From 0e345286158ba568ee242e4842218fcb9a029697 Mon Sep 17 00:00:00 2001
From: Deepak Cherian <deepak@cherian.net>
Date: Tue, 3 Dec 2024 16:11:45 -0700
Subject: [PATCH 1/2] Cache the result of `DaskManager.normalize_chunks`

This is only used with the backends codepath, where the inputs
are guaranteed to be tuples. By contrast, `dask.array.normalize_chunks`
accepts dicts as inputs and so, is harder to cache transparently
---
 xarray/namedarray/daskmanager.py | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/xarray/namedarray/daskmanager.py b/xarray/namedarray/daskmanager.py
index 6485ba375f5..26bcc3e43e3 100644
--- a/xarray/namedarray/daskmanager.py
+++ b/xarray/namedarray/daskmanager.py
@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 from collections.abc import Callable, Iterable, Sequence
+from functools import lru_cache
 from typing import TYPE_CHECKING, Any
 
 import numpy as np
@@ -19,12 +20,20 @@
 
     try:
         from dask.array import Array as DaskArray
+
     except ImportError:
         DaskArray = np.ndarray[Any, Any]
 
 
 dask_available = module_available("dask")
 
+if dask_available:
+    from dask.array.core import normalize_chunks
+
+    normalize_chunks = lru_cache(normalize_chunks)
+else:
+    normalize_chunks = None
+
 
 class DaskManager(ChunkManagerEntrypoint["DaskArray"]):
     array_cls: type[DaskArray]
@@ -52,8 +61,6 @@ def normalize_chunks(
         previous_chunks: _NormalizedChunks | None = None,
     ) -> Any:
         """Called by open_dataset"""
-        from dask.array.core import normalize_chunks
-
         return normalize_chunks(
             chunks,
             shape=shape,

From de010ea2e60dc6e06b7edc1c7f2d3d93035c6c7f Mon Sep 17 00:00:00 2001
From: Deepak Cherian <deepak@cherian.net>
Date: Tue, 3 Dec 2024 16:13:08 -0700
Subject: [PATCH 2/2] Try using uuids

xref #8902
xref #1525
---
 xarray/core/dataset.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/xarray/core/dataset.py b/xarray/core/dataset.py
index d4a23ac275a..ee706f6e23b 100644
--- a/xarray/core/dataset.py
+++ b/xarray/core/dataset.py
@@ -6,6 +6,7 @@
 import itertools
 import math
 import sys
+import uuid
 import warnings
 from collections import defaultdict
 from collections.abc import (
@@ -257,7 +258,6 @@ def _get_chunk(var: Variable, chunks, chunkmanager: ChunkManagerEntrypoint):
     chunk_shape = chunkmanager.normalize_chunks(
         chunk_shape, shape=shape, dtype=var.dtype, previous_chunks=preferred_chunk_shape
     )
-
     # Warn where requested chunks break preferred chunks, provided that the variable
     # contains data.
     if var.size:
@@ -344,7 +344,8 @@ def _maybe_chunk(
             # by providing chunks as an input to tokenize.
             # subtle bugs result otherwise. see GH3350
             # we use str() for speed, and use the name for the final array name on the next line
-            token2 = tokenize(token if token else var._data, str(chunks))
+            mixin = uuid.uuid4()
+            token2 = tokenize(token if token else var._data, mixin)
             name2 = f"{name_prefix}{name}-{token2}"
 
             from_array_kwargs = utils.consolidate_dask_from_array_kwargs(