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
Copy file name to clipboardExpand all lines: articles/machine-learning/how-to-troubleshoot-online-endpoints.md
+12-1Lines changed: 12 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -88,7 +88,18 @@ By default the logs are pulled from the inference server. Logs include the conso
88
88
89
89
You can also get logs from the storage initializer container by passing `–-container storage-initializer`. These logs contain information on whether code and model data were successfully downloaded to the container.
90
90
91
-
Add `--help` and/or `--debug` to commands to see more information. Include the `x-ms-client-request-id` header to help with troubleshooting.
91
+
Add `--help` and/or `--debug` to commands to see more information.
92
+
93
+
## Request tracing
94
+
95
+
There are three supported tracing headers:
96
+
97
+
-`x-request-id` is reserved for server tracing. We override this header to ensure it's a valid GUID.
98
+
99
+
> [!Note]
100
+
> When you create a support ticket for a failed request, attach the failed request ID to expedite investigation.
101
+
102
+
-`x-ms-request-id` and `x-ms-client-request-id` are available for client tracing scenarios. We sanitize these headers to remove non-alphanumeric symbols. These headers are truncated to 72 characters.
0 commit comments