[model-gateway] add --disable-health-check option to skip worker health probes (#17002)

This commit is contained in:
Ziwen Zhao
2026-01-13 17:28:32 -08:00
committed by GitHub
parent 5938c3b06a
commit cf25852a1d
17 changed files with 159 additions and 14 deletions

View File

@@ -391,6 +391,7 @@ struct Router {
health_check_timeout_secs: u64,
health_check_interval_secs: u64,
health_check_endpoint: String,
disable_health_check: bool,
enable_igw: bool,
queue_size: usize,
queue_timeout_secs: u64,
@@ -591,6 +592,7 @@ impl Router {
timeout_secs: self.health_check_timeout_secs,
check_interval_secs: self.health_check_interval_secs,
endpoint: self.health_check_endpoint.clone(),
disable_health_check: self.disable_health_check,
})
.tokenizer_cache(config::TokenizerCacheConfig {
enable_l0: self.tokenizer_cache_enable_l0,
@@ -692,6 +694,7 @@ impl Router {
health_check_timeout_secs = 5,
health_check_interval_secs = 60,
health_check_endpoint = String::from("/health"),
disable_health_check = false,
enable_igw = false,
queue_size = 100,
queue_timeout_secs = 60,
@@ -777,6 +780,7 @@ impl Router {
health_check_timeout_secs: u64,
health_check_interval_secs: u64,
health_check_endpoint: String,
disable_health_check: bool,
enable_igw: bool,
queue_size: usize,
queue_timeout_secs: u64,
@@ -875,6 +879,7 @@ impl Router {
health_check_timeout_secs,
health_check_interval_secs,
health_check_endpoint,
disable_health_check,
enable_igw,
queue_size,
queue_timeout_secs,

View File

@@ -86,6 +86,7 @@ class RouterArgs:
health_check_timeout_secs: int = 5
health_check_interval_secs: int = 60
health_check_endpoint: str = "/health"
disable_health_check: bool = False
# Circuit breaker configuration
cb_failure_threshold: int = 10
cb_success_threshold: int = 3
@@ -599,6 +600,12 @@ class RouterArgs:
default=RouterArgs.health_check_endpoint,
help="Health check endpoint path",
)
health_group.add_argument(
f"--{prefix}disable-health-check",
action="store_true",
default=RouterArgs.disable_health_check,
help="Disable all worker health checks at startup",
)
# Tokenizer configuration
tokenizer_group.add_argument(
f"--{prefix}model-path",