def test_pop_db_memory(self):
"Test pop_db data memory usage"
print ""
pop_db = PopDBService(self.config)
api = 'getDSdata'
sitename = 'summary'
aggr = 'day'
n = 200000
orderby = 'totcpu'
tstart = datetime_to_string(datetime_day(datetime.datetime.utcnow() - datetime.timedelta(days=10)))
tstop = datetime_to_string(datetime_day(datetime.datetime.utcnow()))
params = {'sitename':sitename, 'tstart':tstart, 'tstop':tstop, 'aggr':aggr, 'n':n, 'orderby':orderby}
pop_db_data = pop_db.fetch(api=api, params=params, cache=False)
total_size = total_size_of(pop_db_data)
logger.info('Total size of Pop DB data in memory is %d bytes (%dMB)', total_size, total_size/10**6)
def test_pop_db_memory(self):
"Test pop_db data memory usage"
print ""
pop_db = PopDBService(self.config)
api = 'getDSdata'
sitename = 'summary'
aggr = 'day'
n = 200000
orderby = 'totcpu'
tstart = datetime_to_string(datetime_day(datetime.datetime.utcnow() - datetime.timedelta(days=10)))
tstop = datetime_to_string(datetime_day(datetime.datetime.utcnow()))
params = {'sitename':sitename, 'tstart':tstart, 'tstop':tstop, 'aggr':aggr, 'n':n, 'orderby':orderby}
pop_db_data = pop_db.fetch(api=api, params=params, cache=False)
total_size = total_size_of(pop_db_data)
logger.info('Total size of Pop DB data in memory is %d bytes (%dMB)', total_size, total_size/10**6)
def get_site_popularity(self, site_name, date=datetime_day(datetime.datetime.utcnow())):
"""
Get popularity for site
"""
# get all datasets with a replica at the site and how many replicas it has
coll = 'dataset_data'
pipeline = list()
match = {'$match':{'replicas':site_name}}
pipeline.append(match)
project = {'$project':{'name':1, '_id':0}}
pipeline.append(project)
data = self.storage.get_data(coll=coll, pipeline=pipeline)
popularity = 0.0
dataset_names = [dataset_data['name'] for dataset_data in data]
# get the popularity of the dataset and decide by number of replicas
coll = 'dataset_rankings'
pipeline = list()
match = {'$match':{'date':date}}
pipeline.append(match)
match = {'$match':{'name':{'$in':dataset_names}}}
pipeline.append(match)
group = {'$group':{'_id':'$date', 'total_popularity':{'$sum':'$popularity'}}}
pipeline.append(group)
project = {'$project':{'total_popularity':1, '_id':0}}
pipeline.append(project)
data = self.storage.get_data(coll=coll, pipeline=pipeline)
try:
popularity = data[0]['total_popularity']
except:
popularity = 0.0
return popularity
def update_db(self):
"""
Fetch latest popularity data not in database
"""
# get dates
coll = 'dataset_popularity'
pipeline = list()
sort = {'$sort':{'date':-1}}
pipeline.append(sort)
limit = {'$limit':1}
pipeline.append(limit)
project = {'$project':{'date':1, '_id':0}}
pipeline.append(project)
data = self.storage.get_data(coll=coll, pipeline=pipeline)
try:
start_date = data[0]['date']
except:
self.logger.warning('Popularity needs to be initiated')
self.initiate_db()
return
q = Queue.Queue()
for i in range(self.MAX_THREADS):
worker = threading.Thread(target=self.insert_popularity_data, args=(i, q))
worker.daemon = True
worker.start()
start_date = start_date + datetime.timedelta(days=1)
end_date = datetime_day(datetime.datetime.utcnow())
# fetch popularity data
t1 = datetime.datetime.utcnow()
for date in daterange(start_date, end_date):
q.put(date)
q.join()
t2 = datetime.datetime.utcnow()
td = t2 - t1
self.logger.info('Updating Pop DB data took %s', str(td))
def get_site_rankings(self, date=datetime_day(datetime.datetime.utcnow())):
"""
Generate site rankings
"""
# get all sites which can be replicated to
site_names = self.sites.get_available_sites()
site_rankings = dict()
for site_name in site_names:
# get popularity
popularity = self.get_site_popularity(site_name, date)
# get cpu and storage (performance)
performance = self.sites.get_performance(site_name)
# get available storage
available_storage_tb = self.sites.get_available_storage(site_name)/10**3
if available_storage_tb <= 0:
available_storage_tb = 0
else:
available_storage_tb = 1
#calculate rank
try:
rank = (performance*available_storage_tb)/popularity
except:
rank = 0.0
# store into dict
site_rankings[site_name] = rank
# insert into database
coll = 'site_rankings'
query = {'name':site_name, 'date':date}
data = {'$set':{'name':site_name, 'date':date, 'rank':rank, 'popularity':popularity}}
self.storage.update_data(coll=coll, query=query, data=data, upsert=True)
return site_rankings
def get_site_popularity(self, site_name):
"""
Get delta popularity for site
"""
date = datetime_day(datetime.datetime.utcnow())
# get all datasets with a replica at the site and how many replicas it has
coll = 'dataset_data'
pipeline = list()
match = {'$match':{'replicas':site_name}}
pipeline.append(match)
project = {'$project':{'name':1, '_id':0}}
pipeline.append(project)
data = self.storage.get_data(coll=coll, pipeline=pipeline)
popularity = 0.0
for dataset in data:
dataset_name = dataset['name']
# get the popularity of the dataset and dicide by number of replicas
coll = 'dataset_popularity'
pipeline = list()
match = {'$match':{'name':dataset_name, 'date':date}}
pipeline.append(match)
project = {'$project':{'delta_popularity':1, '_id':0}}
pipeline.append(project)
data = self.storage.get_data(coll=coll, pipeline=pipeline)
popularity += data[0]['delta_popularity']
return popularity
def insert_cache(self, coll, api, params=dict(), data=dict()):
"""
Insert data into collection
Collection should be the service it is caching data for
Use update to have the possibility to force cache update
"""
result = list()
db_coll = self.db[coll]
object_id = get_object_id(str(api)+str(params))
data['_id'] = object_id
data['datetime'] = datetime_day(datetime.datetime.utcnow())
for i in range(2):
try:
result = db_coll.replace_one({'_id':object_id}, data, upsert=True)
except DocumentTooLarge:
self.logger.warning('DocumentTooLarge error for %s api %s', coll, api)
break
except AutoReconnect:
call(["start_mongodb", self.OPT_PATH])
continue
else:
if (result.modified_count == 0) and (not result.upserted_id):
self.logger.debug('Failed to insert %s cache for api %s\n\tData: %s', coll, api, str(data))
break
else:
self.logger.error("Couldn't establish connection to mongodb server %s", self.URI)
return result
def site_rankings(self):
"""
Generate site rankings
"""
date = datetime_day(datetime.datetime.utcnow())
# get all sites which can be replicated to
site_names = self.sites.get_available_sites()
site_rankings = dict()
for site_name in site_names:
# get popularity
popularity = float(self.get_site_popularity(site_name))
# get cpu and storage (performance)
performance = float(self.sites.get_performance(site_name))
# get available storage
available_storage = float(self.sites.get_available_storage(site_name))
if available_storage <= 0:
available_storage = 0.0
# insert into database
coll = 'site_popularity'
query = {'name':site_name, 'date':date}
data = {'$set':{'name':site_name, 'date':date, 'delta_popularity':popularity, 'performance':performance, 'available_storage':available_storage}}
self.storage.update_data(coll=coll, query=query, data=data, upsert=True)
#calculate rank
try:
rank = (performance*available_storage)/popularity
except:
rank = 0.0
# store into dict
site_rankings[site_name] = rank
# insert into database
coll = 'site_rankings'
query = {'name':site_name, 'date':date}
data = {'$set':{'name':site_name, 'date':date, 'delta_rank':rank}}
self.storage.update_data(coll=coll, query=query, data=data, upsert=True)
return site_rankings
def subscribe(self, subscriptions):
"""
Make subscriptions to phedex
subscriptions = [(dataset_name, site_name), ...]
"""
new_subscriptions = dict()
for subscription in subscriptions:
dataset_name = subscription[0]
site_name = subscription[1]
try:
new_subscriptions[site_name].append(dataset_name)
except:
new_subscriptions[site_name] = list()
new_subscriptions[site_name].append(dataset_name)
for site_name, dataset_names in new_subscriptions.items():
data = self.phedex.generate_xml(dataset_names)
comments = (
"This dataset is predicted to become popular and has therefore been automatically replicated by cuadrnt"
)
api = "subscribe"
params = [
("node", site_name),
("data", data),
("level", "dataset"),
("move", "n"),
("custodial", "n"),
("group", "AnalysisOps"),
("request_only", "n"),
("no_mail", "n"),
("comments", comments),
]
json_data = self.phedex.fetch(api=api, params=params, method="post")
# insert into db
group_name = "AnalysisOps"
request_id = 0
request_type = 0
try:
request = json_data["phedex"]
request_id = request["request_created"][0]["id"]
request_created = timestamp_to_datetime(request["request_timestamp"])
except:
self.logger.warning(
"Subscription did not succeed\n\tSite:%s\n\tDatasets: %s", str(site_name), str(dataset_names)
)
continue
for dataset_name in dataset_names:
coll = "dataset_rankings"
date = datetime_day(datetime.datetime.utcnow())
pipeline = list()
match = {"$match": {"name": dataset_name, "date": date}}
pipeline.append(match)
project = {"$project": {"delta_rank": 1, "_id": 0}}
pipeline.append(project)
data = self.storage.get_data(coll=coll, pipeline=pipeline)
dataset_rank = data[0]["delta_rank"]
query = "INSERT INTO Requests(RequestId, RequestType, DatasetId, SiteId, GroupId, Rank, Date) SELECT %s, %s, Datasets.DatasetId, Sites.SiteId, Groups.GroupId, %s, %s FROM Datasets, Sites, Groups WHERE Datasets.DatasetName=%s AND Sites.SiteName=%s AND Groups.GroupName=%s"
values = (request_id, request_type, dataset_rank, request_created, dataset_name, site_name, group_name)
self.mit_db.query(query=query, values=values, cache=False)
def initiate_db(self):
"""
Collect popularity data
"""
q = Queue.Queue()
for i in range(self.MAX_THREADS):
worker = threading.Thread(target=self.insert_popularity_data, args=(i, q))
worker.daemon = True
worker.start()
start_date = datetime_day(datetime.datetime.utcnow() - datetime.timedelta(days=90))
end_date = datetime_day(datetime.datetime.utcnow())
# fetch popularity data
t1 = datetime.datetime.utcnow()
for date in daterange(start_date, end_date):
q.put(date)
q.join()
t2 = datetime.datetime.utcnow()
td = t2 - t1
self.logger.info('Inserting Pop DB data took %s', str(td))
def get_dataset_popularity(self, dataset_name):
"""
Get delta popularity for dataset
"""
coll = 'dataset_popularity'
start_date = datetime_day(datetime.datetime.utcnow()) - datetime.timedelta(days=14)
end_date = datetime_day(datetime.datetime.utcnow()) - datetime.timedelta(days=8)
pipeline = list()
match = {'$match':{'name':dataset_name}}
pipeline.append(match)
match = {'$match':{'date':{'$gte':start_date, '$lte':end_date}}}
pipeline.append(match)
group = {'$group':{'_id':'$name', 'old_popularity':{'$sum':{'$multiply':['$n_accesses', '$n_cpus']}}}}
pipeline.append(group)
data = self.storage.get_data(coll=coll, pipeline=pipeline)
try:
old_pop = float(data[0]['old_popularity'])
except:
old_pop = 0.0
start_date = datetime_day(datetime.datetime.utcnow()) - datetime.timedelta(days=7)
end_date = datetime_day(datetime.datetime.utcnow()) - datetime.timedelta(days=1)
pipeline = list()
match = {'$match':{'name':dataset_name}}
pipeline.append(match)
match = {'$match':{'date':{'$gte':start_date, '$lte':end_date}}}
pipeline.append(match)
group = {'$group':{'_id':'$name', 'new_popularity':{'$sum': {'$multiply':['$n_accesses', '$n_cpus']}}}}
pipeline.append(group)
data = self.storage.get_data(coll=coll, pipeline=pipeline)
try:
new_pop = float(data[0]['new_popularity'])
except:
new_pop = 0.0
delta_popularity = new_pop - old_pop
if delta_popularity > 1:
delta_popularity = log(delta_popularity)
else:
delta_popularity = 0.0
size_gb = self.datasets.get_size(dataset_name)
return delta_popularity/size_gb
def start(self, date=datetime_day(datetime.datetime.utcnow())):
"""
Begin Rocker Board Algorithm
"""
t1 = datetime.datetime.utcnow()
# Get goals
dataset_rankings = self.rankings.get_dataset_rankings(date)
site_rankings = self.rankings.get_site_rankings(date)
self.change_dataset_rankings(dataset_rankings)
subscriptions = self.replicate(dataset_rankings, site_rankings)
self.logger.info('SUBSCRIPTIONS')
for subscription in subscriptions:
self.logger.info('site: %s\tdataset: %s', subscription[1], subscription[0])
# self.subscribe(subscriptions)
t2 = datetime.datetime.utcnow()
td = t2 - t1
self.logger.info('Rocker Board took %s', str(td))
def dataset_rankings(self):
"""
Generate dataset rankings
"""
date = datetime_day(datetime.datetime.utcnow())
dataset_names = self.datasets.get_db_datasets()
dataset_rankings = dict()
coll = 'dataset_popularity'
for dataset_name in dataset_names:
delta_popularity = self.get_dataset_popularity(dataset_name)
# insert into database
query = {'name':dataset_name, 'date':date}
data = {'$set':{'delta_popularity':delta_popularity}}
self.storage.update_data(coll=coll, query=query, data=data, upsert=True)
# store into dict
dataset_rankings[dataset_name] = delta_popularity
return dataset_rankings
def insert_dbs_data(self, dataset_name):
"""
Fetch dbs data about dataset and insert into database
"""
api = 'datasets'
params = {'dataset':dataset_name, 'detail':True, 'dataset_access_type':'*'}
dbs_data = self.dbs.fetch(api=api, params=params)
dataset_data = get_json(dbs_data, 'data')[0]
ds_name = get_json(dataset_data, 'primary_ds_name')
physics_group = get_json(dataset_data, 'physics_group_name')
data_tier = get_json(dataset_data, 'data_tier_name')
creation_date = datetime_day(timestamp_to_datetime(get_json(dataset_data, 'creation_date')))
ds_type = get_json(dataset_data, 'primary_ds_type')
coll = 'dataset_data'
query = {'name':dataset_name}
data = {'$set':{'ds_name':ds_name, 'physics_group':physics_group, 'data_tier':data_tier, 'creation_date':creation_date, 'ds_type':ds_type}}
self.storage.update_data(coll=coll, query=query, data=data, upsert=False)
def get_dataset_rankings(self, date=datetime_day(datetime.datetime.utcnow())):
"""
Generate dataset rankings
"""
self.dataset_popularity = dict()
dataset_names = self.datasets.get_db_datasets()
q = Queue.Queue()
for i in range(self.MAX_THREADS):
worker = threading.Thread(target=self.get_dataset_popularity, args=(q,))
worker.daemon = True
worker.start()
# self.dataset_features = self.popularity.get_features(dataset_names, date)
# self.dataset_tiers = self.datasets.get_data_tiers(dataset_names)
for dataset_name in dataset_names:
q.put((dataset_name, date))
q.join()
dataset_rankings = self.normalize_popularity(date)
return dataset_rankings
def subscribe(self, subscriptions):
"""
Make subscriptions to phedex
subscriptions = [(dataset_name, site_name), ...]
"""
new_subscriptions = dict()
for subscription in subscriptions:
dataset_name = subscription[0]
site_name = subscription[1]
try:
new_subscriptions[site_name].append(dataset_name)
except:
new_subscriptions[site_name] = list()
new_subscriptions[site_name].append(dataset_name)
for site_name, dataset_names in new_subscriptions.items():
data = self.phedex.generate_xml(dataset_names)
comments = 'This dataset is predicted to become popular and has therefore been automatically replicated by cuadrnt'
api = 'subscribe'
params = [('node', site_name), ('data', data), ('level','dataset'), ('move', 'n'), ('custodial', 'n'), ('group', 'AnalysisOps'), ('request_only', 'n'), ('no_mail', 'n'), ('comments', comments)]
json_data = self.phedex.fetch(api=api, params=params, method='post')
# insert into db
group_name = 'AnalysisOps'
request_id = 0
request_type = 0
try:
request = json_data['phedex']
request_id = request['request_created'][0]['id']
request_created = timestamp_to_datetime(request['request_timestamp'])
except:
self.logger.warning('Subscription did not succeed\n\tSite:%s\n\tDatasets: %s', str(site_name), str(dataset_names))
continue
for dataset_name in dataset_names:
coll = 'dataset_rankings'
date = datetime_day(datetime.datetime.utcnow())
pipeline = list()
match = {'$match':{'name':dataset_name, 'date':date}}
pipeline.append(match)
project = {'$project':{'delta_rank':1, '_id':0}}
pipeline.append(project)
data = self.storage.get_data(coll=coll, pipeline=pipeline)
dataset_rank = data[0]['delta_rank']
query = "INSERT INTO Requests(RequestId, RequestType, DatasetId, SiteId, GroupId, Rank, Date) SELECT %s, %s, Datasets.DatasetId, Sites.SiteId, Groups.GroupId, %s, %s FROM Datasets, Sites, Groups WHERE Datasets.DatasetName=%s AND Sites.SiteName=%s AND Groups.GroupName=%s"
values = (request_id, request_type, dataset_rank, request_created, dataset_name, site_name, group_name)
self.mit_db.query(query=query, values=values, cache=False)
def subscribe(self, subscriptions):
"""
Make subscriptions to phedex
subscriptions = [(dataset_name, site_name), ...]
"""
new_subscriptions = dict()
for subscription in subscriptions:
dataset_name = subscription[0]
site_name = subscription[1]
try:
new_subscriptions[site_name].append(dataset_name)
except:
new_subscriptions[site_name] = list()
new_subscriptions[site_name].append(dataset_name)
for site_name, dataset_names in new_subscriptions.items():
data = self.phedex.generate_xml(dataset_names)
comments = 'This dataset is predicted to become popular and has therefore been automatically replicated by cuadrnt'
api = 'subscribe'
params = [('node', site_name), ('data', data), ('level','dataset'), ('move', 'n'), ('custodial', 'n'), ('group', 'AnalysisOps'), ('request_only', 'n'), ('no_mail', 'n'), ('comments', comments)]
json_data = self.phedex.fetch(api=api, params=params, method='post')
# insert into db
group_name = 'AnalysisOps'
request_id = 0
request_type = 0
try:
request = json_data['phedex']
request_id = request['request_created'][0]['id']
request_created = timestamp_to_datetime(request['request_timestamp'])
except:
self.logger.warning('Subscription did not succeed\n\tSite:%s\n\tDatasets: %s', str(site_name), str(dataset_names))
continue
for dataset_name in dataset_names:
coll = 'dataset_popularity'
date = datetime_day(datetime.datetime.utcnow())
pipeline = list()
match = {'$match':{'name':dataset_name, 'date':date}}
pipeline.append(match)
project = {'$project':{'delta_popularity':1, '_id':0}}
pipeline.append(project)
data = self.storage.get_data(coll=coll, pipeline=pipeline)
dataset_rank = data[0]['delta_popularity']
query = "INSERT INTO Requests(RequestId, RequestType, DatasetId, SiteId, GroupId, Rank, Date) SELECT %s, %s, Datasets.DatasetId, Sites.SiteId, Groups.GroupId, %s, %s FROM Datasets, Sites, Groups WHERE Datasets.DatasetName=%s AND Sites.SiteName=%s AND Groups.GroupName=%s"
values = (request_id, request_type, dataset_rank, request_created, dataset_name, site_name, group_name)
self.mit_db.query(query=query, values=values, cache=False)
def get_site_rankings(self, date=datetime_day(datetime.datetime.utcnow())):
"""
Generate site rankings
"""
# get all sites which can be replicated to
site_names = self.sites.get_available_sites()
site_rankings = dict()
for site_name in site_names:
# get popularity
popularity = self.get_site_popularity(site_name, date)
# get cpu and storage (performance)
performance = self.sites.get_performance(site_name)
# get available storage
available_storage_tb = self.sites.get_available_storage(
site_name) / 10**3
if available_storage_tb <= 0:
available_storage_tb = 0
else:
available_storage_tb = 1
#calculate rank
try:
rank = (performance * available_storage_tb) / popularity
except:
rank = 0.0
# store into dict
site_rankings[site_name] = rank
# insert into database
coll = 'site_rankings'
query = {'name': site_name, 'date': date}
data = {
'$set': {
'name': site_name,
'date': date,
'rank': rank,
'popularity': popularity
}
}
self.storage.update_data(coll=coll,
query=query,
data=data,
upsert=True)
return site_rankings
def get_dataset_rankings(self,
date=datetime_day(datetime.datetime.utcnow())):
"""
Generate dataset rankings
"""
self.dataset_popularity = dict()
dataset_names = self.datasets.get_db_datasets()
q = Queue.Queue()
for i in range(self.MAX_THREADS):
worker = threading.Thread(target=self.get_dataset_popularity,
args=(q, ))
worker.daemon = True
worker.start()
# self.dataset_features = self.popularity.get_features(dataset_names, date)
# self.dataset_tiers = self.datasets.get_data_tiers(dataset_names)
for dataset_name in dataset_names:
q.put((dataset_name, date))
q.join()
dataset_rankings = self.normalize_popularity(date)
return dataset_rankings
def get_site_popularity(self,
site_name,
date=datetime_day(datetime.datetime.utcnow())):
"""
Get popularity for site
"""
# get all datasets with a replica at the site and how many replicas it has
coll = 'dataset_data'
pipeline = list()
match = {'$match': {'replicas': site_name}}
pipeline.append(match)
project = {'$project': {'name': 1, '_id': 0}}
pipeline.append(project)
data = self.storage.get_data(coll=coll, pipeline=pipeline)
popularity = 0.0
dataset_names = [dataset_data['name'] for dataset_data in data]
# get the popularity of the dataset and decide by number of replicas
coll = 'dataset_rankings'
pipeline = list()
match = {'$match': {'date': date}}
pipeline.append(match)
match = {'$match': {'name': {'$in': dataset_names}}}
pipeline.append(match)
group = {
'$group': {
'_id': '$date',
'total_popularity': {
'$sum': '$popularity'
}
}
}
pipeline.append(group)
project = {'$project': {'total_popularity': 1, '_id': 0}}
pipeline.append(project)
data = self.storage.get_data(coll=coll, pipeline=pipeline)
try:
popularity = data[0]['total_popularity']
except:
popularity = 0.0
return popularity
def start(self, date=datetime_day(datetime.datetime.utcnow())):
"""
Begin Rocker Board Algorithm
"""
t1 = datetime.datetime.utcnow()
# Get goals
dataset_rankings = self.rankings.get_dataset_rankings(date)
site_rankings = self.rankings.get_site_rankings(date)
self.change_dataset_rankings(dataset_rankings)
subscriptions = self.replicate(dataset_rankings, site_rankings)
self.logger.info("SUBSCRIPTIONS")
for subscription in subscriptions:
self.logger.info("site: %s\tdataset: %s", subscription[1], subscription[0])
# site_storage = self.rankings.get_site_storage_rankings(subscriptions)
# deletions = self.clean(dataset_rankings, site_storage)
# self.logger.info('DELETIONS')
# for deletion in deletions:
# self.logger.info('site: %s\tdataset: %s', deletion[1], deletion[0])
# self.delete(deletions)
self.subscribe(subscriptions)
# self.datasets.update_replicas(subscriptions, deletions)
t2 = datetime.datetime.utcnow()
td = t2 - t1
self.logger.info("Rocker Board took %s", str(td))
def test_datetime_day(self):
"Test datetime_day function"
datetime_ = datetime.datetime(1987, 10, 27, 3, 6, 9)
expected = datetime.datetime(year=1987, month=10, day=27)
result = datetime_day(datetime_)
self.assertEqual(result, expected)
def test_datetime_day(self):
"Test datetime_day function"
datetime_ = datetime.datetime(1987, 10, 27, 3, 6, 9)
expected = datetime.datetime(year=1987, month=10, day=27)
result = datetime_day(datetime_)
self.assertEqual(result, expected)
