[SUPPORT] Hudi COW performance issue, bottleneck in "Doing partition and writing data" stage

**Describe the problem you faced**
We are using Hudi on AWS Glue to continuously merge small batches of data to bronze tables, and noticing slow write performance in upsert mode to COW table (20+ minutes).

The target table is ~small, approximately 6 million rows x 1000 columns, and the incoming batches have less than 50,000 records (which during preCombine step are reduced to less than 10,000 unique records). The table is not partitioned because it is small, and currently configured with simple global index.

**Expected behavior**

I would expect writes of this size to take a few minutes, similar to vanilla Spark job writing to S3 in parquet files.

**Environment Description**

* Hudi version : 0.12.1
* Spark version : 3.3
* Hive version : n/a
* Hadoop version : n/a
* Storage (HDFS/S3/GCS..) : S3
* Running on Docker? (yes/no) : no (AWS Glue 4.0)
* Resources: 4 G1X workers (1 driver + 3 executors), each has 4 vCPUs & 16 GB of memory.

**Additional context**

Table config in `/.hoodie/hoodie.properties`:
```
#Updated at 2023-08-14T16:51:53.434Z
#Mon Aug 14 16:51:53 UTC 2023
hoodie.table.timeline.timezone=LOCAL
hoodie.table.keygenerator.class=org.apache.hudi.keygen.NonpartitionedKeyGenerator
hoodie.table.precombine.field=clusterTime
hoodie.table.version=5
hoodie.database.name=
hoodie.datasource.write.hive_style_partitioning=false
hoodie.table.checksum=3456772992
hoodie.partition.metafile.use.base.format=false
hoodie.archivelog.folder=archived
hoodie.table.name=hudi_raw_mytable
hoodie.populate.meta.fields=true
hoodie.table.type=COPY_ON_WRITE
hoodie.datasource.write.partitionpath.urlencode=false
hoodie.table.base.file.format=PARQUET
hoodie.datasource.write.drop.partition.columns=false
hoodie.table.metadata.partitions=
hoodie.timeline.layout.version=1
hoodie.table.recordkey.fields=documentKey
hoodie.table.partition.fields=
```

Hudi config:
```
"hoodie.table.name": TABLE,
"hoodie.datasource.write.recordkey.field": "documentKey",
"hoodie.datasource.write.precombine.field": "clusterTime",
"hoodie.datasource.write.reconcile.schema": "false",
"hoodie.schema.on.read.enable": "true",
"hoodie.bulkinsert.sort.mode": "GLOBAL_SORT",
"hoodie.metadata.enable": "false",
"hoodie.datasource.hive_sync.database": DB_NAME,
"hoodie.datasource.hive_sync.table": TABLE,
"hoodie.datasource.hive_sync.use_jdbc": "false",
"hoodie.datasource.hive_sync.enable": "true",
"hoodie.datasource.hive_sync.partition_extractor_class": "org.apache.hudi.hive.NonPartitionedExtractor",
"hoodie.datasource.hive_sync.partition_value_extractor": "org.apache.hudi.hive.SlashEncodedDayPartitionValueExtractor",
"hoodie.index.type": "GLOBAL_SIMPLE",
"hoodie.datasource.write.keygenerator.class": "org.apache.hudi.keygen.NonpartitionedKeyGenerator"
```

Spark stages show that majority of time (20+ minutes) is spent in "Doing partition and writing data"

Start with the Spark UI stage labeled "Doing partition and writing data" and review the supplied Hudi 0.12.1 configuration, especially the nonpartitioned COW table and GLOBAL_SIMPLE index. Compare the stage timing with the table size, batch size, and AWS Glue worker resources. Done means the write bottleneck is identified and the observed performance is explained or a measured improvement is demonstrated.

Written by the indexing model from the issue text.