docs: clarify size limitations for AppendRowsRequest (#474)

* docs: clarify size limitations for AppendRowsRequest chore: add preferred_min_stream_count to CreateReadSessionRequest chore: add write_stream to AppendRowsResponse PiperOrigin-RevId: 463602530 Source-Link: googleapis/googleapis@d33b3fa Source-Link: googleapis/googleapis-gen@90995f6 Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiOTA5OTVmNjQzM2QwZWNkMjkwZjE4NjE2OGNlOTU3ZDZhMGRiOWM2OCJ9 * 🦉 Updates from OwlBot post-processor See https://github.com/googleapis/repo-automation-bots/blob/main/packages/owl-bot/README.md Co-authored-by: Owl Bot <gcf-owl-bot[bot]@users.noreply.github.com>

Author: gcf-owl-bot[bot]

google/cloud/bigquery_storage_v1/services/big_query_write/async_client.py

@@ -431,6 +431,9 @@ def request_generator():
  streaming RPC, certain parts of the AppendRowsRequest
  need only be specified for the first request sent each
  time the gRPC network connection is opened/reopened.
+ The size of a single AppendRowsRequest must be less than
+ 10 MB in size. Requests larger than this return an
+ error, typically `INVALID_ARGUMENT`.
  retry (google.api_core.retry.Retry): Designation of what errors, if any,
  should be retried.
  timeout (float): The timeout for this request.

google/cloud/bigquery_storage_v1/services/big_query_write/client.py

@@ -664,6 +664,9 @@ def request_generator():
  streaming RPC, certain parts of the AppendRowsRequest
  need only be specified for the first request sent each
  time the gRPC network connection is opened/reopened.
+ The size of a single AppendRowsRequest must be less than
+ 10 MB in size. Requests larger than this return an
+ error, typically `INVALID_ARGUMENT`.
  retry (google.api_core.retry.Retry): Designation of what errors, if any,
  should be retried.
  timeout (float): The timeout for this request.

google/cloud/bigquery_storage_v1/types/storage.py

@@ -73,6 +73,18 @@ class CreateReadSessionRequest(proto.Message):
  leave this unset to let the system to determine an upper
  bound OR set this a size for the maximum "units of work" it
  can gracefully handle.
+ preferred_min_stream_count (int):
+ The minimum preferred stream count. This
+ parameter can be used to inform the service that
+ there is a desired lower bound on the number of
+ streams. This is typically a target parallelism
+ of the client (e.g. a Spark cluster with
+ N-workers would set this to a low multiple of N
+ to ensure good cluster utilization).
+
+ The system will make a best effort to provide at
+ least this number of streams, but in some cases
+ might provide less.
  """
 
  parent = proto.Field(
@@ -88,6 +100,10 @@ class CreateReadSessionRequest(proto.Message):
  proto.INT32,
  number=3,
  )
+ preferred_min_stream_count = proto.Field(
+ proto.INT32,
+ number=4,
+ )
 
 
 class ReadRowsRequest(proto.Message):
@@ -343,6 +359,10 @@ class AppendRowsRequest(proto.Message):
  the first request sent each time the gRPC network connection is
  opened/reopened.
 
+ The size of a single AppendRowsRequest must be less than 10 MB in
+ size. Requests larger than this return an error, typically
+ ``INVALID_ARGUMENT``.
+
 
  .. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields
 
@@ -478,6 +498,9 @@ class AppendRowsResponse(proto.Message):
  rows in the batch will be appended. The API will
  return row level error info, so that the caller
  can remove the bad rows and retry the request.
+ write_stream (str):
+ The target of the append operation. Matches the write_stream
+ in the corresponding request.
  """
 
  class AppendResult(proto.Message):
@@ -518,6 +541,10 @@ class AppendResult(proto.Message):
  number=4,
  message="RowError",
  )
+ write_stream = proto.Field(
+ proto.STRING,
+ number=5,
+ )
 
 
 class GetWriteStreamRequest(proto.Message):

scripts/fixup_bigquery_storage_v1_keywords.py

@@ -41,7 +41,7 @@ class bigquery_storageCallTransformer(cst.CSTTransformer):
  METHOD_TO_PARAMS: Dict[str, Tuple[str]] = {
  'append_rows': ('write_stream', 'offset', 'proto_rows', 'trace_id', ),
  'batch_commit_write_streams': ('parent', 'write_streams', ),
- 'create_read_session': ('parent', 'read_session', 'max_stream_count', ),
+ 'create_read_session': ('parent', 'read_session', 'max_stream_count', 'preferred_min_stream_count', ),
  'create_write_stream': ('parent', 'write_stream', ),
  'finalize_write_stream': ('name', ),
  'flush_rows': ('write_stream', 'offset', ),