From e74c29777ebf7d0bf15f88c9b0f9c07176d43460 Mon Sep 17 00:00:00 2001
From: ShaochenYu-YW <72957335+ShaochenYu-YW@users.noreply.github.com>
Date: Tue, 14 Jan 2025 22:07:01 -0800
Subject: [PATCH] [Ray Data] Add environment variable overrides for
 max_safe_block_size_factor

We can increase this max_safe_block_size_factor to avoid block slicing in output_buffer.py

Signed-off-by: ShaochenYu-YW <72957335+ShaochenYu-YW@users.noreply.github.com>
---
 python/ray/data/context.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/python/ray/data/context.py b/python/ray/data/context.py
index 823fd37e5957..339c18d2f750 100644
--- a/python/ray/data/context.py
+++ b/python/ray/data/context.py
@@ -34,7 +34,7 @@
 # We will attempt to slice blocks whose size exceeds this factor *
 # target_max_block_size. We will warn the user if slicing fails and we produce
 # blocks larger than this threshold.
-MAX_SAFE_BLOCK_SIZE_FACTOR = 1.5
+MAX_SAFE_BLOCK_SIZE_FACTOR = float(os.environ.get("RAY_DATA_MAX_SAFE_BLOCK_SIZE_FACTOR", "1.5"))
 
 DEFAULT_TARGET_MIN_BLOCK_SIZE = 1 * 1024 * 1024