def fetch(self, api, params=None):
"Fetch data for given api"
if api == 'sites':
api = 'site-names'
url = '%s/%s' % (self.url, api)
data = super(SiteDBService, self).fetch(url, params)
for row in sitedb_parser(data):
if api == 'people':
rid = genkey(str(row['dn']), truncate=5)
rec = {'dn':row['dn'], 'rid':rid}
if api == 'site-names':
rid = genkey(str(row['alias']), truncate=5)
rec = {'site':row['alias'], 'rid':rid}
yield rec
def fetch(self, url, params, cache=True):
"Fetch data for given api"
debug = 0
data = "[]"
if cache:
docid = genkey("url=%s params=%s" % (url, params))
res = self.storage.fetch_one('cache', {'_id':docid})
if res and 'data' in res:
if self.verbose:
print("%s::fetch url=%s, params=%s, docid=%s" \
% (self.name, url, params, docid))
return res['data']
if self.verbose:
print("%s::fetch url=%s, params=%s" % (self.name, url, params))
debug = self.verbose-1
try:
data = getdata(url, params, debug=debug)
except Exception as exc:
print(str(exc))
for attempt in xrange(3):
time.sleep(0.1)
print("Attempt %s" % attempt)
try:
data = getdata(url, params, debug=debug)
break
except Exception as err:
print(str(err))
pass
if cache:
self.storage.insert('cache', {'_id':docid, 'data': data, 'url': url, 'params': params})
return data
def fetch(self, api, params=None):
"Fetch data for given api"
url = '%s/%s/?%s' % (self.url, api, urllib.urlencode(params, doseq=True))
docid = genkey("url=%s params=%s" % (url, params))
res = self.storage.fetch_one('cache', {'_id':docid})
if res and 'data' in res:
if self.verbose:
print("%s::fetch url=%s, params=%s, docid=%s" \
% (self.name, url, params, docid))
data = res['data']
else:
if self.verbose:
print("%s::fetch url=%s, params=%s" % (self.name, url, params))
# NOTE: popularity DB has two different access points, one
# within CERN network and out outside. The former does not require
# authentication, while later passes through CERN SSO.
# The following block reflects this, in a future, when popularity DB
# will move into cmsweb domain we'll no longer need it
if self.url.find('cms-popularity-prod') != -1 or \
self.url.find('cmsweb') != -1:
data = getdata(url, ckey=self.ckey, cert=self.cert, debug=self.verbose)
else:
data = sso_getdata(url, ckey=self.ckey, cert=self.cert, debug=self.verbose)
self.storage.insert('cache', {'_id':docid, 'data': data, 'url': url, 'params': params})
data = json.loads(data)
for row in data['DATA']:
yield row
def convert(config, sep=',', sortby='tier'):
"Lookup DBS data tiers"
dbs = DBSService(config)
tiers = {}
salt = config.get('core', {}).get('salt', 'secret sauce')
for tier in dbs.data_tiers():
tid = genkey(tier, salt, 5)
if sortby == 'tier':
tiers[tier] = tid
else:
tiers[tid] = tier
for tier in sorted(tiers.keys()):
if sortby == 'tier':
print('%s%s%s' % (tiers[tier], sep, tier))
else:
print('%s%s%s' % (tier, sep, tiers[tier]))
def convert(config, sep=',', sortby='tier'):
"Lookup DBS data tiers"
dbs = DBSService(config)
tiers = {}
salt = config.get('core', {}).get('salt', 'secret sauce')
for tier in dbs.data_tiers():
tid = genkey(tier, salt, 5)
if sortby == 'tier':
tiers[tier] = tid
else:
tiers[tid] = tier
for tier in sorted(tiers.keys()):
if sortby == 'tier':
print('%s%s%s' % (tiers[tier], sep, tier))
else:
print('%s%s%s' % (tier, sep, tiers[tier]))
def fetch(self, api, params=None):
"Fetch data for given api"
url = '%s/%s/?%s' % (self.url, api, urllib.urlencode(params, doseq=True))
docid = genkey("url=%s params=%s" % (url, params))
res = self.storage.fetch_one('cache', {'_id':docid})
if res and 'data' in res:
if self.verbose:
print("%s::fetch url=%s, params=%s, docid=%s" \
% (self.name, url, params, docid))
data = res['data']
else:
if self.verbose:
print("%s::fetch url=%s, params=%s" % (self.name, url, params))
data = getdata(url, ckey=self.ckey, cert=self.cert, debug=self.verbose)
self.storage.insert('cache', {'_id':docid, 'data': data, 'url': url, 'params': params})
data = json.loads(data)
for row in data['DATA']:
yield row
def fetch(self, api, params=None, dbsinst='prod/global', cache=True):
"Fetch data for given api"
if dbsinst:
dbs_url = self.url.replace('prod/global', dbsinst)
inst = {'dbs_instance': self.all_dbs.index(dbsinst)}
if api == 'releases':
url = '%s/releaseversions' % dbs_url
else:
url = '%s/%s' % (dbs_url, api)
data = json.loads(super(DBSService, self).fetch(url, params, cache))
if api == 'releases':
data = data[0]['release_version']
for row in data:
if api == 'datasets':
try:
row['rid'] = row['dataset_id']
except KeyError:
print("Unable to process dataset row", row)
if 'dataset' in row:
h = hashlib.md5()
h.update(row['dataset'])
row['rid'] = int(h.hexdigest()[:10], 16)
print("Generated new dataset_id", row['dataset'],
h.hexdigest(), row['rid'])
except:
print("Unable to process dataset row", row)
raise
row.update(inst)
yield row
elif api == 'releases':
rid = genkey(row, truncate=5)
rec = {'release': row, 'rid': rid}
yield rec
elif api == 'filesummaries':
yield row
else:
yield row
def fetch(self, api, params=None, dbsinst='prod/global', cache=True):
"Fetch data for given api"
if dbsinst:
dbs_url = self.url.replace('prod/global', dbsinst)
inst = {'dbs_instance':self.all_dbs.index(dbsinst)}
if api == 'releases':
url = '%s/releaseversions' % dbs_url
else:
url = '%s/%s' % (dbs_url, api)
data = json.loads(super(DBSService, self).fetch(url, params, cache))
if api == 'releases':
data = data[0]['release_version']
for row in data:
if api == 'datasets':
try:
row['rid'] = row['dataset_id']
except KeyError:
print("Unable to process dataset row", row)
if 'dataset' in row:
h = hashlib.md5()
h.update(row['dataset'])
row['rid'] = int(h.hexdigest()[:10], 16)
print("Generated new dataset_id", row['dataset'], h.hexdigest(), row['rid'])
except:
print("Unable to process dataset row", row)
raise
row.update(inst)
yield row
elif api == 'releases':
rid = genkey(row, truncate=5)
rec = {'release':row, 'rid':rid}
yield rec
elif api == 'filesummaries':
yield row
else:
yield row
def fetch(self, url, params, cache=True):
"Fetch data for given api"
debug = 0
data = "[]"
if cache:
docid = genkey("url=%s params=%s" % (url, params))
res = self.storage.fetch_one('cache', {'_id': docid})
if res and 'data' in res:
if self.verbose:
print("%s::fetch url=%s, params=%s, docid=%s" \
% (self.name, url, params, docid))
return res['data']
if self.verbose:
print("%s::fetch url=%s, params=%s" % (self.name, url, params))
debug = self.verbose - 1
try:
data = getdata(url, params, debug=debug)
except Exception as exc:
print(str(exc))
for attempt in xrange(3):
time.sleep(0.1)
print("Attempt %s" % attempt)
try:
data = getdata(url, params, debug=debug)
break
except Exception as err:
print(str(err))
pass
if cache:
self.storage.insert('cache', {
'_id': docid,
'data': data,
'url': url,
'params': params
})
return data
def dataset_info(self, timeframe, dataset, dtypes, stypes, rtypes, tiers, dformat, target=0):
"Return common dataset info in specified data format"
dbsinst = self.dbs.dataset_dbsinst(dataset)
if not dbsinst:
return
row = self.dbs.dataset_info(dataset, dbsinst)
if row:
if self.multitask:
releases, sites, parents, summary, dashboard = \
self.dataset_info_all(dataset, dbsinst, timeframe)
else:
releases = [rname for rname in self.dbs.dataset_release_versions(dataset, dbsinst)]
sites = [sname for sname in self.phedex.sites(dataset)]
parents = [r for r in self.dbs.dataset_parents(dataset, dbsinst)]
summary = self.dbs.dataset_summary(dataset, dbsinst)
dashboard = self.dashboard.dataset_info(dataset, timeframe[0], timeframe[1])
nrels = len(releases)
series = rtypes['series']
majors = rtypes['majors']
minors = rtypes['minors']
relclf = rtypes['rtypes']
for rel in releases:
rserie, rmajor, rminor = rel_ver(rel)
if not cmssw_test(rserie, rmajor, rminor):
continue
rtype = rel_type(rel)
try:
series['rel1_%s'%rserie] += 1
except:
pass
try:
majors['rel2_%s'%rmajor] += 1
except:
pass
try:
minors['rel3_%s'%rminor] += 1
except:
pass
try:
relclf['relt_%s'%rtype] += 1
except:
pass
nsites = len(sites)
for site in sites:
stier = site_tier(site)
stypes['s_%s'%stier] += 1
dataset_id = row['rid']
era = genkey(row['acquisition_era_name'], self.salt, 5)
create_dn = self.sitedb.dnid(row['create_by'])
dbsinstid = row['dbs_instance']
dtype = row['primary_ds_type']
# number of data types should be small and simple
# list look-up shouldn't be a problem
if dtype not in dtypes:
dtypes.append(dtype)
dtype = dtypes.index(dtype)
_, prim, proc, tier = dataset.split('/')
prim = genkey(prim, self.salt, 5)
proc = genkey(proc, self.salt, 5)
if tier not in tiers:
tiers.append(tier)
tier = genkey(tier, self.salt, 5)
parent = parents[0] if len(parents) else 0
uid = genuid(yyyymmdd(timeframe[0]), dbsinstid, dataset_id)
size_norm = 2**30 # normalization factor for file size
rec = dict(id=uid, dataset=dataset_id, primds=prim, procds=proc, tier=tier,
dtype=dtype, creator=create_dn, nrel=nrels, nsites=nsites,
parent=parent, era=era, dbs=dbsinstid,
nfiles=summary.get('num_file', 0),
nlumis=summary.get('num_lumi', 0),
nblk=summary.get('num_block', 0),
nevt=summary.get('num_event', 0),
size=summary.get('file_size', 0)/size_norm,
cpu=dashboard.get('cpu', 0),
wct=dashboard.get('wct', 0),
proc_evts=dashboard.get('nevt', 0))
if isinstance(target, dict):
rec.update(target)
for key,val in series.items():
rec.update({key:val})
for key, val in majors.items():
rec.update({key:val})
for key, val in minors.items():
rec.update({key:val})
for key, val in relclf.items():
rec.update({key:val})
for key, val in stypes.items():
rec.update({key:val})
headers = rec.keys()
headers.sort()
headers.remove('id')
headers = ['id'] + headers # let dataset id be the first column
if dformat == 'headers':
yield headers
elif dformat == 'csv':
res = [str(rec[h]) for h in headers]
yield ','.join(res)
elif dformat == 'vw':
target_str = target.get('rnaccess')
vals = ' '.join([str(rec[h]) for h in headers])
uid = genkey(vals, self.salt, 5) # unique row identified
vwrow = "%s '%s |f %s" % (target_str, uid, vals)
yield vwrow
def dataset_info(self,
timeframe,
dataset,
dtypes,
stypes,
rtypes,
tiers,
dformat,
target=0):
"Return common dataset info in specified data format"
dbsinst = self.dbs.dataset_dbsinst(dataset)
if not dbsinst:
return
row = self.dbs.dataset_info(dataset, dbsinst)
if row:
if self.multitask:
releases, sites, parents, summary, dashboard = \
self.dataset_info_all(dataset, dbsinst, timeframe)
else:
releases = [
rname for rname in self.dbs.dataset_release_versions(
dataset, dbsinst)
]
sites = [sname for sname in self.phedex.sites(dataset)]
parents = [
r for r in self.dbs.dataset_parents(dataset, dbsinst)
]
summary = self.dbs.dataset_summary(dataset, dbsinst)
dashboard = self.dashboard.dataset_info(
dataset, timeframe[0], timeframe[1])
nrels = len(releases)
series = {}
for k in rtypes['series'].keys():
series[k] = 0
majors = {}
for k in rtypes['majors'].keys():
majors[k] = 0
minors = {}
for k in rtypes['minors'].keys():
minors[k] = 0
relclf = {}
for k in rtypes['rtypes'].keys():
relclf[k] = 0
for rel in releases:
rserie, rmajor, rminor = rel_ver(rel)
if not cmssw_test(rserie, rmajor, rminor):
continue
rtype = rel_type(rel)
try:
series['rel1_%s' % rserie] += 1
except:
pass
try:
majors['rel2_%s' % rmajor] += 1
except:
pass
try:
minors['rel3_%s' % rminor] += 1
except:
pass
try:
relclf['relt_%s' % rtype] += 1
except:
pass
nsites = len(sites)
for site in sites:
stier = site_tier(site)
stypes['s_%s' % stier] += 1
dataset_id = row['rid']
era = genkey(row['acquisition_era_name'], self.salt, 5)
create_dn = self.sitedb.dnid(row['create_by'])
dbsinstid = row['dbs_instance']
dtype = row['primary_ds_type']
# number of data types should be small and simple
# list look-up shouldn't be a problem
if dtype not in dtypes:
dtypes.append(dtype)
dtype = dtypes.index(dtype)
_, prim, proc, tier = dataset.split('/')
prim = genkey(prim, self.salt, 5)
proc = genkey(proc, self.salt, 5)
if tier not in tiers:
tiers.append(tier)
tier = genkey(tier, self.salt, 5)
parent = parents[0] if len(parents) else 0
uid = genuid(yyyymmdd(timeframe[0]), dbsinstid, dataset_id)
size_norm = 2**30 # normalization factor for file size
if not summary:
summary = {} # we need a dict type
rec = dict(id=uid,
dataset=dataset_id,
primds=prim,
procds=proc,
tier=tier,
dtype=dtype,
creator=create_dn,
nrel=nrels,
nsites=nsites,
parent=parent,
era=era,
dbs=dbsinstid,
nfiles=summary.get('num_file', 0),
nlumis=summary.get('num_lumi', 0),
nblk=summary.get('num_block', 0),
nevt=summary.get('num_event', 0),
size=summary.get('file_size', 0) / size_norm,
cpu=dashboard.get('cpu', 0),
wct=dashboard.get('wct', 0),
proc_evts=dashboard.get('nevt', 0))
if isinstance(target, dict):
rec.update(target)
for key, val in series.items():
rec.update({key: val})
for key, val in majors.items():
rec.update({key: val})
for key, val in minors.items():
rec.update({key: val})
for key, val in relclf.items():
rec.update({key: val})
for key, val in stypes.items():
rec.update({key: val})
headers = rec.keys()
headers.sort()
headers.remove('id')
headers = ['id'] + headers # let dataset id be the first column
if dformat == 'headers':
yield headers
elif dformat == 'csv':
res = [str(rec[h]) for h in headers]
yield ','.join(res)
elif dformat == 'vw':
target_str = target.get('rnaccess')
vals = ' '.join([str(rec[h]) for h in headers])
uid = genkey(vals, self.salt, 5) # unique row identified
vwrow = "%s '%s |f %s" % (target_str, uid, vals)
yield vwrow
