Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[bugfix] Restart k8s log stream on urllib3 failure #26760

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
+28 −22
Open

[bugfix] Restart k8s log stream on urllib3 failure #26760

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7931e59
Restart k8s log stream on urllib3 failure
OrenLederman Dec 30, 2024
6c561db
moving the stream() call inside the try clause
OrenLederman Dec 30, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
50 changes: 28 additions & 22 deletions python_modules/libraries/dagster-k8s/dagster_k8s/ops/k8s_job_op.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
from dagster._annotations import experimental
from dagster._core.errors import DagsterExecutionInterruptedError
from dagster._utils.merger import merge_dicts
from urllib3.exceptions import ProtocolError

from dagster_k8s.client import DEFAULT_JOB_POD_COUNT, DagsterKubernetesClient, k8s_api_retry
from dagster_k8s.container_context import K8sContainerContext
Expand Down Expand Up @@ -377,33 +378,38 @@ def execute_k8s_job(
start_time=start_time, # pyright: ignore[reportArgumentType]
)

log_stream = watch.stream(
api_client.core_api.read_namespaced_pod_log,
name=pod_to_watch,
namespace=namespace,
container=container_name,
)

while True:
if timeout and time.time() - start_time > timeout:
watch.stop()
raise Exception("Timed out waiting for pod to finish")
try:
log_entry = k8s_api_retry(
lambda: next(log_stream),
max_retries=int(
os.getenv("DAGSTER_EXECUTE_K8S_JOB_STREAM_LOGS_RETRIES", "3")
),
timeout=int(
os.getenv(
"DAGSTER_EXECUTE_K8S_JOB_STREAM_LOGS_WAIT_BETWEEN_ATTEMPTS", "5"
)
),
log_stream = watch.stream(
api_client.core_api.read_namespaced_pod_log,
name=pod_to_watch,
namespace=namespace,
container=container_name,
)
print(log_entry) # noqa: T201
while True:
if timeout and time.time() - start_time > timeout:
watch.stop()
raise Exception("Timed out waiting for pod to finish")

log_entry = k8s_api_retry(
lambda: next(log_stream),
max_retries=int(
os.getenv("DAGSTER_EXECUTE_K8S_JOB_STREAM_LOGS_RETRIES", "3")
),
timeout=int(
os.getenv(
"DAGSTER_EXECUTE_K8S_JOB_STREAM_LOGS_WAIT_BETWEEN_ATTEMPTS", "5"
)
),
)
print(log_entry) # noqa: T201
except StopIteration:
break
else:
except ProtocolError as e:
context.log.warning(
f"urllib3.exceptions.ProtocolError. Pausing and will reconnect. {e}"
)
time.sleep(5)
context.log.info("Pod logs are disabled, because restart_policy is not Never")

if job_spec_config and job_spec_config.get("parallelism"):
Expand Down