You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The timeout setting of api_server and runner is not working in bentoml.
i'm using bentoml 1.0.20.post11 version
The default configuration is as follows
version: 1api_server:
workers: ~ # cpu_count() will be used when nulltimeout: 60backlog: 2048# the maximum number of connections that will be made to any given runner server at oncemax_runner_connections: 16metrics:
enabled: truenamespace: bentoml_api_serverduration:
# https://github.com/prometheus/client_python/blob/f17a8361ad3ed5bc47f193ac03b00911120a8d81/prometheus_client/metrics.py#L544buckets: [0.005, 0.01, 0.025, 0.05, 0.075, 0.1, 0.25, 0.5, 0.75, 1.0, 2.5, 5.0, 7.5, 10.0]min: ~max: ~factor: ~logging:
access:
enabled: truerequest_content_length: truerequest_content_type: trueresponse_content_length: trueresponse_content_type: trueformat:
trace_id: 032xspan_id: 016xssl:
enabled: falsecertfile: ~keyfile: ~keyfile_password: ~ca_certs: ~version: 17# ssl.PROTOCOL_TLS_SERVERcert_reqs: 0# ssl.CERT_NONEciphers: TLSv1 # default ciphershttp:
host: 0.0.0.0port: 3000cors:
enabled: falseaccess_control_allow_origins: ~access_control_allow_credentials: ~access_control_allow_methods: ~access_control_allow_headers: ~access_control_allow_origin_regex: ~access_control_max_age: ~access_control_expose_headers: ~response:
trace_id: falsegrpc:
host: 0.0.0.0port: 3000max_concurrent_streams: ~maximum_concurrent_rpcs: ~max_message_length: -1reflection:
enabled: falsechannelz:
enabled: falsemetrics:
host: 0.0.0.0port: 3001runner_probe: # configure whether the API server's health check endpoints (readyz, livez, healthz) also check the runnersenabled: truetimeout: 1period: 10runners:
resources: ~workers_per_resource: 1timeout: 300batching:
enabled: truemax_batch_size: 100max_latency_ms: 10000logging:
access:
enabled: truerequest_content_length: truerequest_content_type: trueresponse_content_length: trueresponse_content_type: truemetrics:
enabled: truenamespace: bentoml_runnertracing:
exporter_type: ~sample_rate: ~excluded_urls: ~timeout: ~max_tag_value_length: ~zipkin:
endpoint: ~local_node_ipv4: ~local_node_ipv6: ~local_node_port: ~jaeger:
protocol: thriftcollector_endpoint: ~thrift:
agent_host_name: ~agent_port: ~udp_split_oversized_batches: ~grpc:
insecure: ~otlp:
protocol: ~endpoint: ~compression: ~http:
certificate_file: ~headers: ~grpc:
headers: ~insecure: ~monitoring:
enabled: truetype: defaultoptions:
log_config_file: ~log_path: monitoring
I modified the timeout of the api_server and the timeout of the runners, but the settings are not applied
When I write service.py as below and enter kentoml serve and test it, it doesn't work normally.
I tried changing the default configuration
I wrote configuration.yaml and tried changing it.
I also checked that it changed properly by printing the config setting.
Describe the bug
The timeout setting of api_server and runner is not working in bentoml.
i'm using bentoml 1.0.20.post11 version
The default configuration is as follows
I modified the timeout of the api_server and the timeout of the runners, but the settings are not applied
When I write service.py as below and enter kentoml serve and test it, it doesn't work normally.
I tried changing the default configuration
I wrote configuration.yaml and tried changing it.
I also checked that it changed properly by printing the config setting.
but not work, please help me
Please Help Me
To reproduce
No response
Expected behavior
No response
Environment
bentoml: 1.0.20.post11
python: 3.10.12
The text was updated successfully, but these errors were encountered: