[Bugfix] Use monotonic clocks for test server startup timeouts (#7628)
Signed-off-by: psv666 <2693925048@qq.com> Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
This commit is contained in:
1 parent
470ec60848
commit
f90c267ffb
2 files changed
+100
-6
No files matched your search
@@ -38,6 +38,8 @@ from vllm_omni.outputs import OmniRequestOutput
|
||||
|
||||
logger = init_logger(__name__)
|
||||
|
||||
SERVER_STARTUP_TIMEOUT_S = 1200
|
||||
|
||||
PromptAudioInput = list[tuple[Any, int]] | tuple[Any, int] | None
|
||||
PromptImageInput = list[Any] | Any | None
|
||||
PromptVideoInput = list[Any] | Any | None
|
||||
@@ -246,9 +248,10 @@ class OmniServer:
|
||||
cwd=_omni_subprocess_cwd(),
|
||||
)
|
||||
|
||||
max_wait = 1200
|
||||
start_time = time.time()
|
||||
while time.time() - start_time < max_wait:
|
||||
max_wait = SERVER_STARTUP_TIMEOUT_S
|
||||
# System clock corrections must not shorten or extend startup waits.
|
||||
start_time = time.monotonic()
|
||||
while time.monotonic() - start_time < max_wait:
|
||||
ret = self.proc.poll()
|
||||
if ret is not None:
|
||||
raise RuntimeError(f"Server processes exited with code {ret} before becoming ready.")
|
||||
@@ -550,9 +553,10 @@ class OmniServerStageCli(OmniServer):
|
||||
for replica_id in range(self.stage_replica_counts.get(stage_id, 1)):
|
||||
self._launch_stage(stage_id, headless=True, replica_id=replica_id)
|
||||
|
||||
max_wait = 1200
|
||||
start_time = time.time()
|
||||
while time.time() - start_time < max_wait:
|
||||
max_wait = SERVER_STARTUP_TIMEOUT_S
|
||||
# System clock corrections must not shorten or extend startup waits.
|
||||
start_time = time.monotonic()
|
||||
while time.monotonic() - start_time < max_wait:
|
||||
self._ensure_stage_processes_alive()
|
||||
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock:
|
||||
sock.settimeout(1)
|
||||
|
||||
Reference in new issue
Block a user