Develop Reference

Python error when trying to execute a script to shutdown GCP VM

The functionality of this script to shutdown GCP VM's based on some logic. Currently we are trying shut it down at night, but the scripts are failing before it could shutdown the VM. We shutdown based on time. At evenings and night the VM are shutdown using these scripts
Script to turn off instances overnight
Environment: Runs in Google Cloud Functions (Python3.7)
import datetime
import json
from pprint import pformat
import pytz
import re
import modules.common.cfcommon as cfcommon
import modules.utilities.dateutilities as dateutilities
from modules.compute.instances import InstanceList, Instance
from modules.compute.compute_service import ComputeServiceContext
from modules.utilities.printutilities import print_message, debug_message
from modules.pubsub.topic import PublishMessage
from modules.common.labels import VMAUTOSHUTDOWN_LABEL, VMAUTOSHUTDOWN_DEFER_LABEL, ShutdownDeferLabelValueIsValid, ShutdownLabelValueIsValid
from templates.renderer import render_template
# Takes a list in the following format and checks if the 'Instance' object is within it
# list must contain dictionaries in the following format:
# {"name": "instancename", "zone": "zonename"}
# Example: {"name": "test-01", "zone": "us-east4-c"}
#
# Parameters:
# inputList - list of dictionary objects
# instance - Instance object
def isInstanceInList(inputList, instance):
if not isinstance(inputList, list):
raise TypeError("Provided inputList is not a list")
if not isinstance(instance, Instance):
raise TypeError("Provided instance is not of type 'Instance'")
# Iterate over every item in inputList and check if the name and zone match
for cItem in inputList:
if cItem["name"].lower() == instance.properties["name"].lower() and cItem["zone"].lower() == instance.GetShortZoneName().lower():
return True
# No match found
return False
# Takes a list of Instance objects and sees if their shutdown timezone is within the graceperiod of the shutdownHour
#
# Example: is shutdown hour is 23 and the gracePeriodMin is 15 then if the function is called at 23:12, the instance will be included in the shutdown list
#
# Parameters:
# instanceList - List of Instance objects
# shutdownHour - number (0-23) 0 = Midnight, 23 = 11PM
# gracePeriodMin - number
def getInstancesToStop(instanceList, gracePeriodMin):
instancesToStop = []
debug_message("Entering getInstancesToStop")
for cInstance in instanceList:
debug_message("Instance: %s (ID: %s, Zone: %s, Project: %s)" % (cInstance.GetName(), cInstance.GetId(), cInstance.GetShortZoneName(), cInstance.project))
labels = cInstance.GetLabels()
if VMAUTOSHUTDOWN_LABEL in labels.keys():
labelValue = labels.get(VMAUTOSHUTDOWN_LABEL, '')
pattern = '\d\d-\d\d-\d\d'
match = re.match(pattern, labelValue)
if not match or not ShutdownLabelValueIsValid(labelValue):
debug_message(f'Label {labelValue} does not match the correct format')
instancesToStop.append(cInstance)
continue
else:
debug_message(f'Label {VMAUTOSHUTDOWN_LABEL} not found. Adding to shutdown list')
instancesToStop.append(cInstance)
continue
shutdown_deferred_utc_datetime = None
if VMAUTOSHUTDOWN_DEFER_LABEL in labels.keys():
labelValue = labels.get(VMAUTOSHUTDOWN_DEFER_LABEL, '')
pattern = '\d\d\d\d-\d\d-\d\dt\d\d-\d\d-\d\d'
match = re.match(pattern, labelValue)
if match and ShutdownDeferLabelValueIsValid(labelValue):
shutdown_deferred_utc_date, shutdown_deferred_utc_time = labelValue.split('t')
year, month, day = shutdown_deferred_utc_date.split('-')
hour, minute, second = shutdown_deferred_utc_time.split('-')
shutdown_deferred_utc_datetime = datetime.datetime.now(pytz.timezone('GMT')).replace(
year=int(year), month=int(month), day=int(day), hour=int(hour), minute=int(minute), second=int(second)
)
else:
debug_message(f'Label {labels[VMAUTOSHUTDOWN_DEFER_LABEL]} does not match the correct format')
instancesToStop.append(cInstance)
continue
current_utc_time = dateutilities.get_current_datetime()
# If defer date is in the future, and not in grace window time, skip shutting down
if shutdown_deferred_utc_datetime is not None and shutdown_deferred_utc_datetime > current_utc_time:
debug_message(f'Instance {cInstance.GetName()} shutdown deferred until after {labels[VMAUTOSHUTDOWN_DEFER_LABEL]}')
continue
# If defer time is in past, continue with the vm hour shutdown
shutdown_utc_hour = labels[VMAUTOSHUTDOWN_LABEL].split('-')[0]
# Convert shutdown UTC hour into datetime object
shutdown_utc_time = datetime.datetime.now(pytz.timezone('GMT')).replace(hour=int(shutdown_utc_hour), minute=0, second=0)
shutdown_utc_grace_time = shutdown_utc_time + datetime.timedelta(minutes=gracePeriodMin)
debug_message(f"Shutdown UTC time {shutdown_utc_time}")
debug_message(f"Shutdown UTC grace time {shutdown_utc_grace_time}")
# Check if shutdown is within time window
if current_utc_time >= shutdown_utc_time and current_utc_time <= shutdown_utc_grace_time:
debug_message("We're in the time window")
instancesToStop.append(cInstance)
else:
debug_message("We're outside the time window. Not adding to stop list")
return instancesToStop
# This is the main entry point that cloud functions calls
def AutoStopVMInstances(config, policy=None, payload=None, generate_local_report=False):
FUNCTION_NAME = "AutoStopVMInstances"
# Populated by config later...
QUERY_PROJECT_IDS = None # List of project IDs
INSTANCE_WHITELIST = None # List of dictionaries in format {"name": "instancename", "zone": "zonename", "project": "projectid"}
PREVIEW_MODE = True
SHUTDOWN_GRACEPERIOD_MIN = 30
# Start
startTime = datetime.datetime.now()
print_message("Started %s within Cloud Function %s [%s]" % (FUNCTION_NAME, cfcommon.CLOUD_FUNCTION_NAME, startTime))
debug_message("")
# For ease of access, assign from config values
debug_message("Processing Configuration...")
QUERY_PROJECT_IDS = config.get("QueryProjectIDs", []) # Required field
INSTANCE_WHITELIST = config.get("InstanceWhiteList", []) # Optional Field
PREVIEW_MODE = config.get("PreviewMode", True) # Required field
SHUTDOWN_GRACEPERIOD_MIN = config.get("ShutdownGracePeriodMin", None) # Required field
SKIP_INSTANCE_GROUPS = config.get("SkipInstanceGroups", False) # Optional
EMAIL_PUB_SUB_PROJECT = config.get("EmailPubSubProject", None) # Optional
EMAIL_PUB_SUB_TOPIC = config.get("EmailPubSubTopic", None) # Optional
EMAIL_TO = config.get("EmailTo", []) # Optional
EMAIL_CC = config.get("EmailCC", None) # Optional
EMAIL_BCC = config.get("EmailBCC", None) # Optional
EMAIL_FROM = config.get("EmailFrom", "noreply-ei-cs-cloudops-resource-administration#ei-cs-cloudops.local") # Optional
EMAIL_SUBJECT = config.get("EmailSubject", "Nightly VM Instance Shutdown Summary") # Optional
cfLogger = cfcommon.CloudFunctionLog()
# Validate whitelist
if INSTANCE_WHITELIST is None:
raise Exception("Unable to get whitelist")
debug_message("Whitelist loaded:")
debug_message(pformat((INSTANCE_WHITELIST)))
# Re-init Compute service - execution environment in cloud functions can be shared among each other. Let's re-init our connection every execution.
ComputeServiceContext.InitComputeService()
# Build the service object.
allRunningInstances = []
for cProjectId in QUERY_PROJECT_IDS:
debug_message("Checking Project: %s" % (cProjectId))
# Main Loop - Let's get and analyze all instances from our project
# Paginated within the 'request' object
runningInstances = []
allInstances = []
debug_message("Building Instance List...", end="")
instances = InstanceList(cProjectId)
instances.PopulateInstances()
debug_message("Done")
for cInstance in instances.GetAllInstances():
debug_message("Found Instance %s in %s [%s - %s]" % (cInstance.GetName(), cInstance.GetZone(), cInstance.GetId(), cInstance.GetStatus()))
# Check if whitelisted. If it is, skip it
if isInstanceInList(INSTANCE_WHITELIST, cInstance):
debug_message(" Instance is whitelisted. Skipping.")
continue
# Check if we should skip instance groups
if SKIP_INSTANCE_GROUPS and cInstance.IsWithinInstanceGroup():
debug_message(" Instance is within an instance group. Skipping.")
continue
debug_message(" Is Running: %s" % (cInstance.IsRunning()))
owner = cInstance.GetOwner()
if owner in ("devops", "ei devops", "eicsdevopseng"):
debug_message("Skipping instance owned by devops")
continue
# # TODO: FOR USE WHEN TESTING
# if VMAUTOSHUTDOWN_LABEL not in labels.keys():
# continue
# Keep track of this instance
allInstances.append(cInstance)
# If it's running, it's a candidate to stop
if cInstance.IsRunning():
runningInstances.append(cInstance)
# Handle no instances found
if len(allInstances) == 0:
debug_message("INFO: No Instances found.")
# Summarize for user
debug_message("")
if len(runningInstances) > 0:
debug_message("Found %s/%s non-whitelisted instances are running (project: %s)" % (len(runningInstances), len(allInstances), cProjectId))
else:
debug_message("All %s non-whitelisted instances are good (project: %s)" % (len(allInstances), cProjectId))
# Main loop to stop
debug_message("")
allRunningInstances = allRunningInstances + runningInstances
instancesToBeStopped = getInstancesToStop(allRunningInstances, SHUTDOWN_GRACEPERIOD_MIN)
stoppedCount = 0
instanceSummary = []
if len(instancesToBeStopped) == 0:
print_message("No instances are due to be stopped")
else:
for cInstance in instancesToBeStopped:
summaryEntry = {
"Name": cInstance.GetName(),
"ID": cInstance.GetId(),
"Zone": cInstance.GetShortZoneName(),
"Project": cInstance.GetProject(),
"Preview": PREVIEW_MODE,
"Stopped": False,
"InstanceLink": cInstance.GetSelfLinkToConsole()
}
logMessage = "Stopping Instance: {name} (ID: {id}, Zone: {zone}, Project: {project})".format(
name=summaryEntry.get("Name"),
id=summaryEntry.get("ID"),
zone=summaryEntry.get("Zone"),
project=summaryEntry.get("Project")
)
if PREVIEW_MODE:
print_message("(PREVIEW) " + logMessage )
else:
print_message(logMessage)
cInstance.Stop()
summaryEntry["Stopped"] = True
stoppedCount += 1
instanceSummary.append(summaryEntry)
if EMAIL_PUB_SUB_PROJECT is not None and EMAIL_PUB_SUB_TOPIC is not None:
debug_message("It looks like we have an email config. Attempting to send email")
emailBody = render_template(
'shutdown_report',
instance_summary=instanceSummary,
config=json.dumps(config, indent=4, sort_keys=True),
preview_mode=PREVIEW_MODE,
generation_time=datetime.datetime.now().astimezone(pytz.utc)
)
emailPayload = {
"To": EMAIL_TO,
"From": EMAIL_FROM,
"Subject": EMAIL_SUBJECT,
"BodyHtml": emailBody
}
if EMAIL_CC is not None:
emailPayload["CC"] = EMAIL_CC
if EMAIL_BCC is not None:
emailPayload["BCC"] = EMAIL_BCC
if not generate_local_report:
print_message("Sending email...", end="")
PublishMessage(EMAIL_PUB_SUB_PROJECT, EMAIL_PUB_SUB_TOPIC, json.dumps(emailPayload))
else:
print_message('Generating local HTML report')
with open('./html_reports/shutdown_report.html', 'w') as r:
r.write(emailBody)
print_message("Done")
# We want to log a nice structured json line to stackdriver for easy reporting.
cfLogger.log({
"StartTime": startTime.isoformat(),
"InstancesStoppedCount": stoppedCount,
"PreviewMode": PREVIEW_MODE,
"Instances": instanceSummary,
"Whitelist": INSTANCE_WHITELIST,
"EndTime": datetime.datetime.now().isoformat(),
"LogLine": "Summary"
})
print_message("DONE [%s]" % (datetime.datetime.now()))
The error I'm getting when trying to run a VM shutdown script:
Caught exception while running VMNightlyShutdown. Exception Text: Traceback (most recent call last):
File "/workspace/main.py", line 248, in StartCloudFunction
policy=policy_config)
File "/workspace/vm_nightly_shutdown.py", line 256, in AutoStopVMInstances
cInstance.Stop()
File "/workspace/modules/compute/instances.py", line 729, in Stop
stop_instance(self.project, self.GetShortZoneName(), self.GetName(), waitForCompletion=waitForCompletion)
File "/workspace/modules/compute/instances.py", line 45, in stop_instance
return wait_for_operation(project, zone, response["name"])
File "/workspace/modules/compute/instances.py", line 27, in wait_for_operation
operation=operation
File "/layers/google.python.pip/pip/lib/python3.7/site-packages/googleapiclient/_helpers.py", line 130, in positional_wrapper
return wrapped(*args, **kwargs)
File "/layers/google.python.pip/pip/lib/python3.7/site-packages/googleapiclient/http.py", line 932, in execute
headers=self.headers,
File "/layers/google.python.pip/pip/lib/python3.7/site-packages/googleapiclient/http.py", line 222, in _retry_request
raise exception
File "/layers/google.python.pip/pip/lib/python3.7/site-packages/googleapiclient/http.py", line 191, in _retry_request
resp, content = http.request(uri, method, *args, **kwargs)
File "/layers/google.python.pip/pip/lib/python3.7/site-packages/google_auth_httplib2.py", line 225, in request
**kwargs
File "/layers/google.python.pip/pip/lib/python3.7/site-packages/httplib2/__init__.py", line 1721, in request
conn, authority, uri, request_uri, method, body, headers, redirections, cachekey,
File "/layers/google.python.pip/pip/lib/python3.7/site-packages/httplib2/__init__.py", line 1440, in _request
(response, content) = self._conn_request(conn, request_uri, method, body, headers)
File "/layers/google.python.pip/pip/lib/python3.7/site-packages/httplib2/__init__.py", line 1392, in _conn_request
response = conn.getresponse()
File "/layers/google.python.runtime/python/lib/python3.7/http/client.py", line 1373, in getresponse
response.begin()
File "/layers/google.python.runtime/python/lib/python3.7/http/client.py", line 319, in begin
version, status, reason = self._read_status()
File "/layers/google.python.runtime/python/lib/python3.7/http/client.py", line 280, in _read_status
line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
File "/layers/google.python.runtime/python/lib/python3.7/socket.py", line 589, in readinto
return self._sock.recv_into(b)
File "/layers/google.python.runtime/python/lib/python3.7/ssl.py", line 1071, in recv_into
return self.read(nbytes, buffer)
File "/layers/google.python.runtime/python/lib/python3.7/ssl.py", line 929, in read
return self._sslobj.read(len, buffer)
ssl.SSLError: [SSL: DECRYPTION_FAILED_OR_BAD_RECORD_MAC] decryption failed or bad record mac (_ssl.c:2570)",
}

i am trying to unload data from snowflake internal stage to unix file path using COPY INTO and GET command, but getting error

I am running all the sql scripts under the scripts path in a for loop and copying the data into #priya_stage area in snowflake and then using GET command , i am unloading data from stage area to my Unix path in csv format. But I am getting error.
Note: this same code works on my MAC but not on unix server.
import logging
import os
import snowflake.connector
from snowflake.connector import DictCursor as dict
from os import walk
try:
conn = snowflake.connector.connect(
account = 'xxx' ,
user = 'xxx' ,
password = 'xxx' ,
database = 'xxx' ,
schema = 'xxx' ,
warehouse = 'xxx' ,
role = 'xxx' ,
)
conn.cursor().execute('USE WAREHOUSE xxx')
conn.cursor().execute('USE DATABASE xxx')
conn.cursor().execute('USE SCHEMA xxx')
take = []
scripts = '/xxx/apps/xxx/xxx/scripts/snow/scripts/'
os.chdir('/xxx/apps/xxx/xxx/scripts/snow/scripts/')
for root , dirs , files in walk(scripts):
for file in files:
inbound = file[0:-4]
sql = open(file , 'r').read()
# file_number = 0
# file_number += 1
file_prefix = 'bridg_' + inbound
file_name = file_prefix
result_query = conn.cursor(dict).execute(sql)
query_id = result_query.sfqid
sql_copy_into = f'''
copy into #priya_stage/{file_name}
from (SELECT * FROM TABLE(RESULT_SCAN('{query_id}')))
DETAILED_OUTPUT = TRUE
HEADER = TRUE
SINGLE = FALSE
OVERWRITE = TRUE
max_file_size=4900000000'''
rs_copy_into = conn.cursor(dict).execute(sql_copy_into)
for row_copy in rs_copy_into:
file_name_in_stage = row_copy["FILE_NAME"]
sql_get_to_local = f"""
GET #priya_stage/{file_name_in_stage} file:///xxx/apps/xxx/xxx/inbound/zip_files/{inbound}/"""
rs_get_to_local = conn.cursor(dict).execute(sql_get_to_local)
except snowflake.connector.errors.ProgrammingError as e:
print('Error {0} ({1}): {2} ({3})'.format(e.errno , e.sqlstate , e.msg , e.sfqid))
finally:
conn.cursor().close()
conn.close()
Error
Traceback (most recent call last):
File "Generic_local.py", line 52, in <module>
rs_get_to_local = conn.cursor(dict).execute(sql_get_to_local)
File "/usr/local/lib64/python3.6/site-packages/snowflake/connector/cursor.py", line
746, in execute
sf_file_transfer_agent.execute()
File "/usr/local/lib64/python3.6/site-
packages/snowflake/connector/file_transfer_agent.py", line 379, in execute
self._transfer_accelerate_config()
File "/usr/local/lib64/python3.6/site-
packages/snowflake/connector/file_transfer_agent.py", line 671, in
_transfer_accelerate_config
self._use_accelerate_endpoint = client.transfer_accelerate_config()
File "/usr/local/lib64/python3.6/site-
packages/snowflake/connector/s3_storage_client.py", line 572, in
transfer_accelerate_config
url=url, verb="GET", retry_id=retry_id, query_parts=dict(query_parts)
File "/usr/local/lib64/python3.6/site-
packages/snowflake/connector/s3_storage_client.py", line 353, in _.
send_request_with_authentication_and_retry
verb, generate_authenticated_url_and_args_v4, retry_id
File "/usr/local/lib64/python3.6/site-
packages/snowflake/connector/storage_client.py", line 313, in
_send_request_with_retry
f"{verb} with url {url} failed for exceeding maximum retries."
snowflake.connector.errors.RequestExceedMaxRetryError: GET with url b'https://xxx-
xxxxx-xxx-x-customer-stage.xx.amazonaws.com/https://xxx-xxxxx-xxx-x-customer-
stage.xx.amazonaws.com/?accelerate' failed for exceeding maximum retries.
This link redirects me to a error message .
https://xxx-
xxxxx-xxx-x-customer-stage.xx.amazonaws.com/https://xxx-xxxxx-xxx-x-customer-
stage.xx.amazonaws.com/?accelerate
Access Denied error :
<Error>
<Code>AccessDenied</Code>
<Message>Access Denied</Message>
<RequestId>1X1Z8G0BTX8BAHXK</RequestId>
<HostId>QqdCqaSK7ogAEq3sNWaQVZVXUGaqZnPv78FiflvVzkF6nSYXTSKu3iSiYlUOU0ka+0IMzErwGC4=</HostId>
</Error>

Unexpected keyword in sublime text 3 when using a package command

Introduction
I am developping a sublime text 3 package.
Suddenly, the command I am adding the the package broke. It throws every time the following error in the console:
Traceback (most recent call last):
File "C:\Program Files\Sublime Text 3\Lib\python33\sublime_plugin.py", line 1456, in run_
return self.run(**args)
TypeError: run() got an unexpected keyword argument 'redeploy_module'
This appears in "dirty" sublime as well as in clean state.
This happens when I add a list input handler.
This works
class ProjectNameInputHandler(sublime_plugin.TextInputHandler):
def placeholder(self):
return "Project's name - must already exist"
# def next_input(self, args):
# if 'module' not in args:
# return RedeployModuleInputHandler()
# class RedeployModuleInputHandler(sublime_plugin.ListInputHandler):
# def placeholder(self):
# return "Module to create template for"
# def list_items(self):
# return [("Manager (v1)", "manager"),
# ("Projects (v2)", "projects")]
class RedeployJobCommand(sublime_plugin.WindowCommand):
def run(self, project_name):
plugin_path = str(os.path.dirname(__file__))
template_cli = "\"{}\\template-python-cli\\cli.py\""\
.format(plugin_path)
folder = self.window.extract_variables()['folder']
args = "redeployJob {}".format(project_name)
command = "echo 'python {} {}'".format(template_cli, args)
self.window.run_command("exec", {
"shell_cmd": command,
"working_dir": folder
})
def input(self, args):
if 'project_name' not in args:
return ProjectNameInputHandler()
# elif 'module' not in args:
# return RedeployModuleInputHandler()
This does not work
import sublime_plugin
import os
class ProjectNameInputHandler(sublime_plugin.TextInputHandler):
def placeholder(self):
return "Project's name - must already exist"
def next_input(self, args):
if 'module' not in args:
return RedeployModuleInputHandler()
class RedeployModuleInputHandler(sublime_plugin.ListInputHandler):
def placeholder(self):
return "Module to create template for"
def list_items(self):
return [("Manager (v1)", "manager"),
("Projects (v2)", "projects")]
class RedeployJobCommand(sublime_plugin.WindowCommand):
def run(self, project_name, module):
plugin_path = str(os.path.dirname(__file__))
template_cli = "\"{}\\template-python-cli\\cli.py\""\
.format(plugin_path)
folder = self.window.extract_variables()['folder']
args = "redeployJob {}".format(project_name)
command = "echo 'python {} {}'".format(template_cli, args)
self.window.run_command("exec", {
"shell_cmd": command,
"working_dir": folder
})
def input(self, args):
if 'project_name' not in args:
return ProjectNameInputHandler()
elif 'module' not in args:
return RedeployModuleInputHandler()
It throws the error described in the introduction.
I do not understand why it does that. What I am doing wrong ?

In
def run(self, project_name, module):
rename module to redeploy_module
def run(self, project_name, redeploy_module):

python multiprocessing + peewee + postgresql fails with SSL error

I am trying to write a Python model which is capable of doing some processing in a PostgreSQL database using the multi-threading module and peewee.
In single core mode the code works, however, when I try to run the code with multiple cores I am running into a SSL error.
I would like to post the structure of my model in the hope that somebody can advice how to set of my model in a proper way. Currently, I have chosen to use an object oriented approach in which I make one connection which is shared in a pool. To clarify what I have done, I will now show the source code I have so far
I have three files: main.py, models.py and parser.py. The contents is the following
models.py defines the peewee postgresql table and makes a connection to the postgres server
import peewee as pw
from playhouse.pool import PooledPostgresqlExtDatabase
KVK_KEY = "id_number"
NAME_KEY = "name"
N_VOWELS_KEY = "n_vowels"
# initialise the data base
database = PooledPostgresqlExtDatabase(
"testdb", user="postgres", host="localhost", port=5432, password="xxxx",
max_connections=8, stale_timeout=300 )
class BaseModel(pw.Model):
class Meta:
database = database
only_save_dirty = True
# this class describes the format of the sql data base
class Company(BaseModel):
id_number = pw.IntegerField(primary_key=True)
name = pw.CharField(null=True)
n_vowels = pw.IntegerField(default=-1)
processor = pw.IntegerField(default=-1)
def connect_database(database_name, reset_database=False):
""" connect the database """
database.connect()
if reset_database:
database.drop_tables([Company])
database.create_tables([Company])
parser.py contains the CompanyParser class which is used as the engine of the code to do all the processing. It generates some artificial data which is stored to the postgresql database and then the run method is used to do some processing with the data already stored in the database
import pandas as pd
import numpy as np
import random
import string
import peewee as pw
from models import (Company, database, KVK_KEY, NAME_KEY)
import multiprocessing as mp
MAX_SQL_CHUNK = 1000
np.random.seed(0)
def random_name(size=8, chars=string.ascii_lowercase):
""" Create a random character string of 'size' characters """
return "".join(random.choice(chars) for _ in range(size))
def vowel_count(characters):
"""
Count the number of vowels in the string 'characters' and return as an integer
"""
count = 0
for char in characters:
if char in list("aeiou"):
count += 1
return count
class CompanyParser(mp.Process):
def __init__(self, number_of_companies=100, i_proc=None,
number_of_procs=1,
first_id=None, last_id=None):
if i_proc is not None and number_of_procs > 1:
mp.Process.__init__(self)
self.i_proc = i_proc
self.number_of_procs = number_of_procs
self.n_companies = number_of_companies
self.data_df: pd.DataFrame = None
self.first_id = first_id
self.last_id = last_id
def generate_data(self):
""" Create a dataframe with fake company data and id's """
id_list = np.random.randint(1000000, 9999999, self.n_companies)
company_list = np.array([random_name() for _ in range(self.n_companies)])
self.data_df = pd.DataFrame(data=np.vstack([id_list, company_list]).T,
columns=[KVK_KEY, NAME_KEY])
self.data_df.sort_values([KVK_KEY], inplace=True)
def store_to_database(self):
"""
Store the company data to a sql database
"""
record_list = list(self.data_df.to_dict(orient="index").values())
n_batch = int(len(record_list) / MAX_SQL_CHUNK) + 1
with database.atomic():
for cnt, batch in enumerate(pw.chunked(record_list, MAX_SQL_CHUNK)):
print(f"writing {cnt}/{n_batch}")
Company.insert_many(batch).execute()
def run(self):
print("Making query at {}".format(self.i_proc))
query = (Company.
select().
where(Company.id_number.between(self.first_id, self.last_id)))
print("Found {} companies".format(query.count()))
for cnt, company in enumerate(query):
print("Processing # {} - {}: company {}/{}".format(self.i_proc, cnt,
company.id_number,
company.name))
number_of_vowels = vowel_count(company.name)
company.n_vowels = number_of_vowels
company.processor = self.i_proc
print(f"storing number of vowels: {number_of_vowels}")
company.save()
Finally, my main script load the class stored in the models.py and parser.py and launches the code.
from models import (Company, connect_database)
from parser import CompanyParser
number_of_processors = 2
connect_database(None, reset_database=True)
# init an object of the CompanyParser and use the create database
parser = CompanyParser()
company_ids = Company.select(Company.id_number)
parser.generate_data()
parser.store_to_database()
n_companies = company_ids.count()
n_comp_per_proc = int(n_companies / number_of_processors)
print("Found {} companies: {} per proc".format(n_companies, n_comp_per_proc))
for i_proc in range(number_of_processors):
i_start = i_proc * n_comp_per_proc
first_id = company_ids[i_start]
last_id = company_ids[i_start + n_comp_per_proc - 1]
print(f"Running proc {i_proc} for id {first_id} until id {last_id}")
sub_parser = CompanyParser(first_id=first_id, last_id=last_id,
i_proc=i_proc,
number_of_procs=number_of_processors)
if number_of_processors > 1:
sub_parser.start()
else:
sub_parser.run()
In case that the number_of_processors = 1 this script works perfectly fine. It generates artificial data, stores it to the PostgreSQL database and does some processing on the data (it counts the number of vowels in the name and stores it to the n_vowels column)
However, in case I am trying to run this with 2 cores with number_of_processors = 2, I run into the following error
/opt/miniconda3/bin/python /home/eelco/PycharmProjects/multiproc_peewee/main.py
writing 0/1
Found 100 companies: 50 per proc
Running proc 0 for id 1020737 until id 5295565
Running proc 1 for id 5302405 until id 9891087
Making query at 0
Found 50 companies
Processing # 0 - 0: company 1020737/wqrbgxiu
storing number of vowels: 2
Making query at 1
Process CompanyParser-1:
Processing # 0 - 1: company 1086107/lkbagrbc
storing number of vowels: 1
Processing # 0 - 2: company 1298367/nsdjsqio
storing number of vowels: 2
Traceback (most recent call last):
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2714, in execute_sql
cursor.execute(sql, params or ())
psycopg2.OperationalError: SSL error: sslv3 alert bad record mac
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/opt/miniconda3/lib/python3.7/multiprocessing/process.py", line 297, in _bootstrap
self.run()
File "/home/eelco/PycharmProjects/multiproc_peewee/parser.py", line 82, in run
company.save()
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 5748, in save
rows = self.update(**field_dict).where(self._pk_expr()).execute()
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1625, in inner
return method(self, database, *args, **kwargs)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1696, in execute
return self._execute(database)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2121, in _execute
cursor = database.execute(self)
File "/opt/miniconda3/lib/python3.7/site-packages/playhouse/postgres_ext.py", line 468, in execute
cursor = self.execute_sql(sql, params, commit=commit)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2721, in execute_sql
self.commit()
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2512, in __exit__
reraise(new_type, new_type(*exc_args), traceback)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 186, in reraise
raise value.with_traceback(tb)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2714, in execute_sql
cursor.execute(sql, params or ())
peewee.OperationalError: SSL error: sslv3 alert bad record mac
Process CompanyParser-2:
Traceback (most recent call last):
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2714, in execute_sql
cursor.execute(sql, params or ())
psycopg2.OperationalError: SSL error: decryption failed or bad record mac
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/opt/miniconda3/lib/python3.7/multiprocessing/process.py", line 297, in _bootstrap
self.run()
File "/home/eelco/PycharmProjects/multiproc_peewee/parser.py", line 72, in run
print("Found {} companies".format(query.count()))
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1625, in inner
return method(self, database, *args, **kwargs)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1881, in count
return Select([clone], [fn.COUNT(SQL('1'))]).scalar(database)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1625, in inner
return method(self, database, *args, **kwargs)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1866, in scalar
row = self.tuples().peek(database)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1625, in inner
return method(self, database, *args, **kwargs)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1853, in peek
rows = self.execute(database)[:n]
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1625, in inner
return method(self, database, *args, **kwargs)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1696, in execute
return self._execute(database)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 1847, in _execute
cursor = database.execute(self)
File "/opt/miniconda3/lib/python3.7/site-packages/playhouse/postgres_ext.py", line 468, in execute
cursor = self.execute_sql(sql, params, commit=commit)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2721, in execute_sql
self.commit()
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2512, in __exit__
reraise(new_type, new_type(*exc_args), traceback)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 186, in reraise
raise value.with_traceback(tb)
File "/opt/miniconda3/lib/python3.7/site-packages/peewee.py", line 2714, in execute_sql
cursor.execute(sql, params or ())
peewee.OperationalError: SSL error: decryption failed or bad record mac
Process finished with exit code 0
Somehow something goes wrong as soon as the second thread start to do something with the database. Does somebody has advice to get this code working. I have tried the following already
Try the PooledPostgresDatabase and normal PostgresqlDatabase to
connect to the database. This leads to the same error
Try using sqlite in stead of postgres. This works for 2 cores, but only if the two processes are not interfering too much; otherwise I
can some locking problems. I was in the impression that postgres
would be better for doing multiprocessing then sqlite (is that true?)
When putting a break after launching the first process(so effectively using only one core), the code works, showing that the start method is called correctly.
Hopefully somebody can advise.
Regards
Eelco

After some searching on the internet today I found the solution for my problem here:github.com/coleifer. As coleifer mentions: you apparently first have to set up all the forks before you start connecting to the database. Based on this idea I have modified my code and it is working now.
For those interested I will post my python scripts again so you can see how I did it. This because I there is not so much explicit examples out there, so perhaps it may help others.
First of all, all the database and peewee modules are now moved into initialization functions which are only called inside the constructor of the CompanyParser class.
So models.py looks like
import peewee as pw
from playhouse.pool import PooledPostgresqlExtDatabase, PostgresqlDatabase, PooledPostgresqlDatabase
KVK_KEY = "id_number"
NAME_KEY = "name"
N_VOWELS_KEY = "n_vowels"
def init_database():
db = PooledPostgresqlDatabase(
"testdb", user="postgres", host="localhost", port=5432, password="xxxxx",
max_connections=8, stale_timeout=300)
return db
def init_models(db, reset_tables=False):
class BaseModel(pw.Model):
class Meta:
database = db
# this class describes the format of the sql data base
class Company(BaseModel):
id_number = pw.IntegerField(primary_key=True)
name = pw.CharField(null=True)
n_vowels = pw.IntegerField(default=-1)
processor = pw.IntegerField(default=-1)
if db.is_closed():
db.connect()
if reset_tables and Company.table_exists():
db.drop_tables([Company])
db.create_tables([Company])
return Company
Then, the worker class CompanyParser is defined in the parser.py script and looks like this
import multiprocessing as mp
import random
import string
import numpy as np
import pandas as pd
import peewee as pw
from models import (KVK_KEY, NAME_KEY, init_database, init_models)
MAX_SQL_CHUNK = 1000
np.random.seed(0)
def random_name(size=32, chars=string.ascii_lowercase):
""" Create a random character string of 'size' characters """
return "".join(random.choice(chars) for _ in range(size))
def vowel_count(characters):
"""
Count the number of vowels in the string 'characters' and return as an integer
"""
count = 0
for char in characters:
if char in list("aeiou"):
count += 1
return count
class CompanyParser(mp.Process):
def __init__(self, reset_tables=False,
number_of_companies=100, i_proc=None,
number_of_procs=1, first_id=None, last_id=None):
if i_proc is not None and number_of_procs > 1:
mp.Process.__init__(self)
self.i_proc = i_proc
self.reset_tables = reset_tables
self.number_of_procs = number_of_procs
self.n_companies = number_of_companies
self.data_df: pd.DataFrame = None
self.first_id = first_id
self.last_id = last_id
# initialise the database and models
self.database = init_database()
self.Company = init_models(self.database, reset_tables=self.reset_tables)
def generate_data(self):
""" Create a dataframe with fake company data and id's and return the array of id's"""
id_list = np.random.randint(1000000, 9999999, self.n_companies)
company_list = np.array([random_name() for _ in range(self.n_companies)])
self.data_df = pd.DataFrame(data=np.vstack([id_list, company_list]).T,
columns=[KVK_KEY, NAME_KEY])
self.data_df.drop_duplicates([KVK_KEY], inplace=True)
self.data_df.sort_values([KVK_KEY], inplace=True)
return self.data_df[KVK_KEY].values
def store_to_database(self):
"""
Store the company data to a sql database
"""
record_list = list(self.data_df.to_dict(orient="index").values())
n_batch = int(len(record_list) / MAX_SQL_CHUNK) + 1
with self.database.atomic():
for cnt, batch in enumerate(pw.chunked(record_list, MAX_SQL_CHUNK)):
print(f"writing {cnt}/{n_batch}")
self.Company.insert_many(batch).execute()
def run(self):
query = (self.Company.
select().
where(self.Company.id_number.between(self.first_id, self.last_id)))
for cnt, company in enumerate(query):
print("Processing # {} - {}: company {}/{}".format(self.i_proc, cnt, company.id_number,
company.name))
number_of_vowels = vowel_count(company.name)
company.n_vowels = number_of_vowels
company.processor = self.i_proc
try:
company.save()
except (pw.OperationalError, pw.InterfaceError) as err:
print("failed save for {} {}: {}".format(self.i_proc, cnt, err))
else:
pass
Finally, the main.py script which launches the processes:
from parser import CompanyParser
import time
def main():
number_of_processors = 2
number_of_companies = 10000
parser = CompanyParser(number_of_companies=number_of_companies, reset_tables=True)
company_ids = parser.generate_data()
parser.store_to_database()
n_companies = company_ids.size
n_comp_per_proc = int(n_companies / number_of_processors)
print("Found {} companies: {} per proc".format(n_companies, n_comp_per_proc))
if not parser.database.is_closed():
parser.database.close()
processes = list()
for i_proc in range(number_of_processors):
i_start = i_proc * n_comp_per_proc
first_id = company_ids[i_start]
last_id = company_ids[i_start + n_comp_per_proc - 1]
print(f"Running proc {i_proc} for id {first_id} until id {last_id}")
sub_parser = CompanyParser(first_id=first_id, last_id=last_id, i_proc=i_proc,
number_of_procs=number_of_processors)
if number_of_processors > 1:
sub_parser.start()
else:
sub_parser.run()
processes.append(sub_parser)
# this blocks the script until all processes are done
for job in processes:
job.join()
# make sure all the connections are closed
for i_proc in range(number_of_processors):
db = processes[i_proc].database
if not db.is_closed():
db.close()
print("Goodbye!")
if __name__ == "__main__":
start = time.time()
main()
duration = time.time() - start
print(f"Done in {duration} s")
As you can see, the database connection is done per process inside the class.
This example works and is a full example of multiprocessing + peewee and PostgreSQL. Hopefully this may help others. In case you have any comments or suggestions for improvement please let me know.

I did get this error too but with flask + peewee + rq in Heroku. Below is how I solved it:
If you have a simple app that you use with RQ, I would suggest to use SimpleWorker
RQ suggest to use rq.worker.HerokuWorker but I still received a ssl error with this.
The error appeared in a case where I have created a follow-up(chain) tasks, where execution of 1 depends on another tasks success.
Also I am using flask-rq2 but applies to normal usage as well as shown below:
# app.py
app = Flask(__name__)
app.config['RQ_WORKER_CLASS'] = os.getenv('RQ_WORKER_CLASS', 'rq.worker.Worker')
rq = RQ(app)
I solved it by changing the following in heroku config:
set your RQ_WORKER_CLASS to rq.worker.SimpleWorker

Unable to create filterPolicy on DVS port on vCenter (VMWare)

I am tring to make script controlling firewall rules on DVS ports.
Here is my script(I have tried to post only relevant part, but even it big enough):
#!/usr/bin/evn python
import sys
import pprint
from oslo.vmware import api as vmware_api
from oslo.vmware import vim_util
vcenter_host = 'vcenter-hostname.tld'
vcenter_login = 'login'
vcenter_password = 'password'
vcenter_retry_count = 4
vcenter_retry_interval = 2
def main():
vcenter = _make_connect()
dvs = _lookup_dvs(vcenter, 'dvSwitch')
port = _lookup_dvs_port(vcenter, dvs, '4853')
spec_factory = vcenter.vim.client.factory
port_spec = spec_factory.create('ns0:DVPortConfigSpec')
port_spec.operation = 'edit'
port_spec.key = port.key
port_spec.configVersion = port.config.configVersion
port_spec.setting = port_setting = spec_factory.create('ns0:DVPortSetting')
port_setting.filterPolicy = filter_policy = spec_factory.create(
'ns0:DvsFilterPolicy')
filter_policy.filterConfig.append(spec_factory.create(
'ns0:DvsTrafficFilterConfig'))
filter_policy.inherited = False
filter_config = filter_policy.filterConfig[0]
filter_config.agentName = "custom-dvs-firewall-agent"
filter_config.inherited = False
filter_config.trafficRuleset = traffic_ruleset = spec_factory.create(
'ns0:DvsTrafficRuleset')
traffic_ruleset.enabled = True
traffic_ruleset.rules.append(spec_factory.create('ns0:DvsTrafficRule'))
rule = traffic_ruleset.rules[0]
rule.description = "Port rule 0"
rule.sequence = 10
rule.direction = "incomingPackets"
rule.action = spec_factory.create('ns0:DvsDropNetworkRuleAction')
rule.qualifier.append(spec_factory.create('ns0:DvsIpNetworkRuleQualifier'))
match = rule.qualifier[0]
match.protocol = proto = spec_factory.create('ns0:IntExpression')
proto.value = 6
proto.negate = False
match.destinationIpPort = port = spec_factory.create('ns0:DvsSingleIpPort')
port.portNumber = 50001
port.negate = False
# import pdb; pdb.set_trace()
task = vcenter.invoke_api(
vcenter.vim,
'ReconfigureDVPort_Task',
dvs, port=[port_spec]
)
result = vcenter.wait_for_task(task)
pprint.pprint(result)
def _make_connect():
return vmware_api.VMwareAPISession(
vcenter_host,
vcenter_login,
vcenter_password,
vcenter_retry_count,
vcenter_retry_interval)
def _lookup_dvs(vcenter, name):
network_folder = _lookup_net_folder(vcenter)
networks = vcenter.invoke_api(
vim_util, 'get_object_property', vcenter.vim,
network_folder, 'childEntity').ManagedObjectReference
for dvs in _filter_objects_by_type(
networks, 'VmwareDistributedVirtualSwitch'):
dvs_name = vcenter.invoke_api(
vim_util, 'get_object_property',
vcenter.vim, dvs, 'name')
if dvs_name != name:
continue
break
else:
raise RuntimeError('DVS name=="{}" not found'.format(name))
return dvs
def _lookup_dvs_port(vcenter, dvs, port_key):
spec_factory = vcenter.vim.client.factory
criteria = spec_factory.create(
'ns0:DistributedVirtualSwitchPortCriteria')
criteria.portKey = port_key
try:
port = vcenter.invoke_api(
vcenter.vim, 'FetchDVPorts', dvs, criteria=criteria)[0]
except IndexError:
raise RuntimeError('DVS port key=="{}" not found'.format(port_key))
return port
def _lookup_net_folder(vcenter):
dc = _lookup_datacenter(vcenter)
return vcenter.invoke_api(
vim_util, 'get_object_property', vcenter.vim,
dc, 'networkFolder')
def _lookup_datacenter(vcenter):
return vcenter.invoke_api(
vim_util, 'get_objects', vcenter.vim,
'Datacenter', 100, ['name']).objects[0].obj
def _filter_objects_by_type(sequence, value):
return (obj for obj in sequence
if obj._type == value)
if __name__ == '__main__':
sys.exit(main())
results:
Traceback (most recent call last):
File "_dev_/dvs-port-filterPolicy.py", line 137, in <module>
sys.exit(main())
File "_dev_/dvs-port-filterPolicy.py", line 70, in main
result = vcenter.wait_for_task(task)
File "/home/dbogun/.venv/cisco0-neutron/lib/python2.7/site-packages/oslo_vmware/api.py", line 380, in wait_for_task
return evt.wait()
File "/home/dbogun/.venv/cisco0-neutron/lib/python2.7/site-packages/eventlet/event.py", line 121, in wait
return hubs.get_hub().switch()
File "/home/dbogun/.venv/cisco0-neutron/lib/python2.7/site-packages/eventlet/hubs/hub.py", line 294, in switch
return self.greenlet.switch()
File "/home/dbogun/.venv/cisco0-neutron/lib/python2.7/site-packages/oslo_vmware/common/loopingcall.py", line 76, in _inner
self.f(*self.args, **self.kw)
File "/home/dbogun/.venv/cisco0-neutron/lib/python2.7/site-packages/oslo_vmware/api.py", line 397, in _poll_task
'info')
File "/home/dbogun/.venv/cisco0-neutron/lib/python2.7/site-packages/oslo_vmware/api.py", line 341, in invoke_api
return _invoke_api(module, method, *args, **kwargs)
File "/home/dbogun/.venv/cisco0-neutron/lib/python2.7/site-packages/oslo_vmware/api.py", line 122, in func
return evt.wait()
File "/home/dbogun/.venv/cisco0-neutron/lib/python2.7/site-packages/eventlet/event.py", line 121, in wait
return hubs.get_hub().switch()
File "/home/dbogun/.venv/cisco0-neutron/lib/python2.7/site-packages/eventlet/hubs/hub.py", line 294, in switch
return self.greenlet.switch()
File "/home/dbogun/.venv/cisco0-neutron/lib/python2.7/site-packages/oslo_vmware/common/loopingcall.py", line 123, in _inner
idle = self.f(*self.args, **self.kw)
File "/home/dbogun/.venv/cisco0-neutron/lib/python2.7/site-packages/oslo_vmware/api.py", line 95, in _func
result = f(*args, **kwargs)
File "/home/dbogun/.venv/cisco0-neutron/lib/python2.7/site-packages/oslo_vmware/api.py", line 324, in _invoke_api
raise clazz(six.text_type(excep), excep.details)
oslo_vmware.exceptions.VMwareDriverException: The object has already been deleted or has not been completely created
Cause: Server raised fault: 'The object has already been deleted or has not been completely created'
Faults: [ManagedObjectNotFound]
Details: {'obj': 'task-5189'}
PortGroup config's trafficFilterOverrideAllowed option must be set to True. Or you get "oslo_vmware.exceptions.VMwareDriverException: A specified parameter was not correct.\nfilterPolicy". What is completely unusable and give absolutely no information about real problem.
Can point me on error in my understanding of this task? Or maybe someone have example of similar script?
PS: vCenter v5.5

You have to set:
filter_config.agentName = "dvfilter-generic-vmware"
I don't know why, but only with this agent name dvs apply ACL rules.