diff --git a/shards/README.md b/shards/README.md index f59eca0460..1e0b000af5 100644 --- a/shards/README.md +++ b/shards/README.md @@ -54,7 +54,7 @@ Follow below steps to start a standalone Milvus instance with Mishards from sour 3. Start Milvus server. ```shell - $ sudo nvidia-docker run --rm -d -p 19530:19530 -v /tmp/milvus/db:/opt/milvus/db milvusdb/milvus:0.5.0-d102119-ede20b + $ sudo nvidia-docker run --rm -d -p 19530:19530 -v /tmp/milvus/db:/opt/milvus/db milvusdb/milvus ``` 4. Update path permissions. diff --git a/shards/README_CN.md b/shards/README_CN.md index 24e019d001..98264b206b 100644 --- a/shards/README_CN.md +++ b/shards/README_CN.md @@ -48,7 +48,7 @@ Python 版本为3.6及以上。 3. 启动 Milvus 服务。 ```shell - $ sudo nvidia-docker run --rm -d -p 19530:19530 -v /tmp/milvus/db:/opt/milvus/db milvusdb/milvus:0.5.0-d102119-ede20b + $ sudo nvidia-docker run --rm -d -p 19530:19530 -v /tmp/milvus/db:/opt/milvus/db milvusdb/milvus ``` 4. 更改目录权限。 diff --git a/shards/all_in_one/all_in_one.yml b/shards/all_in_one/all_in_one.yml index 40473fe8b9..75a3340068 100644 --- a/shards/all_in_one/all_in_one.yml +++ b/shards/all_in_one/all_in_one.yml @@ -3,14 +3,15 @@ services: milvus_wr: runtime: nvidia restart: always - image: milvusdb/milvus:0.5.0-d102119-ede20b + image: milvusdb/milvus volumes: - /tmp/milvus/db:/opt/milvus/db + - ./wr_server.yml:/opt/milvus/conf/server_config.yaml milvus_ro: runtime: nvidia restart: always - image: milvusdb/milvus:0.5.0-d102119-ede20b + image: milvusdb/milvus volumes: - /tmp/milvus/db:/opt/milvus/db - ./ro_server.yml:/opt/milvus/conf/server_config.yaml diff --git a/shards/all_in_one/ro_server.yml b/shards/all_in_one/ro_server.yml index 10cf695448..09857ee9c8 100644 --- a/shards/all_in_one/ro_server.yml +++ b/shards/all_in_one/ro_server.yml @@ -12,7 +12,7 @@ db_config: # Keep 'dialect://:@:/', and replace other texts with real values # Replace 'dialect' with 'mysql' or 'sqlite' - insert_buffer_size: 4 # GB, maximum insert buffer size allowed + insert_buffer_size: 1 # GB, maximum insert buffer size allowed # sum of insert_buffer_size and cpu_cache_capacity cannot exceed total memory preload_table: # preload data at startup, '*' means load all tables, empty value means no preload @@ -25,14 +25,14 @@ metric_config: port: 8080 # port prometheus uses to fetch metrics cache_config: - cpu_cache_capacity: 16 # GB, CPU memory used for cache + cpu_cache_capacity: 4 # GB, CPU memory used for cache cpu_cache_threshold: 0.85 # percentage of data that will be kept when cache cleanup is triggered - gpu_cache_capacity: 4 # GB, GPU memory used for cache + gpu_cache_capacity: 1 # GB, GPU memory used for cache gpu_cache_threshold: 0.85 # percentage of data that will be kept when cache cleanup is triggered cache_insert_data: false # whether to load inserted data into cache engine_config: - use_blas_threshold: 20 # if nq < use_blas_threshold, use SSE, faster with fluctuated response times + use_blas_threshold: 800 # if nq < use_blas_threshold, use SSE, faster with fluctuated response times # if nq >= use_blas_threshold, use OpenBlas, slower with stable response times resource_config: diff --git a/shards/all_in_one/wr_server.yml b/shards/all_in_one/wr_server.yml new file mode 100644 index 0000000000..5d7d855c03 --- /dev/null +++ b/shards/all_in_one/wr_server.yml @@ -0,0 +1,41 @@ +server_config: + address: 0.0.0.0 # milvus server ip address (IPv4) + port: 19530 # port range: 1025 ~ 65534 + deploy_mode: cluster_writable # deployment type: single, cluster_readonly, cluster_writable + time_zone: UTC+8 + +db_config: + primary_path: /opt/milvus # path used to store data and meta + secondary_path: # path used to store data only, split by semicolon + + backend_url: sqlite://:@:/ # URI format: dialect://username:password@host:port/database + # Keep 'dialect://:@:/', and replace other texts with real values + # Replace 'dialect' with 'mysql' or 'sqlite' + + insert_buffer_size: 2 # GB, maximum insert buffer size allowed + # sum of insert_buffer_size and cpu_cache_capacity cannot exceed total memory + + preload_table: # preload data at startup, '*' means load all tables, empty value means no preload + # you can specify preload tables like this: table1,table2,table3 + +metric_config: + enable_monitor: false # enable monitoring or not + collector: prometheus # prometheus + prometheus_config: + port: 8080 # port prometheus uses to fetch metrics + +cache_config: + cpu_cache_capacity: 2 # GB, CPU memory used for cache + cpu_cache_threshold: 0.85 # percentage of data that will be kept when cache cleanup is triggered + gpu_cache_capacity: 2 # GB, GPU memory used for cache + gpu_cache_threshold: 0.85 # percentage of data that will be kept when cache cleanup is triggered + cache_insert_data: false # whether to load inserted data into cache + +engine_config: + use_blas_threshold: 800 # if nq < use_blas_threshold, use SSE, faster with fluctuated response times + # if nq >= use_blas_threshold, use OpenBlas, slower with stable response times + +resource_config: + search_resources: # define the GPUs used for search computation, valid value: gpux + - gpu0 + index_build_device: gpu0 # GPU used for building index diff --git a/shards/mishards/.env.example b/shards/mishards/.env.example index f1c812a269..91b67760af 100644 --- a/shards/mishards/.env.example +++ b/shards/mishards/.env.example @@ -1,7 +1,7 @@ DEBUG=True WOSERVER=tcp://127.0.0.1:19530 -SERVER_PORT=19532 +SERVER_PORT=19535 SERVER_TEST_PORT=19888 #SQLALCHEMY_DATABASE_URI=mysql+pymysql://root:root@127.0.0.1:3306/milvus?charset=utf8mb4 @@ -19,7 +19,7 @@ TRACER_CLASS_NAME=jaeger TRACING_SERVICE_NAME=fortest TRACING_SAMPLER_TYPE=const TRACING_SAMPLER_PARAM=1 -TRACING_LOG_PAYLOAD=True +TRACING_LOG_PAYLOAD=False #TRACING_SAMPLER_TYPE=probabilistic #TRACING_SAMPLER_PARAM=0.5