def test_null_groups(pipeline, clean_db):
"""
Verify that null group columns are considered equal
"""
pipeline.create_stream('s', x='int', y='int', z='int')
q = """
SELECT x::integer, y::integer, z::integer, COUNT(*) FROM s
GROUP BY x, y, z;
"""
desc = ('x', 'y', 'z')
pipeline.create_cv('test_null_groups', q)
pipeline.create_table('test_null_groups_t',
x='integer',
y='integer',
z='integer')
rows = []
for n in range(10000):
vals = list(random.randint(0, 10) for n in range(3))
vals = map(lambda n: random.random() > 0.1 and n or None, vals)
rows.append(tuple(vals))
pipeline.insert('s', desc, rows)
pipeline.insert('test_null_groups_t', desc, rows)
table_q = """
SELECT x, y, z, COUNT(*) FROM test_null_groups_t
GROUP BY x, y, z ORDER BY x, y, z;
"""
expected = pipeline.execute(table_q)
result = pipeline.execute(
'SELECT x, y, z, count FROM test_null_groups ORDER BY x, y, z')
for r, e in zip(result, expected):
assert r == e
def test_combine_in_view(pipeline, clean_db):
"""
Verify that combines in views on top of continuous views work
"""
q = """
SELECT x::integer, avg(y::integer) FROM stream0 GROUP BY x
"""
desc = ('x', 'y')
pipeline.create_stream('stream0', x='int', y='float8')
pipeline.create_cv('test_combine_view', q)
pipeline.execute(
'CREATE VIEW v AS SELECT combine(avg) FROM test_combine_view')
rows = []
for n in range(10000):
rows.append((random.randint(1, 256), random.randint(1, 1024)))
pipeline.insert('stream0', desc, rows)
view = pipeline.execute('SELECT * FROM v')
assert len(view) == 1
expected = sum(r[1] for r in rows) / float(len(rows))
assert abs(float(view[0][0]) - expected) < 0.00001
pipeline.execute('DROP VIEW v')
def test_filter_clause(pipeline, clean_db):
"""
Verify that FILTER clauses work on aggregates and sliding window aggregates
"""
pipeline.create_stream("test_filter_stream", x="int")
q = """
SELECT SUM(x::int) FILTER (WHERE mod(x, 2) = 0) AS sum2, SUM(x::int) FILTER (WHERE mod(x, 3) = 0) AS sum3 FROM test_filter_stream
"""
sw = """
WHERE arrival_timestamp > clock_timestamp() - interval '30 second'
"""
pipeline.create_cv("test_filter", q)
pipeline.create_cv("test_filter_sw", "%s %s" % (q, sw))
desc = ("x",)
rows = []
for n in range(1000):
rows.append((n,))
pipeline.insert("test_filter_stream", desc, rows)
sum2 = sum(filter(lambda x: x % 2 == 0, map(lambda x: x[0], rows)))
sum3 = sum(filter(lambda x: x % 3 == 0, map(lambda x: x[0], rows)))
result1 = pipeline.execute("SELECT * FROM test_filter").first()
result2 = pipeline.execute("SELECT * FROM test_filter_sw").first()
assert result1["sum2"] == result2["sum2"] == sum2
assert result1["sum3"] == result2["sum3"] == sum3
def test_single_continuous_view(pipeline, clean_db):
"""
Verify that specific continuous views can be dropped and restored
"""
pipeline.create_stream('stream0', x='int')
pipeline.create_cv('test_single0', 'SELECT COUNT(*) FROM stream0')
pipeline.create_cv('test_single1', 'SELECT COUNT(*) FROM stream0')
pipeline.insert('stream0', ('x', ), [(x, ) for x in range(10)])
result = pipeline.execute('SELECT count FROM test_single0').first()
assert result['count'] == 10
result = pipeline.execute('SELECT count FROM test_single1').first()
assert result['count'] == 10
_dump(pipeline,
'test_single.sql',
tables=['test_single0', 'stream0', 'test_single0_mrel'])
pipeline.drop_all()
_restore(pipeline, 'test_single.sql')
result = pipeline.execute('SELECT count FROM test_single0').first()
assert result['count'] == 10
# We didn't dump this one
result = list(
pipeline.execute(
'SELECT * FROM pg_class WHERE relname LIKE \'%%test_single1%%\''))
assert not result
def test_online_add_column(pipeline, clean_db):
"""
Verify that we can add columns to a stream while not affecting running CQs
"""
pipeline.create_stream("stream0", c0="integer")
pipeline.create_cv("cv0", "SELECT c0 FROM stream0")
pipeline.insert("stream0", ("c0",), [(n,) for n in range(0, 1000)])
result = list(pipeline.execute("SELECT * FROM cv0"))
assert len(result) == 1000
for row in result:
for col in row:
assert col is not None
pipeline.execute("ALTER STREAM stream0 ADD c1 integer")
pipeline.create_cv("cv1", "SELECT c0, c1 FROM stream0")
pipeline.insert("stream0", ("c0", "c1"), [(n, n) for n in range(1000, 2000)])
result = list(pipeline.execute("SELECT * FROM cv1 WHERE c1 >= 1000"))
assert len(result) == 1000
for row in result:
for col in row:
assert col is not None
pipeline.execute("ALTER STREAM stream0 ADD c2 integer")
pipeline.create_cv("cv2", "SELECT c0, c1, c2 FROM stream0")
pipeline.insert("stream0", ("c0", "c1", "c2"), [(n, n, n) for n in range(2000, 3000)])
result = list(pipeline.execute("SELECT * FROM cv2 WHERE c2 >= 2000"))
assert len(result) == 1000
for row in result:
for col in row:
assert col is not None
pipeline.execute("ALTER STREAM stream0 ADD c3 integer")
pipeline.create_cv("cv3", "SELECT c0, c1, c2, c3 FROM stream0")
pipeline.insert("stream0", ("c0", "c1", "c2", "c3"), [(n, n, n, n) for n in range(3000, 4000)])
result = list(pipeline.execute("SELECT * FROM cv3 WHERE c3 >= 3000"))
assert len(result) == 1000
for row in result:
for col in row:
assert col is not None
pipeline.execute("ALTER STREAM stream0 ADD c4 integer")
pipeline.create_cv("cv4", "SELECT c0, c1, c2, c3, c4 FROM stream0")
pipeline.insert("stream0", ("c0", "c1", "c2", "c3", "c4"), [(n, n, n, n, n) for n in range(4000, 5000)])
result = list(pipeline.execute("SELECT * FROM cv4 WHERE c4 >= 4000"))
assert len(result) == 1000
for row in result:
for col in row:
assert col is not None
def test_prepared_extended(pipeline, clean_db):
"""
Verify that we can write to streams using the extended protocol. This test
shells out to a binary because psycopg2 doesn't use the extended protocol.
"""
pipeline.create_stream('extended_stream', x='int', y='int', z='int')
q = """
SELECT COUNT(x::integer) AS x, COUNT(y::integer) AS y, COUNT(z::integer) AS z FROM extended_stream
"""
pipeline.create_cv('test_prepared_extended', q)
# This will insert 1000 via a paramaterized insert, and 1000 via unparamaterized insert
cmd = ['./extended', 'pipeline', str(pipeline.port), 'extended_stream', '1000']
stdout, stderr = subprocess.Popen(cmd).communicate()
assert stdout is None
assert stderr is None
rows = list(pipeline.execute('SELECT x, y, z FROM test_prepared_extended'))
assert len(rows) == 1
result = rows[0]
assert result['x'] == 2000
assert result['y'] == 2000
assert result['z'] == 2000
def test_colums_subset(pipeline, clean_db):
"""
Verify that copying data from a file into a stream works when the file's input
columns are a subset of the stream0's columns
"""
pipeline.create_stream("stream0", x="int", y="float8", z="numeric", m="int")
q = "SELECT sum(x::integer) AS s0, sum(y::float8) AS s1, avg(z::numeric), max(m::integer) FROM stream0"
pipeline.create_cv("test_copy_subset", q)
pipeline.create_table("test_copy_subset_t", x="integer", y="float8", z="numeric")
path = os.path.abspath(os.path.join(pipeline.tmp_dir, "test_copy.csv"))
rows = []
for n in range(10000):
row = random.randint(1, 1024), random.randint(1, 1024), random.random()
rows.append(row)
_generate_csv(path, rows, desc=("x", "y", "z"))
pipeline.execute("COPY test_copy_subset_t (x, y, z) FROM '%s' HEADER CSV" % path)
pipeline.execute("COPY stream0 (x, y, z) FROM '%s' HEADER CSV" % path)
expected = pipeline.execute(
"SELECT sum(x::integer) AS s0, sum(y::float8) AS s1, avg(z::numeric) FROM test_copy_subset_t"
).first()
result = list(pipeline.execute("SELECT s0, s1, avg FROM test_copy_subset"))
assert len(result) == 1
result = result[0]
assert result[0] == expected[0]
assert result[1] == expected[1]
assert result[2] == expected[2]
def test_prepared_extended(pipeline, clean_db):
"""
Verify that we can write to streams using the extended protocol. This test
shells out to a binary because psycopg2 doesn't use the extended protocol.
"""
pipeline.create_stream('extended_stream', x='int', y='int', z='int')
q = """
SELECT COUNT(x::integer) AS x, COUNT(y::integer) AS y, COUNT(z::integer) AS z FROM extended_stream
"""
pipeline.create_cv('test_prepared_extended', q)
# This will insert 1000 via a paramaterized insert, and 1000 via unparamaterized insert
cmd = [
'./extended', 'postgres',
str(pipeline.port), 'extended_stream', '1000'
]
stdout, stderr = subprocess.Popen(cmd).communicate()
assert stdout is None
assert stderr is None
rows = pipeline.execute('SELECT x, y, z FROM test_prepared_extended')
assert len(rows) == 1
result = rows[0]
assert result['x'] == 2000
assert result['y'] == 2000
assert result['z'] == 2000
def test_sliding_windows(pipeline, clean_db):
"""
Verify that sliding window queries are properly dumped and restored
"""
pipeline.create_stream('stream0', x='int')
pipeline.execute(
'CREATE CONTINUOUS VIEW sw_v WITH (sw = \'20 seconds\') AS SELECT count(*) FROM stream0'
)
pipeline.insert('stream0', ('x', ), [(x, ) for x in range(10)])
result = pipeline.execute('SELECT count FROM sw_v').first()
assert result['count'] == 10
_dump(pipeline, 'test_sw.sql')
pipeline.drop_all()
_restore(pipeline, 'test_sw.sql')
result = pipeline.execute('SELECT count FROM sw_v').first()
assert result['count'] == 10
# We should still drop back to 0 within 20 seconds
result = pipeline.execute('SELECT count FROM sw_v').first()
while result['count'] > 0:
time.sleep(1)
result = pipeline.execute('SELECT count FROM sw_v').first()
result = pipeline.execute('SELECT count FROM sw_v').first()
assert result['count'] == 0
def test_null_groups(pipeline, clean_db):
"""
Verify that null group columns are considered equal
"""
pipeline.create_stream("s", x="int", y="int", z="int")
q = """
SELECT x::integer, y::integer, z::integer, COUNT(*) FROM s
GROUP BY x, y, z;
"""
desc = ("x", "y", "z")
pipeline.create_cv("test_null_groups", q)
pipeline.create_table("test_null_groups_t", x="integer", y="integer", z="integer")
rows = []
for n in range(10000):
vals = list(random.randint(0, 10) for n in range(3))
vals = map(lambda n: random.random() > 0.1 and n or None, vals)
rows.append(tuple(vals))
pipeline.insert("s", desc, rows)
pipeline.insert("test_null_groups_t", desc, rows)
table_q = """
SELECT x, y, z, COUNT(*) FROM test_null_groups_t
GROUP BY x, y, z ORDER BY x, y, z;
"""
expected = list(pipeline.execute(table_q))
result = list(pipeline.execute("SELECT x, y, z, count FROM test_null_groups ORDER BY x, y, z"))
for r, e in zip(result, expected):
assert r == e
def test_freq_agg(pipeline, clean_db):
"""
Test freq_agg, freq_merge_agg
"""
pipeline.create_stream('test_cmsketch_stream', k='int', x='int')
q = """
SELECT k::integer, freq_agg(x::int) AS c FROM test_cmsketch_stream
GROUP BY k
"""
desc = ('k', 'x')
pipeline.create_cv('test_cmsketch_agg', q)
rows = []
for n in range(1000):
rows.append((0, n % 20))
rows.append((1, n % 50))
pipeline.insert('test_cmsketch_stream', desc, rows)
result = pipeline.execute(
'SELECT freq(c, 10) AS x, freq(c, 40) AS y, freq(c, 60) FROM test_cmsketch_agg ORDER BY k'
)
assert len(result) == 2
assert (result[0][0], result[0][1], result[0][2]) == (50, 0, 0)
assert (result[1][0], result[1][1], result[1][2]) == (20, 20, 0)
result = pipeline.execute(
'SELECT freq(combine(c), 10) AS x, freq(combine(c), 40) AS y, freq(combine(c), 60) FROM test_cmsketch_agg'
)
assert len(result) == 1
(result[0][0], result[0][1], result[0][2]) == (70, 20, 0)
def test_simple_crash(pipeline, clean_db):
"""
Test simple worker and combiner crashes.
"""
pipeline.create_stream('stream0', x='int')
q = 'SELECT COUNT(*) FROM stream0'
pipeline.create_cv('test_simple_crash', q)
pipeline.insert('stream0', ['x'], [(1,), (1,)])
result = pipeline.execute('SELECT * FROM test_simple_crash').first()
assert result['count'] == 2
# This batch can potentially get lost.
pipeline.insert('stream0', ['x'], [(1,), (1,)])
assert kill_worker()
pipeline.insert('stream0', ['x'], [(1,), (1,)])
result = pipeline.execute('SELECT * FROM test_simple_crash').first()
assert result['count'] in [4, 6]
# This batch can potentially get lost.
pipeline.insert('stream0', ['x'], [(1,), (1,)])
assert kill_combiner()
pipeline.insert('stream0', ['x'], [(1,), (1,)])
result = pipeline.execute('SELECT * FROM test_simple_crash').first()
assert result['count'] in [6, 8, 10]
# To ensure that all remaining events in ZMQ queues have been consumed
time.sleep(2)
def test_restart_recovery(pipeline, clean_db):
pipeline.create_stream('stream0', x='int')
q = 'SELECT COUNT(*) FROM stream0'
pipeline.create_cv('test_restart_recovery', q)
pipeline.insert('stream0', ['x'], [(1,), (1,)])
result = pipeline.execute('SELECT * FROM test_restart_recovery').first()
assert result['count'] == 2
# Need to sleep here, otherwise on restart the materialization table is
# empty. Not sure why.
time.sleep(0.1)
# Restart.
pipeline.stop()
pipeline.run()
result = pipeline.execute('SELECT * FROM test_restart_recovery').first()
assert result['count'] == 2
pipeline.insert('stream0', ['x'], [(1,), (1,)])
result = pipeline.execute('SELECT * FROM test_restart_recovery').first()
assert result['count'] == 4
def test_simple_aggs(pipeline, clean_db):
"""
Verify that combines work properly on simple aggs
"""
q = """
SELECT x::integer % 10 AS k,
avg(x), sum(y::float8), count(*) FROM stream0 GROUP BY k;
"""
desc = ('x', 'y')
pipeline.create_stream('stream0', x='int', y='float8')
pipeline.create_cv('test_simple_aggs', q)
pipeline.create_table('test_simple_aggs_t', x='integer', y='float8')
rows = []
for n in range(10000):
row = (random.randint(0, 1000), random.random())
rows.append(row)
pipeline.insert('stream0', desc, rows)
pipeline.insert('test_simple_aggs_t', desc, rows)
table_result = pipeline.execute(
'SELECT avg(x), sum(y::float8), count(*) FROM test_simple_aggs_t')
cv_result = pipeline.execute(
'SELECT combine(avg), combine(sum), combine(count) FROM test_simple_aggs'
)
assert len(table_result) == len(cv_result)
for tr, cr in zip(table_result, cv_result):
assert abs(tr[0] - cr[0]) < 0.00001
assert abs(tr[1] - cr[1]) < 0.00001
assert abs(tr[2] - cr[2]) < 0.00001
def test_fss_agg(pipeline, clean_db):
pipeline.create_stream('test_fss_stream', x='int', k='text')
q = """
SELECT k::text, fss_agg(x::int, 5) FROM test_fss_stream
GROUP BY k
"""
desc = ('k', 'x')
pipeline.create_cv('test_fss_agg', q)
items = range(14)
random.shuffle(items)
a_items = items
b_items = list(reversed(items))
values = map(lambda i: ('a', i), get_geometric_dist(a_items))
values.extend(map(lambda i: ('b', i), get_geometric_dist(b_items)))
random.shuffle(values)
pipeline.insert('test_fss_stream', desc, values)
result = list(
pipeline.execute(
'SELECT k, fss_topk_values(fss_agg) FROM test_fss_agg ORDER BY k'))
topk = map(int, result[0][1].rstrip('}').lstrip('{').split(','))
assert sorted(topk) == sorted(a_items[-5:])
topk = map(int, result[1][1].rstrip('}').lstrip('{').split(','))
assert sorted(topk) == sorted(b_items[-5:])
def assert_result_changes(func, args):
"""
Verifies that the result of the given function changes with time
"""
pipeline.create_stream('stream', x='int', y='text', z='int')
name = 'assert_%s_decreases' % func
pipeline.create_cv(name,
"SELECT %s(%s) FROM stream WHERE arrival_timestamp > clock_timestamp() - interval '2 seconds'" % (func, args))
rows = [(n, str(n), n + 1) for n in range(1000)]
pipeline.insert('stream', ('x', 'y', 'z'), rows)
current = 1
results = []
while current:
row = pipeline.execute('SELECT * FROM %s' % name).first()
current = row[func]
if current is None:
break
results.append(current)
# Verify that we actually read something
assert results
pipeline.drop_cv(name)
def test_cmsketch_agg(pipeline, clean_db):
"""
Test cmsketch_agg, cmsketch_merge_agg, cmsketch_cdf, cmsketch_quantile
"""
pipeline.create_stream('test_cmsketch_stream', k='int', x='int')
q = """
SELECT k::integer, cmsketch_agg(x::int) AS c FROM test_cmsketch_stream
GROUP BY k
"""
desc = ('k', 'x')
pipeline.create_cv('test_cmsketch_agg', q)
rows = []
for n in range(1000):
rows.append((0, n % 20))
rows.append((1, n % 50))
pipeline.insert('test_cmsketch_stream', desc, rows)
result = list(pipeline.execute(
'SELECT cmsketch_frequency(c, 10) AS x, cmsketch_frequency(c, 40) AS y, '
'cmsketch_frequency(c, 60) FROM test_cmsketch_agg ORDER BY k').fetchall())
assert len(result) == 2
assert tuple(result[0]) == (50, 0, 0)
assert tuple(result[1]) == (20, 20, 0)
result = list(pipeline.execute(
'SELECT cmsketch_frequency(combine(c), 10) AS x, '
'cmsketch_frequency(combine(c), 40) AS y, cmsketch_frequency(combine(c), 60) '
'FROM test_cmsketch_agg').fetchall())
assert len(result) == 1
assert tuple(result[0]) == (70, 20, 0)
def test_concurrent_vacuum_full(pipeline, clean_db):
pipeline.create_stream('test_vacuum_stream', x='int')
pipeline.create_cv(
'test_vacuum_full',
'SELECT x::int, COUNT(*) FROM test_vacuum_stream GROUP BY x')
stop = False
def insert():
while not stop:
values = [(random.randint(0, 1000000),) for _ in xrange(1000)]
pipeline.insert('test_vacuum_stream', ('x',), values)
time.sleep(0.01)
threads = [threading.Thread(target=insert) for _ in range(4)]
map(lambda t: t.start(), threads)
# Insert data for a little bit so we have enough work to do while
# vacuuming.
time.sleep(20)
conn = psycopg2.connect('dbname=pipeline user=%s host=localhost port=%s' %
(getpass.getuser(), pipeline.port))
conn.set_isolation_level(psycopg2.extensions.ISOLATION_LEVEL_AUTOCOMMIT)
cur = conn.cursor()
cur.execute('VACUUM FULL test_vacuum_full')
conn.close()
# Now kill the insert threads.
stop = True
map(lambda t: t.join(), threads)
def test_stream_stats(pipeline, clean_db):
"""
Verify that stream-level statistics collection works
"""
# create a few streams
for n in range(8):
sname = 's%d' % n
pipeline.create_stream(sname, x='int')
cvname = 'cv%d' % n
pipeline.create_cv(cvname, 'SELECT count(*) FROM %s' % sname)
for n in range(8):
sname = 's%d' % n
x = n + 1
values = [(v, ) for v in range(1000 * x)]
pipeline.insert(sname, ('x', ), values)
time.sleep(2)
for n in range(8):
sname = 's%d' % n
row = pipeline.execute(
"SELECT stream, input_rows, input_batches, input_bytes FROM pipelinedb.stream_stats WHERE stream = '%s'"
% sname)[0]
x = n + 1
assert row['input_rows'] == 1000 * x
def assert_result_changes(func, args):
"""
Verifies that the result of the given function changes with time
"""
pipeline.create_stream('stream0', x='int', y='text', z='int')
name = 'assert_%s_decreases' % func
pipeline.create_cv(
name,
"SELECT %s(%s) FROM stream0 WHERE arrival_timestamp > clock_timestamp() - interval '2 seconds'"
% (func, args))
rows = [(n, str(n), n + 1) for n in range(1000)]
pipeline.insert('stream0', ('x', 'y', 'z'), rows)
current = 1
results = []
while current:
row = pipeline.execute('SELECT * FROM %s' % name).first()
current = row[func]
if current is None:
break
results.append(current)
# Verify that we actually read something
assert results
pipeline.drop_cv(name)
def test_bloom_intersection(pipeline, clean_db):
"""
Verify that bloom_intersection works
"""
pipeline.create_stream('test_bloom_stream', x='int', k='int')
q = """
SELECT k::int, bloom_agg(x::integer) FROM test_bloom_stream GROUP BY k
"""
desc = ('k', 'x')
pipeline.create_cv('test_bloom_intersection', q)
rows = []
for i in range(10000):
rows.append((0, 2 * i))
rows.append((1, i))
pipeline.insert('test_bloom_stream', desc, rows)
cvq = """
SELECT bloom_cardinality(bloom_intersection_agg(bloom_agg))
FROM test_bloom_intersection
"""
result = list(pipeline.execute(cvq))
assert len(result) == 1
result = result[0]
assert result[0] == 5530
def test_join_with_where(pipeline, clean_db):
"""
Verify that stream-table joins using a WHERE clause work properly
"""
num_cols = 4
q = """
SELECT s.col0::integer FROM stream0 s, wt WHERE s.col0 = 1 AND wt.col0 = 1
"""
wt_cols = dict([('col%d' % n, 'integer') for n in range(num_cols)])
pipeline.create_table('wt', **wt_cols)
pipeline.create_table('wt_s', **wt_cols)
wt = _generate_rows(num_cols, 64)
s = _generate_rows(num_cols, 64)
_insert(pipeline, 'wt', wt, 0.1)
_insert(pipeline, 'wt_s', s, 0.1)
pipeline.create_stream('stream0', **wt_cols)
pipeline.create_cv('test_join_where', q)
_insert(pipeline, 'stream0', s)
expected = pipeline.execute('SELECT COUNT(*) FROM wt_s s, wt WHERE s.col0 = 1 AND wt.col0 = 1')[0]
result = pipeline.execute('SELECT COUNT(*) FROM test_join_where')[0]
assert result['count'] == expected['count']
def test_concurrent_vacuum_full(pipeline, clean_db):
pipeline.create_stream('test_vacuum_stream', x='int')
pipeline.create_cv(
'test_vacuum_full',
'SELECT x::int, COUNT(*) FROM test_vacuum_stream GROUP BY x')
stop = False
def insert():
while not stop:
values = [(random.randint(0, 1000000), ) for _ in xrange(1000)]
pipeline.insert('test_vacuum_stream', ('x', ), values)
time.sleep(0.01)
threads = [threading.Thread(target=insert) for _ in range(4)]
map(lambda t: t.start(), threads)
# Insert data for a little bit so we have enough work to do while
# vacuuming.
time.sleep(20)
conn = psycopg2.connect('dbname=pipeline user=%s host=localhost port=%s' %
(getpass.getuser(), pipeline.port))
conn.set_isolation_level(psycopg2.extensions.ISOLATION_LEVEL_AUTOCOMMIT)
cur = conn.cursor()
cur.execute('VACUUM FULL test_vacuum_full')
conn.close()
# Now kill the insert threads.
stop = True
map(lambda t: t.join(), threads)
def test_incremental_join(pipeline, clean_db):
"""
Verify that join results increase appropriately as we incrementally
add stream events to the input
"""
num_cols = 4
join_cols = [0, 1]
t_cols = dict([('col%d' % n, 'integer') for n in range(num_cols)])
pipeline.create_table('inc', **t_cols)
pipeline.create_stream('stream0', **t_cols)
q = """
SELECT s.col0::integer FROM inc JOIN stream0 s ON inc.col0 = s.col0
AND inc.col1 = s.col1::integer
"""
t = _generate_rows(num_cols, 64)
_insert(pipeline, 'inc', t, 0.1)
pipeline.create_cv('test_join', q)
s = []
for n in range(2):
row = _generate_row(num_cols)
_insert(pipeline, 'stream0', [row])
s.append(row)
expected = _join(t, s, join_cols)
result = pipeline.execute('SELECT COUNT(*) FROM test_join')[0]
assert result['count'] == len(expected)
def test_indexed(pipeline, clean_db):
"""
Verify that stream-table joins involving indexed tables work
"""
pipeline.create_stream('stream0', x='int', y='int')
q = """
SELECT stream0.x::integer, count(*) FROM stream0
JOIN test_indexed_t t ON stream0.x = t.x GROUP BY stream0.x
"""
pipeline.create_table('test_indexed_t', x='integer', y='integer')
pipeline.execute('CREATE INDEX idx ON test_indexed_t(x)')
t = _generate_rows(2, 1000)
s = _generate_rows(2, 1000)
pipeline.insert('test_indexed_t', ('x', 'y'), t)
time.sleep(0.1)
pipeline.create_cv('test_indexed', q)
pipeline.insert('stream0', ('x', 'y'), s)
expected = _join(s, t, [0])
result = pipeline.execute('SELECT sum(count) FROM test_indexed')[0]
assert result['sum'] == len(expected)
def test_hll_agg_hashing(pipeline, clean_db):
"""
Verify that hll_agg correctly hashes different input types
"""
pipeline.create_stream('test_hll_stream', x='int', y='text', z='float8')
q = """
SELECT hll_agg(x::integer) AS i,
hll_agg(y::text) AS t,
hll_agg(z::float8) AS f FROM test_hll_stream
"""
desc = ('x', 'y', 'z')
pipeline.create_cv('test_hll_hashing', q)
rows = []
for n in range(10000):
rows.append((n, '%d' % n, float(n)))
rows.append((n, '%05d' % n, float(n)))
pipeline.insert('test_hll_stream', desc, rows)
cvq = """
SELECT hll_cardinality(i),
hll_cardinality(t), hll_cardinality(f) FROM test_hll_hashing
"""
result = list(pipeline.execute(cvq))
assert len(result) == 1
result = result[0]
assert result[0] == 9976
assert result[1] == 19951
assert result[2] == 10062
def test_combine_in_view(pipeline, clean_db):
"""
Verify that combines in views on top of continuous views work
"""
q = """
SELECT x::integer, avg(y::integer) FROM stream0 GROUP BY x
"""
desc = ('x', 'y')
pipeline.create_stream('stream0', x='int', y='float8')
pipeline.create_cv('test_combine_view', q)
pipeline.execute('CREATE VIEW v AS SELECT combine(avg) FROM test_combine_view')
rows = []
for n in range(10000):
rows.append((random.randint(1, 256), random.randint(1, 1024)))
pipeline.insert('stream0', desc, rows)
view = list(pipeline.execute('SELECT * FROM v'))
assert len(view) == 1
expected = sum(r[1] for r in rows) / float(len(rows))
assert abs(float(view[0][0]) - expected) < 0.00001
pipeline.execute('DROP VIEW v')
def test_join_with_where(pipeline, clean_db):
"""
Verify that stream-table joins using a WHERE clause work properly
"""
num_cols = 4
q = """
SELECT s.col0::integer FROM stream s, wt WHERE s.col0 = 1 AND wt.col0 = 1
"""
wt_cols = dict([('col%d' % n, 'integer') for n in range(num_cols)])
pipeline.create_table('wt', **wt_cols)
pipeline.create_table('wt_s', **wt_cols)
wt = _generate_rows(num_cols, 64)
s = _generate_rows(num_cols, 64)
_insert(pipeline, 'wt', wt, 0.1)
_insert(pipeline, 'wt_s', s, 0.1)
pipeline.create_stream('stream', **wt_cols)
pipeline.create_cv('test_join_where', q)
_insert(pipeline, 'stream', s)
expected = pipeline.execute('SELECT COUNT(*) FROM wt_s s, wt WHERE s.col0 = 1 AND wt.col0 = 1').first()
result = pipeline.execute('SELECT COUNT(*) FROM test_join_where').first()
assert result['count'] == expected['count']
def test_hll_agg_hashing(pipeline, clean_db):
"""
Verify that hll_agg correctly hashes different input types
"""
pipeline.create_stream('test_hll_stream', x='int', y='text', z='float8')
q = """
SELECT hll_agg(x::integer) AS i,
hll_agg(y::text) AS t,
hll_agg(z::float8) AS f FROM test_hll_stream
"""
desc = ('x', 'y', 'z')
pipeline.create_cv('test_hll_hashing', q)
rows = []
for n in range(10000):
rows.append((n, '%d' % n, float(n)))
rows.append((n, '%05d' % n, float(n)))
pipeline.insert('test_hll_stream', desc, rows)
cvq = """
SELECT hll_cardinality(i),
hll_cardinality(t), hll_cardinality(f) FROM test_hll_hashing
"""
result = list(pipeline.execute(cvq))
assert len(result) == 1
result = result[0]
assert result[0] == 9976
assert result[1] == 19951
assert result[2] == 10062
def test_bloom_contains(pipeline, clean_db):
"""
Verify that bloom_contains works
"""
pipeline.create_stream("test_bloom_stream", x="int")
q = """
SELECT bloom_agg(x::integer) FROM test_bloom_stream
"""
desc = "x"
pipeline.create_cv("test_bloom_contains", q)
rows = []
for i in range(10000):
rows.append((2 * i,))
pipeline.insert("test_bloom_stream", desc, rows)
cvq = """
SELECT bloom_contains(bloom_agg, 0), bloom_contains(bloom_agg, 5000),
bloom_contains(bloom_agg, 1), bloom_contains(bloom_agg, 5001)
FROM test_bloom_contains
"""
result = list(pipeline.execute(cvq))
assert len(result) == 1
result = result[0]
assert result[0] == True
assert result[1] == True
assert result[2] == False
assert result[3] == False
def test_colums_subset(pipeline, clean_db):
"""
Verify that copying data from a file into a stream works when the file's input
columns are a subset of the stream0's columns
"""
pipeline.create_stream('stream0', x='int', y='float8', z='numeric', m='int')
q = 'SELECT sum(x::integer) AS s0, sum(y::float8) AS s1, avg(z::numeric), max(m::integer) FROM stream0'
pipeline.create_cv('test_copy_subset', q)
pipeline.create_table('test_copy_subset_t', x='integer', y='float8', z='numeric')
path = os.path.abspath(os.path.join(pipeline.data_dir, 'test_copy.csv'))
rows = []
for n in range(10000):
row = random.randint(1, 1024), random.randint(1, 1024), random.random()
rows.append(row)
_generate_csv(path, rows, desc=('x', 'y', 'z'))
pipeline.execute('COPY test_copy_subset_t (x, y, z) FROM \'%s\' HEADER CSV' % path)
pipeline.execute('COPY stream0 (x, y, z) FROM \'%s\' HEADER CSV' % path)
expected = pipeline.execute('SELECT sum(x::integer) AS s0, sum(y::float8) AS s1, avg(z::numeric) FROM test_copy_subset_t')[0]
result = pipeline.execute('SELECT s0, s1, avg FROM test_copy_subset')
assert len(result) == 1
result = result[0]
assert result[0] == expected[0]
assert result[1] == expected[1]
assert result[2] == expected[2]
def test_restart_recovery(pipeline, clean_db):
pipeline.create_stream('stream0', x='int')
q = 'SELECT COUNT(*) FROM stream0'
pipeline.create_cv('test_restart_recovery', q)
pipeline.insert('stream0', ['x'], [(1, ), (1, )])
result = pipeline.execute('SELECT * FROM test_restart_recovery').first()
assert result['count'] == 2
# Need to sleep here, otherwise on restart the materialization table is
# empty. Not sure why.
time.sleep(0.1)
# Restart.
pipeline.stop()
pipeline.run()
result = pipeline.execute('SELECT * FROM test_restart_recovery').first()
assert result['count'] == 2
pipeline.insert('stream0', ['x'], [(1, ), (1, )])
result = pipeline.execute('SELECT * FROM test_restart_recovery').first()
assert result['count'] == 4
def test_simple_crash(pipeline, clean_db):
"""
Test simple worker and combiner crashes.
"""
pipeline.create_stream('stream0', x='int')
q = 'SELECT COUNT(*) FROM stream0'
pipeline.create_cv('test_simple_crash', q)
pipeline.insert('stream0', ['x'], [(1, ), (1, )])
result = pipeline.execute('SELECT * FROM test_simple_crash').first()
assert result['count'] == 2
# This batch can potentially get lost.
pipeline.insert('stream0', ['x'], [(1, ), (1, )])
assert kill_worker()
pipeline.insert('stream0', ['x'], [(1, ), (1, )])
result = pipeline.execute('SELECT * FROM test_simple_crash').first()
assert result['count'] in [4, 6]
# This batch can potentially get lost.
pipeline.insert('stream0', ['x'], [(1, ), (1, )])
assert kill_combiner()
pipeline.insert('stream0', ['x'], [(1, ), (1, )])
result = pipeline.execute('SELECT * FROM test_simple_crash').first()
assert result['count'] in [6, 8, 10]
# To ensure that all remaining events in ZMQ queues have been consumed
time.sleep(2)
def test_null_groups(pipeline, clean_db):
"""
Verify that null group columns are considered equal
"""
pipeline.create_stream('stream', x='int', y='int', z='int')
q = """
SELECT x::integer, y::integer, z::integer, COUNT(*) FROM stream
GROUP BY x, y, z;
"""
desc = ('x', 'y', 'z')
pipeline.create_cv('test_null_groups', q)
pipeline.create_table('test_null_groups_t', x='integer', y='integer', z='integer')
rows = []
for n in range(10000):
vals = list(random.randint(0, 10) for n in range(3))
vals = map(lambda n: random.random() > 0.1 and n or None, vals)
rows.append(tuple(vals))
pipeline.insert('stream', desc, rows)
pipeline.insert('test_null_groups_t', desc, rows)
table_q = """
SELECT x, y, z, COUNT(*) FROM test_null_groups_t
GROUP BY x, y, z ORDER BY x, y, z;
"""
expected = list(pipeline.execute(table_q))
result = list(pipeline.execute('SELECT x, y, z, count FROM test_null_groups ORDER BY x, y, z'))
for r, e in zip(result, expected):
assert r == e
def test_bloom_contains(pipeline, clean_db):
"""
Verify that bloom_contains works
"""
pipeline.create_stream('test_bloom_stream', x='int')
q = """
SELECT bloom_agg(x::integer) FROM test_bloom_stream
"""
desc = ('x')
pipeline.create_cv('test_bloom_contains', q)
rows = []
for i in range(10000):
rows.append((2 * i, ))
pipeline.insert('test_bloom_stream', desc, rows)
cvq = """
SELECT bloom_contains(bloom_agg, 0), bloom_contains(bloom_agg, 5000),
bloom_contains(bloom_agg, 1), bloom_contains(bloom_agg, 5001)
FROM test_bloom_contains
"""
result = list(pipeline.execute(cvq))
assert len(result) == 1
result = result[0]
assert result[0] == True
assert result[1] == True
assert result[2] == False
assert result[3] == False
def test_sliding_windows(pipeline, clean_db):
"""
Verify that sliding window queries are properly dumped and restored
"""
pipeline.create_stream('stream0', x='int')
pipeline.execute('CREATE VIEW sw_v WITH (sw = \'20 seconds\') AS SELECT count(*) FROM stream0')
pipeline.insert('stream0', ('x',), [(x,) for x in range(10)])
result = pipeline.execute('SELECT count FROM sw_v')[0]
assert result['count'] == 10
_dump(pipeline, 'test_sw.sql')
pipeline.drop_all()
_restore(pipeline, 'test_sw.sql')
result = pipeline.execute('SELECT count FROM sw_v')[0]
assert result['count'] == 10
# We should still drop back to 0 within 20 seconds
result = pipeline.execute('SELECT count FROM sw_v')[0]
while result['count'] > 0:
time.sleep(1)
result = pipeline.execute('SELECT count FROM sw_v')[0]
result = pipeline.execute('SELECT count FROM sw_v')[0]
# Disabled until #157 (currently combine doesn't return 0 on NULL input for this aggregate)
# assert result == 0
assert result['count'] is None
def test_join_multiple_tables(pipeline, clean_db):
"""
Verify that stream-table joins involving multiple tables work
"""
num_cols = 8
join_cols = [0]
t0_cols = dict([('col%d' % n, 'integer') for n in range(num_cols)])
t1_cols = dict([('col%d' % n, 'integer') for n in range(num_cols)])
pipeline.create_table('t0', **t0_cols)
pipeline.create_table('t1', **t1_cols)
pipeline.create_stream('stream', **t0_cols)
q = """
SELECT s.col0::integer FROM t0 JOIN t1 ON t0.col0 = t1.col0
JOIN stream s ON t1.col0 = s.col0
"""
t0 = _generate_rows(num_cols, 64)
t1 = _generate_rows(num_cols, 64)
s = _generate_rows(num_cols, 64)
_insert(pipeline, 't1', t1, 0.1)
_insert(pipeline, 't0', t0, 0.1)
pipeline.create_cv('test_join_multi', q)
_insert(pipeline, 'stream', s)
expected = _join(t0, _join(s, t1, join_cols), join_cols)
result = pipeline.execute('SELECT COUNT(*) FROM test_join_multi').first()
assert result['count'] == len(expected)
def test_bloom_intersection(pipeline, clean_db):
"""
Verify that bloom_intersection works
"""
pipeline.create_stream("test_bloom_stream", x="int", k="int")
q = """
SELECT k::int, bloom_agg(x::integer) FROM test_bloom_stream GROUP BY k
"""
desc = ("k", "x")
pipeline.create_cv("test_bloom_intersection", q)
rows = []
for i in range(10000):
rows.append((0, 2 * i))
rows.append((1, i))
pipeline.insert("test_bloom_stream", desc, rows)
cvq = """
SELECT bloom_cardinality(bloom_intersection_agg(bloom_agg))
FROM test_bloom_intersection
"""
result = list(pipeline.execute(cvq))
assert len(result) == 1
result = result[0]
assert result[0] == 5530
def test_indexed(pipeline, clean_db):
"""
Verify that stream-table joins involving indexed tables work
"""
pipeline.create_stream('stream', x='int', y='int')
q = """
SELECT stream.x::integer, count(*) FROM stream
JOIN test_indexed_t t ON stream.x = t.x GROUP BY stream.x
"""
pipeline.create_table('test_indexed_t', x='integer', y='integer')
pipeline.execute('CREATE INDEX idx ON test_indexed_t(x)')
t = _generate_rows(2, 1000)
s = _generate_rows(2, 1000)
pipeline.insert('test_indexed_t', ('x', 'y'), t)
time.sleep(0.1)
pipeline.create_cv('test_indexed', q)
pipeline.insert('stream', ('x', 'y'), s)
expected = _join(s, t, [0])
result = pipeline.execute('SELECT sum(count) FROM test_indexed').first()
assert result['sum'] == len(expected)
def test_filter_clause(pipeline, clean_db):
"""
Verify that FILTER clauses work on aggregates and sliding window aggregates
"""
pipeline.create_stream('test_filter_stream', x='int')
q = """
SELECT SUM(x::int) FILTER (WHERE mod(x, 2) = 0) AS sum2, SUM(x::int) FILTER (WHERE mod(x, 3) = 0) AS sum3 FROM test_filter_stream
"""
sw = """
WHERE arrival_timestamp > clock_timestamp() - interval '30 second'
"""
pipeline.create_cv('test_filter', q)
pipeline.create_cv('test_filter_sw', '%s %s' % (q, sw))
desc = ('x', )
rows = []
for n in range(1000):
rows.append((n, ))
pipeline.insert('test_filter_stream', desc, rows)
sum2 = sum(filter(lambda x: x % 2 == 0, map(lambda x: x[0], rows)))
sum3 = sum(filter(lambda x: x % 3 == 0, map(lambda x: x[0], rows)))
result1 = pipeline.execute('SELECT * FROM test_filter').first()
result2 = pipeline.execute('SELECT * FROM test_filter_sw').first()
assert result1['sum2'] == result2['sum2'] == sum2
assert result1['sum3'] == result2['sum3'] == sum3
def test_user_low_and_high_card(pipeline, clean_db):
"""
Verify that HLL's with low and high cardinalities are correcly combined
"""
pipeline.create_stream('test_hll_stream', x='int', k='integer')
q = """
SELECT k::integer, hll_agg(x::integer) FROM test_hll_stream GROUP BY k
"""
desc = ('k', 'x')
pipeline.create_cv('test_hll_agg', q)
# Low cardinalities
rows = []
for n in range(1000):
rows.append((0, random.choice((-1, -2))))
rows.append((1, random.choice((-3, -4))))
# High cardinalities
for n in range(10000):
rows.append((2, n))
rows.append((3, n))
pipeline.insert('test_hll_stream', desc, rows)
result = pipeline.execute('SELECT hll_cardinality(combine(hll_agg)) '
'FROM test_hll_agg WHERE k in (0, 1)').first()
assert result[0] == 4
result = pipeline.execute('SELECT hll_cardinality(combine(hll_agg)) '
'FROM test_hll_agg WHERE k in (2, 3)').first()
assert result[0] == 9976
result = pipeline.execute('SELECT hll_cardinality(combine(hll_agg)) '
'FROM test_hll_agg').first()
assert result[0] == 9983
def test_sliding_windows(pipeline, clean_db):
"""
Verify that sliding window queries are properly dumped and restored
"""
pipeline.create_stream('stream0', x='int')
pipeline.execute('CREATE CONTINUOUS VIEW sw_v WITH (sw = \'20 seconds\') AS SELECT count(*) FROM stream0')
pipeline.insert('stream0', ('x',), [(x,) for x in range(10)])
result = pipeline.execute('SELECT count FROM sw_v').first()
assert result['count'] == 10
_dump(pipeline, 'test_sw.sql')
pipeline.drop_all()
_restore(pipeline, 'test_sw.sql')
result = pipeline.execute('SELECT count FROM sw_v').first()
assert result['count'] == 10
# We should still drop back to 0 within 20 seconds
result = pipeline.execute('SELECT count FROM sw_v').first()
while result['count'] > 0:
time.sleep(1)
result = pipeline.execute('SELECT count FROM sw_v').first()
result = pipeline.execute('SELECT count FROM sw_v').first()
assert result['count'] == 0
def test_user_low_and_high_card(pipeline, clean_db):
"""
Verify that HLL's with low and high cardinalities are correcly combined
"""
pipeline.create_stream('test_hll_stream', x='int', k='integer')
q = """
SELECT k::integer, hll_agg(x::integer) FROM test_hll_stream GROUP BY k
"""
desc = ('k', 'x')
pipeline.create_cv('test_hll_agg', q)
# Low cardinalities
rows = []
for n in range(1000):
rows.append((0, random.choice((-1, -2))))
rows.append((1, random.choice((-3, -4))))
# High cardinalities
for n in range(10000):
rows.append((2, n))
rows.append((3, n))
pipeline.insert('test_hll_stream', desc, rows)
result = pipeline.execute('SELECT hll_cardinality(combine(hll_agg)) '
'FROM test_hll_agg WHERE k in (0, 1)').first()
assert result[0] == 4
result = pipeline.execute('SELECT hll_cardinality(combine(hll_agg)) '
'FROM test_hll_agg WHERE k in (2, 3)').first()
assert result[0] == 9976
result = pipeline.execute('SELECT hll_cardinality(combine(hll_agg)) '
'FROM test_hll_agg').first()
assert result[0] == 9983
def test_single_continuous_view(pipeline, clean_db):
"""
Verify that specific continuous views can be dropped and restored
"""
pipeline.create_stream('stream0', x='int')
pipeline.create_cv('test_single0', 'SELECT COUNT(*) FROM stream0')
pipeline.create_cv('test_single1', 'SELECT COUNT(*) FROM stream0')
pipeline.insert('stream0', ('x',), [(x,) for x in range(10)])
result = pipeline.execute('SELECT count FROM test_single0').first()
assert result['count'] == 10
result = pipeline.execute('SELECT count FROM test_single1').first()
assert result['count'] == 10
_dump(pipeline, 'test_single.sql', tables=['test_single0', 'stream0', 'test_single0_mrel'])
pipeline.drop_all()
_restore(pipeline, 'test_single.sql')
result = pipeline.execute('SELECT count FROM test_single0').first()
assert result['count'] == 10
# We didn't dump this one
result = list(pipeline.execute('SELECT * FROM pg_class WHERE relname LIKE \'%%test_single1%%\''))
assert not result
def test_copy_to_typed_stream(pipeline, clean_db):
"""
Verify that copying data from a file into a typed stream works.
"""
pipeline.create_stream('stream', x='integer', y='float8', z='numeric')
q = 'SELECT sum(x) AS s0, sum(y) AS s1, avg(z) FROM stream'
pipeline.create_cv('test_copy_to_typed_stream', q)
pipeline.create_table('test_copy_to_typed_stream_t', x='integer', y='float8', z='numeric')
path = os.path.abspath(os.path.join(pipeline.tmp_dir, 'test_copy.csv'))
rows = []
for n in range(10000):
row = random.randint(1, 1024), random.randint(1, 1024), random.random()
rows.append(row)
_generate_csv(path, rows, desc=('x', 'y', 'z'))
pipeline.execute('COPY test_copy_to_typed_stream_t (x, y, z) FROM \'%s\' HEADER CSV' % path)
pipeline.execute('COPY stream (x, y, z) FROM \'%s\' HEADER CSV' % path)
expected = pipeline.execute('SELECT sum(x) AS s0, sum(y) AS s1, avg(z) FROM test_copy_to_typed_stream_t').first()
result = list(pipeline.execute('SELECT s0, s1, avg FROM test_copy_to_typed_stream'))
assert len(result) == 1
result = result[0]
assert result[0] == expected[0]
assert result[1] == expected[1]
assert result[2] == expected[2]
def test_simple_aggs(pipeline, clean_db):
"""
Verify that combines work properly on simple aggs
"""
q = """
SELECT x::integer %% 10 AS k,
avg(x), sum(y::float8), count(*) FROM stream0 GROUP BY k;
"""
desc = ('x', 'y')
pipeline.create_stream('stream0', x='int', y='float8')
pipeline.create_cv('test_simple_aggs', q)
pipeline.create_table('test_simple_aggs_t', x='integer', y='float8')
rows = []
for n in range(10000):
row = (random.randint(0, 1000), random.random())
rows.append(row)
pipeline.insert('stream0', desc, rows)
pipeline.insert('test_simple_aggs_t', desc, rows)
table_result = list(pipeline.execute('SELECT avg(x), sum(y::float8), count(*) FROM test_simple_aggs_t'))
cv_result = list(pipeline.execute('SELECT combine(avg), combine(sum), combine(count) FROM test_simple_aggs'))
assert len(table_result) == len(cv_result)
for tr, cr in zip(table_result, cv_result):
assert abs(tr[0] - cr[0]) < 0.00001
assert abs(tr[1] - cr[1]) < 0.00001
assert abs(tr[2] - cr[2]) < 0.00001
def test_join_across_batches(pipeline, clean_db):
"""
Verify that stream-table joins are properly built when they
span across multiple input batches
"""
num_cols = 4
join_cols = [0]
t_cols = dict([('col%d' % n, 'integer') for n in range(num_cols)])
pipeline.create_table('batch', **t_cols)
pipeline.create_stream('stream0', **t_cols)
q = """
SELECT s.col0::integer FROM batch JOIN stream0 s ON batch.col0 = s.col0
"""
t = _generate_rows(num_cols, 64)
_insert(pipeline, 'batch', t, 0.1)
s = _generate_rows(num_cols, 64)
pipeline.create_cv('test_batched_join', q)
_insert(pipeline, 'stream0', s)
expected = _join(t, s, join_cols)
result = pipeline.execute('SELECT COUNT(*) FROM test_batched_join')[0]
assert result['count'] == len(expected)
def test_join_across_batches(pipeline, clean_db):
"""
Verify that stream-table joins are properly built when they
span across multiple input batches
"""
num_cols = 4
join_cols = [0]
t_cols = dict([('col%d' % n, 'integer') for n in range(num_cols)])
pipeline.create_table('batch', **t_cols)
pipeline.create_stream('stream', **t_cols)
q = """
SELECT s.col0::integer FROM batch JOIN stream s ON batch.col0 = s.col0
"""
t = _generate_rows(num_cols, 64)
_insert(pipeline, 'batch', t, 0.1)
s = _generate_rows(num_cols, 64)
pipeline.create_cv('test_batched_join', q)
_insert(pipeline, 'stream', s)
expected = _join(t, s, join_cols)
result = pipeline.execute('SELECT COUNT(*) FROM test_batched_join').first()
assert result['count'] == len(expected)
def test_join_multiple_tables(pipeline, clean_db):
"""
Verify that stream-table joins involving multiple tables work
"""
num_cols = 8
join_cols = [0]
t0_cols = dict([('col%d' % n, 'integer') for n in range(num_cols)])
t1_cols = dict([('col%d' % n, 'integer') for n in range(num_cols)])
pipeline.create_table('t0', **t0_cols)
pipeline.create_table('t1', **t1_cols)
pipeline.create_stream('stream0', **t0_cols)
q = """
SELECT s.col0::integer FROM t0 JOIN t1 ON t0.col0 = t1.col0
JOIN stream0 s ON t1.col0 = s.col0
"""
t0 = _generate_rows(num_cols, 64)
t1 = _generate_rows(num_cols, 64)
s = _generate_rows(num_cols, 64)
_insert(pipeline, 't1', t1, 0.1)
_insert(pipeline, 't0', t0, 0.1)
pipeline.create_cv('test_join_multi', q)
_insert(pipeline, 'stream0', s)
expected = _join(t0, _join(s, t1, join_cols), join_cols)
result = pipeline.execute('SELECT COUNT(*) FROM test_join_multi')[0]
assert result['count'] == len(expected)
def test_incremental_join(pipeline, clean_db):
"""
Verify that join results increase appropriately as we incrementally
add stream events to the input
"""
num_cols = 4
join_cols = [0, 1]
t_cols = dict([('col%d' % n, 'integer') for n in range(num_cols)])
pipeline.create_table('inc', **t_cols)
pipeline.create_stream('stream', **t_cols)
q = """
SELECT s.col0::integer FROM inc JOIN stream s ON inc.col0 = s.col0
AND inc.col1 = s.col1::integer
"""
t = _generate_rows(num_cols, 64)
_insert(pipeline, 'inc', t, 0.1)
pipeline.create_cv('test_join', q)
s = []
for n in range(2):
row = _generate_row(num_cols)
_insert(pipeline, 'stream', [row])
s.append(row)
expected = _join(t, s, join_cols)
result = pipeline.execute('SELECT COUNT(*) FROM test_join').first()
assert result['count'] == len(expected)
def test_bloom_agg_hashing(pipeline, clean_db):
"""
Verify that bloom_agg correctly hashes different input types
"""
pipeline.create_stream("test_bloom_stream", x="int", y="text", z="float8")
q = """
SELECT bloom_agg(x::integer) AS i,
bloom_agg(y::text) AS t,
bloom_agg(z::float8) AS f FROM test_bloom_stream
"""
desc = ("x", "y", "z")
pipeline.create_cv("test_bloom_hashing", q)
rows = []
for n in range(10000):
rows.append((n, "%d" % n, float(n)))
rows.append((n, "%05d" % n, float(n)))
pipeline.insert("test_bloom_stream", desc, rows)
cvq = """
SELECT bloom_cardinality(i),
bloom_cardinality(t), bloom_cardinality(f) FROM test_bloom_hashing
"""
result = list(pipeline.execute(cvq))
assert len(result) == 1
result = result[0]
assert result[0] == 8879
assert result[1] == 15614
assert result[2] == 8855
def test_regression(pipeline, clean_db):
path = os.path.abspath(os.path.join(pipeline.tmp_dir, 'test_copy.csv'))
_generate_csv(path, [['2015-06-01 00:00:00','De','Adam_Babareka','1','37433']], desc=('day', 'project', 'title', 'count', 'size'))
pipeline.create_stream('copy_regression_stream', count='int', day='timestamp', project='text', title='text', size='int')
pipeline.create_cv('test_copy_regression', 'SELECT sum(count) FROM copy_regression_stream')
pipeline.execute("COPY copy_regression_stream (day, project, title, count, size) FROM '%s' CSV HEADER" % path)
def test_online_drop_column(pipeline, clean_db):
pipeline.create_stream('stream1', c0='integer')
try:
pipeline.execute('ALTER STREAM stream1 DROP c0')
assert False
except:
pass
def test_online_drop_column(pipeline, clean_db):
pipeline.create_stream("stream1", c0="integer")
try:
pipeline.execute("ALTER STREAM stream1 DROP c0")
assert False
except:
pass
def test_regression(pipeline, clean_db):
path = os.path.abspath(os.path.join(pipeline.data_dir, 'test_copy.csv'))
_generate_csv(path, [['2015-06-01 00:00:00', 'De', 'Adam_Babareka', '1', '37433']], desc=('day', 'project', 'title', 'count', 'size'))
pipeline.create_stream('copy_regression_stream', count='int', day='timestamp', project='text', title='text', size='int')
pipeline.create_cv('test_copy_regression', 'SELECT sum(count) FROM copy_regression_stream')
pipeline.execute("COPY copy_regression_stream (day, project, title, count, size) FROM '%s' CSV HEADER" % path)
def test_cq_stats(pipeline, clean_db):
"""
Verify that CQ statistics collection works
"""
num_combiners = int(pipeline.execute('SHOW continuous_query_num_combiners').first()['continuous_query_num_combiners'])
num_workers = int(pipeline.execute('SHOW continuous_query_num_workers').first()['continuous_query_num_workers'])
pipeline.create_stream('stream0', x='int')
# 10 rows
q = 'SELECT x::integer %% 10 AS g, COUNT(*) FROM stream0 GROUP BY g'
pipeline.create_cv('test_10_groups', q)
# 1 row
q = 'SELECT COUNT(*) FROM stream0'
pipeline.create_cv('test_1_group', q)
values = [(random.randint(1, 1024),) for n in range(1000)]
pipeline.insert('stream0', ('x',), values)
pipeline.insert('stream0', ('x',), values)
# Sleep a little so that the next time we insert, we force the stats collector.
# Must be >= 1s since that's the force interval.
time.sleep(1)
pipeline.insert('stream0', ('x',), values)
pipeline.insert('stream0', ('x',), values)
# Sleep a little so the stats collector flushes all the stats.
time.sleep(1)
proc_result = list(pipeline.execute('SELECT * FROM pipeline_proc_stats'))
cq_result = list(pipeline.execute('SELECT * FROM pipeline_query_stats'))
proc_rows = len(proc_result)
cq_rows = len(cq_result)
# We are guaranteed to send data to all combiners but only at least 1 worker
# since we randomly select which worker to send the data to.
assert proc_rows >= num_combiners + 1
assert proc_rows <= num_combiners + num_workers
assert cq_rows == 4
# We get 2000 in case the first two microbatches go to the same worker
# and the second two go to a different one. In this case, both will flush
# the first microbatch they see, so 1000 + 1000.
result = pipeline.execute("SELECT * FROM pipeline_query_stats WHERE name = 'test_10_groups' AND type = 'worker'").first()
assert result['input_rows'] in [2000, 3000, 4000]
result = pipeline.execute("SELECT * FROM pipeline_query_stats WHERE name = 'test_10_groups' AND type = 'combiner'").first()
assert result['output_rows'] == 10
result = pipeline.execute("SELECT * FROM pipeline_query_stats WHERE name = 'test_1_group' AND type = 'worker'").first()
assert result['input_rows'] in [2000, 3000, 4000]
result = pipeline.execute("SELECT * FROM pipeline_query_stats WHERE name = 'test_1_group' AND type = 'combiner'").first()
assert result['output_rows'] == 1
def test_cq_stats(pipeline, clean_db):
"""
Verify that CQ statistics collection works
"""
num_combiners = int(pipeline.execute('SHOW continuous_query_num_combiners').first()['continuous_query_num_combiners'])
num_workers = int(pipeline.execute('SHOW continuous_query_num_workers').first()['continuous_query_num_workers'])
pipeline.create_stream('stream', x='int')
# 10 rows
q = 'SELECT x::integer %% 10 AS g, COUNT(*) FROM stream GROUP BY g'
pipeline.create_cv('test_10_groups', q)
# 1 row
q = 'SELECT COUNT(*) FROM stream'
pipeline.create_cv('test_1_group', q)
values = [(random.randint(1, 1024),) for n in range(1000)]
pipeline.insert('stream', ('x',), values)
pipeline.insert('stream', ('x',), values)
# Sleep a little so that the next time we insert, we force the stats collector.
# Must be >= 1s since that's the force interval.
time.sleep(1)
pipeline.insert('stream', ('x',), values)
pipeline.insert('stream', ('x',), values)
# Sleep a little so the stats collector flushes all the stats.
time.sleep(1)
proc_result = list(pipeline.execute('SELECT * FROM pipeline_proc_stats'))
cq_result = list(pipeline.execute('SELECT * FROM pipeline_query_stats'))
proc_rows = len(proc_result)
cq_rows = len(cq_result)
# We are guaranteed to send data to all combiners but only at least 1 worker
# since we randomly select which worker to send the data to.
assert proc_rows >= num_combiners + 1
assert proc_rows <= num_combiners + num_workers
assert cq_rows == 4
# We get 2000 in case the first two microbatches go to the same worker
# and the second two go to a different one. In this case, both will flush
# the first microbatch they see, so 1000 + 1000.
result = pipeline.execute("SELECT * FROM pipeline_query_stats WHERE name = 'test_10_groups' AND type = 'worker'").first()
assert result['input_rows'] in [2000, 3000, 4000]
result = pipeline.execute("SELECT * FROM pipeline_query_stats WHERE name = 'test_10_groups' AND type = 'combiner'").first()
assert result['output_rows'] == 10
result = pipeline.execute("SELECT * FROM pipeline_query_stats WHERE name = 'test_1_group' AND type = 'worker'").first()
assert result['input_rows'] in [2000, 3000, 4000]
result = pipeline.execute("SELECT * FROM pipeline_query_stats WHERE name = 'test_1_group' AND type = 'combiner'").first()
assert result['output_rows'] == 1
def test_join_ordering(pipeline, clean_db):
"""
Verify that the correct plan is generated regardless of the ordering of
streams and tables.
"""
num_cols = 8
join_cols = [0]
ordering0_cols = dict([('col%d' % n, 'integer') for n in range(num_cols)])
ordering1_cols = dict([('col%d' % n, 'integer') for n in range(num_cols)])
pipeline.create_table('ordering0', **ordering0_cols)
pipeline.create_table('ordering1', **ordering1_cols)
ordering0 = _generate_rows(num_cols, 64)
ordering1 = _generate_rows(num_cols, 64)
_insert(pipeline, 'ordering0', ordering0, 0.1)
_insert(pipeline, 'ordering1', ordering1, 0.1)
pipeline.create_stream('stream', **ordering0_cols)
# stream, table, table
q0 = """
SELECT s.col0::integer, ordering0.col3, ordering1.col4 FROM
stream s JOIN ordering0 ON s.col0 = ordering0.col0
JOIN ordering1 ON ordering0.col0 = ordering1.col0
"""
pipeline.create_cv('test_ordering0', q0)
# table, stream, table
q1 = """
SELECT s.col0::integer, ordering0.col3, ordering1.col4 FROM
ordering0 JOIN stream s ON s.col0 = ordering0.col0
JOIN ordering1 ON ordering0.col0 = ordering1.col0
"""
pipeline.create_cv('test_ordering1', q1)
# table, table, stream
q2 = """
SELECT s.col0::integer, ordering0.col3, ordering1.col4 FROM
ordering0 JOIN ordering1 ON ordering0.col0 = ordering1.col0
JOIN stream s ON s.col0 = ordering0.col0
"""
pipeline.create_cv('test_ordering2', q2)
s = _generate_rows(num_cols, 64)
_insert(pipeline, 'stream', s)
expected = _join(ordering0, _join(ordering1, s, join_cols), join_cols)
result0 = pipeline.execute('SELECT COUNT(*) FROM test_ordering0').first()
result1 = pipeline.execute('SELECT COUNT(*) FROM test_ordering1').first()
result2 = pipeline.execute('SELECT COUNT(*) FROM test_ordering2').first()
assert result0['count'] == len(expected)
assert result1['count'] == len(expected)
assert result2['count'] == len(expected)
def test_join_ordering(pipeline, clean_db):
"""
Verify that the correct plan is generated regardless of the ordering of
streams and tables.
"""
num_cols = 8
join_cols = [0]
ordering0_cols = dict([('col%d' % n, 'integer') for n in range(num_cols)])
ordering1_cols = dict([('col%d' % n, 'integer') for n in range(num_cols)])
pipeline.create_table('ordering0', **ordering0_cols)
pipeline.create_table('ordering1', **ordering1_cols)
ordering0 = _generate_rows(num_cols, 64)
ordering1 = _generate_rows(num_cols, 64)
_insert(pipeline, 'ordering0', ordering0, 0.1)
_insert(pipeline, 'ordering1', ordering1, 0.1)
pipeline.create_stream('stream0', **ordering0_cols)
# stream, table, table
q0 = """
SELECT s.col0::integer, ordering0.col3, ordering1.col4 FROM
stream0 s JOIN ordering0 ON s.col0 = ordering0.col0
JOIN ordering1 ON ordering0.col0 = ordering1.col0
"""
pipeline.create_cv('test_ordering0', q0)
# table, stream, table
q1 = """
SELECT s.col0::integer, ordering0.col3, ordering1.col4 FROM
ordering0 JOIN stream0 s ON s.col0 = ordering0.col0
JOIN ordering1 ON ordering0.col0 = ordering1.col0
"""
pipeline.create_cv('test_ordering1', q1)
# table, table, stream
q2 = """
SELECT s.col0::integer, ordering0.col3, ordering1.col4 FROM
ordering0 JOIN ordering1 ON ordering0.col0 = ordering1.col0
JOIN stream0 s ON s.col0 = ordering0.col0
"""
pipeline.create_cv('test_ordering2', q2)
s = _generate_rows(num_cols, 64)
_insert(pipeline, 'stream0', s)
expected = _join(ordering0, _join(ordering1, s, join_cols), join_cols)
result0 = pipeline.execute('SELECT COUNT(*) FROM test_ordering0')[0]
result1 = pipeline.execute('SELECT COUNT(*) FROM test_ordering1')[0]
result2 = pipeline.execute('SELECT COUNT(*) FROM test_ordering2')[0]
assert result0['count'] == len(expected)
assert result1['count'] == len(expected)
assert result2['count'] == len(expected)
def test_multiple_databases(pipeline, clean_db):
conn = psycopg2.connect('dbname=postgres user=%s host=localhost port=%s' %
(getpass.getuser(), pipeline.port))
conn.set_isolation_level(ISOLATION_LEVEL_AUTOCOMMIT)
cur = conn.cursor()
cur.execute('CREATE DATABASE tmp_pipeline')
cur.close()
q = 'SELECT x::int FROM dbstream'
pipeline.create_stream('dbstream', x='int')
pipeline.create_cv('test_multiple_databases', q)
# Insert data in first database.
pipeline.insert('dbstream', ['x'], map(lambda x: (x, ), range(0, 10, 2)))
result = pipeline.execute('SELECT * FROM test_multiple_databases')
assert sorted(row['x'] for row in result) == range(0, 10, 2)
# Create same CV in the other database, make sure its created and write different data to it.
tmp_conn = psycopg2.connect(
'dbname=tmp_pipeline user=%s host=localhost port=%s' %
(getpass.getuser(), pipeline.port))
cur = tmp_conn.cursor()
cur.execute('CREATE EXTENSION pipelinedb')
cur.execute('CREATE FOREIGN TABLE dbstream (x int) SERVER pipelinedb')
cur.execute('CREATE VIEW test_multiple_databases AS %s' % q)
tmp_conn.commit()
cur.execute('INSERT INTO dbstream (x) VALUES %s' %
', '.join(map(lambda x: '(%d)' % x, range(1, 11, 2))))
cur.execute('SELECT * FROM test_multiple_databases')
tmp_conn.commit()
assert sorted(row[0] for row in cur) == range(1, 11, 2)
# Ensure that the data written to the other database isn't seen by the first database.
result = pipeline.execute('SELECT * FROM test_multiple_databases')
assert sorted(row['x'] for row in result) == range(0, 10, 2)
# Insert new data to both databases.
pipeline.insert('dbstream', ['x'], map(lambda x: (x, ), range(10, 20, 2)))
cur.execute('INSERT INTO dbstream (x) VALUES %s' %
', '.join(map(lambda x: '(%d)' % x, range(11, 21, 2))))
# Ensure both databases still saw the data written out to them.
result = pipeline.execute('SELECT * FROM test_multiple_databases')
assert sorted(row['x'] for row in result) == range(0, 20, 2)
cur.execute('SELECT * FROM test_multiple_databases')
tmp_conn.commit()
assert sorted(row[0] for row in cur) == range(1, 21, 2)
cur.close()
tmp_conn.close()
cur = conn.cursor()
cur.execute('DROP DATABASE tmp_pipeline')
cur.close()
conn.close()
