cartodb4/observatory-extension
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'improve-perftest' into complex-geom-perf-improvements

Browse Source
This commit is contained in:
John Krauss
2016-12-05 22:57:03 +00:00
parent 44932be1f5 255f8dc18e
commit 1aca5b5ff0
4 changed files with 2726 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2609
release/observatory--1.1.5.sql Normal file
View File

File diff suppressed because one or more lines are too long

2
release/observatory.control
View File

@@ -1,5 +1,5 @@
comment = 'CartoDB Observatory backend extension'
default_version = '1.1.4'
default_version = '1.1.5'
requires = 'postgis, postgres_fdw'
superuser = true
schema = cdb_observatory

2
src/pg/observatory.control
View File

@@ -1,5 +1,5 @@
comment = 'CartoDB Observatory backend extension'
default_version = '1.1.4'
default_version = '1.1.5'
requires = 'postgis, postgres_fdw'
superuser = true
schema = cdb_observatory

150
src/python/test/perftest.py
View File

@@ -5,17 +5,47 @@ from util import query, commit
from time import time
import json
import os
USE_SCHEMA = True
for q in (
'DROP TABLE IF EXISTS obs_censustest',
'''CREATE TABLE obs_censustest (cartodb_id SERIAL PRIMARY KEY,
the_geom GEOMETRY, name TEXT, measure NUMERIC, category TEXT)''',
'''INSERT INTO obs_censustest (the_geom, name)
SELECT * FROM {schema}OBS_GetBoundariesByGeometry(
st_makeenvelope(-74.05437469482422,40.66319159533881,
-73.81885528564453,40.745696344339564, 4326),
'us.census.tiger.block_group_clipped') As m(the_geom, geoid)'''
'DROP TABLE IF EXISTS obs_perftest_simple',
'''CREATE TABLE obs_perftest_simple (cartodb_id SERIAL PRIMARY KEY,
point GEOMETRY,
geom GEOMETRY,
offset_geom GEOMETRY,
name TEXT, measure NUMERIC, category TEXT)''',
'''INSERT INTO obs_perftest_simple (point, geom, offset_geom, name)
SELECT ST_PointOnSurface(the_geom) point,
the_geom geom,
ST_Translate(the_geom, -0.1, 0.1) offset_geom,
geom_refs AS name
FROM (SELECT * FROM {schema}OBS_GetBoundariesByGeometry(
st_makeenvelope(-74.05437469482422,40.66319159533881,
-73.81885528564453,40.745696344339564, 4326),
'us.census.tiger.census_tract_clipped')) foo
ORDER BY ST_NPoints(the_geom) ASC
LIMIT 50''',
'DROP TABLE IF EXISTS obs_perftest_complex',
'''CREATE TABLE obs_perftest_complex (cartodb_id SERIAL PRIMARY KEY,
point GEOMETRY,
geom GEOMETRY,
offset_geom GEOMETRY,
name TEXT, measure NUMERIC, category TEXT)''',
'''INSERT INTO obs_perftest_complex (point, geom, offset_geom, name)
SELECT ST_PointOnSurface(the_geom) point,
the_geom geom,
ST_Translate(the_geom, -0.1, 0.1) offset_geom,
geom_refs AS name
FROM (SELECT * FROM {schema}OBS_GetBoundariesByGeometry(
st_makeenvelope(-75.05437469482422,40.66319159533881,
-73.81885528564453,41.745696344339564, 4326),
'us.census.tiger.county_clipped')) foo
ORDER BY ST_NPoints(the_geom) DESC
LIMIT 50;''',
'''SET statement_timeout = 5000;'''
):
query(q.format(
schema='cdb_observatory.' if USE_SCHEMA else '',
@@ -24,39 +54,89 @@ for q in (
ARGS = {
'OBS_GetMeasureByID': "name, 'us.census.acs.B01001002', '{}'",
'OBS_GetMeasure': "{}, 'us.census.acs.B01001002'",
'OBS_GetCategory': "{}, 'us.census.spielman_singleton_segments.X10'",
('OBS_GetMeasureByID', None): "name, 'us.census.acs.B01001002', '{}'",
('OBS_GetMeasure', 'predenominated'): "{}, 'us.census.acs.B01003001'",
('OBS_GetMeasure', 'area'): "{}, 'us.census.acs.B01001002', 'area'",
('OBS_GetMeasure', 'denominator'): "{}, 'us.census.acs.B01001002', 'denominator'",
('OBS_GetCategory', None): "{}, 'us.census.spielman_singleton_segments.X10'",
}
GEOMS = {
'point': 'ST_PointOnSurface(the_geom)',
'polygon_match': 'the_geom',
'polygon_buffered': 'ST_Buffer(the_geom::GEOGRAPHY, 1000)::GEOMETRY(GEOMETRY, 4326)',
}
def record(params, results):
sha = os.environ['OBS_EXTENSION_SHA']
fpath = os.path.join(os.environ['OBS_PERFTEST_DIR'], sha + '.json')
if os.path.isfile(fpath):
tests = json.load(open(fpath, 'r'))
else:
tests = {}
with open(fpath, 'w') as fhandle:
tests[json.dumps(params)] = {
'params': params,
'results': results
}
json.dump(tests, fhandle)
@parameterized([
('OBS_GetMeasureByID', 'us.census.tiger.block_group_clipped'),
('OBS_GetMeasureByID', 'us.census.tiger.county'),
('OBS_GetMeasure', GEOMS['point']),
('OBS_GetMeasure', GEOMS['polygon_match']),
('OBS_GetMeasure', GEOMS['polygon_buffered']),
('OBS_GetCategory', GEOMS['point']),
('OBS_GetCategory', GEOMS['polygon_match']),
('OBS_GetCategory', GEOMS['polygon_buffered']),
('simple', 'OBS_GetMeasureByID', None, 'us.census.tiger.census_tract'),
('complex', 'OBS_GetMeasureByID', None, 'us.census.tiger.county'),
('simple', 'OBS_GetMeasure', 'predenominated', 'point'),
('simple', 'OBS_GetMeasure', 'predenominated', 'geom'),
('simple', 'OBS_GetMeasure', 'predenominated', 'offset_geom'),
('simple', 'OBS_GetMeasure', 'area', 'point'),
('simple', 'OBS_GetMeasure', 'area', 'geom'),
('simple', 'OBS_GetMeasure', 'area', 'offset_geom'),
('simple', 'OBS_GetMeasure', 'denominator', 'point'),
('simple', 'OBS_GetMeasure', 'denominator', 'geom'),
('simple', 'OBS_GetMeasure', 'denominator', 'offset_geom'),
('simple', 'OBS_GetCategory', None, 'point'),
('simple', 'OBS_GetCategory', None, 'geom'),
('simple', 'OBS_GetCategory', None, 'offset_geom'),
#('complex', 'OBS_GetMeasure', 'predenominated', 'point'),
#('complex', 'OBS_GetMeasure', 'predenominated', 'geom'),
#('complex', 'OBS_GetMeasure', 'predenominated', 'offset_geom'),
#('complex', 'OBS_GetMeasure', 'area', 'point'),
#('complex', 'OBS_GetMeasure', 'area', 'geom'),
#('complex', 'OBS_GetMeasure', 'area', 'offset_geom'),
#('complex', 'OBS_GetMeasure', 'denominator', 'point'),
#('complex', 'OBS_GetMeasure', 'denominator', 'geom'),
#('complex', 'OBS_GetMeasure', 'denominator', 'offset_geom'),
#('complex', 'OBS_GetCategory', None, 'point'),
#('complex', 'OBS_GetCategory', None, 'geom'),
#('complex', 'OBS_GetCategory', None, 'offset_geom'),
])
def test_performance(api_method, arg):
print api_method, arg
def test_performance(geom_complexity, api_method, normalization, geom):
print api_method, geom_complexity, normalization, geom
col = 'measure' if 'measure' in api_method.lower() else 'category'
for rows in (1, 10, 50, 100):
q = 'UPDATE obs_censustest SET {col} = {schema}{api_method}({args}) WHERE cartodb_id < {n}'.format(
col=col,
schema='cdb_observatory.' if USE_SCHEMA else '',
api_method=api_method,
args=ARGS[api_method].format(arg),
n=rows+1)
results = []
for rows in (1, 5, 10, ):
stmt = '''UPDATE obs_perftest_{complexity}
SET {col} = {schema}{api_method}({args})
WHERE cartodb_id < {n}'''.format(
col=col,
complexity=geom_complexity,
schema='cdb_observatory.' if USE_SCHEMA else '',
api_method=api_method,
args=ARGS[api_method, normalization].format(geom),
n=rows+1)
start = time()
query(q)
query(stmt)
end = time()
print rows, ': ', (rows / (end - start)), ' QPS'
qps = (rows / (end - start))
results.append({
'rows': rows,
'qps': qps,
'stmt': stmt
})
print rows, ': ', qps, ' QPS'
if 'OBS_RECORD_TEST' in os.environ:
record({
'geom_complexity': geom_complexity,
'api_method': api_method,
'normalization': normalization,
'geom': geom
}, results)