%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/talandel/TOOLS/monitor-sedna/notebook/core/monitor.py'>

If you submit the job with job scheduler; 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 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'

• #%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

save output file used for plotting

• #%env lazy=False

using kerchunked file -> False, not using kerhcunk -> True

• #%env control=FWC_SSH

name of control file to be used for computation/plots/save/ We have number of M_xxx.csv

Monitor.sh automate all of above enviroment settings.

Monitor.sh calls M_MLD_2D

and AWTD.sh, Fluxnet.sh, Siconc.sh, IceClim.sh, FWC_SSH.sh, Integrals.sh , Sections.sh

• AWTD.sh

M_AWTMD

• Fluxnet.sh

M_Fluxnet

• Siconc.sh

M_Ice_quantities

• IceClim.sh

M_IceClim M_IceConce M_IceThick

• FWC_SSH.sh

M_FWC_2D M_FWC_integrals M_FWC_SSH M_SSH_anomaly

• Integrals.sh

M_Mean_temp_velo M_Mooring

• Sections.sh

M_Sectionx M_Sectiony

# For debugging this cell can help turn this cell to 'code' and modify variables manually. %env file_exp=SEDNA_DELTA_MONITOR %env year=2012 %env month=01 #0[1-2] %env ychunk=10 %env ychunk=False %env save=False %env plot=True %env calc=True # %env lazy=False #False %env control=M_Fluxnet #M_Sectiony ok with ychunk=False local=True lazy=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= irene4994.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  irene4994.c-irene.mg1.tgcc.ccc.cea.fr using  SEDNA_DELTA_MONITOR file experiment, read from  ../lib/SEDNA_DELTA_MONITOR.yaml  on year= 2015  on month= 04  outputpath= ../results/SEDNA_DELTA_MONITOR/ daskreport= ../results/dask/7449019irene4994.c-irene.mg1.tgcc.ccc.cea.fr_SEDNA_DELTA_MONITOR_04M_FWC_2D/
CPU times: user 465 ms, sys: 102 ms, total: 567 ms
Wall time: 16.5 s

Client

Client-9867beb5-6f42-11ed-a47c-080038b9396d

Connection method: Cluster object	Cluster type: distributed.LocalCluster
Dashboard: http://127.0.0.1:8787/status

Cluster Info

LocalCluster

4575c319

Dashboard: http://127.0.0.1:8787/status	Workers: 16
Total threads: 128	Total memory: 221.88 GiB
Status: running	Using processes: True

Scheduler Info

Scheduler

Scheduler-4d689cc3-83c8-4ce1-a8b2-01310ede348e

Comm: tcp://127.0.0.1:43977	Workers: 16
Dashboard: http://127.0.0.1:8787/status	Total threads: 128
Started: Just now	Total memory: 221.88 GiB

Workers

Worker: 0

Comm: tcp://127.0.0.1:36177	Total threads: 8
Dashboard: http://127.0.0.1:41857/status	Memory: 13.87 GiB
Nanny: tcp://127.0.0.1:38303
Local directory: /tmp/dask-worker-space/worker-b6xsw069

Worker: 1

Comm: tcp://127.0.0.1:36709	Total threads: 8
Dashboard: http://127.0.0.1:37893/status	Memory: 13.87 GiB
Nanny: tcp://127.0.0.1:37896
Local directory: /tmp/dask-worker-space/worker-refot3z9

Worker: 2

Comm: tcp://127.0.0.1:36997	Total threads: 8
Dashboard: http://127.0.0.1:38625/status	Memory: 13.87 GiB
Nanny: tcp://127.0.0.1:38732
Local directory: /tmp/dask-worker-space/worker-ayez0ge1

Worker: 3

Comm: tcp://127.0.0.1:39693	Total threads: 8
Dashboard: http://127.0.0.1:45355/status	Memory: 13.87 GiB
Nanny: tcp://127.0.0.1:39845
Local directory: /tmp/dask-worker-space/worker-4vqqxryu

Worker: 4

Comm: tcp://127.0.0.1:42475	Total threads: 8
Dashboard: http://127.0.0.1:36471/status	Memory: 13.87 GiB
Nanny: tcp://127.0.0.1:40994
Local directory: /tmp/dask-worker-space/worker-ufmt3zrn

Worker: 5

Comm: tcp://127.0.0.1:40849	Total threads: 8
Dashboard: http://127.0.0.1:36905/status	Memory: 13.87 GiB
Nanny: tcp://127.0.0.1:38143
Local directory: /tmp/dask-worker-space/worker-3e8ao356

Worker: 6

Comm: tcp://127.0.0.1:46584	Total threads: 8
Dashboard: http://127.0.0.1:32957/status	Memory: 13.87 GiB
Nanny: tcp://127.0.0.1:40831
Local directory: /tmp/dask-worker-space/worker-mxkzerfq

Worker: 7

Comm: tcp://127.0.0.1:39732	Total threads: 8
Dashboard: http://127.0.0.1:39716/status	Memory: 13.87 GiB
Nanny: tcp://127.0.0.1:44105
Local directory: /tmp/dask-worker-space/worker-bx8pib07

Worker: 8

Comm: tcp://127.0.0.1:36031	Total threads: 8
Dashboard: http://127.0.0.1:40975/status	Memory: 13.87 GiB
Nanny: tcp://127.0.0.1:45738
Local directory: /tmp/dask-worker-space/worker-25q4p6xh

Worker: 9

Comm: tcp://127.0.0.1:45595	Total threads: 8
Dashboard: http://127.0.0.1:42558/status	Memory: 13.87 GiB
Nanny: tcp://127.0.0.1:45563
Local directory: /tmp/dask-worker-space/worker-e49g0gyi

Worker: 10

Comm: tcp://127.0.0.1:45127	Total threads: 8
Dashboard: http://127.0.0.1:43353/status	Memory: 13.87 GiB
Nanny: tcp://127.0.0.1:39187
Local directory: /tmp/dask-worker-space/worker-aw8788z0

Worker: 11

Comm: tcp://127.0.0.1:34035	Total threads: 8
Dashboard: http://127.0.0.1:38016/status	Memory: 13.87 GiB
Nanny: tcp://127.0.0.1:42775
Local directory: /tmp/dask-worker-space/worker-pymcptzk

Worker: 12

Comm: tcp://127.0.0.1:44981	Total threads: 8
Dashboard: http://127.0.0.1:38502/status	Memory: 13.87 GiB
Nanny: tcp://127.0.0.1:43702
Local directory: /tmp/dask-worker-space/worker-ws512r40

Worker: 13

Comm: tcp://127.0.0.1:34252	Total threads: 8
Dashboard: http://127.0.0.1:40984/status	Memory: 13.87 GiB
Nanny: tcp://127.0.0.1:44294
Local directory: /tmp/dask-worker-space/worker-4spbj_9l

Worker: 14

Comm: tcp://127.0.0.1:34574	Total threads: 8
Dashboard: http://127.0.0.1:37651/status	Memory: 13.87 GiB
Nanny: tcp://127.0.0.1:34986
Local directory: /tmp/dask-worker-space/worker-bsqbtrgl

Worker: 15

Comm: tcp://127.0.0.1:33387	Total threads: 8
Dashboard: http://127.0.0.1:45445/status	Memory: 13.87 GiB
Nanny: tcp://127.0.0.1:39324
Local directory: /tmp/dask-worker-space/worker-ucy5dtuk

read plotting information from a csv file

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
	FWC_2D	gridS.vosaline,param.mask,param.e3t,param.e1te2t	calc.FWC2D_UFUNC(data)	BBFG	maps	Spectral_r	(0,24)	m	S-1

Computation starts here

Each computation consists of

1. Load NEMO data set
2. Zoom data set
3. Compute (or load computed data set)
4. Save
5. Plot
6. Close

%%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= False
../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/talandel/TOOLS/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 gridS ['vosaline']
lazy= False
using load_data_xios_kerchunk reading  gridS
using load_data_xios_kerchunk reading  <bound method DataSourceBase.describe of sources:
  data_xios_kerchunk:
    args:
      consolidated: false
      storage_options:
        fo: file:////ccc/cont003/home/ra5563/ra5563/catalogue/DELTA/201504/gridS_0[0-5][0-9][0-9].json
        target_protocol: file
      urlpath: reference://
    description: CREG025 NEMO outputs from different xios server in kerchunk format
    driver: intake_xarray.xzarr.ZarrSource
    metadata:
      catalog_dir: /ccc/work/cont003/gen7420/talandel/TOOLS/monitor-sedna/notebook/../lib/
>
      took 65.41075086593628 seconds
0 merging gridS ['vosaline']
param mask will be included in data
param mask2d will be included in data
param nav_lon will be included in data
param e3t will be included in data
param nav_lat will be included in data
param e1te2t will be included in data
ychunk= 10 calldatas_y_rechunk
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 22.2 s, sys: 4.16 s, total: 26.4 s
Wall time: 1min 24s

<xarray.Dataset>
Dimensions:   (t: 30, z: 150, y: 6540, x: 6560)
Coordinates:
  * t         (t) object 2015-04-01 12:00:00 ... 2015-04-30 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
  * z         (z) int64 1 2 3 4 5 6 7 8 9 ... 143 144 145 146 147 148 149 150
    mask      (z, y, x) bool dask.array<chunksize=(150, 130, 6560), meta=np.ndarray>
    mask2d    (y, x) bool dask.array<chunksize=(130, 6560), meta=np.ndarray>
    nav_lon   (y, x) float32 dask.array<chunksize=(130, 6560), meta=np.ndarray>
    e3t       (z, y, x) float64 dask.array<chunksize=(150, 130, 6560), meta=np.ndarray>
    nav_lat   (y, x) float32 dask.array<chunksize=(130, 6560), meta=np.ndarray>
    e1te2t    (y, x) float64 dask.array<chunksize=(130, 6560), meta=np.ndarray>
Data variables:
    vosaline  (t, z, y, x) float32 dask.array<chunksize=(1, 150, 130, 6560), meta=np.ndarray>
Attributes: (12/26)
    CASE:                    DELTA
    CONFIG:                  SEDNA
    Conventions:             CF-1.6
    DOMAIN_dimensions_ids:   [2, 3]
    DOMAIN_halo_size_end:    [0, 0]
    DOMAIN_halo_size_start:  [0, 0]
    ...                      ...
    nj:                      13
    output_frequency:        1d
    start_date:              20090101
    timeStamp:               2022-Aug-10 14:15:34 GMT
    title:                   ocean T grid variables
    uuid:                    ff447a34-04b8-481f-a3d2-a5361bb0def0

xarray.Dataset

• Dimensions:
  • t: 30
  • z: 150
  • y: 6540
  • x: 6560
• Coordinates: (10)
  • t
    (t)
    object
    2015-04-01 12:00:00 ... 2015-04-...

    axis :

    T

    bounds :

    time_counter_bounds

    long_name :

    Time axis

    standard_name :

    time

    time_origin :

    1900-01-01 00:00:00

    array([cftime.DatetimeNoLeap(2015, 4, 1, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 2, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 3, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 4, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 5, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 6, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 7, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 8, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 9, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 10, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 11, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 12, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 13, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 14, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 15, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 16, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 17, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 18, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 19, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 20, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 21, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 22, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 23, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 24, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 25, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 26, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 27, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 28, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 29, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 30, 12, 0, 0, 0, has_year_zero=True)],
          dtype=object)

  • y
    (y)
    int64
    1 2 3 4 5 ... 6537 6538 6539 6540

    array([   1,    2,    3, ..., 6538, 6539, 6540])

  • x
    (x)
    int64
    1 2 3 4 5 ... 6557 6558 6559 6560

    array([   1,    2,    3, ..., 6558, 6559, 6560])

  • z
    (z)
    int64
    1 2 3 4 5 6 ... 146 147 148 149 150

    array([  1,   2,   3,   4,   5,   6,   7,   8,   9,  10,  11,  12,  13,  14,
            15,  16,  17,  18,  19,  20,  21,  22,  23,  24,  25,  26,  27,  28,
            29,  30,  31,  32,  33,  34,  35,  36,  37,  38,  39,  40,  41,  42,
            43,  44,  45,  46,  47,  48,  49,  50,  51,  52,  53,  54,  55,  56,
            57,  58,  59,  60,  61,  62,  63,  64,  65,  66,  67,  68,  69,  70,
            71,  72,  73,  74,  75,  76,  77,  78,  79,  80,  81,  82,  83,  84,
            85,  86,  87,  88,  89,  90,  91,  92,  93,  94,  95,  96,  97,  98,
            99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112,
           113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126,
           127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140,
           141, 142, 143, 144, 145, 146, 147, 148, 149, 150])

  • mask
    (z, y, x)
    bool
    dask.array<chunksize=(150, 130, 6560), meta=np.ndarray>

    Array Chunk Bytes 5.99 GiB 121.99 MiB Shape (150, 6540, 6560) (150, 130, 6560) Count 1687 Tasks 55 Chunks Type bool numpy.ndarray

  • mask2d
    (y, x)
    bool
    dask.array<chunksize=(130, 6560), meta=np.ndarray>

    Array Chunk Bytes 40.91 MiB 832.81 kiB Shape (6540, 6560) (130, 6560) Count 1687 Tasks 55 Chunks Type bool numpy.ndarray

  • nav_lon
    (y, x)
    float32
    dask.array<chunksize=(130, 6560), meta=np.ndarray>

    Array Chunk Bytes 163.66 MiB 3.25 MiB Shape (6540, 6560) (130, 6560) Count 1687 Tasks 55 Chunks Type float32 numpy.ndarray

  • e3t
    (z, y, x)
    float64
    dask.array<chunksize=(150, 130, 6560), meta=np.ndarray>

    Array Chunk Bytes 47.95 GiB 0.95 GiB Shape (150, 6540, 6560) (150, 130, 6560) Count 1687 Tasks 55 Chunks Type float64 numpy.ndarray

  • nav_lat
    (y, x)
    float32
    dask.array<chunksize=(130, 6560), meta=np.ndarray>

    Array Chunk Bytes 163.66 MiB 3.25 MiB Shape (6540, 6560) (130, 6560) Count 1687 Tasks 55 Chunks Type float32 numpy.ndarray

  • e1te2t
    (y, x)
    float64
    dask.array<chunksize=(130, 6560), meta=np.ndarray>

    Array Chunk Bytes 327.32 MiB 6.51 MiB Shape (6540, 6560) (130, 6560) Count 1687 Tasks 55 Chunks Type float64 numpy.ndarray

• Data variables: (1)
  • vosaline
    (t, z, y, x)
    float32
    dask.array<chunksize=(1, 150, 130, 6560), meta=np.ndarray>

    cell_methods :

    time: mean (interval: 40 s)

    interval_operation :

    40 s

    interval_write :

    1 d

    long_name :

    salinity

    online_operation :

    average

    standard_name :

    sea_water_practical_salinity

    units :

    1e-3

    Array Chunk Bytes 719.21 GiB 487.98 MiB Shape (30, 150, 6540, 6560) (1, 150, 130, 6560) Count 34834 Tasks 1650 Chunks Type float32 numpy.ndarray

• Attributes: (26)

  CASE :

  DELTA

  CONFIG :

  SEDNA

  Conventions :

  CF-1.6

  DOMAIN_dimensions_ids :

  [2, 3]

  DOMAIN_halo_size_end :

  [0, 0]

  DOMAIN_halo_size_start :

  [0, 0]

  DOMAIN_number :

  0

  DOMAIN_number_total :

  544

  DOMAIN_position_first :

  [1, 1]

  DOMAIN_position_last :

  [6560, 13]

  DOMAIN_size_global :

  [6560, 6540]

  DOMAIN_size_local :

  [6560, 13]

  DOMAIN_type :

  box

  NCO :

  netCDF Operators version 4.9.1 (Homepage = http://nco.sf.net, Code = http://github.com/nco/nco)

  description :

  ocean T grid variables

  history :

  Thu Aug 11 12:22:01 2022: ncks -4 -L 1 SEDNA-DELTA_1d_gridS_201504-201504_NOZIP_0000.nc /ccc/scratch/cont003/gen7420/talandel/SEDNA/SEDNA-DELTA-S/SPLIT/1d/2015/04/SEDNA-DELTA_1d_gridS_201504-201504_0000.nc Thu Aug 11 12:21:47 2022: ncrcat -n 30,2,1 SEDNA-DELTA_1d_gridS_0000_01.nc SEDNA-DELTA_1d_gridS_201504-201504_NOZIP_0000.nc

  ibegin :

  0

  jbegin :

  0

  name :

  /ccc/scratch/cont003/ra5563/talandel/ONGOING-RUNS/SEDNA-DELTA-XIOS.86/SEDNA-DELTA_1d_gridS

  ni :

  6560

  nj :

  13

  output_frequency :

  1d

  start_date :

  20090101

  timeStamp :

  2022-Aug-10 14:15:34 GMT

  title :

  ocean T grid variables

  uuid :

  ff447a34-04b8-481f-a3d2-a5361bb0def0

%%time
monitor.auto(df,data,savefig,daskreport,outputpath,file_exp='SEDNA'
            )

#calc= True
#save= True
#plot= False
Value='FWC_2D'
Zone='BBFG'
Plot='maps'
cmap='Spectral_r'
clabel='m'
clim= (0, 24)
outputpath='../results/SEDNA_DELTA_MONITOR/'
nc_outputpath='../nc_results/SEDNA_DELTA_MONITOR/'
filename='SEDNA_maps_BBFG_FWC_2D'
data=monitor.optimize_dataset(data)
#2 Zooming Data
data= zoom.BBFG(data)
data=monitor.optimize_dataset(data)

<xarray.Dataset>
Dimensions:   (t: 30, z: 150, y: 5264, x: 6560)
Coordinates:
  * t         (t) object 2015-04-01 12:00:00 ... 2015-04-30 12:00:00
  * y         (y) int64 1277 1278 1279 1280 1281 ... 6536 6537 6538 6539 6540
  * x         (x) int64 1 2 3 4 5 6 7 8 ... 6554 6555 6556 6557 6558 6559 6560
  * z         (z) int64 1 2 3 4 5 6 7 8 9 ... 143 144 145 146 147 148 149 150
    mask      (z, y, x) bool dask.array<chunksize=(150, 56, 6560), meta=np.ndarray>
    mask2d    (y, x) bool dask.array<chunksize=(56, 6560), meta=np.ndarray>
    nav_lon   (y, x) float32 dask.array<chunksize=(56, 6560), meta=np.ndarray>
    e3t       (z, y, x) float64 dask.array<chunksize=(150, 56, 6560), meta=np.ndarray>
    nav_lat   (y, x) float32 dask.array<chunksize=(56, 6560), meta=np.ndarray>
    e1te2t    (y, x) float64 dask.array<chunksize=(56, 6560), meta=np.ndarray>
Data variables:
    vosaline  (t, z, y, x) float32 dask.array<chunksize=(1, 150, 56, 6560), meta=np.ndarray>
Attributes: (12/26)
    CASE:                    DELTA
    CONFIG:                  SEDNA
    Conventions:             CF-1.6
    DOMAIN_dimensions_ids:   [2, 3]
    DOMAIN_halo_size_end:    [0, 0]
    DOMAIN_halo_size_start:  [0, 0]
    ...                      ...
    nj:                      13
    output_frequency:        1d
    start_date:              20090101
    timeStamp:               2022-Aug-10 14:15:34 GMT
    title:                   ocean T grid variables
    uuid:                    ff447a34-04b8-481f-a3d2-a5361bb0def0

xarray.Dataset

• Dimensions:
  • t: 30
  • z: 150
  • y: 5264
  • x: 6560
• Coordinates: (10)
  • t
    (t)
    object
    2015-04-01 12:00:00 ... 2015-04-...

    axis :

    T

    bounds :

    time_counter_bounds

    long_name :

    Time axis

    standard_name :

    time

    time_origin :

    1900-01-01 00:00:00

    array([cftime.DatetimeNoLeap(2015, 4, 1, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 2, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 3, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 4, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 5, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 6, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 7, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 8, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 9, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 10, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 11, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 12, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 13, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 14, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 15, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 16, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 17, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 18, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 19, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 20, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 21, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 22, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 23, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 24, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 25, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 26, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 27, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 28, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 29, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 30, 12, 0, 0, 0, has_year_zero=True)],
          dtype=object)

  • y
    (y)
    int64
    1277 1278 1279 ... 6538 6539 6540

    array([1277, 1278, 1279, ..., 6538, 6539, 6540])

  • x
    (x)
    int64
    1 2 3 4 5 ... 6557 6558 6559 6560

    array([   1,    2,    3, ..., 6558, 6559, 6560])

  • z
    (z)
    int64
    1 2 3 4 5 6 ... 146 147 148 149 150

    array([  1,   2,   3,   4,   5,   6,   7,   8,   9,  10,  11,  12,  13,  14,
            15,  16,  17,  18,  19,  20,  21,  22,  23,  24,  25,  26,  27,  28,
            29,  30,  31,  32,  33,  34,  35,  36,  37,  38,  39,  40,  41,  42,
            43,  44,  45,  46,  47,  48,  49,  50,  51,  52,  53,  54,  55,  56,
            57,  58,  59,  60,  61,  62,  63,  64,  65,  66,  67,  68,  69,  70,
            71,  72,  73,  74,  75,  76,  77,  78,  79,  80,  81,  82,  83,  84,
            85,  86,  87,  88,  89,  90,  91,  92,  93,  94,  95,  96,  97,  98,
            99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112,
           113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126,
           127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140,
           141, 142, 143, 144, 145, 146, 147, 148, 149, 150])

  • mask
    (z, y, x)
    bool
    dask.array<chunksize=(150, 56, 6560), meta=np.ndarray>

    Array Chunk Bytes 4.82 GiB 112.61 MiB Shape (150, 5264, 6560) (150, 120, 6560) Count 1732 Tasks 45 Chunks Type bool numpy.ndarray

  • mask2d
    (y, x)
    bool
    dask.array<chunksize=(56, 6560), meta=np.ndarray>

    Array Chunk Bytes 32.93 MiB 768.75 kiB Shape (5264, 6560) (120, 6560) Count 1732 Tasks 45 Chunks Type bool numpy.ndarray

  • nav_lon
    (y, x)
    float32
    dask.array<chunksize=(56, 6560), meta=np.ndarray>

    Array Chunk Bytes 131.73 MiB 3.00 MiB Shape (5264, 6560) (120, 6560) Count 1732 Tasks 45 Chunks Type float32 numpy.ndarray

  • e3t
    (z, y, x)
    float64
    dask.array<chunksize=(150, 56, 6560), meta=np.ndarray>

    Array Chunk Bytes 38.59 GiB 900.88 MiB Shape (150, 5264, 6560) (150, 120, 6560) Count 1732 Tasks 45 Chunks Type float64 numpy.ndarray

  • nav_lat
    (y, x)
    float32
    dask.array<chunksize=(56, 6560), meta=np.ndarray>

    Array Chunk Bytes 131.73 MiB 3.00 MiB Shape (5264, 6560) (120, 6560) Count 1732 Tasks 45 Chunks Type float32 numpy.ndarray

  • e1te2t
    (y, x)
    float64
    dask.array<chunksize=(56, 6560), meta=np.ndarray>

    Array Chunk Bytes 263.46 MiB 6.01 MiB Shape (5264, 6560) (120, 6560) Count 1732 Tasks 45 Chunks Type float64 numpy.ndarray

• Data variables: (1)
  • vosaline
    (t, z, y, x)
    float32
    dask.array<chunksize=(1, 150, 56, 6560), meta=np.ndarray>

    cell_methods :

    time: mean (interval: 40 s)

    interval_operation :

    40 s

    interval_write :

    1 d

    long_name :

    salinity

    online_operation :

    average

    standard_name :

    sea_water_practical_salinity

    units :

    1e-3

    Array Chunk Bytes 578.89 GiB 450.44 MiB Shape (30, 150, 5264, 6560) (1, 150, 120, 6560) Count 31225 Tasks 1350 Chunks Type float32 numpy.ndarray

• Attributes: (26)

  CASE :

  DELTA

  CONFIG :

  SEDNA

  Conventions :

  CF-1.6

  DOMAIN_dimensions_ids :

  [2, 3]

  DOMAIN_halo_size_end :

  [0, 0]

  DOMAIN_halo_size_start :

  [0, 0]

  DOMAIN_number :

  0

  DOMAIN_number_total :

  544

  DOMAIN_position_first :

  [1, 1]

  DOMAIN_position_last :

  [6560, 13]

  DOMAIN_size_global :

  [6560, 6540]

  DOMAIN_size_local :

  [6560, 13]

  DOMAIN_type :

  box

  NCO :

  netCDF Operators version 4.9.1 (Homepage = http://nco.sf.net, Code = http://github.com/nco/nco)

  description :

  ocean T grid variables

  history :

  Thu Aug 11 12:22:01 2022: ncks -4 -L 1 SEDNA-DELTA_1d_gridS_201504-201504_NOZIP_0000.nc /ccc/scratch/cont003/gen7420/talandel/SEDNA/SEDNA-DELTA-S/SPLIT/1d/2015/04/SEDNA-DELTA_1d_gridS_201504-201504_0000.nc Thu Aug 11 12:21:47 2022: ncrcat -n 30,2,1 SEDNA-DELTA_1d_gridS_0000_01.nc SEDNA-DELTA_1d_gridS_201504-201504_NOZIP_0000.nc

  ibegin :

  0

  jbegin :

  0

  name :

  /ccc/scratch/cont003/ra5563/talandel/ONGOING-RUNS/SEDNA-DELTA-XIOS.86/SEDNA-DELTA_1d_gridS

  ni :

  6560

  nj :

  13

  output_frequency :

  1d

  start_date :

  20090101

  timeStamp :

  2022-Aug-10 14:15:34 GMT

  title :

  ocean T grid variables

  uuid :

  ff447a34-04b8-481f-a3d2-a5361bb0def0

#3 Start computing 
data= calc.FWC2D_UFUNC(data)
monitor.optimize_dataset(data)
add optimise here once otimise can recognise

<xarray.Dataset>
Dimensions:  (t: 30, y: 5264, x: 6560)
Coordinates:
  * t        (t) object 2015-04-01 12:00:00 ... 2015-04-30 12:00:00
  * y        (y) int64 1277 1278 1279 1280 1281 ... 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=(56, 6560), meta=np.ndarray>
    nav_lon  (y, x) float32 dask.array<chunksize=(56, 6560), meta=np.ndarray>
    nav_lat  (y, x) float32 dask.array<chunksize=(56, 6560), meta=np.ndarray>
    e1te2t   (y, x) float64 dask.array<chunksize=(56, 6560), meta=np.ndarray>
Data variables:
    FWC2D    (t, y, x) float32 dask.array<chunksize=(1, 56, 6560), meta=np.ndarray>

xarray.Dataset

• Dimensions:
  • t: 30
  • y: 5264
  • x: 6560
• Coordinates: (7)
  • t
    (t)
    object
    2015-04-01 12:00:00 ... 2015-04-...

    array([cftime.DatetimeNoLeap(2015, 4, 1, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 2, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 3, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 4, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 5, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 6, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 7, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 8, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 9, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 10, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 11, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 12, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 13, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 14, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 15, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 16, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 17, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 18, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 19, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 20, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 21, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 22, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 23, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 24, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 25, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 26, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 27, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 28, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 29, 12, 0, 0, 0, has_year_zero=True),
           cftime.DatetimeNoLeap(2015, 4, 30, 12, 0, 0, 0, has_year_zero=True)],
          dtype=object)

  • y
    (y)
    int64
    1277 1278 1279 ... 6538 6539 6540

    array([1277, 1278, 1279, ..., 6538, 6539, 6540])

  • x
    (x)
    int64
    1 2 3 4 5 ... 6557 6558 6559 6560

    array([   1,    2,    3, ..., 6558, 6559, 6560])

  • mask2d
    (y, x)
    bool
    dask.array<chunksize=(56, 6560), meta=np.ndarray>

    Array Chunk Bytes 32.93 MiB 768.75 kiB Shape (5264, 6560) (120, 6560) Count 1732 Tasks 45 Chunks Type bool numpy.ndarray

  • nav_lon
    (y, x)
    float32
    dask.array<chunksize=(56, 6560), meta=np.ndarray>

    Array Chunk Bytes 131.73 MiB 3.00 MiB Shape (5264, 6560) (120, 6560) Count 1732 Tasks 45 Chunks Type float32 numpy.ndarray

  • nav_lat
    (y, x)
    float32
    dask.array<chunksize=(56, 6560), meta=np.ndarray>

    Array Chunk Bytes 131.73 MiB 3.00 MiB Shape (5264, 6560) (120, 6560) Count 1732 Tasks 45 Chunks Type float32 numpy.ndarray

  • e1te2t
    (y, x)
    float64
    dask.array<chunksize=(56, 6560), meta=np.ndarray>

    Array Chunk Bytes 263.46 MiB 6.01 MiB Shape (5264, 6560) (120, 6560) Count 1732 Tasks 45 Chunks Type float64 numpy.ndarray

• Data variables: (1)
  • FWC2D
    (t, y, x)
    float32
    dask.array<chunksize=(1, 56, 6560), meta=np.ndarray>

    long_name :

    Fresh Water Content 2D

    Array Chunk Bytes 3.86 GiB 3.00 MiB Shape (30, 5264, 6560) (1, 120, 6560) Count 42879 Tasks 1350 Chunks Type float32 numpy.ndarray

• Attributes: (0)

#4 Saving  SEDNA_maps_BBFG_FWC_2D
data=save.datas(data,plot=Plot,path=nc_outputpath,filename=filename)
start saving data
saving data in a file
t (1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1)
0
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
slice(0, 1, None)

2022-11-28 18:35:16,166 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36177
Traceback (most recent call last):
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 223, in read
    frames_nbytes = await stream.read_bytes(fmt_size)
asyncio.exceptions.CancelledError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/asyncio/tasks.py", line 456, in wait_for
    return fut.result()
asyncio.exceptions.CancelledError

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/comm/core.py", line 328, in connect
    handshake = await asyncio.wait_for(comm.read(), time_left())
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/asyncio/tasks.py", line 458, in wait_for
    raise exceptions.TimeoutError() from exc
asyncio.exceptions.TimeoutError

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 2702, in _get_data
    comm = await rpc.connect(worker)
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 1371, in connect
    return await connect_attempt
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 1307, in _connect
    comm = await connect(
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/core.py", line 333, in connect
    raise OSError(
OSError: Timed out during handshake while connecting to tcp://127.0.0.1:36177 after 30 s
2022-11-28 18:35:44,772 - distributed.worker_memory - WARNING - Worker is at 80% memory usage. Pausing worker.  Process memory: 11.20 GiB -- Worker memory limit: 13.87 GiB
2022-11-28 18:36:07,119 - distributed.worker_memory - WARNING - Worker is at 68% memory usage. Resuming worker. Process memory: 9.46 GiB -- Worker memory limit: 13.87 GiB
2022-11-28 18:37:35,532 - distributed.worker_memory - WARNING - Worker is at 88% memory usage. Pausing worker.  Process memory: 12.24 GiB -- Worker memory limit: 13.87 GiB
2022-11-28 18:37:40,570 - distributed.worker_memory - WARNING - Worker is at 66% memory usage. Resuming worker. Process memory: 9.28 GiB -- Worker memory limit: 13.87 GiB
2022-11-28 18:37:42,124 - distributed.worker_memory - WARNING - Worker is at 84% memory usage. Pausing worker.  Process memory: 11.68 GiB -- Worker memory limit: 13.87 GiB
2022-11-28 18:37:43,629 - distributed.worker_memory - WARNING - Worker tcp://127.0.0.1:44981 (pid=42197) exceeded 95% memory budget. Restarting...
2022-11-28 18:37:44,653 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:44981
Traceback (most recent call last):
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 223, in read
    frames_nbytes = await stream.read_bytes(fmt_size)
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://127.0.0.1:42362 remote=tcp://127.0.0.1:44981>: Stream is closed
2022-11-28 18:37:44,691 - distributed.nanny - WARNING - Restarting worker

slice(1, 2, None)

2022-11-28 18:39:02,430 - distributed.worker_memory - WARNING - Worker tcp://127.0.0.1:45127 (pid=42222) exceeded 95% memory budget. Restarting...
2022-11-28 18:39:03,118 - distributed.worker - ERROR - failed during get data with tcp://127.0.0.1:39732 -> tcp://127.0.0.1:45127
Traceback (most recent call last):
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 223, in read
    frames_nbytes = await stream.read_bytes(fmt_size)
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 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 144, in convert_stream_closed_error
    raise CommClosedError(f"in {obj}: {exc}") from exc
distributed.comm.core.CommClosedError: in <TCP (closed)  local=tcp://127.0.0.1:39732 remote=tcp://127.0.0.1:57258>: Stream is closed
2022-11-28 18:39:03,118 - distributed.worker - ERROR - failed during get data with tcp://127.0.0.1:40849 -> tcp://127.0.0.1:45127
Traceback (most recent call last):
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 223, in read
    frames_nbytes = await stream.read_bytes(fmt_size)
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 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 144, in convert_stream_closed_error
    raise CommClosedError(f"in {obj}: {exc}") from exc
distributed.comm.core.CommClosedError: in <TCP (closed)  local=tcp://127.0.0.1:40849 remote=tcp://127.0.0.1:51902>: Stream is closed
2022-11-28 18:39:03,118 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45127
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/comm/core.py", line 328, in connect
    handshake = await asyncio.wait_for(comm.read(), time_left())
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/asyncio/tasks.py", line 445, in wait_for
    return fut.result()
  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://127.0.0.1:46514 remote=tcp://127.0.0.1:45127>: 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 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 2702, in _get_data
    comm = await rpc.connect(worker)
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 1371, in connect
    return await connect_attempt
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 1307, in _connect
    comm = await connect(
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/core.py", line 333, in connect
    raise OSError(
OSError: Timed out during handshake while connecting to tcp://127.0.0.1:45127 after 30 s
2022-11-28 18:39:03,125 - distributed.worker - ERROR - failed during get data with tcp://127.0.0.1:36997 -> tcp://127.0.0.1:45127
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://127.0.0.1:36997 remote=tcp://127.0.0.1:50248>: ConnectionResetError: [Errno 104] Connection reset by peer
2022-11-28 18:39:03,126 - distributed.worker - ERROR - failed during get data with tcp://127.0.0.1:36177 -> tcp://127.0.0.1:45127
Traceback (most recent call last):
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 223, in read
    frames_nbytes = await stream.read_bytes(fmt_size)
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 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 144, in convert_stream_closed_error
    raise CommClosedError(f"in {obj}: {exc}") from exc
distributed.comm.core.CommClosedError: in <TCP (closed)  local=tcp://127.0.0.1:36177 remote=tcp://127.0.0.1:39340>: Stream is closed
2022-11-28 18:39:03,126 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45127
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 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 142, in convert_stream_closed_error
    raise CommClosedError(f"in {obj}: {exc.__class__.__name__}: {exc}") from exc
distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46496 remote=tcp://127.0.0.1:45127>: ConnectionResetError: [Errno 104] Connection reset by peer
2022-11-28 18:39:03,126 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45127
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://127.0.0.1:46492 remote=tcp://127.0.0.1:45127>: Stream is closed
2022-11-28 18:39:03,147 - distributed.nanny - WARNING - Restarting worker
2022-11-28 18:39:04,513 - distributed.worker - ERROR - failed during get data with tcp://127.0.0.1:33387 -> tcp://127.0.0.1:45127
Traceback (most recent call last):
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 223, in read
    frames_nbytes = await stream.read_bytes(fmt_size)
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 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 144, in convert_stream_closed_error
    raise CommClosedError(f"in {obj}: {exc}") from exc
distributed.comm.core.CommClosedError: in <TCP (closed)  local=tcp://127.0.0.1:33387 remote=tcp://127.0.0.1:49258>: Stream is closed
2022-11-28 18:39:05,771 - distributed.worker - ERROR - failed during get data with tcp://127.0.0.1:35881 -> tcp://127.0.0.1:45127
Traceback (most recent call last):
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 223, in read
    frames_nbytes = await stream.read_bytes(fmt_size)
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 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 144, in convert_stream_closed_error
    raise CommClosedError(f"in {obj}: {exc}") from exc
distributed.comm.core.CommClosedError: in <TCP (closed)  local=tcp://127.0.0.1:35881 remote=tcp://127.0.0.1:48800>: Stream is closed
2022-11-28 18:39:06,955 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45127
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 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 142, in convert_stream_closed_error
    raise CommClosedError(f"in {obj}: {exc.__class__.__name__}: {exc}") from exc
distributed.comm.core.CommClosedError: in <TCP (closed) Ephemeral Worker->Worker for gather local=tcp://127.0.0.1:46288 remote=tcp://127.0.0.1:45127>: ConnectionResetError: [Errno 104] Connection reset by peer
2022-11-28 18:39:06,956 - distributed.worker - ERROR - failed during get data with tcp://127.0.0.1:34035 -> tcp://127.0.0.1:45127
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://127.0.0.1:34035 remote=tcp://127.0.0.1:34664>: ConnectionResetError: [Errno 104] Connection reset by peer
2022-11-28 18:39:09,500 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:45127
Traceback (most recent call last):
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 315, in write
    raise StreamClosedError()
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 916, in send_recv
    await comm.write(msg, serializers=serializers, on_error="raise")
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 326, in write
    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://127.0.0.1:46278 remote=tcp://127.0.0.1:45127>: Stream is closed
2022-11-28 18:39:10,750 - distributed.worker - ERROR - failed during get data with tcp://127.0.0.1:39693 -> tcp://127.0.0.1:45127
Traceback (most recent call last):
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 223, in read
    frames_nbytes = await stream.read_bytes(fmt_size)
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 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 144, in convert_stream_closed_error
    raise CommClosedError(f"in {obj}: {exc}") from exc
distributed.comm.core.CommClosedError: in <TCP (closed)  local=tcp://127.0.0.1:39693 remote=tcp://127.0.0.1:50446>: Stream is closed

slice(2, 3, None)

2022-11-28 18:41:47,920 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:36997
Traceback (most recent call last):
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 264, in write
    async def write(self, msg, serializers=None, on_error="message"):
asyncio.exceptions.CancelledError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/asyncio/tasks.py", line 418, in wait_for
    return fut.result()
asyncio.exceptions.CancelledError

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/comm/core.py", line 329, in connect
    await asyncio.wait_for(comm.write(local_info), time_left())
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/asyncio/tasks.py", line 420, in wait_for
    raise exceptions.TimeoutError() from exc
asyncio.exceptions.TimeoutError

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 2702, in _get_data
    comm = await rpc.connect(worker)
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 1371, in connect
    return await connect_attempt
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 1307, in _connect
    comm = await connect(
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/core.py", line 333, in connect
    raise OSError(
OSError: Timed out during handshake while connecting to tcp://127.0.0.1:36997 after 30 s
2022-11-28 18:41:51,842 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:35881
Traceback (most recent call last):
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/tcp.py", line 223, in read
    frames_nbytes = await stream.read_bytes(fmt_size)
asyncio.exceptions.CancelledError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/asyncio/tasks.py", line 456, in wait_for
    return fut.result()
asyncio.exceptions.CancelledError

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/comm/core.py", line 328, in connect
    handshake = await asyncio.wait_for(comm.read(), time_left())
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/asyncio/tasks.py", line 458, in wait_for
    raise exceptions.TimeoutError() from exc
asyncio.exceptions.TimeoutError

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 2702, in _get_data
    comm = await rpc.connect(worker)
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 1371, in connect
    return await connect_attempt
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/core.py", line 1307, in _connect
    comm = await connect(
  File "/ccc/cont003/home/ra5563/ra5563/monitor/lib/python3.10/site-packages/distributed/comm/core.py", line 333, in connect
    raise OSError(
OSError: Timed out during handshake while connecting to tcp://127.0.0.1:35881 after 30 s

slice(3, 4, None)
slice(4, 5, None)
slice(5, 6, None)
slice(6, 7, None)
slice(7, 8, None)
slice(8, 9, None)
slice(9, 10, None)

2022-11-28 18:53:09,829 - distributed.worker_memory - WARNING - Worker is at 86% memory usage. Pausing worker.  Process memory: 11.96 GiB -- Worker memory limit: 13.87 GiB
2022-11-28 18:53:18,801 - distributed.worker_memory - WARNING - Worker is at 58% memory usage. Resuming worker. Process memory: 8.16 GiB -- Worker memory limit: 13.87 GiB

slice(10, 11, None)
slice(11, 12, None)
slice(12, 13, None)
slice(13, 14, None)
slice(14, 15, None)
slice(15, 16, None)
slice(16, 17, None)
slice(17, 18, None)
slice(18, 19, None)
slice(19, 20, None)
slice(20, 21, None)
slice(21, 22, None)
slice(22, 23, None)
slice(23, 24, None)
slice(24, 25, None)
slice(25, 26, None)
slice(26, 27, None)
slice(27, 28, None)
slice(28, 29, None)
slice(29, 30, None)
CPU times: user 7min 56s, sys: 1min 40s, total: 9min 36s
Wall time: 51min 21s