fix(ingest): increasing default ingestion REST timeout to 30 seconds (#3095)

shirshanka · web-flow · commit 39a0081800e5 · 2021-08-13T11:05:44.000-07:00
diff --git a/metadata-ingestion/sink_docs/datahub.md b/metadata-ingestion/sink_docs/datahub.md
@@ -35,7 +35,7 @@ Note that a `.` is used to denote nested fields in the YAML recipe.
 | Field    | Required | Default | Description                  |
 | -------- | -------- | ------- | ---------------------------- |
 | `server` | ✅       |         | URL of DataHub GMS endpoint. |
-| `timeout_sec` |     | 2       | Per-HTTP request timeout.    |
+| `timeout_sec` |     | 30      | Per-HTTP request timeout.    |
 
 ## DataHub Kafka
 
diff --git a/metadata-ingestion/src/datahub/emitter/rest_emitter.py b/metadata-ingestion/src/datahub/emitter/rest_emitter.py
@@ -39,9 +39,9 @@ def _make_curl_command(
 
 
 class DatahubRestEmitter:
-    DEFAULT_CONNECT_TIMEOUT_SEC = 10  # 10 seconds should be plenty to connect
+    DEFAULT_CONNECT_TIMEOUT_SEC = 30  # 30 seconds should be plenty to connect
     DEFAULT_READ_TIMEOUT_SEC = (
-        2  # Any ingest call taking longer than 2 seconds should be abandoned
+        30  # Any ingest call taking longer than 30 seconds should be abandoned
     )
 
     _gms_server: str

Original file line number	Diff line number	Diff line change
`@@ -39,9 +39,9 @@ def _make_curl_command(`
`39`	`39`
`40`	`40`
`41`	`41`	`class DatahubRestEmitter:`
`42`		`- DEFAULT_CONNECT_TIMEOUT_SEC = 10 # 10 seconds should be plenty to connect`
	`42`	`+ DEFAULT_CONNECT_TIMEOUT_SEC = 30 # 30 seconds should be plenty to connect`
`43`	`43`	`DEFAULT_READ_TIMEOUT_SEC = (`
`44`		`- 2 # Any ingest call taking longer than 2 seconds should be abandoned`
	`44`	`+ 30 # Any ingest call taking longer than 30 seconds should be abandoned`
`45`	`45`	`)`
`46`	`46`
`47`	`47`	`_gms_server: str`