From 80999cc5086c635ad8ca564c648eaed45c99ecbc Mon Sep 17 00:00:00 2001
From: Haoyu Zhang <haoyuzhang@google.com>
Date: Mon, 19 Oct 2020 18:35:15 -0700
Subject: [PATCH] Remove catching InternalError for failed tensor copies as
worker failures.
PiperOrigin-RevId: 337976482
Change-Id: Ic385376d39cd6928b39dea985a300a0be14bcc74
---
tensorflow/python/distribute/client/client.py | 8 +-------
1 file changed, 1 insertion(+), 7 deletions(-)
diff --git a/tensorflow/python/distribute/client/client.py b/tensorflow/python/distribute/client/client.py
index be7157c1fea..a5eb9ff5e21 100644
--- a/tensorflow/python/distribute/client/client.py
+++ b/tensorflow/python/distribute/client/client.py
@@ -1180,14 +1180,8 @@ def _is_worker_failure(error):
# remote_handle" part.
return True
- # TODO(b/162541228): The following 3 types of errors are very rare and only
+ # TODO(b/162541228): The following 2 types of errors are very rare and only
# observed in large-scale testing. The types of errors should be reduced.
- # This error could show up when copying function inputs from remote tasks.
- if isinstance(error, errors.InternalError):
- if ("Failed copying input tensor" in str(error) or
- "Unable to find a context_id" in str(error)):
- return True
-
# This could happen when the function registration fails. In the observed
# cases this only happens to the dataset related functions.
if isinstance(error, errors.NotFoundError):