milvus/shards/all_in_one/ro_server.yml

42 lines
2.2 KiB
YAML
Raw Normal View History

server_config:
address: 0.0.0.0 # milvus server ip address (IPv4)
port: 19530 # port range: 1025 ~ 65534
deploy_mode: cluster_readonly # 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: 4 # 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: 16 # 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_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
# 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