def test_expand_data_node(self):
"""
target: test create and insert api after expand dataNode pod
method: 1.create collection a and insert df
2.expand dataNode pod from 1 to 2
3.verify collection a property and verify create and insert of new collection
expected: two collection create and insert op are both correctly
"""
# deploy all nodes one pod cluster milvus with helm
release_name = "scale-data"
env = HelmEnv(release_name=release_name)
host = env.helm_install_cluster_milvus()
# connect
connections.add_connection(default={"host": host, "port": 19530})
connections.connect(alias='default')
# create
c_name = cf.gen_unique_str(prefix)
collection_w = ApiCollectionWrapper()
collection_w.init_collection(name=c_name,
schema=cf.gen_default_collection_schema())
# # insert
data = cf.gen_default_list_data(ct.default_nb)
mutation_res, _ = collection_w.insert(data)
assert mutation_res.insert_count == ct.default_nb
# scale dataNode to 2 pods
env.helm_upgrade_cluster_milvus(dataNode=2)
# after scale, assert data consistent
assert utility.has_collection(c_name)
assert collection_w.num_entities == ct.default_nb
# assert new operations
new_cname = cf.gen_unique_str(prefix)
new_collection_w = ApiCollectionWrapper()
new_collection_w.init_collection(
name=new_cname, schema=cf.gen_default_collection_schema())
new_mutation_res, _ = new_collection_w.insert(data)
assert new_mutation_res.insert_count == ct.default_nb
assert new_collection_w.num_entities == ct.default_nb
# assert old collection ddl
mutation_res_2, _ = collection_w.insert(data)
assert mutation_res.insert_count == ct.default_nb
assert collection_w.num_entities == ct.default_nb * 2
collection_w.drop()
new_collection_w.drop()
def test_expand_data_node(self):
"""
target: test create and insert api after expand dataNode pod
method: 1.create collection a and insert df
2.expand dataNode pod from 1 to 2
3.verify collection a property and verify create and insert of new collection
expected: two collection create and insert op are both correctly
"""
release_name = "scale-data"
milvusOp, host, port = scale_common.deploy_default_milvus(release_name)
# connect
connections.add_connection(default={"host": host, "port": port})
connections.connect(alias='default')
# create
c_name = cf.gen_unique_str(prefix)
collection_w = ApiCollectionWrapper()
collection_w.init_collection(name=c_name, schema=cf.gen_default_collection_schema())
# # insert
data = cf.gen_default_list_data()
mutation_res, _ = collection_w.insert(data)
assert mutation_res.insert_count == ct.default_nb
# scale dataNode to 2 pods
milvusOp.upgrade(release_name, {'spec.components.dataNode.replicas': 2}, constants.NAMESPACE)
milvusOp.wait_for_healthy(release_name, constants.NAMESPACE)
# after scale, assert data consistent
assert utility.has_collection(c_name)
assert collection_w.num_entities == ct.default_nb
# assert new operations
new_cname = cf.gen_unique_str(prefix)
new_collection_w = ApiCollectionWrapper()
new_collection_w.init_collection(name=new_cname, schema=cf.gen_default_collection_schema())
new_mutation_res, _ = new_collection_w.insert(data)
assert new_mutation_res.insert_count == ct.default_nb
assert new_collection_w.num_entities == ct.default_nb
# assert old collection ddl
mutation_res_2, _ = collection_w.insert(data)
assert mutation_res.insert_count == ct.default_nb
assert collection_w.num_entities == ct.default_nb*2
collection_w.drop()
new_collection_w.drop()
def hello_milvus(collection_name):
import time
# create collection
dim = 128
default_fields = [
FieldSchema(name="int64", dtype=DataType.INT64, is_primary=True),
FieldSchema(name="float", dtype=DataType.FLOAT),
FieldSchema(name="varchar", dtype=DataType.VARCHAR, max_length=65535),
FieldSchema(name="float_vector", dtype=DataType.FLOAT_VECTOR, dim=dim)
]
default_schema = CollectionSchema(fields=default_fields,
description="test collection")
if utility.has_collection(collection_name):
print("collection is exist")
collection = Collection(name=collection_name)
default_schema = collection.schema
dim = [
field.params['dim'] for field in default_schema.fields
if field.dtype in [101, 102]
][0]
print(f"\nCreate collection...")
collection = Collection(name=collection_name, schema=default_schema)
# insert data
nb = 3000
vectors = [[random.random() for _ in range(dim)] for _ in range(nb)]
t0 = time.time()
collection.insert([[i for i in range(nb)],
[np.float32(i) for i in range(nb)],
[str(i) for i in range(nb)], vectors])
t1 = time.time()
print(f"\nInsert {nb} vectors cost {t1 - t0:.4f} seconds")
t0 = time.time()
print(f"\nGet collection entities...")
print(collection.num_entities)
t1 = time.time()
print(f"\nGet collection entities cost {t1 - t0:.4f} seconds")
# create index and load table
default_index = {
"index_type": "IVF_SQ8",
"metric_type": "L2",
"params": {
"nlist": 64
}
}
print(f"\nCreate index...")
t0 = time.time()
collection.create_index(field_name="float_vector",
index_params=default_index)
t1 = time.time()
print(f"\nCreate index cost {t1 - t0:.4f} seconds")
print("\nGet replicas number")
try:
replicas_info = collection.get_replicas()
replica_number = len(replicas_info.groups)
print(f"\nReplicas number is {replica_number}")
except Exception as e:
print(str(e))
replica_number = 1
print(f"\nload collection...")
t0 = time.time()
collection.load(replica_number=replica_number)
t1 = time.time()
print(f"\nload collection cost {t1 - t0:.4f} seconds")
# load and search
topK = 5
search_params = {"metric_type": "L2", "params": {"nprobe": 10}}
t0 = time.time()
print(f"\nSearch...")
# define output_fields of search result
res = collection.search(vectors[-2:],
"float_vector",
search_params,
topK,
"int64 > 100",
output_fields=["int64", "float"],
timeout=TIMEOUT)
t1 = time.time()
print(f"search cost {t1 - t0:.4f} seconds")
# show result
for hits in res:
for hit in hits:
# Get value of the random value field for search result
print(hit, hit.entity.get("float"))
# query
expr = "int64 in [2,4,6,8]"
output_fields = ["int64", "float"]
res = collection.query(expr, output_fields, timeout=TIMEOUT)
sorted_res = sorted(res, key=lambda k: k['int64'])
for r in sorted_res:
print(r)
def test_expand_data_node(self):
"""
target: test create and insert api after expand dataNode pod
method: 1.create collection a and insert df
2.expand dataNode pod from 1 to 2
3.verify collection a property and verify create and insert of new collection
expected: two collection create and insert op are both correctly
"""
# deploy all nodes one pod cluster milvus with helm
release_name = "scale-data"
# env = HelmEnv(release_name=release_name)
# host = env.helm_install_cluster_milvus()
# deploy cluster milvus with dataNode 1 replicas
default_config = {
'metadata.namespace': constants.NAMESPACE,
'metadata.name': release_name,
'spec.components.image':
'milvusdb/milvus-dev:master-20211020-b40513b',
'spec.components.proxy.serviceType': 'LoadBalancer',
'dependencies.etcd.inCluster.deletionPolicy': 'Delete',
'dependencies.etcd.inCluster.pvcDeletion': 'true',
'dependencies.pulsar.inCluster.deletionPolicy': 'Delete',
'dependencies.pulsar.inCluster.pvcDeletion': 'true',
'dependencies.storage.inCluster.deletionPolicy': 'Delete',
'dependencies.storage.inCluster.pvcDeletion': 'true',
}
milvusOp = MilvusOperator()
milvusOp.install(default_config)
if milvusOp.wait_for_healthy(release_name,
namespace=constants.NAMESPACE):
endpoint = milvusOp.endpoint(release_name, constants.NAMESPACE)
endpoint = endpoint.split(':')
host = endpoint[0]
port = int(endpoint[-1])
else:
raise Exception(f"Failed to install {release_name}")
# connect
connections.add_connection(default={"host": host, "port": port})
connections.connect(alias='default')
# create
c_name = cf.gen_unique_str(prefix)
collection_w = ApiCollectionWrapper()
collection_w.init_collection(name=c_name,
schema=cf.gen_default_collection_schema())
# # insert
data = cf.gen_default_list_data(ct.default_nb)
mutation_res, _ = collection_w.insert(data)
assert mutation_res.insert_count == ct.default_nb
# scale dataNode to 2 pods
milvusOp.upgrade(release_name,
{'spec.components.dataNode.replicas': 2},
constants.NAMESPACE)
# env.helm_upgrade_cluster_milvus(dataNode=2)
# after scale, assert data consistent
assert utility.has_collection(c_name)
assert collection_w.num_entities == ct.default_nb
# assert new operations
new_cname = cf.gen_unique_str(prefix)
new_collection_w = ApiCollectionWrapper()
new_collection_w.init_collection(
name=new_cname, schema=cf.gen_default_collection_schema())
new_mutation_res, _ = new_collection_w.insert(data)
assert new_mutation_res.insert_count == ct.default_nb
assert new_collection_w.num_entities == ct.default_nb
# assert old collection ddl
mutation_res_2, _ = collection_w.insert(data)
assert mutation_res.insert_count == ct.default_nb
assert collection_w.num_entities == ct.default_nb * 2
collection_w.drop()
new_collection_w.drop()
def test_exist_collection(name):
assert utility.has_collection(name) is True
collection = Collection(name)
collection.drop()
def test_chaos_data_consist(self, connection, chaos_yaml):
"""
target: verify data consistence after chaos injected and recovered
method: 1. create a collection, insert some data, search and query
2. inject a chaos object
3. reconnect to service
4. verify a) data entities persists, index persists,
b) search and query results persist
expected: collection data and results persist
"""
c_name = cf.gen_unique_str('chaos_collection_')
nb = 5000
i_name = cf.gen_unique_str('chaos_index_')
index_params = {
"index_type": "IVF_SQ8",
"metric_type": "L2",
"params": {
"nlist": 64
}
}
# create
t0 = datetime.datetime.now()
collection_w = ApiCollectionWrapper()
collection_w.init_collection(name=c_name,
schema=cf.gen_default_collection_schema())
tt = datetime.datetime.now() - t0
log.info(f"assert create: {tt}")
assert collection_w.name == c_name
# insert
data = cf.gen_default_list_data(nb=nb)
t0 = datetime.datetime.now()
_, res = collection_w.insert(data)
tt = datetime.datetime.now() - t0
log.info(f"assert insert: {tt}")
assert res
# flush
t0 = datetime.datetime.now()
assert collection_w.num_entities == nb
tt = datetime.datetime.now() - t0
log.info(f"assert flush: {tt}")
# search
collection_w.load()
search_vectors = cf.gen_vectors(1, ct.default_dim)
t0 = datetime.datetime.now()
search_params = {"metric_type": "L2", "params": {"nprobe": 16}}
search_res, _ = collection_w.search(
data=search_vectors,
anns_field=ct.default_float_vec_field_name,
param=search_params,
limit=1)
tt = datetime.datetime.now() - t0
log.info(f"assert search: {tt}")
assert len(search_res) == 1
# index
t0 = datetime.datetime.now()
index, _ = collection_w.create_index(
field_name=ct.default_float_vec_field_name,
index_params=index_params,
name=i_name)
tt = datetime.datetime.now() - t0
log.info(f"assert index: {tt}")
assert len(collection_w.indexes) == 1
# query
term_expr = f'{ct.default_int64_field_name} in [1001,1201,999,99]'
t0 = datetime.datetime.now()
query_res, _ = collection_w.query(term_expr)
tt = datetime.datetime.now() - t0
log.info(f"assert query: {tt}")
assert len(query_res) == 4
# reboot a pod
reboot_pod(chaos_yaml)
# parse chaos object
chaos_config = cc.gen_experiment_config(chaos_yaml)
meta_name = chaos_config.get('metadata', None).get('name', None)
# wait all pods ready
log.info(
f"wait for pods in namespace {constants.CHAOS_NAMESPACE} with label app.kubernetes.io/instance={meta_name}"
)
wait_pods_ready(constants.CHAOS_NAMESPACE,
f"app.kubernetes.io/instance={meta_name}")
log.info(
f"wait for pods in namespace {constants.CHAOS_NAMESPACE} with label release={meta_name}"
)
wait_pods_ready(constants.CHAOS_NAMESPACE, f"release={meta_name}")
log.info("all pods are ready")
# reconnect if needed
sleep(constants.WAIT_PER_OP * 3)
reconnect(connections, alias='default')
# verify collection persists
assert utility.has_collection(c_name)
log.info("assert collection persists")
collection_w2 = ApiCollectionWrapper()
collection_w2.init_collection(c_name)
# verify data persist
assert collection_w2.num_entities == nb
log.info("assert data persists")
# verify index persists
assert collection_w2.has_index(i_name)
log.info("assert index persists")
# verify search results persist
collection_w2.load()
search_res, _ = collection_w.search(
data=search_vectors,
anns_field=ct.default_float_vec_field_name,
param=search_params,
limit=1)
tt = datetime.datetime.now() - t0
log.info(f"assert search: {tt}")
assert len(search_res) == 1
# verify query results persist
query_res2, _ = collection_w2.query(term_expr)
assert len(query_res2) == len(query_res)
log.info("assert query result persists")
def has_collection(name):
return utility.has_collection(name)
def test_chaos_data_consist(self, connection, chaos_yaml):
c_name = cf.gen_unique_str('chaos_collection_')
nb = 5000
i_name = cf.gen_unique_str('chaos_index_')
index_params = {
"index_type": "IVF_SQ8",
"metric_type": "L2",
"params": {
"nlist": 64
}
}
# create
t0 = datetime.datetime.now()
collection_w = ApiCollectionWrapper()
collection_w.init_collection(name=c_name,
schema=cf.gen_default_collection_schema())
tt = datetime.datetime.now() - t0
log.debug(f"assert create: {tt}")
assert collection_w.name == c_name
# insert
data = cf.gen_default_list_data(nb=nb)
t0 = datetime.datetime.now()
_, res = collection_w.insert(data)
tt = datetime.datetime.now() - t0
log.debug(f"assert insert: {tt}")
assert res
# flush
t0 = datetime.datetime.now()
assert collection_w.num_entities == nb
tt = datetime.datetime.now() - t0
log.debug(f"assert flush: {tt}")
# search
collection_w.load()
search_vectors = cf.gen_vectors(1, ct.default_dim)
t0 = datetime.datetime.now()
search_res, _ = collection_w.search(
data=search_vectors,
anns_field=ct.default_float_vec_field_name,
param={"nprobe": 16},
limit=1)
tt = datetime.datetime.now() - t0
log.debug(f"assert search: {tt}")
assert len(search_res) == 1
# index
t0 = datetime.datetime.now()
index, _ = collection_w.create_index(
field_name=ct.default_float_vec_field_name,
index_params=index_params,
name=i_name)
tt = datetime.datetime.now() - t0
log.debug(f"assert index: {tt}")
assert len(collection_w.indexes) == 1
# query
term_expr = f'{ct.default_int64_field_name} in [3001,4001,4999,2999]'
t0 = datetime.datetime.now()
query_res, _ = collection_w.query(term_expr)
tt = datetime.datetime.now() - t0
log.debug(f"assert query: {tt}")
assert len(query_res) == 4
# reboot a pod
reboot_pod(chaos_yaml)
# reconnect if needed
sleep(constants.WAIT_PER_OP * 4)
reconnect(connections, self.host, self.port)
# verify collection persists
assert utility.has_collection(c_name)
log.debug("assert collection persists")
collection_w2 = ApiCollectionWrapper()
collection_w2.init_collection(c_name)
# verify data persist
assert collection_w2.num_entities == nb
log.debug("assert data persists")
# verify index persists
assert collection_w2.has_index(i_name)
log.debug("assert index persists")
# verify search results persist
# verify query results persist
query_res2, _ = collection_w2.query(term_expr)
assert query_res2 == query_res
log.debug("assert query result persists")
fmt = "\n=== {:30} ===\n"
search_latency_fmt = "search latency = {:.4f}s"
num_entities, dim = 3000, 8
#################################################################################
# 1. connect to Milvus
# Add a new connection alias `default` for Milvus server in `localhost:19530`
# Actually the "default" alias is a buildin in PyMilvus.
# If the address of Milvus is the same as `localhost:19530`, you can omit all
# parameters and call the method as: `connections.connect()`.
#
# Note: the `using` parameter of the following methods is default to "default".
print(fmt.format("start connecting to Milvus"))
connections.connect("default", host="localhost", port="19530")
has = utility.has_collection("hello_milvus")
print(f"Does collection hello_milvus exist in Milvus: {has}")
#################################################################################
# 2. create collection
# We're going to create a collection with 3 fields.
# +-+------------+------------+------------------+------------------------------+
# | | field name | field type | other attributes | field description |
# +-+------------+------------+------------------+------------------------------+
# |1| "pk" | Int64 | is_primary=True | "primary field" |
# | | | | auto_id=False | |
# +-+------------+------------+------------------+------------------------------+
# |2| "random" | Double | | "a double field" |
# +-+------------+------------+------------------+------------------------------+
# |3|"embeddings"| FloatVector| dim=8 | "float vector with dim 8" |
# +-+------------+------------+------------------+------------------------------+
def teardown():
if utility.has_collection(name_A):
utility.drop_collection(name_A)
if utility.has_collection(name_B):
utility.drop_collection(name_B)
def test_has_collection(self):
assert utility.has_collection(gen_collection_name()) is False
