chore: import upstream snapshot with attribution

tests/python_client/chaos/scripts/get_all_collections.py

@@ -0,0 +1,36 @@
+from collections import defaultdict
+import json
+import argparse
+from pymilvus import connections, list_collections
+TIMEOUT = 120
+
+
+def save_all_checker_collections(host="127.0.0.1", prefix="Checker"):
+    # create connection
+    connections.connect(host=host, port="19530")
+    all_collections = list_collections()
+    if prefix is None:
+        all_collections = [c_name for c_name in all_collections]
+    else:
+        all_collections = [c_name for c_name in all_collections if prefix in c_name]
+    m = defaultdict(list)
+    for c_name in all_collections:
+        prefix = c_name.split("_")[0]
+        if len(m[prefix]) <= 10:
+            m[prefix].append(c_name)
+    selected_collections = []
+    for v in m.values():
+        selected_collections.extend(v)
+    data = {
+        "all": selected_collections
+    }
+    print("selected_collections is")
+    print(selected_collections)
+    with open("/tmp/ci_logs/all_collections.json", "w") as f:
+        f.write(json.dumps(data))
+
+
+parser = argparse.ArgumentParser(description='host ip')
+parser.add_argument('--host', type=str, default='127.0.0.1', help='host ip')
+args = parser.parse_args()
+save_all_checker_collections(args.host)

tests/python_client/chaos/scripts/hello_milvus.py

@@ -0,0 +1,128 @@
+# Copyright (C) 2019-2020 Zilliz. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance
+# with the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software distributed under the License
+# is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express
+# or implied. See the License for the specific language governing permissions and limitations under the License.
+
+
+import random
+import numpy as np
+import time
+import argparse
+from pymilvus import (
+    connections, list_collections,
+    FieldSchema, CollectionSchema, DataType,
+    Collection
+)
+TIMEOUT = 120
+
+
+def hello_milvus(host="127.0.0.1"):
+    import time
+    # create connection
+    connections.connect(host=host, port="19530")
+
+    print(f"\nList collections...")
+    print(list_collections())
+
+    # 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")
+
+    print(f"\nCreate collection...")
+    collection = Collection(name="hello_milvus", schema=default_schema)
+
+    print(f"\nList collections...")
+    print(list_collections())
+
+    #  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...")
+    collection.flush()
+    print(collection.num_entities)
+    t1 = time.time()
+    print(f"\nGet collection entities 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
+
+    # 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.release()
+
+    collection.create_index(field_name="float_vector", index_params=default_index)
+    t1 = time.time()
+    print(f"\nCreate index cost {t1 - t0:.4f} seconds")
+    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)
+
+
+parser = argparse.ArgumentParser(description='host ip')
+parser.add_argument('--host', type=str, default='127.0.0.1', help='host ip')
+args = parser.parse_args()
+# add time stamp
+print(f"\nStart time: {time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time()))}")
+hello_milvus(args.host)

tests/python_client/chaos/scripts/install_milvus.sh

@@ -0,0 +1,17 @@
+
+release=${1:-"milvs-chaos"}
+milvus_mode=${2:-"cluster"}
+ns=${3:-"chaos-testing"}
+bash uninstall_milvus.sh ${release} ${ns}|| true
+
+helm repo add milvus https://zilliztech.github.io/milvus-helm/
+helm repo update
+if [[ ${milvus_mode} == "cluster" ]];
+then
+    helm install --wait --timeout 360s ${release} milvus/milvus -f ../cluster-values.yaml --set metrics.serviceMonitor.enabled=true -n=${ns}
+fi
+
+if [[ ${milvus_mode} == "standalone" ]];
+then
+    helm install --wait --timeout 360s ${release} milvus/milvus -f ../standalone-values.yaml --set metrics.serviceMonitor.enabled=true -n=${ns}
+fi

tests/python_client/chaos/scripts/install_milvus_cluster.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+set -e
+
+release=${1:-"milvs-chaos"}
+ns=${2:-"chaos-testing"}
+bash uninstall_milvus.sh ${release} ${ns}|| true
+
+echo "insatll cluster"
+helm install --wait --debug --timeout 600s ${RELEASE_NAME:-$release} milvus/milvus \
+                            --set image.all.repository=${REPOSITORY:-"milvusdb/milvus"} \
+                            --set image.all.tag=${IMAGE_TAG:-"master-latest"} \
+                            --set metrics.serviceMonitor.enabled=true \
+                            -f ../cluster-values.yaml -n=${ns}

tests/python_client/chaos/scripts/install_milvus_standalone.sh

@@ -0,0 +1,12 @@
+#!/bin/bash
+set -e
+
+release=${1:-"milvs-chaos"}
+ns=${2:-"chaos-testing"}
+bash uninstall_milvus.sh ${release} ${ns}|| true
+echo "insatll standalone"
+helm install --wait --debug --timeout 600s ${RELEASE_NAME:-$release} milvus/milvus \
+                            --set image.all.repository=${REPOSITORY:-"milvusdb/milvus"} \
+                            --set image.all.tag=${IMAGE_TAG:-"master-latest"} \
+                            --set metrics.serviceMonitor.enabled=true \
+                            -f ../standalone-values.yaml -n=${ns}

tests/python_client/chaos/scripts/modify_config.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+set -e
+set -x
+
+
+echo "check os env"
+platform='Linux'
+unamestr=$(uname)
+if [[ "$unamestr" == 'Linux' ]]; then
+   platform='Linux'
+elif [[ "$unamestr" == 'Darwin' ]]; then
+   platform='Mac'
+fi
+echo "platform: $platform"
+
+if [ "$platform" == "Mac" ];
+then
+    sed -i "" "s/TESTS_CONFIG_LOCATION =.*/TESTS_CONFIG_LOCATION = \'chaos_objects\/${CHAOS_TYPE/-/_}\/'/g" constants.py
+    sed -i "" "s/ALL_CHAOS_YAMLS =.*/ALL_CHAOS_YAMLS = \'chaos_${POD_NAME}_${CHAOS_TYPE/-/_}.yaml\'/g" constants.py
+    sed -i "" "s/RELEASE_NAME =.*/RELEASE_NAME = \'${RELEASE_NAME}\'/g" constants.py
+else
+    sed -i "s/TESTS_CONFIG_LOCATION =.*/TESTS_CONFIG_LOCATION = \'chaos_objects\/${CHAOS_TYPE/-/_}\/'/g" constants.py
+    sed -i "s/ALL_CHAOS_YAMLS =.*/ALL_CHAOS_YAMLS = \'chaos_${POD_NAME}_${CHAOS_TYPE/-/_}.yaml\'/g" constants.py
+    sed -i "s/RELEASE_NAME =.*/RELEASE_NAME = \'${RELEASE_NAME}\'/g" constants.py
+fi

tests/python_client/chaos/scripts/uninstall_milvus.sh

@@ -0,0 +1,8 @@
+
+# Exit immediately for non zero status
+set -e
+release=${1:-"milvus-chaos"}
+ns=${2:-"chaos-testing"}
+helm uninstall ${release} -n=${ns}
+kubectl delete pvc -l release=${release} -n=${ns}
+kubectl delete pvc -l app.kubernetes.io/instance=${release} -n=${ns}

tests/python_client/chaos/scripts/uninstall_milvus_for_operator.sh

@@ -0,0 +1,30 @@
+
+# Exit immediately for non zero status
+set -e
+release=${1:-"milvus-chaos"}
+ns=${2:-"chaos-testing"}
+kubectl delete milvus ${release} -n=${ns} || echo "delete milvus ${release} failed"
+
+# uninstall helm release
+helm_release_list=('minio' 'etcd' 'kafka' 'pulsar')
+for helm_release in ${helm_release_list[*]}; do
+    echo "unistall helm release ${release}-${helm_release}"
+    helm uninstall ${release}-${helm_release} -n=${ns} || echo "delete helm release ${release}-${helm_release} failed"
+done
+# delete pvc for storage
+pvc_list=('minio')
+for pvc in ${pvc_list[*]}; do
+    echo "delete pvc with label release=${release}-${pvc}"
+    kubectl delete pvc -l release=${release}-${pvc} -n=${ns} || echo "delete pvc with label release=${release}-${pvc} failed"
+done
+
+# delete pvc of etcd and message queue
+pvc_list=('etcd' 'kafka' 'pulsar')
+for pvc in ${pvc_list[*]}; do
+    echo "delete pvc with label app.kubernetes.io/instance=${release}-${pvc}"
+    kubectl delete pvc -l app.kubernetes.io/instance=${release}-${pvc} -n=${ns} || echo "delete pvc with label release=${release}-${pvc} failed"
+done
+
+
+
+

tests/python_client/chaos/scripts/verify_all_collections.py

@@ -0,0 +1,138 @@
+# Copyright (C) 2019-2020 Zilliz. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance
+# with the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software distributed under the License
+# is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express
+# or implied. See the License for the specific language governing permissions and limitations under the License.
+
+from collections import defaultdict
+import random
+import numpy as np
+import time
+import argparse
+from pymilvus import (
+    connections, list_collections,
+    FieldSchema, CollectionSchema, DataType,
+    Collection, utility
+)
+TIMEOUT = 120
+
+
+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...")
+    collection.flush()
+    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)
+
+
+parser = argparse.ArgumentParser(description='host ip')
+parser.add_argument('--host', type=str, default='127.0.0.1', help='host ip')
+args = parser.parse_args()
+# add time stamp
+print(f"\nStart time: {time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time()))}")
+# create connection
+connections.connect(host=args.host, port="19530")
+print("\nList collections...")
+all_collections = list_collections()
+print(all_collections)
+all_collections = [c_name for c_name in all_collections if "Checker" in c_name]
+m = defaultdict(list)
+for c_name in all_collections:
+    prefix = c_name.split("_")[0]
+    if len(m[prefix]) <= 5:
+        m[prefix].append(c_name)
+selected_collections = []
+for v in m.values():
+    selected_collections.extend(v)
+print("selected_collections is")
+print(selected_collections)
+cnt = 0
+for collection_name in selected_collections:
+    print(f"check collection {collection_name}")
+    hello_milvus(collection_name)

tests/python_client/chaos/scripts/workflow_analyse.py

@@ -0,0 +1,41 @@
+import requests
+requests.packages.urllib3.disable_warnings() # noqa
+url = "https://api.github.com/repos/milvus-io/milvus/actions/workflows"
+
+payload = {}
+token = ""  # your token
+headers = {
+    "Authorization": f"token {token}",
+}
+
+response = requests.request("GET", url, headers=headers, data=payload)
+
+
+def analysis_workflow(workflow_name, workflow_response):
+    """
+    Used to count the number of successes and failures of jobs in the chaos test workflow, 
+    so as to understand the robustness of different components(each job represents a component).
+    """
+    workflow_id = [w["id"] for w in workflow_response.json()["workflows"] if workflow_name in w["name"]][0]    
+    runs_response = requests.request("GET", f"https://api.github.com/repos/milvus-io/milvus/actions/workflows/{workflow_id}/runs", headers=headers, data=payload, verify=False)    
+    workflow_runs = [r["id"] for r in runs_response.json()["workflow_runs"] if r["status"] == "completed" and r["event"] == "schedule"]
+    results = {}
+    for run in workflow_runs:
+        job_url = f"https://api.github.com/repos/milvus-io/milvus/actions/runs/{run}/jobs"
+        job_response = requests.request("GET", job_url, headers=headers, data=payload, verify=False)
+        for r in job_response.json()["jobs"]:
+            if r["name"] not in results:
+                results[r["name"]] = {"success": 0, "failure": 0}
+            if r["status"] == "completed" and r["conclusion"] == "success":
+                results[r["name"]]["success"] += 1
+            elif r["status"] == "completed" and r["conclusion"] != "success":
+                results[r["name"]]["failure"] += 1
+    return results
+
+
+for workflow in ["Pod Kill"]:
+    result = analysis_workflow(workflow, response)
+    print(f"{workflow}:")
+    for k, v in result.items():
+        print(f"{k} success: {v['success']}, failure: {v['failure']}")    
+    print("\n")