increase default healthCheckTimeout to 120s
This commit is contained in:
@@ -63,9 +63,10 @@ models:
|
||||
<summary>But also very powerful ...</summary>
|
||||
|
||||
```yaml
|
||||
# Seconds to wait for llama.cpp to load and be ready to serve requests
|
||||
# Default (and minimum) is 15 seconds
|
||||
healthCheckTimeout: 60
|
||||
# Seconds to wait for upstream to load and be ready to serve requests
|
||||
# minimum is 15 seconds
|
||||
# default is 120 seconds
|
||||
healthCheckTimeout: 500
|
||||
|
||||
# Valid log levels: debug, info (default), warn, error
|
||||
logLevel: info
|
||||
|
||||
@@ -113,7 +113,12 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
|
||||
return Config{}, err
|
||||
}
|
||||
|
||||
if config.HealthCheckTimeout < 15 {
|
||||
if config.HealthCheckTimeout == 0 {
|
||||
// this high default timeout helps avoid failing health checks
|
||||
// for configurations that wait for docker or have slower startup
|
||||
config.HealthCheckTimeout = 120
|
||||
} else if config.HealthCheckTimeout < 15 {
|
||||
// set a minimum of 15 seconds
|
||||
config.HealthCheckTimeout = 15
|
||||
}
|
||||
|
||||
|
||||
@@ -100,7 +100,7 @@ func NewProcess(ID string, healthCheckTimeout int, config ModelConfig, processLo
|
||||
concurrencyLimitSemaphore: make(chan struct{}, concurrentLimit),
|
||||
|
||||
// stop timeout
|
||||
gracefulStopTimeout: 5 * time.Second,
|
||||
gracefulStopTimeout: 10 * time.Second,
|
||||
upstreamWasStoppedWithKill: false,
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user