handle_comm result = handler(comm, **msg) File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in heartbeat_worker parent._tasks[key]: duration for key, duration in executing.items() File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in <dictcomp> parent._tasks[key]: duration for key, duration in executing.items() KeyError: "('open_dataset-concatenate-ba9268119c3d5d45ffa60d45413dfbaa', 21, 41, 0)" distributed.core - ERROR - Exception while handling op heartbeat_worker Traceback (most recent call last): File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/core.py", line 496, in handle_comm result = handler(comm, **msg) File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in heartbeat_worker parent._tasks[key]: duration for key, duration in executing.items() File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in <dictcomp> parent._tasks[key]: duration for key, duration in executing.items() KeyError: "('open_dataset-concatenate-ba9268119c3d5d45ffa60d45413dfbaa', 21, 48, 0)" distributed.core - ERROR - Exception while handling op heartbeat_worker Traceback (most recent call last): File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/core.py", line 496, in handle_comm result = handler(comm, **msg) File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in heartbeat_worker parent._tasks[key]: duration for key, duration in executing.items() File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in <dictcomp> parent._tasks[key]: duration for key, duration in executing.items() KeyError: "('open_dataset-concatenate-ba9268119c3d5d45ffa60d45413dfbaa', 11, 155, 0)" distributed.core - ERROR - Exception while handling op heartbeat_worker Traceback (most recent call last): File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/core.py", line 496, in handle_comm result = handler(comm, **msg) File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in heartbeat_worker parent._tasks[key]: duration for key, duration in executing.items() File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in <dictcomp> parent._tasks[key]: duration for key, duration in executing.items() KeyError: "('open_dataset-concatenate-ba9268119c3d5d45ffa60d45413dfbaa', 0, 49, 0)" distributed.core - ERROR - Exception while handling op heartbeat_worker Traceback (most recent call last): File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/core.py", line 496, in handle_comm result = handler(comm, **msg) File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in heartbeat_worker parent._tasks[key]: duration for key, duration in executing.items() File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in <dictcomp> parent._tasks[key]: duration for key, duration in executing.items() KeyError: "('open_dataset-concatenate-ba9268119c3d5d45ffa60d45413dfbaa', 10, 157, 0)" distributed.nanny - WARNING - Restarting worker distributed.core - ERROR - Exception while handling op heartbeat_worker Traceback (most recent call last): File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/core.py", line 496, in handle_comm result = handler(comm, **msg) File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in heartbeat_worker parent._tasks[key]: duration for key, duration in executing.items() File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in <dictcomp> parent._tasks[key]: duration for key, duration in executing.items() KeyError: "('open_dataset-concatenate-ba9268119c3d5d45ffa60d45413dfbaa', 11, 294, 0)" distributed.core - ERROR - Exception while handling op heartbeat_worker Traceback (most recent call last): File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/core.py", line 496, in handle_comm result = handler(comm, **msg) File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in heartbeat_worker parent._tasks[key]: duration for key, duration in executing.items() File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in <dictcomp> parent._tasks[key]: duration for key, duration in executing.items() KeyError: "('open_dataset-concatenate-ba9268119c3d5d45ffa60d45413dfbaa', 21, 44, 0)" distributed.core - ERROR - Exception while handling op heartbeat_worker Traceback (most recent call last): File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/core.py", line 496, in handle_comm result = handler(comm, **msg) File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in heartbeat_worker parent._tasks[key]: duration for key, duration in executing.items() File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in <dictcomp> parent._tasks[key]: duration for key, duration in executing.items() KeyError: "('open_dataset-concatenate-ba9268119c3d5d45ffa60d45413dfbaa', 20, 151, 0)" distributed.core - ERROR - Exception while handling op heartbeat_worker Traceback (most recent call last): File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/core.py", line 496, in handle_comm result = handler(comm, **msg) File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in heartbeat_worker parent._tasks[key]: duration for key, duration in executing.items() File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in <dictcomp> parent._tasks[key]: duration for key, duration in executing.items() KeyError: "('open_dataset-concatenate-ba9268119c3d5d45ffa60d45413dfbaa', 20, 159, 0)" distributed.core - ERROR - Exception while handling op heartbeat_worker Traceback (most recent call last): File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/core.py", line 496, in handle_comm result = handler(comm, **msg) File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in heartbeat_worker parent._tasks[key]: duration for key, duration in executing.items() File "/ccc/cont003/home/ifremer/odakatin/monitor/lib/python3.7/site-packages/distributed/scheduler.py", line 3431, in <dictcomp> parent._tasks[key]: duration for key, duration in executing.items() KeyError: "('open_dataset-concatenate-ba9268119c3d5d45ffa60d45413dfbaa', 21, 45, 0)"
--------------------------------------------------------------------------- KilledWorker Traceback (most recent call last) <timed eval> in <module> /ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/core/monitor.py in auto(df, val, savefig, daskreport, outputpath, file_exp) 77 print('dtaa=save.datas(data,plot=Plot,path=nc_outputpath,filename=filename)' ) 78 with performance_report(filename=daskreport+"_save_"+step.Value+".html"): ---> 79 save.datas(data,plot=Plot,path=nc_outputpath,filename=filename) 80 # 5. Plot 81 if plotswitch=='True': /ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/core/save.py in datas(data, plot, path, filename) 22 twoD(data,path,filename,nested=False) 23 else : ---> 24 twoD(data,path,filename) 25 return None 26 /ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/core/save.py in twoD(data, path, filename, nested) 55 print('saving data in a file') 56 filesave=path+filename ---> 57 return to_mfnetcdf_map(data,prefix=filesave, nested=nested) 58 59 def twoD_onefile(data /ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/core/save.py in to_mfnetcdf_map(ds, prefix, nested) 226 ,template=template 227 ) --> 228 mapped.compute() 229 230 return mapped#.compute() ~/monitor/lib/python3.7/site-packages/xarray/core/dataset.py in compute(self, **kwargs) 904 """ 905 new = self.copy(deep=False) --> 906 return new.load(**kwargs) 907 908 def _persist_inplace(self, **kwargs) -> "Dataset": ~/monitor/lib/python3.7/site-packages/xarray/core/dataset.py in load(self, **kwargs) 739 740 # evaluate all the dask arrays simultaneously --> 741 evaluated_data = da.compute(*lazy_data.values(), **kwargs) 742 743 for k, data in zip(lazy_data, evaluated_data): ~/monitor/lib/python3.7/site-packages/dask/base.py in compute(*args, **kwargs) 561 postcomputes.append(x.__dask_postcompute__()) 562 --> 563 results = schedule(dsk, keys, **kwargs) 564 return repack([f(r, *a) for r, (f, a) in zip(results, postcomputes)]) 565 ~/monitor/lib/python3.7/site-packages/distributed/client.py in get(self, dsk, keys, workers, allow_other_workers, resources, sync, asynchronous, direct, retries, priority, fifo_timeout, actors, **kwargs) 2653 should_rejoin = False 2654 try: -> 2655 results = self.gather(packed, asynchronous=asynchronous, direct=direct) 2656 finally: 2657 for f in futures.values(): ~/monitor/lib/python3.7/site-packages/distributed/client.py in gather(self, futures, errors, direct, asynchronous) 1968 direct=direct, 1969 local_worker=local_worker, -> 1970 asynchronous=asynchronous, 1971 ) 1972 ~/monitor/lib/python3.7/site-packages/distributed/client.py in sync(self, func, asynchronous, callback_timeout, *args, **kwargs) 837 else: 838 return sync( --> 839 self.loop, func, *args, callback_timeout=callback_timeout, **kwargs 840 ) 841 ~/monitor/lib/python3.7/site-packages/distributed/utils.py in sync(loop, func, callback_timeout, *args, **kwargs) 338 if error[0]: 339 typ, exc, tb = error[0] --> 340 raise exc.with_traceback(tb) 341 else: 342 return result[0] ~/monitor/lib/python3.7/site-packages/distributed/utils.py in f() 322 if callback_timeout is not None: 323 future = asyncio.wait_for(future, callback_timeout) --> 324 result[0] = yield future 325 except Exception as exc: 326 error[0] = sys.exc_info() ~/monitor/lib/python3.7/site-packages/tornado/gen.py in run(self) 760 761 try: --> 762 value = future.result() 763 except Exception: 764 exc_info = sys.exc_info() ~/monitor/lib/python3.7/site-packages/distributed/client.py in _gather(self, futures, errors, direct, local_worker) 1827 exc = CancelledError(key) 1828 else: -> 1829 raise exception.with_traceback(traceback) 1830 raise exc 1831 if errors == "skip": KilledWorker: ("('create_eachfile-026fd1972dcb056178ad56f271fab5e1', 0, 0, 22)", <Worker 'tcp://127.0.0.1:46273', name: 4, memory: 0, processing: 6>)