%matplotlib inline
import pandas as pd
import socket
host = socket.getfqdn()
from core import load, zoom, calc, save,plots,monitor
#reload funcs after updating ./core/*.py
import importlib
importlib.reload(load)
importlib.reload(zoom)
importlib.reload(calc)
importlib.reload(save)
importlib.reload(plots)
importlib.reload(monitor)
<module 'core.monitor' from '/ccc/work/cont003/gen7420/odakatin/monitor-sedna/notebook/core/monitor.py'>
If you submit the job with job scheduler; below are list of enviroment variable one can pass
local : if True run dask local cluster, if not true, put number of workers setted in the 'local' if no 'local ' given, local will be setted automatically to 'True'
%env ychunk='2', #%env tchunk='2'
controls chunk. 'False' sets no modification from original netcdf file's chunk.
ychunk=10 will group the original netcdf file to 10 by 10
tchunk=1 will chunk the time coordinate one by one
%env file_exp=
'file_exp': Which 'experiment' name is it? this corresopnds to intake catalog name without path and .yaml
#%env year=
for Validation, this correspoinds to path/year/month 's year for monitoring, this corresponids to 'date' having means do all files in the monitoring directory setting it as 0[0-9] &1[0-9]& [2-3][0-9], the job can be separated in three lots. For DELTA experiment, year corresponds to really 'year'
%env month=
for monitoring this corresponds to file path path-XIOS.{month}/
For DELTA experiment, year corresponds to really 'month'
proceed saving? True or False , Default is setted as True
proceed plotting? True or False , Default is setted as True
proceed computation? or just load computed result? True or False , Default is setted as True
save output file used for plotting
using kerchunked file -> False, not using kerhcunk -> True
name of control file to be used for computation/plots/save/ We have number of M_xxx.csv
Monitor.sh calls M_MLD_2D
and AWTD.sh, Fluxnet.sh, Siconc.sh, IceClim.sh, FWC_SSH.sh, Integrals.sh , Sections.sh
M_AWTMD
M_Fluxnet
M_Ice_quantities
M_IceClim M_IceConce M_IceThick
M_FWC_2D M_FWC_integrals M_FWC_SSH M_SSH_anomaly
M_Mean_temp_velo M_Mooring
M_Sectionx M_Sectiony
%%time
# 'savefig': Do we save output in html? or not. keep it true.
savefig=True
client,cluster,control,catalog_url,month,year,daskreport,outputpath = load.set_control(host)
!mkdir -p $outputpath
!mkdir -p $daskreport
client
local True using host= irene4988.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 irene4988.c-irene.mg1.tgcc.ccc.cea.fr using SEDNA_DELTA_MONITOR file experiment, read from ../lib/SEDNA_DELTA_MONITOR.yaml on year= 2012 on month= 03 outputpath= ../results/SEDNA_DELTA_MONITOR/ daskreport= ../results/dask/6419607irene4988.c-irene.mg1.tgcc.ccc.cea.fr_SEDNA_DELTA_MONITOR_03M_FWC_2D/ CPU times: user 582 ms, sys: 143 ms, total: 725 ms Wall time: 22.7 s
Client-9dc21de4-13e4-11ed-9963-080038b940e9
Connection method: Cluster object | Cluster type: distributed.LocalCluster |
Dashboard: http://127.0.0.1:8787/status |
c6fd44c4
Dashboard: http://127.0.0.1:8787/status | Workers: 16 |
Total threads: 128 | Total memory: 251.06 GiB |
Status: running | Using processes: True |
Scheduler-32089d94-aa2c-4e98-86a6-e84b1395f14d
Comm: tcp://127.0.0.1:33861 | Workers: 16 |
Dashboard: http://127.0.0.1:8787/status | Total threads: 128 |
Started: Just now | Total memory: 251.06 GiB |
Comm: tcp://127.0.0.1:38971 | Total threads: 8 |
Dashboard: http://127.0.0.1:41905/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:35262 | |
Local directory: /tmp/dask-worker-space/worker-8pk3k1_c |
Comm: tcp://127.0.0.1:37487 | Total threads: 8 |
Dashboard: http://127.0.0.1:35730/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:41088 | |
Local directory: /tmp/dask-worker-space/worker-tgtxt0sn |
Comm: tcp://127.0.0.1:35642 | Total threads: 8 |
Dashboard: http://127.0.0.1:40982/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:41663 | |
Local directory: /tmp/dask-worker-space/worker-az_leden |
Comm: tcp://127.0.0.1:39884 | Total threads: 8 |
Dashboard: http://127.0.0.1:42946/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:39858 | |
Local directory: /tmp/dask-worker-space/worker-n7cke69b |
Comm: tcp://127.0.0.1:40922 | Total threads: 8 |
Dashboard: http://127.0.0.1:37017/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:45625 | |
Local directory: /tmp/dask-worker-space/worker-177g_nqn |
Comm: tcp://127.0.0.1:46220 | Total threads: 8 |
Dashboard: http://127.0.0.1:39845/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:40187 | |
Local directory: /tmp/dask-worker-space/worker-qmdyslli |
Comm: tcp://127.0.0.1:34005 | Total threads: 8 |
Dashboard: http://127.0.0.1:46251/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:46513 | |
Local directory: /tmp/dask-worker-space/worker-n_p7kzt1 |
Comm: tcp://127.0.0.1:38753 | Total threads: 8 |
Dashboard: http://127.0.0.1:43913/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:43502 | |
Local directory: /tmp/dask-worker-space/worker-jalnefby |
Comm: tcp://127.0.0.1:35760 | Total threads: 8 |
Dashboard: http://127.0.0.1:38828/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:44794 | |
Local directory: /tmp/dask-worker-space/worker-znjysplm |
Comm: tcp://127.0.0.1:39597 | Total threads: 8 |
Dashboard: http://127.0.0.1:35684/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:35839 | |
Local directory: /tmp/dask-worker-space/worker-2ogl7tvq |
Comm: tcp://127.0.0.1:38510 | Total threads: 8 |
Dashboard: http://127.0.0.1:33072/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:33874 | |
Local directory: /tmp/dask-worker-space/worker-bm0jiuef |
Comm: tcp://127.0.0.1:35272 | Total threads: 8 |
Dashboard: http://127.0.0.1:39243/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:38355 | |
Local directory: /tmp/dask-worker-space/worker-12kakro0 |
Comm: tcp://127.0.0.1:35950 | Total threads: 8 |
Dashboard: http://127.0.0.1:45324/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:35353 | |
Local directory: /tmp/dask-worker-space/worker-7qdd5hc3 |
Comm: tcp://127.0.0.1:43773 | Total threads: 8 |
Dashboard: http://127.0.0.1:36680/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:34319 | |
Local directory: /tmp/dask-worker-space/worker-ndvqouv0 |
Comm: tcp://127.0.0.1:41651 | Total threads: 8 |
Dashboard: http://127.0.0.1:38639/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:38804 | |
Local directory: /tmp/dask-worker-space/worker-kjljt8ue |
Comm: tcp://127.0.0.1:41082 | Total threads: 8 |
Dashboard: http://127.0.0.1:37483/status | Memory: 15.69 GiB |
Nanny: tcp://127.0.0.1:45199 | |
Local directory: /tmp/dask-worker-space/worker-lubr1rxg |
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 |
Each computation consists of
%%time
import os
calcswitch=os.environ.get('calc', 'True')
lazy=os.environ.get('lazy','False' )
loaddata=((df.Inputs != '').any())
print('calcswitch=',calcswitch,'df.Inputs != nothing',loaddata, 'lazy=',lazy)
data = load.datas(catalog_url,df.Inputs,month,year,daskreport,lazy=lazy) if ((calcswitch=='True' )*loaddata) else 0
data
calcswitch= True df.Inputs != nothing True lazy= 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/odakatin/monitor-sedna/notebook/../lib/ > {'name': 'param_xios', 'container': 'xarray', 'plugin': ['netcdf'], 'driver': ['netcdf'], 'description': 'SEDNA NEMO parameters from MPI output nav_lon lat fails', 'direct_access': 'forbid', 'user_parameters': [{'name': 'path', 'description': 'file coordinate', 'type': 'str', 'default': '/ccc/work/cont003/gen7420/odakatin/CONFIGS/SEDNA/MESH/SEDNA_mesh_mask_Tgt_20210423_tsh10m_L1/param'}], 'metadata': {}, 'args': {'urlpath': '/ccc/work/cont003/gen7420/odakatin/CONFIGS/SEDNA/SEDNA-I/SEDNA_Domain_cfg_Tgt_20210423_tsh10m_L1/param_f32/x_*.nc', 'combine': 'nested', 'concat_dim': 'y'}} 0 read 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/201203/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/odakatin/monitor-sedna/notebook/../lib/ > took 20.131089687347412 seconds 0 merging gridS ['vosaline'] param e1te2t will be included in data param mask2d will be included in data param mask will be included in data param e3t will be included in data param nav_lat will be included in data param nav_lon will be included in data CPU times: user 19.9 s, sys: 2.88 s, total: 22.8 s Wall time: 44.4 s
<xarray.Dataset> Dimensions: (t: 31, z: 150, y: 6540, x: 6560) Coordinates: time_centered (t) object dask.array<chunksize=(1,), meta=np.ndarray> * t (t) object 2012-03-01 12:00:00 ... 2012-03-31 12:00:00 * y (y) int64 1 2 3 4 5 6 7 ... 6535 6536 6537 6538 6539 6540 * x (x) int64 1 2 3 4 5 6 7 ... 6555 6556 6557 6558 6559 6560 * z (z) int64 1 2 3 4 5 6 7 8 ... 143 144 145 146 147 148 149 150 e1te2t (y, x) float64 dask.array<chunksize=(13, 6560), meta=np.ndarray> mask2d (y, x) bool dask.array<chunksize=(13, 6560), meta=np.ndarray> mask (z, y, x) bool dask.array<chunksize=(150, 13, 6560), meta=np.ndarray> e3t (z, y, x) float64 dask.array<chunksize=(150, 13, 6560), meta=np.ndarray> nav_lat (y, x) float32 dask.array<chunksize=(13, 6560), meta=np.ndarray> nav_lon (y, x) float32 dask.array<chunksize=(13, 6560), meta=np.ndarray> Data variables: vosaline (t, z, y, x) float32 dask.array<chunksize=(1, 150, 13, 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-Jan-19 12:40:34 GMT title: ocean T grid variables uuid: b2000bef-0e1f-4f0d-ae2a-b9429429b7a2
%%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: 31, z: 150, y: 5264, x: 6560) Coordinates: time_centered (t) object dask.array<chunksize=(1,), meta=np.ndarray> * t (t) object 2012-03-01 12:00:00 ... 2012-03-31 12:00:00 * y (y) int64 1277 1278 1279 1280 1281 ... 6537 6538 6539 6540 * x (x) int64 1 2 3 4 5 6 7 ... 6555 6556 6557 6558 6559 6560 * z (z) int64 1 2 3 4 5 6 7 8 ... 143 144 145 146 147 148 149 150 e1te2t (y, x) float64 dask.array<chunksize=(8, 6560), meta=np.ndarray> mask2d (y, x) bool dask.array<chunksize=(8, 6560), meta=np.ndarray> mask (z, y, x) bool dask.array<chunksize=(150, 8, 6560), meta=np.ndarray> e3t (z, y, x) float64 dask.array<chunksize=(150, 8, 6560), meta=np.ndarray> nav_lat (y, x) float32 dask.array<chunksize=(8, 6560), meta=np.ndarray> nav_lon (y, x) float32 dask.array<chunksize=(8, 6560), meta=np.ndarray> Data variables: vosaline (t, z, y, x) float32 dask.array<chunksize=(1, 150, 8, 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-Jan-19 12:40:34 GMT title: ocean T grid variables uuid: b2000bef-0e1f-4f0d-ae2a-b9429429b7a2
#3 Start computing data= calc.FWC2D_UFUNC(data) monitor.optimize_dataset(data) add optimise here once otimise can recognise
<xarray.Dataset> Dimensions: (t: 31, y: 5264, x: 6560) Coordinates: time_centered (t) object dask.array<chunksize=(1,), meta=np.ndarray> * t (t) object 2012-03-01 12:00:00 ... 2012-03-31 12:00:00 * y (y) int64 1277 1278 1279 1280 1281 ... 6537 6538 6539 6540 * x (x) int64 1 2 3 4 5 6 7 ... 6555 6556 6557 6558 6559 6560 e1te2t (y, x) float64 dask.array<chunksize=(8, 6560), meta=np.ndarray> mask2d (y, x) bool dask.array<chunksize=(8, 6560), meta=np.ndarray> nav_lat (y, x) float32 dask.array<chunksize=(8, 6560), meta=np.ndarray> nav_lon (y, x) float32 dask.array<chunksize=(8, 6560), meta=np.ndarray> Data variables: FWC2D (t, y, x) float32 dask.array<chunksize=(1, 8, 6560), meta=np.ndarray>
#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, 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 30 slice(0, 1, None)
2022-08-04 13:02:15,347 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:43773 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://127.0.0.1:43773 after 30 s 2022-08-04 13:02:15,356 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:46220 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://127.0.0.1:46220 after 30 s 2022-08-04 13:02:18,466 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:46220 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://127.0.0.1:46220 after 30 s 2022-08-04 13:02:18,469 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:43773 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://127.0.0.1:43773 after 30 s 2022-08-04 13:02:21,474 - distributed.worker - ERROR - Worker stream died during communication: tcp://127.0.0.1:35760 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://127.0.0.1:35760 after 30 s
slice(1, 2, None) slice(2, 3, None) 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) 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) slice(30, 31, None) CPU times: user 14min 33s, sys: 2min 13s, total: 16min 47s Wall time: 55min 15s