Misc hash / hash aggregation performance improvements (#19910)

## Which issue does this PR close?

<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases.
You can link an issue to this PR using the GitHub syntax. For example
`Closes #123` indicates that this PR will close issue #123.
-->

- Closes #19912

## Rationale for this change

Just a couple of optimizations for hash table lookups usage in hash
aggregate.

## What changes are included in this PR?

<!--
There is no need to duplicate the description in the issue here but it
is sometimes worth providing a summary of the individual changes in this
PR.
-->

## Are these changes tested?

<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code

If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
-->

## Are there any user-facing changes?

<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
-->

<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->

Author: Dandandan

datafusion/common/src/utils/proxy.rs

@@ -121,6 +121,8 @@ pub trait HashTableAllocExt {
     ///
     /// Returns the bucket where the element was inserted.
     /// Note that allocation counts capacity, not size.
+    /// Panics:
+    ///     Assumes the element is not already present, and may panic if it does
     ///
     /// # Example:
     /// ```
@@ -134,7 +136,7 @@ pub trait HashTableAllocExt {
     /// assert_eq!(allocated, 64);
     ///
     /// // insert more values
-    /// for i in 0..100 {
+    /// for i in 2..100 {
     ///     table.insert_accounted(i, hash_fn, &mut allocated);
     /// }
     /// assert_eq!(allocated, 400);
@@ -161,22 +163,24 @@ where
     ) {
         let hash = hasher(&x);
 
-        // NOTE: `find_entry` does NOT grow!
-        match self.find_entry(hash, |y| y == &x) {
-            Ok(_occupied) => {}
-            Err(_absent) => {
-                if self.len() == self.capacity() {
-                    // need to request more memory
-                    let bump_elements = self.capacity().max(16);
-                    let bump_size = bump_elements * size_of::<T>();
-                    *accounting = (*accounting).checked_add(bump_size).expect("overflow");
+        if cfg!(debug_assertions) {
+            // In debug mode, check that the element is not already present
+            debug_assert!(
+                self.find_entry(hash, |y| y == &x).is_err(),
+                "attempted to insert duplicate element into HashTableAllocExt::insert_accounted"
+            );
+        }
 
-                    self.reserve(bump_elements, &hasher);
-                }
+        if self.len() == self.capacity() {
+            // need to request more memory
+            let bump_elements = self.capacity().max(16);
+            let bump_size = bump_elements * size_of::<T>();
+            *accounting = (*accounting).checked_add(bump_size).expect("overflow");
 
-                // still need to insert the element since first try failed
-                self.entry(hash, |y| y == &x, hasher).insert(x);
-            }
+            self.reserve(bump_elements, &hasher);
         }
+
+        // We assume the element is not already present
+        self.insert_unique(hash, x, hasher);
     }
 }

datafusion/physical-expr-common/src/binary_map.rs

@@ -389,7 +389,7 @@ where
                 // is value is already present in the set?
                 let entry = self.map.find_mut(hash, |header| {
                     // compare value if hashes match
-                    if header.len != value_len {
+                    if header.hash != hash || header.len != value_len {
                         return false;
                     }
                     // value is stored inline so no need to consult buffer
@@ -427,7 +427,7 @@ where
                 // Check if the value is already present in the set
                 let entry = self.map.find_mut(hash, |header| {
                     // compare value if hashes match
-                    if header.len != value_len {
+                    if header.hash != hash {
                         return false;
                     }
                     // Need to compare the bytes in the buffer

datafusion/physical-expr-common/src/binary_view_map.rs

@@ -273,11 +273,10 @@ where
             let value: &[u8] = value.as_ref();
 
             let entry = self.map.find_mut(hash, |header| {
-                let v = self.builder.get_value(header.view_idx);
-
-                if v.len() != value.len() {
+                if header.hash != hash {
                     return false;
                 }
+                let v = self.builder.get_value(header.view_idx);
 
                 v == value
             });

datafusion/physical-plan/src/aggregates/group_values/single_group_by/primitive.rs

@@ -128,7 +128,9 @@ where
                     let hash = key.hash(state);
                     let insert = self.map.entry(
                         hash,
-                        |&(g, _)| unsafe { self.values.get_unchecked(g).is_eq(key) },
+                        |&(g, h)| unsafe {
+                            hash == h && self.values.get_unchecked(g).is_eq(key)
+                        },
                         |&(_, h)| h,
                     );